Applied Sciences

Research

15 pages, 2038 KiB

Open AccessArticle

A One-Class-Based Supervision System to Detect Unexpected Events in Wastewater Treatment Plants

by Paula Arcano-Bea, Míriam Timiraos, Antonio Díaz-Longueira, Álvaro Michelena, Esteban Jove and José Luis Calvo-Rolle

Appl. Sci. 2024, 14(12), 5185; https://doi.org/10.3390/app14125185 - 14 Jun 2024

Viewed by 290

Abstract

The increasing importance of water quality has led to optimizing the operation of Wastewater Treatment Plants. This implies the monitoring of many parameters that measure aspects such as solid suspension, conductivity, or chemical components, among others. This paper proposes the use of one-class [...] Read more.

The increasing importance of water quality has led to optimizing the operation of Wastewater Treatment Plants. This implies the monitoring of many parameters that measure aspects such as solid suspension, conductivity, or chemical components, among others. This paper proposes the use of one-class algorithms to learn the normal behavior of a Wastewater Treatment Plants and detect situations in which the crucial parameters of Chemical Oxygen Demand, Ammonia, and Kjeldahl Nitrogen present unexpected deviations. The classifiers are tested using different deviations, achieving successful results. The final supervision systems are capable of detecting critical situation, contributing to decision-making and maintenance effectiveness. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

18 pages, 6562 KiB

Open AccessArticle

Outlier Detection for Permanent Magnet Synchronous Motor (PMSM) Fault Detection and Severity Estimation

by Konstantinos Koutrakos and Epameinondas Mitronikas

Appl. Sci. 2024, 14(10), 4318; https://doi.org/10.3390/app14104318 - 20 May 2024

Viewed by 481

Abstract

Today, Permanent Magnet Synchronous Motors (PMSMs) are a dominant choice in industry applications. During operation, different possible faults in the system can occur, so early and automated fault detection and severity estimation are required to ensure smooth operation and optimal maintenance planning. In [...] Read more.

Today, Permanent Magnet Synchronous Motors (PMSMs) are a dominant choice in industry applications. During operation, different possible faults in the system can occur, so early and automated fault detection and severity estimation are required to ensure smooth operation and optimal maintenance planning. In this direction, outlier detection methods are employed in this paper. The motor’s current signals are used to extract useful indicators of the fault, along with d-q transform. Statistical indicators in both time and frequency domains are selected to describe fault-related patterns. Based on the extracted features, three outlier detection methods are investigated: the Isolation Forest, the One Class Support Vector Machine, and the Robust Covariance Ellipse. Each method is investigated through different model parameters to evaluate fault detection and severity estimation capabilities. Finally, an ensemble approach is proposed based on decisions and outlier score ensemble. The proposed methodology is verified through different operating conditions in a PMSM test bench. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

16 pages, 3170 KiB

Open AccessArticle

Enhancing Reliability in Wind Turbine Power Curve Estimation

by Pere Marti-Puig, Jose Ángel Hernández, Jordi Solé-Casals and Moises Serra-Serra

Appl. Sci. 2024, 14(6), 2479; https://doi.org/10.3390/app14062479 - 15 Mar 2024

Viewed by 718

Abstract

Accurate power curve modeling is essential to continuously evaluate the performance of a wind turbine (WT). In this work, we characterize the wind power curves using SCADA data acquired at a frequency of 5 min in a wind farm (WF) consisting of five [...] Read more.

Accurate power curve modeling is essential to continuously evaluate the performance of a wind turbine (WT). In this work, we characterize the wind power curves using SCADA data acquired at a frequency of 5 min in a wind farm (WF) consisting of five WTs. Regarding the non-parametric methods, we select artificial neural networks (ANNs) to make curve estimations. Given that, we have the curves provided by the manufacturer of the WTs given by some very precisely measured pair of wind speed and power points. We can evaluate the difference between the manufacturer characterization and the ones estimated with the data provided by the SCADA system. Before the estimation, we propose a method of filtering the anomalies based on the characteristics provided by the manufacturer. We use three-quarters of the available data for curve estimation and one-quarter for the test. One WT suffered a break in the test part, so we can check how the test estimates reflect this problem in its wind-power curve compared to the estimations obtained in the WTs that worked adequately. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

17 pages, 4858 KiB

Open AccessArticle

Improved Adversarial Transfer Network for Bearing Fault Diagnosis under Variable Working Conditions

by Jun Wang, Hosameldin Ahmed, Xuefeng Chen, Ruqiang Yan and Asoke K. Nandi

Appl. Sci. 2024, 14(6), 2253; https://doi.org/10.3390/app14062253 - 7 Mar 2024

Viewed by 654

Abstract

Bearings are one of the critical components of rotating machinery, and their failure can cause catastrophic consequences. In this regard, previous studies have proposed a variety of intelligent diagnosis methods. Most existing bearing fault diagnosis methods implicitly assume that the training and test [...] Read more.

