Applied Sciences

Research

Jump to: Review

23 pages, 2828 KiB

Open AccessArticle

Modeling and Performance Analysis of a Notification-Based Method for Processing Video Queries on the Fly

by Clayton Kossoski, Jean Marcelo Simão and Heitor Silvério Lopes

Appl. Sci. 2024, 14(9), 3566; https://doi.org/10.3390/app14093566 - 24 Apr 2024

Viewed by 982

Abstract

With the rapid growth of video data, the search for content and events in videos is becoming increasingly relevant, and many challenges arise. Various approaches have been proposed to deal with many issues. However, many open questions are still related to computational cost [...] Read more.

With the rapid growth of video data, the search for content and events in videos is becoming increasingly relevant, and many challenges arise. Various approaches have been proposed to deal with many issues. However, many open questions are still related to computational cost and latency, especially for real-time applications. Considering the need for new and efficient solutions, the so-called NOP (Notification Oriented Paradigm) could be a suitable alternative. NOP introduced a new way of thinking and developing software in which small collaborative entities perform fact execution and logical decision processing based on precise notifications. Following these concepts and practical tools, this paper proposes a new querying processing method based on NOP, focusing on search and matching in a continuous flow context. Experiments on a labeled dataset demonstrated the suitability of the proposed method for low-latency processing with polynomial complexity. The results are better than the state of the art, which works at exponential cost. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

14 pages, 28033 KiB

Open AccessArticle

Optimizing Generative Adversarial Network (GAN) Models for Non-Pneumatic Tire Design

by Ju Yong Seong, Seung-min Ji, Dong-hyun Choi, Seungjae Lee and Sungchul Lee

Appl. Sci. 2023, 13(19), 10664; https://doi.org/10.3390/app131910664 - 25 Sep 2023

Cited by 2 | Viewed by 1596

Abstract

Pneumatic tires are used in diverse industries. However, their design is difficult, as it relies on the knowledge of experienced designers. In this paper, we generate images of non-pneumatic tire designs with patterns based on shapes and lines for different generative adversarial network [...] Read more.

Pneumatic tires are used in diverse industries. However, their design is difficult, as it relies on the knowledge of experienced designers. In this paper, we generate images of non-pneumatic tire designs with patterns based on shapes and lines for different generative adversarial network (GAN) models and test the performance of the models. Using OpenCV, 2000 training images were generated, corresponding to spoke, curve, triangle, and honeycomb non-pneumatic tires. The images created for training were used after removing highly similar images by applying mean squared error (MSE) and structural similarity index (SSIM). To identify the best model for generating patterns of regularly shaped non-pneumatic tires, GAN, deep convolutional generative adversarial network (DCGAN), StarGAN v2, StyleGAN v2-ADA, and ProjectedGAN were compared and analyzed. In the qualitative evaluation, the GAN, DCGAN, StarGAN v2, and StyleGAN v2-ADA models distorted the circle shape and did not maintain a consistent pattern, but ProjectedGAN retained consistency in the circle, and the pattern was less distorted than in the other GAN models. When evaluating quantitative metrics, ProjectedGAN performed the best among several techniques when the difference between the generated and actual image distributions was measured. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

14 pages, 7014 KiB

Open AccessArticle

Design Method for Automatic Assembly Production Line of Electric Valves in Space Propulsion Systems

by Xiaohua Zang, Zhaoqi Zeng, Mingqiang Pan, Kun Cai, Quancheng Liu, Xudong Wang and Yanming Wei

Appl. Sci. 2023, 13(16), 9253; https://doi.org/10.3390/app13169253 - 15 Aug 2023

Viewed by 1726

Abstract

This article proposes a design method for a valve automatic assembly production line in response to the automation assembly requirements of electric valve products in space propulsion systems and the engineering problems of inaccurate loading force control and low valve measurement accuracy in [...] Read more.

This article proposes a design method for a valve automatic assembly production line in response to the automation assembly requirements of electric valve products in space propulsion systems and the engineering problems of inaccurate loading force control and low valve measurement accuracy in existing process methods. This method can achieve five assembly processes during the assembly process of electric valves, including pre-tightening force control, valve-core stroke measurement, performance testing, and shell structure welding. The article introduces the design of platform components such as process execution, positioning, and transportation, as well as the design and operation process of workstations. By combining the design of a three-axis motion mechanism, a small turntable, and a robotic arm, the product can achieve professional, positioning, full process automation, and equipment miniaturization design across multiple workstations. Through the design of precise control of loading force and non-contact optical measurement method of moving structure, compared with the original method, the parameters affecting product performance are precisely controlled and the precision is improved. And the multivariable decoupling of valve product performance is realized by this method. Through application verification, this automatic assembly production line can significantly improve the assembly efficiency of electric valve products and solve difficult problems in product engineering. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

11 pages, 5852 KiB

Open AccessArticle

A Method Based on an Autoencoder for Anomaly Detection in DC Motor Body Temperature

by Emine Hümeyra Demircioğlu and Ersen Yılmaz

Appl. Sci. 2023, 13(15), 8701; https://doi.org/10.3390/app13158701 - 27 Jul 2023

Cited by 1 | Viewed by 1609

Abstract

Anomaly detection has an important role in industrial systems. Abnormal situations occurring in a system cause anomalies, and the anomalies reduce system performance over time, and may also make the system malfunction. Therefore, the correct and timely detection of anomalies is of critical [...] Read more.

Anomaly detection has an important role in industrial systems. Abnormal situations occurring in a system cause anomalies, and the anomalies reduce system performance over time, and may also make the system malfunction. Therefore, the correct and timely detection of anomalies is of critical importance for predictive maintenance. In this study, an autoencoder-based method is proposed for anomaly detection in DC motor body temperature. The performance of the method was examined on a dataset that was created specifically for this study. In the experiments, the three-sigma outlier method was also applied on the same dataset for the same purpose and its performance results are used for comparison. The performance results of both methods are represented in terms of three measures, namely, accuracy, recall, and precision. The experimental study showed that the proposed method achieved over 96% ratios for all three measures, and it can be successfully used for anomaly detection in DC motor body temperature. Additionally, it can be concluded that the proposed system can be preferred for anomaly detection in time series data collected from different types of sensors when the performance results are taken into consideration. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 33350 KiB

Open AccessArticle

Research on Multi-Sensor Simultaneous Localization and Mapping Technology for Complex Environment of Construction Machinery

by Haoling Ren, Yaping Zhao, Tianliang Lin and Jiangdong Wu

Appl. Sci. 2023, 13(14), 8496; https://doi.org/10.3390/app13148496 - 23 Jul 2023

Viewed by 1395

Abstract

Simultaneous localization and mapping (SLAM), as a key task of unmanned vehicles for construction machinery, is of great significance for later path planning and control. Construction tasks in the engineering field are mostly carried out in bridges, tunnels, open fields, etc. The prominent [...] Read more.

