Chinese Journal of Mechanical Engineering >

2021 , Vol. 34 >Issue 3: 44 - 44

DOI: https://doi.org/10.1186/s10033-021-00564-5

Special Issue on AI-Enabled Monitoring Diagnosis & Prognosis

An Interpretable Denoising Layer for Neural Networks Based on Reproducing Kernel Hilbert Space and its Application in Machine Fault Diagnosis

  • Baoxuan Zhao ,
  • Changming Cheng ,
  • Guowei Tu ,
  • Zhike Peng ,
  • Qingbo He ,
  • Guang Meng
展开
  • State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China

收稿日期: 2020-10-22

  修回日期: 2021-03-29

  网络出版日期: 2021-12-21

基金资助

Supported by National Natural Science Foundation of China (Grant Nos. 12072188, 11632011, 11702171, 11572189, 51121063), and Shanghai Municipal Natural Science Foundation of China (Grant No. 20ZR1425200)

收起

An Interpretable Denoising Layer for Neural Networks Based on Reproducing Kernel Hilbert Space and its Application in Machine Fault Diagnosis

  • Baoxuan Zhao ,
  • Changming Cheng ,
  • Guowei Tu ,
  • Zhike Peng ,
  • Qingbo He ,
  • Guang Meng
Expand
  • State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China

Received date: 2020-10-22

  Revised date: 2021-03-29

  Online published: 2021-12-21

Supported by

Supported by National Natural Science Foundation of China (Grant Nos. 12072188, 11632011, 11702171, 11572189, 51121063), and Shanghai Municipal Natural Science Foundation of China (Grant No. 20ZR1425200)

Fold

摘要

Deep learning algorithms based on neural networks make remarkable achievements in machine fault diagnosis, while the noise mixed in measured signals harms the prediction accuracy of networks. Existing denoising methods in neural networks, such as using complex network architectures and introducing sparse techniques, always suffer from the difficulty of estimating hyperparameters and the lack of physical interpretability. To address this issue, this paper proposes a novel interpretable denoising layer based on reproducing kernel Hilbert space (RKHS) as the first layer for standard neural networks, with the aim to combine the advantages of both traditional signal processing technology with physical interpretation and network modeling strategy with parameter adaption. By investigating the influencing mechanism of parameters on the regularization procedure in RKHS, the key parameter that dynamically controls the signal smoothness with low computational cost is selected as the only trainable parameter of the proposed layer. Besides, the forward and backward propagation algorithms of the designed layer are formulated to ensure that the selected parameter can be automatically updated together with other parameters in the neural network. Moreover, exponential and piecewise functions are introduced in the weight updating process to keep the trainable weight within a reasonable range and avoid the ill-conditioned problem. Experiment studies verify the effectiveness and compatibility of the proposed layer design method in intelligent fault diagnosis of machinery in noisy environments.

关键词： Machine fault diagnosis; Reproducing kernel Hilbert space (RKHS); Regularization problem; Denoising layer; Neural network

本文引用格式

Baoxuan Zhao , Changming Cheng , Guowei Tu , Zhike Peng , Qingbo He , Guang Meng . An Interpretable Denoising Layer for Neural Networks Based on Reproducing Kernel Hilbert Space and its Application in Machine Fault Diagnosis[J]. Chinese Journal of Mechanical Engineering, 2021 , 34(3) : 44 -44 . DOI: 10.1186/s10033-021-00564-5

Abstract

Deep learning algorithms based on neural networks make remarkable achievements in machine fault diagnosis, while the noise mixed in measured signals harms the prediction accuracy of networks. Existing denoising methods in neural networks, such as using complex network architectures and introducing sparse techniques, always suffer from the difficulty of estimating hyperparameters and the lack of physical interpretability. To address this issue, this paper proposes a novel interpretable denoising layer based on reproducing kernel Hilbert space (RKHS) as the first layer for standard neural networks, with the aim to combine the advantages of both traditional signal processing technology with physical interpretation and network modeling strategy with parameter adaption. By investigating the influencing mechanism of parameters on the regularization procedure in RKHS, the key parameter that dynamically controls the signal smoothness with low computational cost is selected as the only trainable parameter of the proposed layer. Besides, the forward and backward propagation algorithms of the designed layer are formulated to ensure that the selected parameter can be automatically updated together with other parameters in the neural network. Moreover, exponential and piecewise functions are introduced in the weight updating process to keep the trainable weight within a reasonable range and avoid the ill-conditioned problem. Experiment studies verify the effectiveness and compatibility of the proposed layer design method in intelligent fault diagnosis of machinery in noisy environments.

Key words： Machine fault diagnosis; Reproducing kernel Hilbert space (RKHS); Regularization problem; Denoising layer; Neural network

参考文献

[1] L Lin, C F Hu. HHT-based AE characteristics of natural fatigue cracks in rotating shafts. Mechanical Systems and Signal Processing, 2012, 26: 181-189.
[2] J R Stack, T G Habetler, R G Harley. Fault classification and fault signature production for rolling element bearings in electric machines. IEEE Transactions on Industry Applications, 2004, 40(3): 735-739.
[3] Y Lei, B Yang, X Jiang, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing, 2020, 138: 106587.
[4] X Dai, Z Gao. From model, signal to knowledge: A data-driven perspective of fault detection and diagnosis. IEEE Transactions on Industrial Informatics, 2013, 9 (4): 2226-2238.
[5] R Zhao, R Yan, Z Chen, et al. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 2019, 115: 213-237.
[6] G E Hinton, R R Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504-507.
[7] H Shao, H Jiang, H Zhang, et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network. IEEE Transactions on Industrial Electronics, 2017, 65(3): 2727-2736.
[8] H Shao, H Jiang, X Zhang, et al. Rolling bearing fault diagnosis using an optimization deep belief network. Measurement Science and Technology, 2015, 26(11): 115002.
[9] F Jia, Y Lei, L Guo, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines. Neurocomputing, 2018, 272: 619-628.
[10] W Sun, S Shao, R Zhao, et al. A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Measurement, 2016, 89: 171-178.
[11] X Wu, Y Zhang, C Cheng, et al. A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery. Mechanical Systems and Signal Processing, 2021, 149: 107327.
[12] T Ince, S Kiranyaz, L Eren, et al. Real-time motor fault detection by 1-D convolutional neural networks. IEEE Transactions on Industrial Electronics, 2016, 63(11): 7067-7075.
[13] X Ding, Q He. Energy-fluctuated multiscale feature learning with deep convnet for intelligent spindle bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 2017, 66(8): 1926-1935.
[14] F Jia, Y Lei, N Lu, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization. Mechanical Systems and Signal Processing, 2018, 110: 349-367.
[15] Y Han, B Tang, L Deng. Multi-level wavelet packet fusion in dynamic ensemble convolutional neural network for fault diagnosis. Measurement, 2018, 127: 246-255.
[16] W Sun, B Yao, N Zeng, et al. An intelligent gear fault diagnosis methodology using a complex wavelet enhanced convolutional neural network. Materials, 2017, 10(7): 790.
[17] X Liu, Q Zhou, J Zhao, et al. Fault diagnosis of rotating machinery under noisy environment conditions based on a 1-D convolutional autoencoder and 1-D convolutional neural network. Sensors, 2019, 19(4): 972.
[18] P Vincent, H Larochelle, Y Bengio, et al. Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning, 2008: 1096-1103.
[19] C-Y Lee, P W Gallagher, Z Tu. Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree. Artificial Intelligence and Statistics, 2016: 464-472.
[20] C Lu, Z-Y Wang, W-L Qin, et al. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Processing, 2017, 130: 377-388.
[21] B Ma, H Hu, J Shen, et al. Generalized pooling for robust object tracking. IEEE Transactions on Image Processing, 2016, 25(9): 4199-4208.
[22] A Krizhevsky, I Sutskever, G E Hinton. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012: 1097-1105.
[23] M Zhao, S Zhong, X Fu, et al. Deep residual shrinkage networks for fault diagnosis. IEEE Transactions on Industrial Informatics, 2019, 16(7): 4681-4690.
[24] T Li, Z Zhao, C Sun, et al. Adaptive channel weighted CNN with multi-sensor fusion for condition monitoring of helicopter transmission system. IEEE Sensors Journal, 2020, 99: 1.
[25] G Pillonetto, F Dinuzzo, T Chen, et al. Kernel methods in system identification, machine learning and function estimation: A survey. Automatica, 2014, 50(3): 657-682.
[26] P Bouboulis, K Slavakis, S Theodoridis. Adaptive kernel-based image denoising employing semi-parametric regularization. IEEE Transactions on Image Processing, 2010, 19(6): 1465-1479.
[27] T Evgeniou, M Pontil, T Poggio. Regularization networks and support vector machines. Advances in Computational Mathematics, 2000, 13(1): 1.
[28] B Schölkopf, R Herbrich, A J Smola. A generalized representer theorem. International Conference on Computational Learning Theory, 2001: 416-426.
[29] G Tu, X Dong, S Chen, et al. Iterative nonlinear chirp mode decomposition: A Hilbert-Huang transform-like method in capturing intra-wave modulations of nonlinear responses. Journal of Sound and Vibration, 2020, 485: 115571.
[30] G Tu, X Dong, C Qian, et al. Intra-wave modulations in milling processes. International Journal of Machine Tools and Manufacture, 2021: 103705.
[31] Case Western Reserve University Bearing Data Center, [online]. Available: http://csegroups.case.edu/bearingdatacenter/pages/downloaddata-file.
[32] G E Hinton, S Osindero, Y-W Teh. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527-1554.
[33] G Hinton. A practical guide to training restricted Boltzmann machines. Momentum, 2010, 9: 1
Options
文章导航

/

〈 〉

版权所有 © 《Chinese Journal of Mechanical Engineering》编辑部

技术支持：北京玛格泰克科技发展有限公司