Bearings are one of the critical components of rotating machinery, and their failure can cause catastrophic consequences. In this regard, previous studies have proposed a variety of intelligent diagnosis methods. Most existing bearing fault diagnosis methods implicitly assume that the training and test sets are from the same distribution. However, in real scenarios, bearings have been working in complex and changeable working environments for a long time. The data during their working processes and the data used for model training cannot meet this condition. This paper proposes an improved adversarial transfer network for fault diagnosis under variable working conditions. Specifically, this paper combines an adversarial transfer network with a short-time Fourier transform to obtain satisfactory results with the lighter network. Then, this paper employs a channel attention module to enhance feature fusion. Moreover, this paper designs a novel domain discrepancy hybrid metric loss to improve model transfer learning performance. Finally, this paper verifies the method’s effectiveness on three datasets, including dual-rotor, a Case Western Reserve University dataset and the Ottawa dataset. The proposed method achieves average accuracy, surpassing other methods, and shows better domain alignment capabilities. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

20 pages, 3725 KiB

Open AccessArticle

Pruning Quantized Unsupervised Meta-Learning DegradingNet Solution for Industrial Equipment and Semiconductor Process Anomaly Detection and Prediction

by Yi-Cheng Yu, Shiau-Ru Yang, Shang-Wen Chuang, Jen-Tzung Chien and Chen-Yi Lee

Appl. Sci. 2024, 14(5), 1708; https://doi.org/10.3390/app14051708 - 20 Feb 2024

Viewed by 672

Abstract

Machine- and deep-learning methods are used for industrial applications in prognostics and health management (PHM) for semiconductor processing and equipment anomaly detection to achieve proactive equipment maintenance and prevent process interruptions or equipment downtime. This study proposes a Pruning Quantized Unsupervised Meta-learning DegradingNet [...] Read more.

Machine- and deep-learning methods are used for industrial applications in prognostics and health management (PHM) for semiconductor processing and equipment anomaly detection to achieve proactive equipment maintenance and prevent process interruptions or equipment downtime. This study proposes a Pruning Quantized Unsupervised Meta-learning DegradingNet Solution (PQUM-DNS) for the fast training and retraining of new equipment or processes with limited data for anomaly detection and the prediction of various equipment and process conditions. This study utilizes real data from a factory chiller host motor, the Paderborn current and vibration open dataset, and the SECOM semiconductor open dataset to conduct experimental simulations, calculate the average value, and obtain the results. Compared to conventional deep autoencoders, PQUM-DNS reduces the average data volume required for rapid training and retraining by about 75% with similar AUC. The average RMSE of the predictive degradation degree is 0.037 for Holt–Winters, and the model size is reduced by about 60% through pruning and quantization which can be realized by edge devices, such as Raspberry Pi. This makes the proposed PQUM-DNS very suitable for intelligent equipment management and maintenance in industrial applications. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

15 pages, 3344 KiB

Open AccessArticle

Genetic Multi-Objective Optimization of Sensor Placement for SHM of Composite Structures

by Tomasz Rogala, Mateusz Ścieszka, Andrzej Katunin and Sandris Ručevskis

Appl. Sci. 2024, 14(1), 456; https://doi.org/10.3390/app14010456 - 4 Jan 2024

Cited by 1 | Viewed by 978

Abstract

Increasingly often, due to the high sensitivity level of diagnostic systems, they are also sensitive to the occurrence of a significant number of false alarms. In particular, in structural health monitoring (SHM), the problem of optimal sensor placement (OSP) is appearing due to [...] Read more.