Simultaneous localization and mapping (SLAM), as a key task of unmanned vehicles for construction machinery, is of great significance for later path planning and control. Construction tasks in the engineering field are mostly carried out in bridges, tunnels, open fields, etc. The prominent features of these environments are high scene similarity, few geometric features, and large-scale repetitive texture information, which is prone to sensor detection degradation. This leads to positioning drift and map building failure. The traditional method of motion estimation and 3D reconstruction uses a single sensor, which lacks enough information, has poor adaptability to the environment, and cannot guarantee good positioning accuracy and robustness in complex environments. Currently, the strategy of multi-sensor fusion is proven to be an effective solution and is widely studied. This paper proposes a SLAM framework that integrates LiDAR, IMU, and camera. It tightly couples the texture information observed by camera, the geometric information scanned by LiDAR, and the measured value of IMU, allowing visual-inertial odometry (VIO) and LiDAR-inertial odometry (LIO) common implementation. The LIO subsystem extracts point cloud features and matches them with the global map. The obtained pose estimation can be used for the initialization of the VIO subsystem. The VIO system uses direct method to minimize the photometric error and IMU measurement error between images to estimate the pose of the robot and the geometric structure of the scene. The two subsystems assist each other to perform pose estimation, and can operate normally even when any subsystem fails. A factor graph is used to combine all constraints to achieve global pose optimization. Keyframe and sliding window strategies are used to ensure real-time performance. Through real-vehicle testing, the system can perform incremental and real-time state estimation and reconstruct a dense 3D point cloud map, which can effectively solve the problems of positioning drift and mapping failure in the lack of geometric features or challenging construction environments. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

31 pages, 5413 KiB

Open AccessArticle

Predicting and Evaluating Decoring Behavior of Inorganically Bound Sand Cores, Using XGBoost and Artificial Neural Networks

by Fabian Dobmeier, Rui Li, Florian Ettemeyer, Melvin Mariadass, Philipp Lechner, Wolfram Volk and Daniel Günther

Appl. Sci. 2023, 13(13), 7948; https://doi.org/10.3390/app13137948 - 6 Jul 2023

Cited by 3 | Viewed by 1322

Abstract

Complex casting parts rely on sand cores that are both high-strength and can be easily decored after casting. Previous works have shown the need to understand the influences on the decoring behavior of inorganically bound sand cores. This work uses black box and [...] Read more.

Complex casting parts rely on sand cores that are both high-strength and can be easily decored after casting. Previous works have shown the need to understand the influences on the decoring behavior of inorganically bound sand cores. This work uses black box and explainable machine learning methods to determine the significant influences on the decoring behavior of inorganically bound sand cores based on experimental data. The methods comprise artificial neural networks (ANN), extreme gradient boosting (XGBoost), and SHapley Additive exPlanations (SHAP). The work formulates five hypotheses, for which the available data were split and preprocessed accordingly. The hypotheses were evaluated by comparing the model scores of the various sub-datasets and the overall model performance. One sand-binder system was chosen as a validation system, which was not included in the training. Robust models were successfully trained to predict the decoring behavior for the given sand-binder systems of the test system but only partially for the validation system. Conclusions on which parameters are the main influences on the model behavior were drawn and compared to phenomenological–heuristical models of previous works. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

23 pages, 14796 KiB

Open AccessArticle

Intelligent Machinery Fault Diagnosis Method Based on Adaptive Deep Convolutional Neural Network: Using Dental Milling Cutter Malfunction Classifications as an Example

by Ming-Huang Chen, Shang-Liang Chen, Yu-Sheng Lin and Yu-Jen Chen

Appl. Sci. 2023, 13(13), 7763; https://doi.org/10.3390/app13137763 - 30 Jun 2023

Viewed by 1170

Abstract

Intelligent machinery fault diagnosis is one of the key technologies for the transformation and competitiveness of traditional factories. Complex production environments make it difficult to maintain good prediction performance using traditional methods. This paper proposes a deep convolutional neural network combined with an [...] Read more.

Intelligent machinery fault diagnosis is one of the key technologies for the transformation and competitiveness of traditional factories. Complex production environments make it difficult to maintain good prediction performance using traditional methods. This paper proposes a deep convolutional neural network combined with an adaptive environmental noise method to achieve robust fault classification. The proposed method uses six-dimensional physical signals for data fusion and feature fusion, extracts obvious features and enhances subtle features, and uses continuous wavelets and Gramian angular fields to transform signals with different physical and frequency characteristics into time–frequency maps and two-dimensional images. The fusion technology of different signals can provide comprehensive features for fault prediction, improving upon the blind spots of traditional methods to extract features, and then perform prediction and classification through deep convolutional neural networks. In the experiment, the tool failure classification of the dental milling machine is used as a verification case. The results show that the prediction accuracy of the proposed method is nearly 100%, much better than other comparison methods. In addition, white noise was added in the experiment to verify the noise immunity of the model. The results show that the accuracy of the proposed method is 99%, which is better than other comparison methods in terms of accuracy and robustness, proving the effectiveness of the proposed method for fault diagnosis and classification. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

20 pages, 21339 KiB

Open AccessArticle

EDET: Entity Descriptor Encoder of Transformer for Multi-Modal Knowledge Graph in Scene Parsing

by Sai Ma, Weibing Wan, Zedong Yu and Yuming Zhao

Appl. Sci. 2023, 13(12), 7115; https://doi.org/10.3390/app13127115 - 14 Jun 2023

Cited by 1 | Viewed by 1158

Abstract

In scene parsing, the model is required to be able to process complex multi-modal data such as images and contexts in real scenes, and discover their implicit connections from objects existing in the scene. As a storage method that contains entity information and [...] Read more.

In scene parsing, the model is required to be able to process complex multi-modal data such as images and contexts in real scenes, and discover their implicit connections from objects existing in the scene. As a storage method that contains entity information and the relationship between entities, a knowledge graph can well express objects and the semantic relationship between objects in the scene. In this paper, a new multi-phase process was proposed to solve scene parsing tasks; first, a knowledge graph was used to align the multi-modal information and then the graph-based model generates results. We also designed an experiment of feature engineering’s validation for a deep-learning model to preliminarily verify the effectiveness of this method. Hence, we proposed a knowledge representation method named Entity Descriptor Encoder of Transformer (EDET), which uses both the entity itself and its internal attributes for knowledge representation. This method can be embedded into the transformer structure to solve multi-modal scene parsing tasks. EDET can aggregate the multi-modal attributes of entities, and the results in the scene graph generation and image captioning tasks prove that EDET has excellent performance in multi-modal fields. Finally, the proposed method was applied to the industrial scene, which confirmed the viability of our method. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

19 pages, 6751 KiB

Open AccessArticle

MRS-Transformer: Texture Splicing Method to Remove Defects in Solid Wood Board

by Yizhuo Zhang, Xingyu Liu, Hantao Liu and Huiling Yu

Appl. Sci. 2023, 13(12), 7006; https://doi.org/10.3390/app13127006 - 10 Jun 2023

Viewed by 1376

Abstract

Defects in wood growth affect the product’s quality and grade. At present, the research on texture defects of wood mainly focuses on defect localization, ignoring the splicing problem of maintaining texture consistency. In this paper, we designed the MRS-Transformer network and introduced image [...] Read more.

Defects in wood growth affect the product’s quality and grade. At present, the research on texture defects of wood mainly focuses on defect localization, ignoring the splicing problem of maintaining texture consistency. In this paper, we designed the MRS-Transformer network and introduced image inpainting to the field of solid wood board splicing. First, we proposed an asymmetric encoder-decoder based on Vision Transformer, where the encoder uses a fixed mask(M) strategy, discarding the masked patches and using only the unmasked visual patches as input to reduce model calculations. Second, we designed a reverse Swin (RS) module with multi-scale characteristics as the decoder to adjust the divided image patches’ size and complete the restoration from coarse to fine. Finally, we proposed a weighted L2 loss (MSE, mean square error), which assigns different weights to the unmasked region according to the distance from the defective region, allowing the model to make full use of the effective pixels to repair the masked region. To demonstrate the effectiveness of the designed modules, we used MSE (mean square error), LPIPS (learned perceptual image patch similarity), PSNR (peak signal to noise ratio), SSIM (structural similarity), and FLOPs (floating point operations) to measure the quality of the model generated wood texture images and the model computational complexity, we designed relevant ablation experiments. The results show that the MSE, LPIPS, PSNR, and SSIM of the wood images restored by the MRS-Transformer reached 0.0003, 0.154, 40.12, 0.9173, and the GFLOPs is 20.18. Compared with images generated by the Vision Transformer, the MSE and LPIPS were reduced by 51.7% and 30%, PSNR and SSIM were improved by 12.2% and 7.5%, and the GFLOPs were reduced by 38%. To verify the superiority of MRS-Transformer, we compared the image inpainting algorithms with Deepfill v2 and TG-Net, respectively, in which the MSE was 47.0% and 66.9% lower; the LPIPS was 60.6% and 42.5% lower; the FLOPs was 70.6% and 53.5% lower; the PSNR was 16.1% and 26.2% higher; and the SSIM was 7.3% and 5.8% higher. MRS-Transformer repairs a single image in 0.05 s, nearly five times faster than Deepfill v2 and TG-Net. The experimental results demonstrate that the RSwin module effectively alleviates the sense of fragmentation caused by the division of images into patches, the proposed weighted L2 loss improves the semantic consistency of the edges of the missing regions and makes the generated wood texture more detailed and coherent, and the adopted asymmetric encoder-decoder effectively reduces the computational effort of the model and speeds up the training. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

