Hostname: page-component-f554764f5-wjqwx Total loading time: 0 Render date: 2025-04-21T12:32:49.819Z Has data issue: false hasContentIssue false
  • English
  • Français

Fault diagnosis of proton exchange membrane fuel cells based on improved YOLOv5

Published online by Cambridge University Press:  13 December 2024

Xiangshuai Deng Open the ORCID record for Xiangshuai Deng [Opens in a new window] ,
Dongshen Du ,
Huaisong Fang  and
Yiming Ren
Xiangshuai Deng
Affiliation:
Faculty of Automation, Huaiyin Institute of Technology, Huaian, Jiangsu, China
Dongshen Du*
Affiliation:
Faculty of Automation, Huaiyin Institute of Technology, Huaian, Jiangsu, China
Huaisong Fang
Affiliation:
Faculty of Automation, Huaiyin Institute of Technology, Huaian, Jiangsu, China
Yiming Ren
Affiliation:
Faculty of Automation, Huaiyin Institute of Technology, Huaian, Jiangsu, China
*
Corresponding author: Dongshen Du; Email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

With the widespread application of proton exchange membrane fuel cells (PEMFCs), ensuring the safe and reliable operation of the PEMFCs is becoming more and more important. Timely diagnosis of fault types and the implementation of targeted interventions are crucial for addressing these challenges. In this study, a simulated PEMFC model is firstly introduced by using Fluent, and the effectiveness is validated through experiments involving membrane dry faults, water flooding faults, normal states, and unknown states. Then, a data-driven deep learning convolutional neural network, YOLOv5-CG-AS, is developed, which employs the EfficientViT network as the backbone, incorporating lightweight improvements through the proposed CG-AS attention layer. The results demonstrate that YOLOv5-CG-AS can automatically extract fault features from images for offline fault diagnosis and can perform real-time online diagnosis of multiple parameter curves of PEMFCs. Moreover, the experimental results have validated the feasibility and effectiveness of proposed method and shown the average precision mean Average Precision (mAP) of the trained model reaches 99.50%, superior than other conventional strategies. This has significant implications for advancing fault diagnosis methods, enhancing the reliability and durability of PEMFC systems, and promoting further development in the field.

Keywords

EfficientViTfault diagnosisPEMFCYOLOv5
Type
Research Article
Information
AI EDAM , Volume 38 , 2024 , e21
Check for updates
Copyright
© The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

Footnotes

This work is supported by the National Natural Science Foundation of China (Grant No. 61873107), and the Qinglan Program to Cultivate Middle-aged and Young Science Leaders of Colleges and Universities of Jiangsu Province, China.