Increasingly often, due to the high sensitivity level of diagnostic systems, they are also sensitive to the occurrence of a significant number of false alarms. In particular, in structural health monitoring (SHM), the problem of optimal sensor placement (OSP) is appearing due to the need to reach a balance between performance and cost of the diagnostic system. The applied approach of considering nondominated solutions allows for adaption of the system parameters to the user’s expectations, treating this optimization problem as multi-objective. For this purpose, the NSGA-II algorithm was selected for the determination of an optimal set of parameters in the OSP problem for the detection of delamination in composite structures. The objectives comprise minimization of type-I and type-II errors, and number of sensors to be placed. The advantage of the proposed approach is that it is based on experimental data from the healthy structure, whereas all cases with a presence of delamination were acquired from numerical experiments. This makes it possible to develop a customized SHM system for the arbitrary location of damage. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

27 pages, 22302 KiB

Open AccessArticle

Early Prediction of Remaining Useful Life for Rolling Bearings Based on Envelope Spectral Indicator and Bayesian Filter

by Haobin Wen, Long Zhang and Jyoti K. Sinha

Appl. Sci. 2024, 14(1), 436; https://doi.org/10.3390/app14010436 - 3 Jan 2024

Cited by 1 | Viewed by 941

Abstract

On top of the condition-based maintenance (CBM) practice for rotating machinery, the robust estimation of remaining useful life (RUL) for rolling-element bearings (REB) is of particular interest. The failure of a single bearing often results in secondary defects in the connected structure and [...] Read more.

On top of the condition-based maintenance (CBM) practice for rotating machinery, the robust estimation of remaining useful life (RUL) for rolling-element bearings (REB) is of particular interest. The failure of a single bearing often results in secondary defects in the connected structure and catastrophic system failures. The prediction of RUL facilitates proactive maintenance planning to ensure system reliability and minimize financial loss due to unscheduled downtime. In this paper, to acquire early and reliable estimations of useful life, the RUL prediction of REBs is formulated into nonlinear degradation state estimation tackled by the combination of the envelope spectral indicator (ESI) and extended Kalman filter (EKF). By fusing the spectral energy of the bearing fault characteristic frequencies (FCFs) in the averaged envelope spectrum, the ESI is crafted to remove the interference from rotor-dynamics and reveal the bearing deterioration process. Once the fault is identified, the recursive Bayesian method based on EKF is utilized for estimating the bearing end-of-life time via the exponential state-space model. The distinctive advantage of the proposed approach lies in its ability to make an early prediction of RUL using a small number of ESI observations, offering an efficient practice for predictive health management at the early stage of bearing fault. The performance of the proposed method is validated using publicly available experimental bearing vibration data across three different operating conditions. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

17 pages, 13462 KiB

Open AccessArticle

Main Factors on Effect of Precise Measurement and Precise Tamping Based on BP Neural Network

by Jianjun Qu, Pan Liu, Yiyu Long and Fei Xu

Appl. Sci. 2023, 13(7), 4273; https://doi.org/10.3390/app13074273 - 28 Mar 2023

Viewed by 1260

Abstract

With the continuous development of precise measurement and precise tamping (PMPT) technology on Chinese railway conventional speed lines, the efficiency of machinery tamping operation and the quality of the track have been effectively improved. A variety of PMPT modes have been tried in [...] Read more.

With the continuous development of precise measurement and precise tamping (PMPT) technology on Chinese railway conventional speed lines, the efficiency of machinery tamping operation and the quality of the track have been effectively improved. A variety of PMPT modes have been tried in the field operation, however there are some differences in the operation effect. The quality of the tamping operation is affected by multiple factors. In order to identify the key factors affecting the operation quality and to further improve the tamping operation effect, this paper establishes both the database of PMPT operation modes and the selection index system for evaluating the operation effect. Based on mega multi-source heterogeneous data and track geometry inspection data, this paper adopts the Back Propagation Neural Network (BPNN) prognosis model to quantify and sort the main factors affecting the effect of PMPT. The research results show that the initial quality of the track before tamping, whether the stabilizing operation or the tamping modes have great influence weights. It can scientifically guide the field operation to control the key factors and put forward some practical suggestions for promoting the field application of PMPT and the optimization of operation modes on the conventional speed lines. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

15 pages, 1235 KiB

Open AccessArticle

Reverse Knowledge Distillation with Two Teachers for Industrial Defect Detection

by Mingjing Pei, Ningzhong Liu, Pan Gao and Han Sun

Appl. Sci. 2023, 13(6), 3838; https://doi.org/10.3390/app13063838 - 17 Mar 2023

Cited by 5 | Viewed by 1799

Abstract

Industrial defect detection plays an important role in smart manufacturing and is widely used in various scenarios such as smart inspection and product quality control. Currently, although utilizing a framework for knowledge distillation to identify industrial defects has achieved great progress, it is [...] Read more.

