Unraveling Induction Motor State through Thermal Imaging and Edge Processing : A Step towards Explainable Fault Diagnosis

• Autorzy: Piechocki Mateusz , Pajchrowski Tomasz , Kraft Marek , Wolkiewicz Marcin , Ewert Paweł

Identyfikatory

DOI

10.17531/ein/170114

• Języki publikacji: EN

Abstrakty

EN

Equipment condition monitoring is essential to maintain the reliability of the electromechanical systems. Recently topics related to fault diagnosis have attracted significant interest, rapidly evolving this research area. This study presents a non-invasive method for online state classification of a squirrel-cage induction motor. The solution utilizes thermal imaging for non-contact analysis of thermal changes in machinery. Moreover, used convolutional neural networks (CNNs) streamline extracting relevant features from data and malfunction distinction without defining strict rules. A wide range of neural networks was evaluated to explore the possibilities of the proposed approach and their outputs were verified using model interpretability methods. Besides, the top-performing architectures were optimized and deployed on resource-constrained hardware to examine the system's performance in operating conditions. Overall, the completed tests have confirmed that the proposed approach is feasible, provides accurate results, and successfully operates even when deployed on edge devices.

Słowa kluczowe

EN

thermal imaging; fault diagnosis; squirrel-cage induction motor; convolutional neural network; explainability; edge processing

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2023
• Tom: Vol. 25, no. 3
• Strony: art. no. 170114
• Opis fizyczny: Bibliogr. 56 poz., rys., tab., wykr.

Twórcy

autor

Piechocki Mateusz

• Institute of Robotics and Machine Intelligence, Poznań University of Technology, Poland

• https://orcid.org/0000-0002-3479-0237

autor

Pajchrowski Tomasz

• Institute of Robotics and Machine Intelligence, Poznań University of Technology, Poland

• https://orcid.org/0000-0002-0002-7161

autor

Kraft Marek

• Institute of Robotics and Machine Intelligence, Poznań University of Technology, Poland

• https://orcid.org/0000-0001-6483-2357

autor

Wolkiewicz Marcin

• Department of Electrical Machines,Drivesand Measurements, Wroclaw University of Science and Technology, Poland

• https://orcid.org/0000-0003-1197-8517

autor

Ewert Paweł

• Department of Electrical Machines,Drivesand Measurements, Wroclaw University of Science and Technology, Poland