19 pages, 5156 KiB

Open AccessArticle

Performance Analysis of a Hybrid Dehumidification System Adapted for Suspension Bridge Corrosion Protection: A Numerical Study

by Ding Xue, Jian Liu, Yi Song and Xiaosong Zhang

Appl. Sci. 2023, 13(7), 4219; https://doi.org/10.3390/app13074219 - 27 Mar 2023

Cited by 2 | Viewed by 1717

Abstract

A commonly adopted dehumidification system on a suspension bridge is the desiccant wheel dehumidification system (DWDS), which demonstrates ineffectiveness and energy-intensiveness in high temperature and humidity scenarios. This paper proposes a suspension bridge hybrid dehumidification system (HDS) as a better alternative for corrosion [...] Read more.

A commonly adopted dehumidification system on a suspension bridge is the desiccant wheel dehumidification system (DWDS), which demonstrates ineffectiveness and energy-intensiveness in high temperature and humidity scenarios. This paper proposes a suspension bridge hybrid dehumidification system (HDS) as a better alternative for corrosion protection. A numerical model of HDS was first established. Then, the effects of the main operating parameters on HDS were analyzed, and the dehumidification performance of HDS and DWDS was further compared to illustrate the superiority of HDS to apply on a suspension bridge. In addition, the air supply parameter was discussed, and a low-energy operation strategy of HDS in summer cases was proposed. Finally, limitations and adaptations of heat pump dehumidification system (HPDS) and DWDS on suspension bridges were discussed. The results showed that: (1) HDS realizes the utilization of waste energy from suspension bridges, enhancing the system efficiency. Its specific moisture extraction rate (

S M E R

) reaches 3.16 kg kW⁻¹ h⁻¹ in a high-temperature and -humidity environment (35 °C, 30.82 g kg⁻¹) of the suspension bridge. (2) In the same inlet air conditions, HDS has greater dehumidification capacity than DWDS, and this advantage is enlarged with the increment of inlet air temperature and moisture content. In addition, HDS can strengthen dehumidification ability by decreasing the evaporation temperature and increasing the regeneration temperature to meet peak moisture loads of the suspension bridge. (3) Considering the anti-corrosion effects, energy consumption and drying time, the authors recommend that the moisture content corresponding to the atmospheric temperature and RH of 45% be used for air supply on a suspension bridge. (4) HPDS has poor adaptability to temperatures below 20 °C, while DWDS has poor adaptability to some high temperatures of 24~40 °C and high humidities of 19~30 g kg⁻¹. None of them can meet the air supply requirements of a suspension bridge’s main cable alone. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 5854 KiB

Open AccessArticle

A Novel Fault Diagnosis of a Rolling Bearing Method Based on Variational Mode Decomposition and an Artificial Neural Network

by Xiaobei Liang, Jinyong Yao, Weifang Zhang and Yanrong Wang

Appl. Sci. 2023, 13(6), 3413; https://doi.org/10.3390/app13063413 - 8 Mar 2023

Cited by 9 | Viewed by 1956

Abstract

In recent years, artificial neural networks have been widely used in the fault diagnosis of rolling bearings. To realize real-time diagnosis with high accuracy of the fault of a rolling bearing, in this paper, a bearing fault diagnosis model was designed based on [...] Read more.

In recent years, artificial neural networks have been widely used in the fault diagnosis of rolling bearings. To realize real-time diagnosis with high accuracy of the fault of a rolling bearing, in this paper, a bearing fault diagnosis model was designed based on the combination of VMD and ANN, which ensures a higher fault prediction accuracy with less computational time. This paper works from two aspects, including fault feature extraction and neural network structural parameter optimization to obtain an ANN bearing fault diagnosis model with high performance. The raw vibration signals of 10 fault types were divided into training, verification and testing datasets by the random step increment slip method. The variational mode decomposition method was used to decompose the raw vibration signal into several intrinsic mode functions. A new definition of the energy of each intrinsic mode function based on discrete Fourier transform and information entropy method were used as the input for the artificial neural network. Furthermore, the structural parameters of the artificial neural network were designed to obtain a high-performance neural network. The artificial neural network used in this paper had three hidden layers and 13 neurons in each hidden layer. Compared with several machine and deep learning algorithms, the artificial neural network can better fulfill the classification task of rolling bearing fault types with a mean prediction accuracy of 99.3% and computation time of 2.4 s based on a small training dataset. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

22 pages, 2402 KiB

Open AccessArticle

Intelligent Height Adjustment Method of Shearer Drum Based on Rough Set Significance Reduction and Fuzzy Rough Radial Basis Function Neural Network

by Weibing Wang, Zelin Jing, Shuanfeng Zhao, Zhengxiong Lu, Zhizhong Xing and Shuai Guo

Appl. Sci. 2023, 13(5), 2877; https://doi.org/10.3390/app13052877 - 23 Feb 2023

Cited by 2 | Viewed by 1384

Abstract

The intelligent adjustment method of the shearer drum is the key technology to improve the intelligent level and safety degree of fully mechanized mining face. This paper proposes a shearer drum intelligent height adjustment model based on rough set significance attribute reduction (AR) [...] Read more.

The intelligent adjustment method of the shearer drum is the key technology to improve the intelligent level and safety degree of fully mechanized mining face. This paper proposes a shearer drum intelligent height adjustment model based on rough set significance attribute reduction (AR) and fuzzy rough radial basis function neural network (FRRBFNN) optimized by adaptive immune genetic algorithm (AIGA). The model first selects the parameters of shearer process monitoring based on the importance attribute reduction algorithm of rough set, and establishes the attribute reduction set of shearer operation characteristic parameters and the drum height decision rule base. Next, a fuzzy rough radial basis function neural network determined by the decision rule space is proposed. By introducing the fuzzy rough membership function as the connection weight, the network can accurately describe the complex nonlinear relationship between the working characteristic parameters of the attribute shearer and the drum height, and measure the uncertainty of the coal seam distribution. Finally, to further optimize the performance of FRRBFNN, the adaptive immune genetic algorithm is introduced to optimize its parameters, to build a high-precision shearer drum height prediction system. For the evaluation method of the model, we use three indicators: mean absolute error, mean absolute percentage error, and root mean square error. Based on the measured data in Yujialiang area, Shaanxi Province, the experimental results show that—compared with the FRRBFNN and support vector regression (SVR) models, a gated current neural network (GRU), a radial basis function neural network (RBF), the memory strengthen long short-term memory (MSLSTM) model, and the adaptive fuzzy reasoning Petri net (AFRPN)—the MAE of the AR-AIGA-FRBFNN model for predicting the height of the left and right rollers are 18.3 mm and 17.2 mm, respectively; the MAPE is 0.96% and 0.93%, respectively; and the RMSE is 21.2 mm and 22.4 mm, respectively. The AR-AIGA-FRBFNN model is therefore more effective than the other considered methods. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

14 pages, 7117 KiB

Open AccessArticle

Exploration of Applying Pose Estimation Techniques in Table Tennis

by Chih-Hung Wu, Te-Cheng Wu and Wen-Bin Lin

Appl. Sci. 2023, 13(3), 1896; https://doi.org/10.3390/app13031896 - 1 Feb 2023

Cited by 6 | Viewed by 3423

Abstract

The newly developed computer vision pose estimation technique in artificial intelligence (AI) is an emerging technology with potential advantages, such as high efficiency and contactless detection, for improving competitive advantage in the sports industry. The related literature is currently lacking an integrated and [...] Read more.

The newly developed computer vision pose estimation technique in artificial intelligence (AI) is an emerging technology with potential advantages, such as high efficiency and contactless detection, for improving competitive advantage in the sports industry. The related literature is currently lacking an integrated and comprehensive discussion about the applications and limitations of using the pose estimation technique. The purpose of this study was to apply AI pose estimation techniques, and to discuss the concepts, possible applications, and limitations of these techniques in table tennis. This study implemented the OpenPose pose algorithm in a real-world video of a table tennis game. The research results show that the pose estimation algorithm performs well in estimating table tennis players’ poses from the video in a graphics processing unit (GPU)-accelerated environment. This study proposes an innovative two-stage AI pose estimation method for effectively addressing the current difficulties in applying AI to table tennis players’ pose estimation. Finally, this study provides several recommendations, benefits, and various perspectives (training vs. tactics) of table tennis and pose estimation limitations for the sports industry. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

17 pages, 7800 KiB

Open AccessArticle

Surface Defect Detection of Steel Strip with Double Pyramid Network

by Xinwen Zhou, Mengen Wei, Qianglong Li, Yinghua Fu, Yangzhou Gan, Hao Liu, Jing Ruan and Jiuzhen Liang

Appl. Sci. 2023, 13(2), 1054; https://doi.org/10.3390/app13021054 - 12 Jan 2023

Cited by 11 | Viewed by 2376

Abstract

Defect detection on the surface of the steel strip is essential for the quality assurance of the steel strip. Precise localization and classification, the two significant tasks of defect detection, still need to be completed due to the diversity of defect scales. In [...] Read more.

Defect detection on the surface of the steel strip is essential for the quality assurance of the steel strip. Precise localization and classification, the two significant tasks of defect detection, still need to be completed due to the diversity of defect scales. In this paper, a residual atrous spatial pyramid pooling (RASPP) module is first designed to enrich the multi-scale information of the feature maps and increase the receptive field of the feature maps. Secondly, a double pyramid network (DPN) that combines RASPP and feature pyramid is proposed to fuse multi-scale features further so that similar semantic features are shared among the features of each layer. Finally, DPN-Detector, an automatic surface defects detection network, is proposed, which embeds the DPN module into Faster R-CNN and replaces the original detection head with a designed double head. Experiments are carried out on the steel strip surface defect dataset (NEU-DET), and the results show that the mAP of DPN-Detector is as high as 80.93%, which is 3.52% higher than that of the baseline network Faster R-CNN. The classification accuracy is 74.64%, and the detection speed reaches 18.62 FPS. The proposed method performs better robustness, classification and regression capability than other steel strip defect detection methods. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

17 pages, 13628 KiB

Open AccessArticle

Vision-Guided Object Recognition and 6D Pose Estimation System Based on Deep Neural Network for Unmanned Aerial Vehicles towards Intelligent Logistics

by Sijin Luo, Yu Liang, Zhehao Luo, Guoyuan Liang, Can Wang and Xinyu Wu

Appl. Sci. 2023, 13(1), 115; https://doi.org/10.3390/app13010115 - 22 Dec 2022

Cited by 5 | Viewed by 2559

Abstract

Unmanned aerial vehicle (UAV) express delivery is facing a period of rapid development and continues to promote the aviation logistics industry due to its advantages of elevated delivery efficiency and low labor costs. Automatic detection, localization, and estimation of 6D poses of targets [...] Read more.

Unmanned aerial vehicle (UAV) express delivery is facing a period of rapid development and continues to promote the aviation logistics industry due to its advantages of elevated delivery efficiency and low labor costs. Automatic detection, localization, and estimation of 6D poses of targets in dynamic environments are key prerequisites for UAV intelligent logistics. In this study, we proposed a novel vision system based on deep neural networks to locate targets and estimate their 6D pose parameters from 2D color images and 3D point clouds captured by an RGB-D sensor mounted on a UAV. The workflow of this system can be summarized as follows: detect the targets and locate them, separate the object region from the background using a segmentation network, and estimate the 6D pose parameters from a regression network. The proposed system provides a solid foundation for various complex operations for UAVs. To better verify the performance of the proposed system, we built a small dataset called SIAT comprising some household staff. Comparative experiments with several state-of-the-art networks on the YCB-Video dataset and SIAT dataset verified the effectiveness, robustness, and superior performance of the proposed method, indicating its promising applications in UAV-based delivery tasks. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 3150 KiB

Open AccessArticle

A Nested U-Shaped Residual Codec Network for Strip Steel Defect Detection

by Huaping Guo, Shanggui Zhan, Li Zhang, Wenbo Zhu, Yange Sun and Jing Wang

Appl. Sci. 2022, 12(23), 11967; https://doi.org/10.3390/app122311967 - 23 Nov 2022

Viewed by 1485

Abstract

Strip steel is an important raw material for the related industries, such as aerospace, shipbuilding, and pipelines, and any quality defects in the strip steel would lead to huge economic losses. However, it is still a challenge task to effectively detect the defects [...] Read more.

Strip steel is an important raw material for the related industries, such as aerospace, shipbuilding, and pipelines, and any quality defects in the strip steel would lead to huge economic losses. However, it is still a challenge task to effectively detect the defects from the background of the strip steel due to its complex variations, including variable flaws, chaotic background, and noise invasion. This paper proposes a novel strip steel defect detection method based on a U-shaped residual network, including an encoder and a decoder. The encoder is a fully convolutional neural network in which attention mechanisms are embedded to adequately extract multi-scale defect features and ro ignore irrelevant background regions. The decoder is a U-shaped residual network to capture more contextual data from different scales, without significantly increasing the computational cost due to the pooling operations used in the U-shaped network. Furthermore, a residual refinement module is designed immediately after the decoder to further optimize the coarse defect map. Experimental results show that the proposed method can effectively segment surface defect objects from irrelevant background noise and is superior to other advanced methods with clear boundaries. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

18 pages, 3105 KiB

Open AccessArticle

An Experimental Analysis of Drift Detection Methods on Multi-Class Imbalanced Data Streams

by Abdul Sattar Palli, Jafreezal Jaafar, Heitor Murilo Gomes, Manzoor Ahmed Hashmani and Abdul Rehman Gilal

Appl. Sci. 2022, 12(22), 11688; https://doi.org/10.3390/app122211688 - 17 Nov 2022

Cited by 4 | Viewed by 2700

Abstract

The performance of machine learning models diminishes while predicting the Remaining Useful Life (RUL) of the equipment or fault prediction due to the issue of concept drift. This issue is aggravated when the problem setting comprises multi-class imbalanced data. The existing drift detection [...] Read more.

The performance of machine learning models diminishes while predicting the Remaining Useful Life (RUL) of the equipment or fault prediction due to the issue of concept drift. This issue is aggravated when the problem setting comprises multi-class imbalanced data. The existing drift detection methods are designed to detect certain drifts in specific scenarios. For example, the drift detector designed for binary class data may not produce satisfactory results for applications that generate multi-class data. Similarly, the drift detection method designed for the detection of sudden drift may struggle with detecting incremental drift. Therefore, in this experimental investigation, we seek to investigate the performance of the existing drift detection methods on multi-class imbalanced data streams with different drift types. For this reason, this study simulated the streams with various forms of concept drift and the multi-class imbalance problem to test the existing drift detection methods. The findings of current study will aid in the selection of drift detection methods for use in developing solutions for real-time industrial applications that encounter similar issues. The results revealed that among the compared methods, DDM produced the best average F1 score. The results also indicate that the multi-class imbalance causes the false alarm rate to increase for most of the drift detection methods. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

15 pages, 6085 KiB

Open AccessArticle

UAV Path Planning Model Based on R5DOS Model Improved A-Star Algorithm

by Jian Li, Changyi Liao, Weijian Zhang, Haitao Fu and Shengliang Fu

Appl. Sci. 2022, 12(22), 11338; https://doi.org/10.3390/app122211338 - 8 Nov 2022

Cited by 21 | Viewed by 2435

Abstract

In order to solve the problems of large amounts of calculation and long calculation times of the A-star algorithm in three-dimensional space, based on the R5DOS model, this paper proposes a three-dimensional space UAV path planning model. The improved R5DOS intersection model is [...] Read more.

In order to solve the problems of large amounts of calculation and long calculation times of the A-star algorithm in three-dimensional space, based on the R5DOS model, this paper proposes a three-dimensional space UAV path planning model. The improved R5DOS intersection model is combined with the improved A-star algorithm. Together, they construct a local search process, and the R5DOS path planning model is established by reducing the number of search nodes. The path planning model is simulated through MATLAB software and the model can greatly reduce the number of nodes and computational complexity of the A-star algorithm in three-dimensional spaces, while also reducing the calculation time of the UAV. Finally, we compare the improved A-star algorithm with the original A-star algorithm and the geometric A-star algorithm. The final fitting result proves that the improved A-star algorithm has a shorter computation time and fewer node visits. Overall, the simulation results confirm the effectiveness of the improved A-star algorithm and they can be used as a reference for future research on path planning algorithms. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 6166 KiB

Open AccessArticle

Insulators and Defect Detection Based on the Improved Focal Loss Function

by Yuhang Li, Guoping Zou, Hongliang Zou, Chen Zhou and Siguang An

Appl. Sci. 2022, 12(20), 10529; https://doi.org/10.3390/app122010529 - 18 Oct 2022

Cited by 4 | Viewed by 2303

Abstract

Unmanned aerial vehicle (UAV) inspection has become the mainstream of transmission line inspection, and the detection of insulator defects is an important part of UAV inspection. On the premise of ensuring high accuracy and detection speed, an improved YOLOv5 model is proposed for [...] Read more.

Unmanned aerial vehicle (UAV) inspection has become the mainstream of transmission line inspection, and the detection of insulator defects is an important part of UAV inspection. On the premise of ensuring high accuracy and detection speed, an improved YOLOv5 model is proposed for defect detection of insulators. The algorithm uses the weights trained on conventional large-scale datasets to improve accuracy through the transfer learning method of feature mapping. The algorithm employs the Focal loss function and proposes a dynamic weight assignment method. Compared with the traditional empirical value method, it is more in line with the distribution law of samples in the data set, improves the accuracy of difficult-to-classify samples, and saves a lot of time. The experimental results show that the average accuracy of the insulator and its defect is 98.3%, 5.7% higher than the original model, while the accuracy and recall rate of insulator defects are improved by 5.7% and 7.9%, respectively. The algorithm improves the accuracy and recall of the model and enables faster detection of insulator defects. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

13 pages, 742 KiB

Open AccessArticle

A Lightweight Residual Model for Corrosion Segmentation with Local Contextual Information

by Jingxu Huang, Qiong Liu, Lang Xiang, Guangrui Li, Yiqing Zhang and Wenbai Chen

Appl. Sci. 2022, 12(18), 9095; https://doi.org/10.3390/app12189095 - 9 Sep 2022

Cited by 4 | Viewed by 2080

Abstract

Metal corrosion in high-risk areas, such as high-altitude cables and chemical factories, is very complex and inaccessible to people, which can be a hazard and compromise people’s safety. Embedding deep learning models into edge computing devices is urgently needed to conduct corrosion inspections. [...] Read more.

Metal corrosion in high-risk areas, such as high-altitude cables and chemical factories, is very complex and inaccessible to people, which can be a hazard and compromise people’s safety. Embedding deep learning models into edge computing devices is urgently needed to conduct corrosion inspections. However, the parameters of current state-of-the-art models are too large to meet the computation and storage requirements of mobile devices, while lightweight models perform poorly in complex corrosion environments. To address these issues, a lightweight residual deep-learning model based on an encoder–decoder structure is proposed in this paper. We designed small and large kernels to extract local detailed information and capture distant dependencies at all stages of the encoder. A sequential operation consisting of a channel split, depthwise separable convolution, and channel shuffling were implemented to reduce the size of the model. We proposed a simple, efficient decoder structure by fusing multi-scale features to augment feature representation. In extensive experiments, our proposed model, with only 2.41 MB of parameters, demonstrated superior performance over state-of-the-art segmentation methods: 75.64% mean intersection over union (IoU), 86.07% mean pixel accuracy and a 0.838 F1-score. Moreover, a larger version was designed by increasing the number of output channels, and model accuracy improved further: 79.06% mean IoU, 88.07% mean pixel accuracy, and 0.891 F1-score. The size of the model remained competitive at 8.25 MB. Comparison work with other networks and visualized results were used for validation and to determine the accuracy of metal corrosion surface segmentation with limited resources. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

23 pages, 7643 KiB

Open AccessArticle

Chaos Particle Swarm Optimization Enhancement Algorithm for UAV Safe Path Planning

by Hongyue Chu, Junkai Yi and Fei Yang

Appl. Sci. 2022, 12(18), 8977; https://doi.org/10.3390/app12188977 - 7 Sep 2022

Cited by 26 | Viewed by 2530

Abstract

For safe path planning of unmanned aerial vehicles (UAVs) in a three-dimensional (3D) environment with multiple threats, first, a cost function is introduced according to the terrain constraints and UAV overall performance constraints of the path planning problem. Then, improved nonlinear dynamic inertia [...] Read more.

For safe path planning of unmanned aerial vehicles (UAVs) in a three-dimensional (3D) environment with multiple threats, first, a cost function is introduced according to the terrain constraints and UAV overall performance constraints of the path planning problem. Then, improved nonlinear dynamic inertia weights (INDIW) are introduced into the particle swarm optimization (PSO) algorithm, and when the particles fall into the local optimum, the velocity is perturbed, and the velocity and improved nonlinear dynamic inertia weight PSO (VAINDIWPSO) algorithm are obtained. The algorithm improves the speed of convergence and fitness function value of the PSO algorithm. However, the impact of flyable path optimization is now not obvious. Therefore, to further enhance the overall performance of the VAINDIWPSO algorithm, the adaptive adjustment of the velocity is introduced, the chaotic initialization is carried out, and the improved logistic chaotic map is introduced into the algorithm, and an improved chaotic-VAINDIWPSO (IC-VAINDIWPSO) algorithm is obtained. Then, the corresponding relationship between the algorithm and constraints is used to efficiently search complicated environments and find paths with excessive security and small cost function. The simulation outcomes exhibit that in a complicated environment the IC-VAINDIWPSO algorithm substantially improves the speed of convergence of the algorithm, reduces the fitness function value of the algorithm and the initialization time of the algorithm, and the acquired path is additionally smoother. A near-optimal solution is obtained. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

15 pages, 1791 KiB

Open AccessArticle

Adaptive Industrial Control System Attack Sample Expansion Algorithm Based on Generative Adversarial Network

by Yun Sha, Zhaoyu Chen, Xuejun Liu, Yong Yan, Chenchen Du, Jiayi Liu and Ranran Han

Appl. Sci. 2022, 12(17), 8889; https://doi.org/10.3390/app12178889 - 5 Sep 2022

Cited by 3 | Viewed by 1459

Abstract

The scarcity of attack samples is the bottleneck problem of anomaly detection of underlying business data in the industrial control system. Predecessors have done a lot of research on temporal data generation, but most of them are not suitable for industrial control attack [...] Read more.

The scarcity of attack samples is the bottleneck problem of anomaly detection of underlying business data in the industrial control system. Predecessors have done a lot of research on temporal data generation, but most of them are not suitable for industrial control attack sample generation. The change patterns of the characteristics of the underlying business data attack samples can be divided into three types: oscillation type, step type, and pulse type. This paper proposes an adaptive industrial control attack sample expansion algorithm based on GAN, which expands the three types of features in different ways. The basic network structure of data expansion adopts GAN. According to the characteristics of oscillation type changes, momentum is selected as the optimizer. Aiming at the characteristics of step type changes, the Adam optimization method is improved. For pulse type features, attack samples are generated according to the location and length of the pulse. Compared with previous time-series data generation methods, this method is more targeted for each feature and has higher similarities. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

11 pages, 880 KiB

Open AccessArticle

Research on Unsupervised Classification Algorithm Based on SSVEP

by Yingnian Wu, Rui Yang, Wenbai Chen, Xin Li and Jiaxin Niu

Appl. Sci. 2022, 12(16), 8274; https://doi.org/10.3390/app12168274 - 18 Aug 2022

Cited by 3 | Viewed by 1578

Abstract

Filter Bank Canonical Correlation Analysis (FBCCA) is used to classify electroencephalography (EEG) signals to overcome insufficient training data for EEG signal classification. This approach is not constrained by the training data or time and also performs unsupervised Steady-State Visual Evoked Potential (SSVEP) classification [...] Read more.

Filter Bank Canonical Correlation Analysis (FBCCA) is used to classify electroencephalography (EEG) signals to overcome insufficient training data for EEG signal classification. This approach is not constrained by the training data or time and also performs unsupervised Steady-State Visual Evoked Potential (SSVEP) classification in a short time, which is easy to extend and optimize. By examining the data set from the Brain–Computer Interface (BCI) contest and comparing it to Canonical Correlation Analysis (CCA) using various parameter settings, the results show that FBCCA carries better classification performance than CCA. When the number of harmonics is 4 and the number of subbands is 5, the identification rate of 40 targets with the frequency difference of 0.2 Hz achieves 88.9%, and the maximum information transfer rate (ITR) achieves 88.64 bits/min, which shows superior compatibility and practicability. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

10 pages, 2883 KiB

Open AccessArticle

Analysis and Prediction Research for Bipropellant Thruster Mixture Ratio Based on BP-RNN Chain Method

by Zhen Zhang, Hao Yan, Kun Cai, Shangfeng Yang, Fengshan Wang, Xiaofang Mao and Yusong Yu

Appl. Sci. 2022, 12(16), 7956; https://doi.org/10.3390/app12167956 - 9 Aug 2022

Viewed by 2149

Abstract

In order to improve the mixture ratio accuracy of the bipropellant thruster and prolong the service life of a satellite on orbit, a variety of different liquid-flow tests and the final firing test are critical in the production testing process. However, after comparison [...] Read more.

In order to improve the mixture ratio accuracy of the bipropellant thruster and prolong the service life of a satellite on orbit, a variety of different liquid-flow tests and the final firing test are critical in the production testing process. However, after comparison with a large number of tests data, it was found that the liquid-flow test results were far away from matching the firing-test data without clear regularity, resulting in a qualified rate of mixture ratio of less than 40%. This study developed a BP-RNN (back propagation—recurrent neural network) chain method based on machine learning, which uses multi-dimensional nonlinear parameters to construct the specific dataset after data enhancement. Then, the mapping characteristic of the neural network was used to fit the historical data for the weight analysis and mixture ratio prediction, and effectively improved the qualified rate of the mixture ratio. The back propagation neural network was used to learn the association rules of the 10-dimension characteristic data and the firing test results generated in the historical process of thruster production. Then, the features with high influencing weight were extracted and sorted, so the “many-to-one” mixture ratio prediction was conducted through the subsequent recurrent neural network. The accepted prediction accuracy could reach around 75% after the test data verification. By using this method, most of bipropellant thrusters could directly reach the qualified mixture ratio in the firing test after adjusting the throttle orifice size in the liquid-flow tests. This chain method first bridges the data between the liquid-flow test and the firing test. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

15 pages, 589 KiB

Open AccessArticle

Extension Design Model of Rapid Configuration Design for Complex Mechanical Products Scheme Design

by Tichun Wang, Hao Li and Xianwei Wang

Appl. Sci. 2022, 12(15), 7921; https://doi.org/10.3390/app12157921 - 7 Aug 2022

Cited by 3 | Viewed by 1763

Abstract

This study explores the extension configuration methods of complex product conceptual design, seeking to improve the product design efficiency and design quality. The paper firstly reviews the literature on element representation models of multi-type design knowledge, followed by a review on extension design [...] Read more.

This study explores the extension configuration methods of complex product conceptual design, seeking to improve the product design efficiency and design quality. The paper firstly reviews the literature on element representation models of multi-type design knowledge, followed by a review on extension design models for the rapid configuration of complex product conceptual design. The extension transformation method for the rapid configuration design of complex product conceptual design is also reviewed. With the analysis of the extension reasoning model for the rapid configuration design of complex product conceptual design, the research proposes a new model of extension reasoning for the rapid configuration design of complex product conceptual design. This model of extension design would enhance the rapid configuration design and conceptual design of large and complex products. Detailed steps of the algorithm implementation are also presented. This study also tests the validity and operability of the model and the algorithm with the design case of a large hydro-turbine product design. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 3493 KiB

Open AccessArticle

Fv-AD: F-AnoGAN Based Anomaly Detection in Chromate Process for Smart Manufacturing

by Chanho Park, Sumin Lim, Daniel Cha and Jongpil Jeong

Appl. Sci. 2022, 12(15), 7549; https://doi.org/10.3390/app12157549 - 27 Jul 2022

Cited by 3 | Viewed by 2951

Abstract

Anomaly detection for quality prediction has recently become important, as data collection has increased in various fields, such as smart factories and healthcare systems. Various attempts have been made in the existing manufacturing process to improve discrimination accuracy due to data imbalance in [...] Read more.

Anomaly detection for quality prediction has recently become important, as data collection has increased in various fields, such as smart factories and healthcare systems. Various attempts have been made in the existing manufacturing process to improve discrimination accuracy due to data imbalance in the anomaly detection model. Predicting the quality of a chromate process has a significant influence on the completeness of the process, and anomaly detection is important. Furthermore, obtaining image data, such as monitoring during the manufacturing process, is difficult, and prediction is challenging owing to data imbalance. Accordingly, the model employs an unsupervised learning-based Generative Adversarial Networks (GAN) model, performs learning with only normal data images, and augments the Fast Unsupervised Anomaly Detection with GAN (F-AnoGAN) base with a visualization component to provide a more intuitive judgment of defects with chromate process data. In addition, anomaly scores are calculated based on mapping in the latent space, and new data are applied to confirm anomaly detection and the corresponding location values. As a result, this paper presents a GAN architecture to detect anomalies through chromate facility data in a smart manufacturing environment. It proved meaningful performance and added visualization parts to provide explainable interpretation. Data experiments on the chromate process show that the loss value, anomaly score, and anomaly position are accurately distinguished from abnormal images. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 2961 KiB

Open AccessArticle

Reinforcement-Learning-Based Tracking Control with Fixed-Time Prescribed Performance for Reusable Launch Vehicle under Input Constraints

by Shihao Xu, Yingzi Guan, Changzhu Wei, Yulong Li and Lei Xu

Appl. Sci. 2022, 12(15), 7436; https://doi.org/10.3390/app12157436 - 24 Jul 2022

Cited by 4 | Viewed by 2146

Abstract

This paper proposes a novel reinforcement learning (RL)-based tracking control scheme with fixed-time prescribed performance for a reusable launch vehicle subject to parametric uncertainties, external disturbances, and input constraints. First, a fixed-time prescribed performance function is employed to restrain attitude tracking errors, and [...] Read more.

This paper proposes a novel reinforcement learning (RL)-based tracking control scheme with fixed-time prescribed performance for a reusable launch vehicle subject to parametric uncertainties, external disturbances, and input constraints. First, a fixed-time prescribed performance function is employed to restrain attitude tracking errors, and an equivalent unconstrained system is derived via an error transformation technique. Then, a hyperbolic tangent function is incorporated into the optimal performance index of the unconstrained system to tackle the input constraints. Subsequently, an actor-critic RL framework with super-twisting-like sliding mode control is constructed to establish a practical solution for the optimal control problem. Benefiting from the proposed scheme, the robustness of the RL-based controller against unknown dynamics is enhanced, and the control performance can be qualitatively prearranged by users. Theoretical analysis shows that the attitude tracking errors converge to a preset region within a preassigned fixed time, and the weight estimation errors of the actor-critic networks are uniformly ultimately bounded. Finally, comparative numerical simulation results are provided to illustrate the effectiveness and improved performance of the proposed control scheme. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

18 pages, 1187 KiB

Open AccessArticle

Scorecard Model-Based Motion Stability Evaluation of Manipulators for Robot Training

by Mingming Lin and Li Xu

Appl. Sci. 2022, 12(14), 7100; https://doi.org/10.3390/app12147100 - 14 Jul 2022

Viewed by 1306

Abstract

Motion stability is vital for the industrial application of robotic manipulators; therefore, its evaluation becomes an important task for robot training. This paper proposes an evaluation system based on the scorecard model to evaluate the stability performance of manipulators. Firstly, the wavelet modulus [...] Read more.

Motion stability is vital for the industrial application of robotic manipulators; therefore, its evaluation becomes an important task for robot training. This paper proposes an evaluation system based on the scorecard model to evaluate the stability performance of manipulators. Firstly, the wavelet modulus maximum filtering method is employed to divide the vibration signal into structural vibration components and motion-generated vibration components. Secondly, the evaluation index (EI) is designed based on the processed data to judge whether the vibration signal of the moving process is stable. Finally, the scorecard model is proposed to evaluate the stability of vibration samples, including the process of attribute extraction, binning, WOE coding, feature selection, logistic regression, and score transformation. Additionally, an endpoint localization method is employed to segment the vibration signal of a continuously moving manipulator into single-step motion segments, making it possible to score the motion subprocesses. Experiments are conducted on physical robotic arms to verify the effectiveness of the proposed scheme, and the results show that the model can reasonably score the motion stability of robotic arms for robot training. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

17 pages, 4903 KiB

Open AccessArticle

A Generalized Dynamic Model and Coupling Meshing Force Analysis for Planetary Gear Set Transmissions

by Haiwei Wang, Cheng Ji, Fengxia Lu, Cheng Wang and Xueyan Sun

Appl. Sci. 2022, 12(12), 6279; https://doi.org/10.3390/app12126279 - 20 Jun 2022

Viewed by 2073

Abstract

The dynamics analysis of a planetary gear set transmissions requires the creation of completely different models for different gears, which is very tedious. In this paper, a generalized dynamics modeling process is proposed for a three planetary gear set transmissions, and a generalized [...] Read more.

The dynamics analysis of a planetary gear set transmissions requires the creation of completely different models for different gears, which is very tedious. In this paper, a generalized dynamics modeling process is proposed for a three planetary gear set transmissions, and a generalized dynamic model for multiple gears is established by using the lumped mass method. The analysis of meshing force characteristics is carried out for the second gear position, and the meshing frequency coupling phenomenon between the meshing forces of the three planetary gear sets is investigated. The results show that, for the current gear set of meshing force, the meshing frequency components of other gear sets only appear in a part of the speed, and with the increase in speed, certain low-frequency components of other sets that exist at low speed will decrease or even disappear, and the coupling relationship between the meshing forces of different planetary gear sets is not symmetrical. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

10 pages, 2436 KiB

Open AccessArticle

Cavitation Erosion Characteristics for Different Metal Surface and Influencing Factors in Water Flowing System

by Jie He, Xiumei Liu, Beibei Li, Jixing Zhai and Jiaqing Song

Appl. Sci. 2022, 12(12), 5840; https://doi.org/10.3390/app12125840 - 8 Jun 2022

Cited by 9 | Viewed by 2419

Abstract

The impact of cavitation erosion behavior on different metals in a water flowing system was investigated experimentally. A flowing system of water was built and a transparent observation window is designed to capture the cavitation flow. Erosion tests were carried out on red [...] Read more.

The impact of cavitation erosion behavior on different metals in a water flowing system was investigated experimentally. A flowing system of water was built and a transparent observation window is designed to capture the cavitation flow. Erosion tests were carried out on red copper, brass, pure aluminum, and an aluminum alloy. The cavitation behaviors are presented by the weight loss and cavitation erosion rate, and related changes in the topography of the metal surface are also discussed. The variation in the cavitation erosion on metallic specimens with increasing time could be divided into three stages: rising stage, stable stage, and attenuation stage. The pure aluminum material had the lowest yield strength, and suffered the most severe cavitation erosion while brass had the highest yield strength and good mechanical properties, which suffered the least cavitation erosion. Furthermore, the roughness of the material surface was also one of the important factors affecting the cavitation erosion rate. The weight loss of milling specimens with higher surface roughness was slightly lower than that of grinding. The high roughness of the metallic surface increased the pressure loss along the flow path and the suppressed cavitation strength. This work provides an experimental reference for the anti-cavitation ability improvement in metal materials and promotes an understanding of the related mechanism. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 4973 KiB

Open AccessArticle

Study on the Position Deviation between the Iron Roughneck’s Spin-Rollers and the Drilling Tool

by Yongbai Sha, Quan Li and Xiaoying Zhao

Appl. Sci. 2022, 12(12), 5827; https://doi.org/10.3390/app12125827 - 8 Jun 2022

Cited by 1 | Viewed by 1835

Abstract

The spinner mechanism is one of the main working mechanisms of the iron roughneck, which is used to realize the rapid screwing-in or screwing-out of the drill pipe thread. The main problems of the spinner mechanism and the existing solutions are analyzed in [...] Read more.

The spinner mechanism is one of the main working mechanisms of the iron roughneck, which is used to realize the rapid screwing-in or screwing-out of the drill pipe thread. The main problems of the spinner mechanism and the existing solutions are analyzed in this paper, and the spinner mechanism driven by a single hydraulic cylinder and transmitted by a wedge plate is designed. The upper and lower drilling tools are not concentric and affect the spin effect when the spinner mechanism works, and to address this problem, the influence of deviation in different directions is analyzed, and it is proposed that the lateral position deviation of drilling tools is the key factor affecting the spin performance. The relationship between the position deviation of the spin-roller and the position deviation of the drilling tool is established and solved. A method to reduce the lateral position deviation of drilling tools is proposed, and the effectiveness of this method is verified by experiments. The analysis shows that a spinner mechanism with a single follow-up roller easily causes the lateral position deviation of the drilling tool; the deviation of the spin-roller increases with the increase of the lateral deviation of the drilling tool, and the increase of the longitudinal deviation is more obvious; and with the increase of the drilling tool’s diameter, the deviation increases further. The symmetrical double follow-up roller structure can effectively reduce the lateral deviation of drilling tools and spin-rollers and ensures centering performance and the realization of reliable spin. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

22 pages, 6756 KiB

Open AccessArticle

Research on Meshing Characteristics of Trochoidal Roller Pinion Rack Transmission

by Haiwei Wang, Lulu Li and Geng Liu

Appl. Sci. 2022, 12(11), 5620; https://doi.org/10.3390/app12115620 - 1 Jun 2022

Viewed by 2344

Abstract

As a precision transmission mechanism, the trochoidal roller pinion rack has been paid more and more attention in recent years, but its meshing characteristics have not been deeply explored. In order to investigate the meshing characteristics of the trochoidal roller pinion rack transmission, [...] Read more.