Industrial defect detection plays an important role in smart manufacturing and is widely used in various scenarios such as smart inspection and product quality control. Currently, although utilizing a framework for knowledge distillation to identify industrial defects has achieved great progress, it is still a significant challenge task to extract better image features and prevent overfitting for student networks. In this study, a reverse knowledge distillation framework with two teachers is designed. First, for the teacher network, two teachers with different architectures are used to extract the diverse features of the images from multiple models. Second, considering the different contributions of channels and different teacher networks, the attention mechanism and iterative attention feature fusion idea are introduced. Finally, to prevent overfitting, the student network is designed with a network architecture that is inconsistent with the teacher network. Extensive experiments were conducted on Mvtec and BTAD datasets, which are industrial defect detection datasets. On the Mvtec dataset, the average accuracy values of image-level and pixel-level ROC achieved 99.43% and 97.87%, respectively. On the BTAD dataset, the average accuracy values of image-level and pixel-level ROC reached 94% and 98%, respectively. The performance on both datasets is significantly improved, demonstrating the effectiveness of our method. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

18 pages, 1020 KiB

Open AccessArticle

Label-Free Fault Detection Scheme for Inverters of PV Systems: Deep Reinforcement Learning-Based Dynamic Threshold

by Giup Seo, Seungwook Yoon, Junyoung Song, Ekta Srivastava and Euiseok Hwang

Appl. Sci. 2023, 13(4), 2470; https://doi.org/10.3390/app13042470 - 14 Feb 2023

Cited by 4 | Viewed by 1905

Abstract

Generally, photovoltaic (PV) fault detection approaches can be divided into two groups: end-to-end and threshold methods. The end-to-end method typically uses a deep neural network (DNN) to learn fault patterns from labeled datasets, which directly detect whether faults occur or not. The threshold [...] Read more.

Generally, photovoltaic (PV) fault detection approaches can be divided into two groups: end-to-end and threshold methods. The end-to-end method typically uses a deep neural network (DNN) to learn fault patterns from labeled datasets, which directly detect whether faults occur or not. The threshold method first estimates power generation and uses thresholds to detect atypical deviations of measured values from estimated ones. The former method heavily relies on fault-labeled data and, therefore, requires the collection of abnormal event records, which is usually difficult, due to the sparseness of these events. The latter method typically uses statistical approaches, such as 3-sigma, to find thresholds, and it can be practically utilized without fault labels. However, setting a threshold with a proper confidence interval is still challenging, as PV power generation is sensitive to variations in environmental conditions, such as irradiance, ambient temperature, wind speed and humidity. In this paper, we propose a novel deep reinforcement learning (DRL)-based label-free fault detection scheme in which thresholds are dynamically assigned with suitable confidence intervals under varying environmental conditions. Various weather properties were used as input features (i.e., states) to a DRL agent, and proper thresholds were estimated in real time from the actions of the DRL agent. To this end, a reward function was designed for learning proper thresholds without fault labels under different weather conditions. To evaluate the performance of the proposed scheme, the PV dataset of the National Institute of Standards and Technology (NIST) was used, as it includes paired records of local weather and PV generations. The DRL-based scheme was compared with static and conventional dynamic threshold methods, based on statistical approaches. The results revealed that the proposed scheme outperformed the existing methods, providing a 5.67% higher

F_{1}

-score in the NIST dataset. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

20 pages, 9788 KiB

Open AccessArticle

Predicting Failure Probability in Industry 4.0 Production Systems: A Workload-Based Prognostic Model for Maintenance Planning

by Giuseppe Converso, Mosè Gallo, Teresa Murino and Silvestro Vespoli

Appl. Sci. 2023, 13(3), 1938; https://doi.org/10.3390/app13031938 - 2 Feb 2023

Cited by 8 | Viewed by 1711

Abstract

Maintenance of equipment is a crucial issue in almost all industrial sectors as it impacts the quality, safety, and productivity of any manufacturing system. Additionally, frequent production rescheduling due to unplanned and unintended interruptions can be very time consuming, especially in the case [...] Read more.