• https://orcid.org/0000-0001-9760-7092

Bibliografia

• 1. Achouch M, Dimitrova M, Ziane K, Karganroudi SS, Dhouib R, Ibrahim H, Adda M. On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges. Applied Sciences, 12(16), 2022. https://doi.org/10.3390/app12168081
• 2. Alvarado-HernandezAI, Zamudio-Ramirez I, Jaen-Cuellar AY, Osornio-Rios RA, Donderis-Quiles V, Antonino-Daviu JA. Infrared Thermography Smart Sensor for the Condition Monitoring of Gearbox and Bearings Faults in Induction Motors Sensors, 22(16), 2022. https://doi.org/10.3390/s22166075
• 3. Arm. PyArm NN 32.0.0, 2023. Online 12.04.2023 [https://github.com/ARM-software/armnn]
• 4. Balakrishnan GK, Yaw CT, Koh SP, Abedin T, Ra AA, Tiong SK, Chen CP. A Review of Infrared Thermography for Condition-Based Monitoring in Electrical Energy: Applications and Recommendations. Energies, 15(16), 2022. https://doi.org/10.3390/en15166000
• 5. Buhrmester V, Münch D, Arens M. Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey. Machine Learning and Knowledge Extraction, 3(4):966–989, 2021. https://doi.org/10.3390/make3040048
• 6. Cui C, Gao T, Wei S, Du Y, Guo R, Dong S, Lu B, Zhou Y, Lv X, Liu Q, Hu X, Yu D, Ma Y. PP-LCNet: A Lightweight CPU Convolutional Neural Network. arXiv, 2021. https://doi.org/10.48550/arXiv.2109.15099
• 7. Gangsar P, Tiwari R. Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review. Mechanical Systems and Signal Processing, 144:106908, 2020. https://doi.org/10.1016/j.ymssp.2020.106908
• 8. Gong J, Liu W, Pei M, Wu C, Guo L. ResNet10: A lightweight residual network for remote sensing image classification. 14th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), 975–978, 2022. https://www.doi.org/10.1109/ICMTMA54903.2022.00197
• 9. Google. tflite-runtime 2.11.0, 2022. Online 12.04.2023 [https://www.tensorflow.org/lite]
• 10. Guo D, Li X, Luo F. On-line fault diagnosis of rotating machinery based on deep residual network. 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC), 103–108, 2022. https://www.doi.org/10.1109/YAC57282.2022.10023904
• 11. Halder S, Bhat S, Zychma D, Sowa P. Broken Rotor Bar Fault Diagnosis Techniques Based on Motor Current Signature Analysis forInduction Motor -A Review. Energies, 15(22), 2022. https://doi.org/10.3390/en15228569
• 12. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778, 2016. https://www.doi.org/10.1109/CVPR.2016.90
• 13. Huda ASN,Taib S. Application of infrared thermography for predictive/preventive maintenance of thermal defect in electrical equipment. Applied Thermal Engineering, 61(2):220–227, 2013. https://doi.org/10.1016/j.applthermaleng.2013.07.028
• 14. Ibrahim A, Anayi F, Packianather M. New Machine Learning Model-Based Fault Diagnosis of Induction Motors Using Thermal Images. 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), 58–62, 2022. https://www.doi.org/10.1109/ICACITE53722.2022.9823832
• 15. Intel Corporation. Intel Neural Compute Stick 2, 2019. Online 12.04.2023 [https://intel.com/content/www/us/en/products/sku/140109/intel-neural-compute-stick-2/specifications.html]
• 16. Intel Corporation. Openvino 2022.1, 2022. Online 12.04.2023 [https://docs.openvino.ai/2022.1/index.html]
• 17. Janssens O, Schulz R, Slavkovikj V, Stockman K, Loccufier M, Van de Walle R, Van Hoecke S. Thermal image based fault diagnosis for rotating machinery. Infrared Physics Technology, 73:78–87, 2015. https://doi.org/10.1016/j.infrared.2015.09.004
• 18. Janssens O, Van de Walle R, Loccufier M, Van Hoecke S. Deep Learning for Infrared Thermal Image Based Machine Health Monitoring. IEEE/ASME Transactions on Mechatronics, 23(1):151–159, 2018. https://www.doi.org/10.1109/TMECH.2017.2722479
• 19. Karabacak YE, Gürsel Özmen N, Gümüşel L. Worm gear condition monitoring and fault detection from thermal images via deep learning method. Eksploatacja I Niezawodnosc –Maintenance and Reliability, 22(3):544–556, 2020. https://doi.org/10.17531/ein.2020.3.18
• 20. Kokhlikyan N, Miglani V, Martin M, Wang E, Alsallakh B, Reynolds J, Melnikov A, Kliushkina N, Araya C, Yan S, Reblitz-Richardson O. Captum: A unified and generic model interpretability library for PyTorch, 2020. https://www.doi.org/10.48550/ARXIV.2009.07896
• 21. Li W, Huang R, Li J, Liao Y, Chen Z, He G, Yan R, Gryllias K. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges Mechanical Systems and Signal Processing,167:108487, 2022. https://doi.org/10.1016/j.ymssp.2021.108487
• 22. Li Y, Du X, Wan F, Wang X, and Yu H. Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging. Chinese Journal of Aeronautics, 33(2):427–438, 2020. https://doi.org/10.1016/j.cja.2019.08.014
• 23. Li Y, Gu JX, Zhen D, Xu M, Ball A. An evaluation of gearbox condition monitoring using infrared thermal images applied with convolutional neural networks. Sensors, 19(9), 2019. https://doi.org/10.3390/s19092205
• 24. Liang Y, Li S, Yan C, Li M, Jiang C. Explaining the black-box model: A survey of local interpretation methods for deep neural networks. Neurocomputing, 419:168–182, 2021. https://doi.org/10.1016/j.neucom.2020.08.011
• 25. Lopes JF, da Costa VGT, Barbin DF, Cruz-Tirado LJP, Baeten V, Barbon Junior S. Deep computer vision system for cocoa classification. Multimedia Tools and Applications, 81(28):41059–41077, Nov 2022. https://www.doi.org/10.1007/s11042-022-13097-3
• 26. Loshchilov I, Hutter F. Decoupled weight decay regularization. arXiv, 2019. https://doi.org/10.48550/arXiv.1711.05101
• 27. Luczak D, Brock S, Siembab K. Cloud based fault diagnosis by convolutional neural network as time-frequency RGB image recognition of industrial machine vibration with internet of things connectivity. Sensors, 23(7), 2023. https://doi.org/10.3390/s23073755