References

Allam, A, Michael, M, and Zhang, P. Fault diagnosis of proton exchange membrane fuel cells. 2021 5th International Conference on Control and Fault-Tolerant Systems (SysTol). IEEE, Saint- Raphael, France, 29 September 2021.Google Scholar
Benjumea, A, Teeti, I, Cuzzolin, F, et al. YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles. arXiv preprint arXiv: 2112.11798, 2021.Google Scholar
Calasan, M, Micev, M, Hasanien, HM, et al. (2024) PEM fuel cells: Two novel approaches for mathematical modeling and parameter estimation. Energy 290, 130130CrossRefGoogle Scholar
Cui, D and Xiang, Z (2023) Nonsingular fixed-time fault-tolerant fuzzy control for switched uncertain nonlinear systems. IEEE Transactions on Fuzzy Systems 31(1), 174–183CrossRefGoogle Scholar
Dang, H, Ma, R, Zhou, J, et al. (2020) CNN-based fault diagnosis of proton exchange membrane fuel cell. Power Electronics Technology 54(12), 52–55Google Scholar
Darzentas, D, Wagner, H, Craigon, P, et al. (2022) Data-inspired co-design for museum and gallery visitor experiences. Artificial Intelligence for Engineering Design, Analysis and Manufa,cturing 36, e3CrossRefGoogle Scholar
Du, D, Sheng, Y, Zhao, H, et al. (2023) Fault diagnosis of proton exchange membrane fuel cell system based on VMD. Control Engineering of China 30(07), 1190–1197Google Scholar
Gao, Y, Liu, X and Xiang, J (2021) Fault detection in gears using fault samples enlarged by a combination of numerical simulation and a generative adversarial network. IEEE/ASME Transactions on Mechatronics 27(5), 3798–3805CrossRefGoogle Scholar
Guo, B, Zhu, H, Wei, Y, et al. (2014) 3-D steady-state numerical simulation of proton exchange membrane fuel cells. Computer and Applied Chemistry 31(2), 135–139Google Scholar
Ho, J, Kalchbrenner, N, Weissenborn, D, et al. Axial attention in multidimensional transformers. arXiv preprint arXiv: 1912.12180, 2019.Google Scholar
Huang, F, Geng, L, Liu, F, et al. A review of water fault diagnosis of the proton exchange membrane fuel cell. 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC). IEEE, Chongqing, China, 15 September 2023.Google Scholar
Huang, S and Xiang, Z (2015) Finite-time stabilization of a class of switched stochastic nonlinear systems under arbitrary switching. International Journal of Robust and Nonlinear Control 26(10), 21362152Google Scholar
Jeong, H, Park, B, Park, S, et al. (2019) Fault detection and identification method using observer-based residuals. Reliability Engineering and System Safety 184, 27–40CrossRefGoogle Scholar
Kattenborn, T, Leitloff, J, Schiefer, F, et al. (2021) Review on convolutional neural networks (CNN) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing 173, 24–49CrossRefGoogle Scholar
Kim, J, Kim, N, Park, Y, et al. (2022) Object detection and classification based on YOLO-V5 with improved maritime dataset. Journal of Marine Science and Engineering 10(3), 377CrossRefGoogle Scholar
Lee, B, Cooper, R, Hands, D, et al. (2022) Continuous cycles of data-enabled design: Reimagining the IoT development process. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 36, e11CrossRefGoogle Scholar
Li, K, Wang, J, Jalil, H, et al. (2023) A fast and lightweight detection algorithm for passion fruit pests based on improved YOLOv5. Computers and Electronics in Agriculture 204, 107534CrossRefGoogle Scholar
Liu, G, Hu, Y, Chen, Z, et al. (2023) Lightweight object detection algorithm for robots with improved YOLOv5. Engineering Applications of Artificial Intelligence 123, 106217CrossRefGoogle Scholar
Liu, X, Peng, H, Zheng, N, et al. EfficientViT: Memory efficient vision transformer with cascaded group attention. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 17 June 2023.CrossRefGoogle Scholar
Luo, Y, Kumar, A and Xiang, J (2022) Machinery fault diagnosis based on domain adaptation to bridge the gap between simulation and measured signals. IEEE Transactions on Instrumentation and Measurement 71, 1–9Google Scholar
Ma, R, Dang, H, Zhang, Y, et al. (2024) A review on failure mechanism analysis and diagnosis for proton exchange membrane fuel cell systems. Proceedings of the CSEE 44(01), 407–427Google Scholar
Redmon, J, Farhadi, A. Yolov3: An incremental improvement. arXiv preprint arXiv: 1804.02767, 2018.Google Scholar
Sinha, V and Mondal, S (2021) Adaptive unknown input observer approach for multi-fault diagnosis of PEM fuel cell system with time-delays. Journal of Control and Decision 8(2), 222–232CrossRefGoogle Scholar
Sun, Y, Mao, L, Huang, W, et al. (2022) Fault diagnosis of proton exchange membrane fuel cell using magnetic field data. Journal of Mechanical Engineering 58(22), 106–114Google Scholar
Wang, J, Yang, B, Zeng, C, et al. (2021) Recent advances and summarization of fault diagnosis techniques for proton exchange membrane fuel cell systems: A critical overview. CIESC Journal 500, 229932Google Scholar
Xiang, J, Zhong, Y and Tang, H (2016) A novel personalized diagnosis methodology using numerical simulation and an intelligent method to detect faults in a shaft. Applied Sciences 6(12), 414CrossRefGoogle Scholar
Xiang, Z, Qiao, C and Mahmoud, M (2012) Finite-time analysis and H∞ control for switched stochastic systems. Journal of the Franklin Institute 349(3), 915–927CrossRefGoogle Scholar
Xu, H, Ai, Z and Zhang, Z (2020) A lightweight target detection network based on channel rescheduling. Computer and Modernization (02), 94–98Google Scholar
Xu, Y and Li, C (2021) Lightweight object detection network based on YOLO optimization. Computer Science 48(S2, 265–269Google Scholar
Zhang, X and Guo, X (2021) Fault diagnosis of proton exchange membrane fuel cell system of tram based on information fusion and deep learning. International Journal of Hydrogen Energy 46(60), 30828–30840CrossRefGoogle Scholar
Zhang, X, Jiang, Y, Sun, T, et al. (2020) Review of flooding and membrane drying fault diagnosis in proton exchange membrane fuel cells. Journal of Southwest Jiaotong University 55(04), 828–838Google Scholar
Zhang, Y, He, Y, Tang, H, et al. 2024 Adversarial domain adaptation approach for axial piston pump fault diagnosis under small sample condition based on measured and simulated signals. IEEE Transactions on Instrumentation and Measurement.CrossRefGoogle Scholar
Zheng, Z, Petrone, R, Péra, MC, et al. (2013) A review on non-model based diagnosis methodologies for PEM fuel cell stacks and systems. International Journal of Hydrogen Energy 38(21), 8914–8926CrossRefGoogle Scholar
Zhong, Z, Zhu, X and Cao, G (2006) Modeling a PEMFC by a support vector machine. Journal of Power Sources 160(01), 293–298CrossRefGoogle Scholar
Zhou, S, Ren, H and Pei, F (2015) Research on PEMFC fault diagnosis method based on COMSOL model. Chemical Industry and Engineering 32(4), 56–62Google Scholar