Dynamic Vision Enabled Contactless Intelligent Machine Transfer Diagnosis Method

doi:10.3901/JME.2024.24.001

Abstract

Abstract: Vibration monitoring and signal processing are crucial methods for machine fault diagnosis. Currently, the popular contact vibration measurement method has achieved significant results. However, such methods have high requirements for deployment environments, and are not suitable for many engineering scenarios. Therefore, contactless methods for vibration monitoring and fault diagnosis are gaining increasing attention. Event-based camera is a bio-inspired contactless dynamic visual sensor with extremely high temporal resolution, high dynamic range, and low data redundancy, which can capture mechanical micro-vibrations from a visual perspective. This paper proposes a contactless machine intelligent transfer diagnosis method enabled by dynamic vision. An event-based camera is used to capture the dynamic visual vibration signals of machines. A cross-domain diffusion generation model of dynamic visual data is established, enabling the intelligent generation of visual data in unknown fault states in testing scenarios. A novel intelligent method for processing dynamic visual data and recognizing machine fault patterns is proposed based on the neuromorphic computing framework, achieving cross-domain intelligent transfer diagnosis effect. The proposed method has been validated on a nuclear power plant pump circulation test bench. The results show that the proposed method is able to achieve intelligent transfer diagnosis of machines based on dynamic visual data, and provides an effective and promising solution for vibration measurement and fault diagnosis in engineering scenarios in the perspective of vision.

Key words: intelligent fault diagnosis, contactless vibration monitoring, event-based camera, diffusion model, neuromorphic computing

CLC Number:

TH17

LI Xiang, CHEN Xinrui, LEI Yaguo, LI Naipeng, YANG Bin, YU Shupeng. Dynamic Vision Enabled Contactless Intelligent Machine Transfer Diagnosis Method[J]. Journal of Mechanical Engineering, 2024, 60(24): 1-10.

References

[1] LEI Yaguo，YANG Bin，JIANG Xinwei，et al. Applications of machine learning to machine fault diagnosis: a review and roadmap[J]. Mechanical Systems and Signal Processing，2020，138：106587.
[2] 陈是扦，彭志科，周鹏. 信号分解及其在机械故障诊断中的应用研究综述[J]. 机械工程学报，2020，56(17)：91-107.CHEN Shiqian，PENG Zhike，ZHOU Peng. Review of signal decomposition theory and its applications in machine fault diagnosis[J]. Journal of Mechanical Engineering，2020，56(17)：91-107.
[3] NATH A G，UDMALE S S，SINGH S K. Role of artificial intelligence in rotor fault diagnosis：A comprehensive review[J]. Artificial Intelligence Review，2021，54：2609-2668.
[4] LEI Yaguo，LI Naipeng，LI Xiang. Big data-driven intelligent fault diagnosis and prognosis for mechanical systems[M]. London：Springer，2022.
[5] 李响，付春霖，雷亚国，等. 保证数据隐私的装备协同智能故障诊断联邦迁移学习方法[J]. 机械工程学报，2023，59(6)：1-9.LI Xiang，FU Chunlin，LEI Yaguo，et al. Federated transfer learning method for privacy-preserving collaborative intelligent machinery fault diagnostics[J]. Journal of Mechanical Engineering，2023，59(6)：1-9.
[6] XUE Xiaodong，DONG Yonggui，WU Xu. Motion induced eddy current sensor for non-intrusive vibration measurement[J]. IEEE Sensors Journal，2019，20(2)：735-744.
[7] KAYNARDAG K，YANG C，SALAMONE S. A rail defect detection system based on laser Doppler vibrometer measurements[J]. NDT & E International，2023，137：102858.
[8] JAVED A，LEE H，KIM B，et al. Vibration measurement of a rotating cylindrical structure using subpixel-based edge detection and edge tracking[J]. Mechanical Systems and Signal Processing，2022，166：108437.
[9] LI Xiang，YU Shupeng，LEI Yaguo，et al. Intelligent machinery fault diagnosis with event-based camera[J]. IEEE Transactions on Industrial Informatics，2023，20(1)：380-389.
[10] ZHAO Mingzhe，SHEN Xiaojun，JIANG Fei. Research on mechanical vibration measurement method based on event camera[C]// 20233rd International Conference on Energy Engineering and Power Systems. Dali：IEEE，2023，528-532.
[11] TAVANAEI A，GHODRATI M，KHERADPISHEH S R，et al. Deep learning in spiking neural networks[J]. Neural Networks，2019，111：47-63.
[12] INCE T，MALIK J，DEVECIOGLU O C，et al. Early bearing fault diagnosis of rotating machinery by 1D self-organized operational neural networks[J]. IEEE Access，2021，9：139260-139270.
[13] ELSISI M，TRAN M Q，MAHMOUD K，et al. Effective IoT-based deep learning platform for online fault diagnosis of power transformers against cyberattacks and data uncertainties[J]. Measurement，2022，190：110686.
[14] ZUO Lin，XU Fengjie，ZHANG Changhua，et al. A multi-layer spiking neural network-based approach to bearing fault diagnosis[J]. Reliability Engineering & System Safety，2022，225：108561.
[15] ALI Y H，AHMED F Y H，ABDELRHMAN A M. Novel spiking neural network model for gear fault diagnosis[C]// 20222nd International Conference on Emerging Smart Technologies and Applications. Ibb：Yemen，2022：1-6.
[16] LI Weihua，HUANG Ruyi，LI Jipu，et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios：Theories，applications and challenges[J]. Mechanical Systems and Signal Processing，2022，167：108487.
[17] CHOUDHARY A，MIAN T，FATIMA S，et al. Passive thermography based bearing fault diagnosis using transfer learning with varying working conditions[J]. IEEE Sensors Journal，2023，23(5)：4628-4637.
[18] SCHWENDEMANN S，SIKORA Z A. Bearing fault diagnosis with intermediate domain based layered maximum mean discrepancy：A new transfer learning approach[J]. Engineering Applications of Artificial Intelligence，2021，105：10445.
[19] 贾思祥，孙丁一，毛刚，等. 基于对抗熵的转子系统跨工况故障诊断方法[J]. 机械工程学报，2023，59(15)：110-120.JIA Sixiang，SUN Dingyi，MAO Gang，et al. Adversarial entropy based fault diagnosis method for rotor system across different working conditions[J]. Journal of Mechanical Engineering，2023，59(15)：110-120.
[20] HO J，JAIN A，ABBEEL P. Denoising diffusion probabilistic models[J]. Advances in Neural Information Processing Systems，2020，33：6840-6851.