As a precision transmission mechanism, the trochoidal roller pinion rack has been paid more and more attention in recent years, but its meshing characteristics have not been deeply explored. In order to investigate the meshing characteristics of the trochoidal roller pinion rack transmission, it is particularly important to research its line of action and meshing stiffness. The equation of the line of action of the trochoidal roller pinion rack is deduced by using its tooth profile formation principle. The motion simulation of the trochoidal roller pinion rack transmission is carried out to verify the correctness of the theoretical derivation of the equation of the line of action, and the influence of the basic parameters on the line of action is summarized. The meshing stiffness of the trochoidal roller pinion rack is calculated based on the energy method used for gear meshing stiffness, and the meshing stiffness is defined considering the time-varying characteristics of its pressure angle, and the influence of each basic parameter on the meshing stiffness is studied. The results shows that the meshing stiffness increases first and then decreases in the double tooth meshing area, while the meshing stiffness gradually decreases in the single tooth meshing area. The basic parameters including number of roller pins, the module, the rack tooth profile offset coefficient, the diameter coefficient of roller pin, and the addendum coefficient of rack have different effects on the line of action and meshing stiffness. The research conclusion can provide reference for the parameter design of the trochoidal roller pinion rack, and provide the meshing stiffness calculation method for the dynamic analysis of the transmission. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

16 pages, 27530 KiB

Open AccessArticle

Design and Mechanical Performance of a Fiber-Constrained Annular Flexible Actuator for Direct Ventricular Assist Devices

by Zhong Yun, Chuanchuan Mei, Kang Xu, Xiaoyan Tang and Yunhao Feng

Appl. Sci. 2022, 12(11), 5405; https://doi.org/10.3390/app12115405 - 26 May 2022

Viewed by 1757

Abstract

With the development of various new intelligent materials, pneumatic artificial muscles are becoming widely used as actuators in industry, with their advantages of having a simple and compact structure, smooth action, fast response and movement closer to natural biological muscle movement. This paper [...] Read more.

With the development of various new intelligent materials, pneumatic artificial muscles are becoming widely used as actuators in industry, with their advantages of having a simple and compact structure, smooth action, fast response and movement closer to natural biological muscle movement. This paper introduced the concept of a fiber-constrained flexible actuator for direct ventricular assist devices. The structural parameters of the actuator were initially determined based on the morphology of the human heart; the model of the flexible body with fibers and strain limiting layer was then constructed using SOLIDWORKS; then, the model was imported into the ABAQUS finite element analysis software for simulation in order to determine the feasibility of the structural solution; finally, the structural parameters of the actuator were optimized based on the simulation results. In order to investigate whether the actuator could cause damage to myocardial tissue when squeezing the heart, the actuator was tested for the displacement and the output force. The results showed that fiber-constrained direct ventricular assist devices did not damage the myocardium while assisting the heart to pump blood; moreover, their blood output could meet the requirements of both types of heart failure patients. The annular flexible actuator can provide effective compression of the ventricle and twist at an angle during inflation. This twist adapts to the torsional requirements of the heart, and reduces sliding friction between the device and the heart surface, thereby reducing myocardial damage. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

15 pages, 3272 KiB

Open AccessArticle

An Intelligent Nonlinear Control Method for the Multistage Electromechanical Servo System

by Yunxiao Lian, Yong Zhou, Jianxin Zhang, Shangjun Ma and Shuai Wu

Appl. Sci. 2022, 12(10), 5053; https://doi.org/10.3390/app12105053 - 17 May 2022

Cited by 2 | Viewed by 1491

Abstract

In order to meet the requirements of servo systems, including sensitive and rapid adjustment, high control and motion accuracy, and strong working adaptability, in special application fields, such as high thrust and long travel, an adaptive inversion control method is proposed for the [...] Read more.

In order to meet the requirements of servo systems, including sensitive and rapid adjustment, high control and motion accuracy, and strong working adaptability, in special application fields, such as high thrust and long travel, an adaptive inversion control method is proposed for the lateral force and other nonlinear factors of multistage electromechanical servo system (MEMSS). The position tracking controller of permanent magnet synchronous motor (PMSM), based on an improved adaptive inversion method, was designed and its stability was analyzed, and the Luenberger load torque observer model of PMSM was established. The EMESS simulation model of an adaptive inversion controller was built using the Simulink platform, and the motor multibody dynamics model was established in ADAMS software. Through the joint simulation of Simulink and ADAMS software, the results of EMESS under adaptive inversion controller and traditional PID controller were compared, and the feasibility and reliability of the designed adaptive inversion controller were verified. Finally, the designed controller was tested based on the experimental platform. The experimental results show that the adaptive inversion controller designed in this paper has better robustness and stability than the traditional PID controller. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

Review

Jump to: Research

33 pages, 5131 KiB

Open AccessReview

Re-Thinking Data Strategy and Integration for Artificial Intelligence: Concepts, Opportunities, and Challenges

by Abdulaziz Aldoseri, Khalifa N. Al-Khalifa and Abdel Magid Hamouda

Appl. Sci. 2023, 13(12), 7082; https://doi.org/10.3390/app13127082 - 13 Jun 2023

Cited by 91 | Viewed by 91251

Abstract

The use of artificial intelligence (AI) is becoming more prevalent across industries such as healthcare, finance, and transportation. Artificial intelligence is based on the analysis of large datasets and requires a continuous supply of high-quality data. However, using data for AI is not [...] Read more.

The use of artificial intelligence (AI) is becoming more prevalent across industries such as healthcare, finance, and transportation. Artificial intelligence is based on the analysis of large datasets and requires a continuous supply of high-quality data. However, using data for AI is not without challenges. This paper comprehensively reviews and critically examines the challenges of using data for AI, including data quality, data volume, privacy and security, bias and fairness, interpretability and explainability, ethical concerns, and technical expertise and skills. This paper examines these challenges in detail and offers recommendations on how companies and organizations can address them. By understanding and addressing these challenges, organizations can harness the power of AI to make smarter decisions and gain competitive advantage in the digital age. It is expected, since this review article provides and discusses various strategies for data challenges for AI over the last decade, that it will be very helpful to the scientific research community to create new and novel ideas to rethink our approaches to data strategies for AI. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

15 pages, 1389 KiB

Open AccessReview

The Progress on Lung Computed Tomography Imaging Signs: A Review

by Hanguang Xiao, Yuewei Li, Bin Jiang, Qingling Xia, Yujia Wei and Huanqi Li

Appl. Sci. 2022, 12(18), 9367; https://doi.org/10.3390/app12189367 - 19 Sep 2022

Viewed by 1884

Abstract

Lung cancer is the highest-mortality cancer with the largest number of patients in the world. Early screening and diagnosis of lung cancer by CT imaging is of great significance to improve the cure rate of lung cancer. CT signs mean the information of [...] Read more.

Lung cancer is the highest-mortality cancer with the largest number of patients in the world. Early screening and diagnosis of lung cancer by CT imaging is of great significance to improve the cure rate of lung cancer. CT signs mean the information of comprehensive manifestations of diseases at different pathological stages and levels. Automatic analysis of CT images outputs the locations and sizes of lesion regions which can help radiologists to make a credible diagnosis and effectively improve the speed and accuracy of clinical diagnosis. In this paper, we first review the domestic and foreign research progress of lung CT signs, summarize a generic structure for expressing the implementation process of existing methods, and systematically describe the signs research based on the traditional machine learning method and deep learning method. Furthermore, we provide a systematic summary and comparative analysis of the existing methods. Finally, we point out the challenges ahead and discuss the directions for improvement of future work, providing reference for scholars in related fields. Full article

(This article belongs to the Special Issue AI Applications in the Industrial Technologies)

► Show Figures

Figure 1

Journal Menu

Journal Browser

AI Applications in the Industrial Technologies

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (36 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI