Industrial Machine Learning Application

A special issue of Journal of Imaging (ISSN 2313-433X). This special issue belongs to the section "AI in Imaging".

Deadline for manuscript submissions: closed (20 December 2022) | Viewed by 16642

Special Issue Editors

Department of Engineering and Computer Science, University of Trento, Via Sommarive 9, I-38123 Trento, Italy
Interests: action recognition; image and video understanding

E-Mail Website
Guest Editor
Department of Systems and Informatics, Setubal School of Technology, Polytechnic Institute of Setubal, Campus do IPS, Estefanilha, 2910-761 Setubal, Portugal
Interests: computer vision; machine (deep) learning; data science; artificial intelligence; industry 4.0/5.0; biomedical image and data analysis; medical imaging
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science, University of Verona, 37134 Verona, Italy
Interests: machine learning; artificial intelligence; computer vision; human-robot interaction; multimodal learning; cognitive robotics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

With the advent of Industry 4.0 and Smart Manufacturing paradigms, data have become a valuable resource, and very often an asset, for every manufacturing company. Data from the market, from machines, from warehouses, and from many other sources are now cheaper than ever to collect and store. A study from Juniper Research has identified industrial Internet of Things (IIoT) as a key growth market over the next five years, accounting for an increase in the global number of IIoT connections from 17.7 billion in 2020 to 36.8 billion in 2025, representing an overall growth rate of 107%. With such an amount of data produced every second, classical data analysis approaches are not useful, and only automated learning methods can be applied to produce value, a market estimated at more than 200 billion USD worldwide. Using machine learning techniques, manufacturers can exploit data to significantly impact their bottom line by greatly improving production efficiency, product quality, and employee safety.

The introduction of ML to industry has many benefits that can result in advantages well beyond efficiency improvements, opening doors to new opportunities for both practitioners and researchers. Some direct applications of ML in manufacturing include predictive maintenance, supply chain management, logistics, quality control, human–robot interaction, process monitoring, anomaly detection, and root cause analysis, to name a few.

Topics of Interest

This is an open call for papers, soliciting original contributions considering recent findings in theory, methodologies, and applications in the field of industrial machine learning. Potential topics include but are not limited to:

  • Robustness-oriented learning algorithms;
  • Machine learning for robotics (e.g., learning from demonstration);
  • Continuous and lifelong learning for industrial applications;
  • Transfer learning and domain adaptation;
  • Anomaly detection and process monitoring;
  • ML applications to predictive maintenance;
  • ML applications to supply chain and logistics;
  • ML applications to quality control;
  • ML for flexible manufacturing;
  • Deep learning for industrial applications;
  • Learning from big data;
  • Inference in real-time applications;
  • Machine learning on embedded and edge computing hardware;
  • Multimodal learning for industrial applications;
  • Semantic representation of machine learning models.

All contributions are expected to focus on applications to the industrial sector, possibly with real-world case studies. Position papers presenting new industrial systems and case studies, possibly reporting preliminary validation studies, are also encouraged.

Dr. Paolo Rota
Prof. Dr. Miguel Angel Guevara Lopez
Dr. Francesco Setti
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

2 pages, 161 KiB  
Editorial
Editorial for the Special Issue on Industrial Machine Learning Applications
by Paolo Rota, Miguel Angel Guevara Lopez and Francesco Setti
J. Imaging 2023, 9(12), 278; https://doi.org/10.3390/jimaging9120278 - 14 Dec 2023
Viewed by 1550
Abstract
In the rapidly evolving field of industrial machine learning, this Special Issue on Industrial Machine Learning Applications aims to shed light on the innovative strides made toward more intelligent, more efficient, and adaptive industrial processes [...] Full article
(This article belongs to the Special Issue Industrial Machine Learning Application)

Research

Jump to: Editorial

23 pages, 14839 KiB  
Article
6D Object Localization in Car-Assembly Industrial Environment
by Alexandra Papadaki and Maria Pateraki
J. Imaging 2023, 9(3), 72; https://doi.org/10.3390/jimaging9030072 - 20 Mar 2023
Cited by 5 | Viewed by 3009
Abstract
In this work, a visual object detection and localization workflow integrated into a robotic platform is presented for the 6D pose estimation of objects with challenging characteristics in terms of weak texture, surface properties and symmetries. The workflow is used as part of [...] Read more.
In this work, a visual object detection and localization workflow integrated into a robotic platform is presented for the 6D pose estimation of objects with challenging characteristics in terms of weak texture, surface properties and symmetries. The workflow is used as part of a module for object pose estimation deployed to a mobile robotic platform that exploits the Robot Operating System (ROS) as middleware. The objects of interest aim to support robot grasping in the context of human–robot collaboration during car door assembly in industrial manufacturing environments. In addition to the special object properties, these environments are inherently characterised by cluttered background and unfavorable illumination conditions. For the purpose of this specific application, two different datasets were collected and annotated for training a learning-based method that extracts the object pose from a single frame. The first dataset was acquired in controlled laboratory conditions and the second in the actual indoor industrial environment. Different models were trained based on the individual datasets and a combination of them were further evaluated in a number of test sequences from the actual industrial environment. The qualitative and quantitative results demonstrate the potential of the presented method in relevant industrial applications. Full article
(This article belongs to the Special Issue Industrial Machine Learning Application)
Show Figures

Figure 1

20 pages, 8537 KiB  
Article
Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks
by André Antunes, Bruno Ferreira, Nuno Marques and Nelson Carriço
J. Imaging 2023, 9(3), 68; https://doi.org/10.3390/jimaging9030068 - 14 Mar 2023
Cited by 3 | Viewed by 4318
Abstract
The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training [...] Read more.
The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level. Full article
(This article belongs to the Special Issue Industrial Machine Learning Application)
Show Figures

Figure 1

23 pages, 3320 KiB  
Article
Transfer-Learning-Based Estimation of the Remaining Useful Life of Heterogeneous Bearing Types Using Low-Frequency Accelerometers
by Sebastian Schwendemann and Axel Sikora
J. Imaging 2023, 9(2), 34; https://doi.org/10.3390/jimaging9020034 - 4 Feb 2023
Cited by 7 | Viewed by 2335
Abstract
Deep learning approaches are becoming increasingly important for the estimation of the Remaining Useful Life (RUL) of mechanical elements such as bearings. This paper proposes and evaluates a novel transfer learning-based approach for RUL estimations of different bearing types with small datasets and [...] Read more.
Deep learning approaches are becoming increasingly important for the estimation of the Remaining Useful Life (RUL) of mechanical elements such as bearings. This paper proposes and evaluates a novel transfer learning-based approach for RUL estimations of different bearing types with small datasets and low sampling rates. The approach is based on an intermediate domain that abstracts features of the bearings based on their fault frequencies. The features are processed by convolutional layers. Finally, the RUL estimation is performed using a Long Short-Term Memory (LSTM) network. The transfer learning relies on a fixed-feature extraction. This novel deep learning approach successfully uses data of a low-frequency range, which is a precondition to use low-cost sensors. It is validated against the IEEE PHM 2012 Data Challenge, where it outperforms the winning approach. The results show its suitability for low-frequency sensor data and for efficient and effective transfer learning between different bearing types. Full article
(This article belongs to the Special Issue Industrial Machine Learning Application)
Show Figures

Figure 1

23 pages, 9974 KiB  
Article
Synthetic Data Generation for Automatic Segmentation of X-ray Computed Tomography Reconstructions of Complex Microstructures
by Athanasios Tsamos, Sergei Evsevleev, Rita Fioresi, Francesco Faglioni and Giovanni Bruno
J. Imaging 2023, 9(2), 22; https://doi.org/10.3390/jimaging9020022 - 19 Jan 2023
Cited by 8 | Viewed by 2364
Abstract
The greatest challenge when using deep convolutional neural networks (DCNNs) for automatic segmentation of microstructural X-ray computed tomography (XCT) data is the acquisition of sufficient and relevant data to train the working network. Traditionally, these have been attained by manually annotating a few [...] Read more.
The greatest challenge when using deep convolutional neural networks (DCNNs) for automatic segmentation of microstructural X-ray computed tomography (XCT) data is the acquisition of sufficient and relevant data to train the working network. Traditionally, these have been attained by manually annotating a few slices for 2D DCNNs. However, complex multiphase microstructures would presumably be better segmented with 3D networks. However, manual segmentation labeling for 3D problems is prohibitive. In this work, we introduce a method for generating synthetic XCT data for a challenging six-phase Al–Si alloy composite reinforced with ceramic fibers and particles. Moreover, we propose certain data augmentations (brightness, contrast, noise, and blur), a special in-house designed deep convolutional neural network (Triple UNet), and a multi-view forwarding strategy to promote generalized learning from synthetic data and therefore achieve successful segmentations. We obtain an overall Dice score of 0.77. Lastly, we prove the detrimental effects of artifacts in the XCT data on achieving accurate segmentations when synthetic data are employed for training the DCNNs. The methods presented in this work are applicable to other materials and imaging techniques as well. Successful segmentation coupled with neural networks trained with synthetic data will accelerate scientific output. Full article
(This article belongs to the Special Issue Industrial Machine Learning Application)
Show Figures

Figure 1

14 pages, 4067 KiB  
Article
Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+
by Ping Wang, Chuanxue Li, Qiang Yang, Lin Fu, Fan Yu, Lixiao Min, Dequan Guo and Xinming Li
J. Imaging 2022, 8(10), 257; https://doi.org/10.3390/jimaging8100257 - 21 Sep 2022
Cited by 3 | Viewed by 1890
Abstract
Compared with traditional manual inspection, inspection robots can not only meet the all-weather, real-time, and accurate inspection needs of substation inspection, they also reduce the work intensity of operation and maintenance personnel and decrease the probability of safety accidents. For the urgent demand [...] Read more.
Compared with traditional manual inspection, inspection robots can not only meet the all-weather, real-time, and accurate inspection needs of substation inspection, they also reduce the work intensity of operation and maintenance personnel and decrease the probability of safety accidents. For the urgent demand of substation inspection robot intelligence enhancement, an environment understanding algorithm is proposed in this paper, which is an improved DeepLab V3+ neural network. The improved neural network replaces the original dilate rate combination in the ASPP (atrous spatial pyramid pooling) module with a new dilate rate combination with better segmentation accuracy of object edges and adds a CBAM (convolutional block attention module) in the two up-samplings, respectively. In order to be transplanted to the embedded platform with limited computing resources, the improved neural network is compressed. Multiple sets of comparative experiments on the standard dataset PASCAL VOC 2012 and the substation dataset have been made. Experimental results show that, compared with the DeepLab V3+, the improved DeepLab V3+ has a mean intersection-over-union (mIoU) of eight categories of 57.65% on the substation dataset, with an improvement of 6.39%, and the model size of 13.9 M, with a decrease of 147.1 M. Full article
(This article belongs to the Special Issue Industrial Machine Learning Application)
Show Figures

Figure 1

Back to TopTop