Trustworthy Mechanical Fault Diagnosis Using Uncertainty-aware Network

doi:10.3901/JME.2024.12.194

Abstract

Abstract: Deep learning-based fault diagnosis methods are limited by their black-box nature to give trustworthy and interpretable results. Most of the existing research on interpretable fault diagnosis focuses on developing interpretable modules to be embedded in deep models to give some physical meaning to the results, or using the results as a basis to infer the deeper logic of the model to make such decisions, with limited research on how to quantify the uncertainty in diagnostic results and explain their sources and composition. Uncertainty quantification and decomposition can not only provide confidence in diagnostic results, but also identify the source of unknown factors in the data, ultimately guiding the enhancement of the interpretability of diagnostic models. Therefore, Bayesian variational learning is proposed to be embedded into Transformer to develop an uncertainty-aware network for trustworthy mechanical fault diagnosis. A variational attention mechanism is designed and the corresponding optimization objective function is defined, which can model the prior and variational posterior distributions of attention weights, thus empowering the network to be aware of uncertainty. An uncertainty quantification and decomposition scheme is developed to achieve confidence characterization of diagnostic results and separation of epistemic and aleatoric uncertainty. Using fault diagnosis of planetary gearboxes as an example, the feasibility of the proposed method for trustworthy fault diagnosis is fully validated in an out-of-distribution generalization scenario where the test data contains unknown failure modes, unknown noise levels and unknown operating condition samples.

Key words: trustworthy fault diagnosis, uncertainty-aware network, variational attention, uncertainty quantification and decomposition, Bayesian deep learning

CLC Number:

TG156

SHAO Haidong, XIAO Yiming, DENG Qianwang, REN Yingying, HAN Te. Trustworthy Mechanical Fault Diagnosis Using Uncertainty-aware Network[J]. Journal of Mechanical Engineering, 2024, 60(12): 194-206.

References

[1] LI Y，ZHOU Z，SUN C，et al. Variational attention-based interpretable transformer network for rotary machine fault diagnosis[J]. IEEE Transactions on Neural Networks and Learning Systems，2024，35(5)：6180-6193.
[2] 雷亚国，贾峰，孔德同，等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报，2018，54(5)：94-104. LEI Yaguo，JIA Feng，KONG Detong，et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering，2018，54(5)：94-104.
[3] WANG D，CHEN Y，SHEN C，et al. Fully interpretable neural networks for machine health monitoring[J]. Mechanical Systems and Signal Processing，2022，168：108673.
[4] 邵海东，肖一鸣，颜深，等. 仿真数据驱动的改进无监督域适应轴承故障诊断[J]. 机械工程学报，2023，59(3)：76-85. SHAO Haidong，XIAO Yiming，YAN Shen，et al. Simulation data-driven enhanced unsupervised domain adaptation for bearing fault diagnosis [J]. Journal of Mechanical Engineering，2023，59(3)：76-85.
[5] LI T，ZHAO Z，SUN C，et al. WaveletKernelNet：An interpretable deep neural network for industrial intelligent diagnosis[J]. IEEE Transactions on Systems，Man，and Cybernetics：Systems，2022，52(4)：2302-2312.
[6] SHANG Z，ZHAO Z，YAN R，et al. Denoising fault-aware wavelet network：A signal processing informed neural network for fault diagnosis[J]. Chinese Journal of Mechanical Engineering，2023，36：9.
[7] BLUNDELL C，CORNEBISE J，KAVUKCUOGLU K，et al. Weight uncertainty in neural network[J]. arXiv：1505.05424，2015.
[8] XIAO Y，SHAO H，MIN Z，et al. Multiscale dilated convolutional subdomain adaptation network with attention for unsupervised fault diagnosis of rotating machinery cross operating conditions[J]. Measurement，2022，204：112146.
[9] HAN T，LI Y. Out-of-distribution detection-assisted trustworthy machinery fault diagnosis approach with uncertainty-aware deep ensembles[J]. Reliability Engineering and System Safety，2022，226：108648.
[10] XUE B，HU S，XU J，et al. Bayesian neural network language modeling for speech recognition[J]. IEEE/ACM Transactions on Audio，Speech，and Language Processing，2022，30：2900-2917.
[11] ZHOU T，HAN T，DROGUETTCD E. Towards trustworthy machine fault diagnosis：A probabilistic Bayesian deep learning framework[J]. Reliability Engineering and System Safety，2022，224：108525.
[12] DING Y，JIA M，MIAO Q，et al. A novel time-frequency transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings[J]. Mechanical Systems and Signal Processing，2022，168：108616.
[13] HAN S，SHAO H，CHENG J，et al. Convformer-NSE：A novel end-to-end gearbox fault diagnosis framework under heavy noise using joint global and local information[J]. IEEE/ASME Transactions on Mechatronics，2023，28(1)：340-349.
[14] VASWANI A，SHAZEER N，PARMAR N，et al. Attention is all you need[J]. arXiv：1706.03762，2017.
[15] ZHANG S，FAN X，CHEN B，et al. Bayesian attention belief networks[J]. arXiv：2106.05251，2021.
[16] FAN X，ZHANG S，CHEN B，et al. Bayesian attention modules[J]. arXiv：2010.10604，2020.
[17] DOSOVITSKIY A，BEYER L，KOLESNIKOV A，et al. An image is worth 16×16 words：Transformers for image recognition at scale[J]. arXiv：2010.11929，2020.
[18] CHAI L. Uncertainty estimation in Bayesian neural networks and links to interpretability[D]. Cambridge：University of Cambridge，2018.
[19] ZHAO Z，LI T，WU J，et al. Deep learning algorithms for rotating machinery intelligent diagnosis：An open source benchmark study[J]. ISA Transactions，2020，107：224-255.
[20] HAN T，LIU C，WU L，et al. An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems[J]. Mechanical Systems and Signal Processing，2019，117：170-187.