• 28. Mahendran A, Vedaldi A. Salient deconvolutional networks. In Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling, editors, Computer Vision –ECCV 2016, 120–135, Cham, 2016. Springer International Publishing. https://doi.org/10.1007/978-3-319-46466-4_8
• 29. Mian T, Choudhary A, Fatima S. Multi-sensor fault diagnosis for misalignment and unbalance detection using machine learning. IEEE International Conference on Power Electronics, Smart Grid, and Renewable Energy (PESGRE), 1–6, 2022. https://www.doi.org/10.1109/PESGRE52268.2022.9715938
• 30. Microsoft. ONNX Runtime 1.14.1, 2023. [https://onnxruntime.ai]
• 31. Orlowska-Kowalska T, Wolkiewicz M, Pietrzak P, Skowron M, Ewert P, Tarchala G, Krzysztofiak M, Kowalski CT. Fault diagnosis and fault-tolerant control of PMSM drives–state of the art and future challenges. IEEE Access, 10:59979–60024, 2022. https://www.doi.org/10.1109/ACCESS.2022.3180153
• 32. Ramirez OJV, Cruz de la Cruz JE, Machaca WAM. Agroindustrial plant forthe classification of hass avocados in real-time with ResNet-18 architecture. 5th International Conference on Robotics and Automation Sciences (ICRAS), 206–210, 2021. https://www.doi.org/10.1109/ICRAS52289.2021.9476659
• 33. Ran Y, Zhou X, Lin P, Wen Y, Deng R.A survey of predictive maintenance: Systems, purposes and approaches. arXiv, 2019. https://doi.org/10.48550/arXiv.1912.07383
• 34. Reljic D, Jerkan D, Marcetic D, Oros D. Broken bar fault detection in IM operating under no-load condition. Advances in Electricaland Computer Engineering, 16:63–70, 01 2016. https://www.doi.org/10.4316/AECE.2016.04010
• 35. Reséndiz-Ochoa E, Morales-Hernández LA, Cruz-Albarran IA, Alvarez-Junco S. Induction motor failure analysis using machine learning and infrared thermography. IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), volume 6, 1–6, 2022. https://www.doi.org/10.1109/ROPEC55836.2022.10018653
• 36. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128(2):336–359, Oct 2019. https://doi.org/10.1007%2Fs11263-019-01228-7
• 37. Siemens. The true cost of downtime 2022. Online 12.04.2023 [https://assets.new.siemens.com/siemens/assets/api/uuid:3d606dbe0-43e4-80b1-d04e27ada920/dics-b10153-00-7600truecostofdowntime2022-144.pdf]
• 38. Simonyan K, Vedaldi A, Zisserman A. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv, 2013. https://www.doi.org/10.48550/ARXIV.1312.6034
• 39. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv, 2015. https://doi.org/10.48550/arXiv.1409.1556
• 40. Singh G, Anil Kumar TC, Naikan VNA. Induction motor inter turn fault detection usinginfrared thermographic analysis. Infrared Physics Technology, 77:277–282, 2016. https://doi.org/10.1016/j.infrared.2016.06.010
• 41. Singh G, Naikan VNA. Infrared thermography based diagnosis of inter-turn fault and cooling system failure in three phase induction motor. Infrared Physics Technology, 87:134–138, 2017. https://doi.org/10.1016/j.infrared.2017.10.007
• 42. Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M. Striving for simplicity: The all convolutional net. arXiv, 2015. https://doi.org/10.48550/arXiv.1412.6806
• 43. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9, 2015. https://www.doi.org/10.1109/CVPR.2015.7298594
• 44. Tan M, Chen B, Pang R, Vasudevan V, Sandler M, Howard A, Le QV. MnasNet: Platform-aware neural architecture search for mobile. arXiv, 2018. https://doi.org/10.1109/CVPR.2019.00293
• 45. Tan M, Le QV. MixConv: Mixed depthwise convolutional kernels. arXiv, 2019. https://doi.org/10.48550/arXiv.1907.09595
• 46. Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv, 2020. https://doi.org/10.48550/arXiv.1905.11946
• 47. The Linux Foundation. Pytorch 1.13.1, 2022. Online 12.04.2023 [https://pytorch.org]
• 48. The Raspberry Pi Foundation. Raspberry Pi 4 tech specs, 2019. Online 12.04.2023 [https://www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications]
• 49. Tran MQ, Amer M, Dababat A, Abdelaziz AY,Dai HJ, Liu MK, Elsisi M. Robust fault recognition and correction scheme for induction motors using an effective iot with deep learning approach. Measurement, 207:112398, 2023. https://doi.org/10.1016/j.measurement.2022.112398
• 50. VertivCo. Understanding the cost of data center downtime: An analysis of the financial impact on infrastructure vulnerability. [https://www.vertiv.com/4a3537/globalassets/images/about-images/news-and-insights/articles/white-papers/understanding-the-cost-of-data-center/datacenter-downtime-wp-en-na-sl-24661_51225_1.pdf]
• 51. Verucchi CJ, Giraldo E, Meira M, Ruschetti CR, Bossio JM, Bossio GR. Efficiency assessment of induction motors drives operating under shaft misalignment conditions. Advances in Electrical and Electronic Engineering, 18(3):142–152, 2020. https://www.doi.org/10.15598/aeee.v18i3.3596
• 52. Wang R, Zhan X, Bai H, Dong E, Cheng Z, Jia X. A review of fault diagnosis methods for rotating machinery using infrared thermography. Micromachines, 13(10), 2022. https://www.doi.org/10.3390/mi13101644
• 53. Wightman R. Pytorch image models. GitHub, 2019. https://www.doi.org/10.5281/zenodo.4414861
• 54. Workswell. Workswell infrared camera -stationary radiometric thermal camera, 2020. Online 12.04.2023 [https://workswell-thermal-camera.com/workswell-infrared-camera-wic]
• 55. Zeiler MD and Fergus R. Visualizing and understanding convolutional networks. arXiv, 2013. https://doi.org/10.48550/arXiv.1311.2901
• 56. Zhang H and Wang F. Fault identification of fan blade based on improved ResNet-18. Journal of Physics: Conference Series, 2221(1):012046, May 2022. https://www.doi.org/10.1088/1742-6596/2221/1/012046