Maintenance of equipment is a crucial issue in almost all industrial sectors as it impacts the quality, safety, and productivity of any manufacturing system. Additionally, frequent production rescheduling due to unplanned and unintended interruptions can be very time consuming, especially in the case of centrally controlled systems. Therefore, the ability to estimate the likelihood that a monitored machine will successfully complete a predefined workload, taking into account both historical data from the machine’s sensors and the impending workload, may be essential in supporting a new approach to scheduling activities in an Industry 4.0 production system. This study proposes a novel approach for integrating machine workload information into a well-established PHM algorithm for Industry 4.0, with the aim of improving maintenance strategies in the manufacturing process. The proposed approach utilises a logistic regression model to assess the health condition of equipment and a neural network computational model to estimate its failure probability according to the scheduled workloads. Results from a prototypal case study showed that this approach leads to an improvement in the prediction of the likelihood of completing a scheduled job, resulting in improved autonomy of CPSs in accepting or declining scheduled jobs based on their forecasted health state, and a reduction in maintenance costs while maximising the utilisation of production resources. In conclusion, this study is beneficial for the present research community as it extends the traditional condition-based maintenance diagnostic approach by introducing prognostic capabilities at the plant shop floor, fully leveraging the key enabling technologies of Industry 4.0. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

18 pages, 9633 KiB

Open AccessArticle

Time Series Recovery Using Adjacent Channel Data Based on LSTM: A Case Study of Subway Vibrations

by Tao Xin, Yi Yang, Xiaoli Zheng, Jing Lin, Sen Wang and Pengsong Wang

Appl. Sci. 2022, 12(22), 11497; https://doi.org/10.3390/app122211497 - 12 Nov 2022

Cited by 2 | Viewed by 1441

Abstract

Multi-sensor technology has been widely applied in the condition monitoring of rail transit. In practice, the data of some channels in the high channel counts are often abnormal or lost due to the abnormality and damage of the sensors, thus resulting in a [...] Read more.

Multi-sensor technology has been widely applied in the condition monitoring of rail transit. In practice, the data of some channels in the high channel counts are often abnormal or lost due to the abnormality and damage of the sensors, thus resulting in a large amount of data waste. A method for the data recovery of lost channels by using adjacent channel data is proposed to solve this problem. Based on the LSTM network algorithm, a data recovery model is established based on the “sequence-to-sequence” regression analysis of adjacent channel data. Taking the measured vibration data of a subway as an example, the network is trained with multi-channel measured data to recover the lost channel data of time-series characteristics. The results show that this multi-channel data recovery model is feasible, and the accuracy is up to 98%. This method can also further reduce the number of channels that need to be collected. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

16 pages, 5114 KiB

Open AccessArticle

Intra-Domain Transfer Learning for Fault Diagnosis with Small Samples

by Liangwei Zhang, Junyan Zhang, Yeping Peng and Jing Lin

Appl. Sci. 2022, 12(14), 7032; https://doi.org/10.3390/app12147032 - 12 Jul 2022

Cited by 2 | Viewed by 1631

Abstract

The concept of deep transfer learning has spawned broad research into fault diagnosis with small samples. A considerable covariate shift between the source and target domains, however, could result in negative transfer and lower fault diagnosis task accuracy. To alleviate the adverse impacts [...] Read more.

The concept of deep transfer learning has spawned broad research into fault diagnosis with small samples. A considerable covariate shift between the source and target domains, however, could result in negative transfer and lower fault diagnosis task accuracy. To alleviate the adverse impacts of negative transfer, this research proposes an intra-domain transfer learning strategy that makes use of knowledge from a data-abundant source domain that is akin to the target domain. Concretely, a pre-trained model in the source domain is built via a vanilla transfer from an off-the-shelf inter-domain deep neural network. The model is then transferred to the target domain using shallow-layer freezing and finetuning with those small samples. In a case study involving rotating machinery, where we tested the proposed strategy, we saw improved performance in both training efficiency and prediction accuracy. To demystify the learned neural network, we propose a heat map visualization method using a channel-wise average over the final convolutional layer and up-sampling with interpolation. The findings revealed that the most active neurons coincide with the corresponding fault characteristics. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Graphical abstract

20 pages, 3873 KiB

Open AccessArticle

Rolling Bearing Health Indicator Extraction and RUL Prediction Based on Multi-Scale Convolutional Autoencoder

by Zijian Ye, Qiang Zhang, Siyu Shao, Tianlin Niu and Yuwei Zhao

Appl. Sci. 2022, 12(11), 5747; https://doi.org/10.3390/app12115747 - 6 Jun 2022

Cited by 16 | Viewed by 2566

Abstract

Rolling bearings are some of the most crucial components in rotating machinery systems. Rolling bearing failure may cause substantial economic losses and even endanger operator lives. Therefore, the accurate remaining useful life (RUL) prediction of rolling bearings is of tremendous research importance. Health [...] Read more.

Rolling bearings are some of the most crucial components in rotating machinery systems. Rolling bearing failure may cause substantial economic losses and even endanger operator lives. Therefore, the accurate remaining useful life (RUL) prediction of rolling bearings is of tremendous research importance. Health indicator (HI) construction is the critical step in the data-driven RUL prediction approach. However, existing HI construction methods often require extraction of time-frequency domain features using prior knowledge while artificially determining the failure threshold and do not make full use of sensor information. To address the above issues, this paper proposes an end-to-end HI construction method called a multi-scale convolutional autoencoder (MSCAE) and uses LSTM neural networks for RUL prediction. MSCAE consists of three convolutional autoencoders with different convolutional kernel sizes in parallel, which can fully exploit the global and local information of the vibration signals. First, the raw vibration data and labels are input into MSCAE, and then, MSCAE is trained by minimizing the composite loss function. After that, the vibration data of the test bearings are fed into the trained MSCAE to extract HI. Finally, RUL prediction is performed using the LSTM neural network. The superiority of the HI extracted by MSCAE was verified using the PHM2012 challenge dataset. Compared to state-of-the-art HI construction methods, RUL prediction using MSCAE-extracted HI has the highest prediction accuracy. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

18 pages, 8012 KiB

Open AccessArticle

A Generative Adversarial Network-Based Fault Detection Approach for Photovoltaic Panel

by Fangfang Lu, Ran Niu, Zhihao Zhang, Lingling Guo and Jingjing Chen

Appl. Sci. 2022, 12(4), 1789; https://doi.org/10.3390/app12041789 - 9 Feb 2022

Cited by 17 | Viewed by 2497

Abstract

Photovoltaic (PV) panels are widely adopted and set up on residential rooftops and photovoltaic power plants. However, long-term exposure to ultraviolet rays, high temperature and humid environments accelerates the oxidation of PV panels, which finally results in functional failure. The traditional fault detection [...] Read more.

Photovoltaic (PV) panels are widely adopted and set up on residential rooftops and photovoltaic power plants. However, long-term exposure to ultraviolet rays, high temperature and humid environments accelerates the oxidation of PV panels, which finally results in functional failure. The traditional fault detection approach for photovoltaic panels mainly relies on manual inspection, which is inefficient. Lately, machine vision-based approaches for fault detection have emerged, but lack of negative samples usually results in low accuracy and hinders the wide adoption of machine vision-based approaches. To address this issue, we proposed a semi-supervised anomaly detection model based on the generative adversarial network. The proposed model uses the generator network to learn the data distribution of the normal PV panel dataset during training. When abnormal PV panel data are put into the model in the test phase, the reconstructed image generated by the model does not equal the input image. Since the abnormal PV panel data do not obey the data distribution learned by the generator, the difference between the original image and its reconstructed image exceeds the given threshold. So, the model can filter out the fault PV panel by checking the error value between the original image and its reconstructed image. The model adopts Gradient Centralization and SmoothL1 loss function to improve its generalization performance. Meanwhile, we use the convolutional block attention module (CBAM) to make the model pay more attention to the defective area and greatly improve the performance of the model. In this paper, the photovoltaic panels dataset is collected from a PV power plant located in Zhejiang, China. We compare the proposed approach with state-of-the-art semi-supervised and unsupervised approaches (i.e., AnoGAN (Anomaly Detection with Generative Adversarial Networks), Zhao’s method, GANomaly, and f-AnoGAN), and the result indicates that the Area Under Curve (AUC) increases by 0.06, 0.052, 0.041 and 0.035, respectively, significantly improving the accuracy of photovoltaic panel fault detection. Full article

(This article belongs to the Special Issue Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Industrial AI: Applications in Fault Detection, Diagnosis, and Prognosis

Share This Special Issue

Special Issue Editors

Special Issue Information

Published Papers (15 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI