Chinese Journal of Mechanical Engineering >

2021 , Vol. 34 >Issue 3: 54 - 54

DOI: https://doi.org/10.1186/s10033-021-00569-0

Special Issue on AI-Enabled Monitoring Diagnosis & Prognosis

Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

  • Zhe Yang ,
  • Dejan Gjorgjevikj ,
  • Jianyu Long ,
  • Yanyang Zi ,
  • Shaohui Zhang ,
  • Chuan Li
展开
  • 1. School of Mechanical Engineering, Dongguan University of Technology, Dongguan 523808, China;
    2. School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
    3. Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Skopje, Macedonia

收稿日期: 2020-12-04

  修回日期: 2021-03-16

  网络出版日期: 2021-12-21

基金资助

Supported by National Natural Science Foundation of China (Grant Nos. 52005103, 71801046, 51775112, 51975121), Guangdong Province Basic and Applied Basic Research Foundation of China (Grant No. 2019B1515120095), Intelligent Manufacturing PHM Innovation Team Program (Grant Nos. 2018KCXTD029, TDYB2019010), and MoST International Cooperation Program (6-14)

收起

Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

  • Zhe Yang ,
  • Dejan Gjorgjevikj ,
  • Jianyu Long ,
  • Yanyang Zi ,
  • Shaohui Zhang ,
  • Chuan Li
Expand
  • 1. School of Mechanical Engineering, Dongguan University of Technology, Dongguan 523808, China;
    2. School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
    3. Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Skopje, Macedonia

Received date: 2020-12-04

  Revised date: 2021-03-16

  Online published: 2021-12-21

Supported by

Supported by National Natural Science Foundation of China (Grant Nos. 52005103, 71801046, 51775112, 51975121), Guangdong Province Basic and Applied Basic Research Foundation of China (Grant No. 2019B1515120095), Intelligent Manufacturing PHM Innovation Team Program (Grant Nos. 2018KCXTD029, TDYB2019010), and MoST International Cooperation Program (6-14)

Fold

摘要

Supervised fault diagnosis typically assumes that all the types of machinery failures are known. However, in practice unknown types of defect, i.e., novelties, may occur, whose detection is a challenging task. In this paper, a novel fault diagnostic method is developed for both diagnostics and detection of novelties. To this end, a sparse autoencoder-based multi-head Deep Neural Network (DNN) is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data. The detection of novelties is based on the reconstruction error. Moreover, the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function, instead of performing the pre-training and fine-tuning phases required for classical DNNs. The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer. The results show that its performance is satisfactory both in detection of novelties and fault diagnosis, outperforming other state-of-the-art methods. This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect, but also detect unknown types of defects.

关键词： Deep learning; Fault diagnostics; Novelty detection; Multi-head deep neural network; Sparse autoencoder

本文引用格式

Zhe Yang , Dejan Gjorgjevikj , Jianyu Long , Yanyang Zi , Shaohui Zhang , Chuan Li . Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties[J]. Chinese Journal of Mechanical Engineering, 2021 , 34(3) : 54 -54 . DOI: 10.1186/s10033-021-00569-0

Abstract

Supervised fault diagnosis typically assumes that all the types of machinery failures are known. However, in practice unknown types of defect, i.e., novelties, may occur, whose detection is a challenging task. In this paper, a novel fault diagnostic method is developed for both diagnostics and detection of novelties. To this end, a sparse autoencoder-based multi-head Deep Neural Network (DNN) is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data. The detection of novelties is based on the reconstruction error. Moreover, the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function, instead of performing the pre-training and fine-tuning phases required for classical DNNs. The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer. The results show that its performance is satisfactory both in detection of novelties and fault diagnosis, outperforming other state-of-the-art methods. This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect, but also detect unknown types of defects.

Key words： Deep learning; Fault diagnostics; Novelty detection; Multi-head deep neural network; Sparse autoencoder

参考文献

[1] E Zio. Some challenges and opportunities in reliability engineering. IEEE Trans. Reliab., 2016, 65(4): 1769-1782, https://doi.org/10.1109/TR.2016.2591504.
[2] D Wang, K-L Tsui, Q Miao. Prognostics and health management: A review of vibration based bearing and gear health indicators. IEEE Access, 2018. https://doi.org/10.1109/ACCESS.2017.2774261.
[3] J Zhong, J Long, S Zhang, et al. Flexible kurtogram for extracting repetitive transients for prognostics and health management of rotating components. IEEE Access, 2019, 7: 55631-55639, https://doi.org/10.1109/ACCESS.2019.2912716.
[4] P Baraldi, F Cadini, F Mangili, et al. Model-based and data-driven prognostics under different available information. Probabilistic Eng. Mech., 2013, 32: 66-79, https://doi.org/10.1016/j.probengmech.2013.01.003.
[5] H Wang, J Xu, R Yan, et al. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN. IEEE Trans. Instrum. Meas., 2020, 6(5): 2377-2389, https://doi.org/10.1109/TIM.2019.2956332.
[6] W Chine, A Mellit, V Lughi, et al. A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks. Renew. Energy, 2016, 90: 501-512, https://doi.org/10.1016/j.renene.2016.01.036.
[7] H Malik, Y Pandya, A Parashar, et al. Feature extraction using EMD and classifier through artificial neural networks for gearbox fault diagnosis. Applications of Artificial Intelligence Techniques in Engineering, 2019, 697: 309-317, https://doi.org/10.1007/978-981-13-1822-1_28.
[8] K He, Z Yang, Y Bai, et al. Intelligent fault diagnosis of delta 3D printers using attitude sensors based on support vector machines. Sensors (Switzerland), 2018. https://doi.org/10.3390/s18041298.
[9] X Li, S Wu, X Li, et al. Particle swarm optimization-support vector machine model for machinery fault diagnoses in high-voltage circuit breakers. Chinese J. Mech. Eng., 2020, 33: 6, https://doi.org/10.1186/s10033-019-0428-5.
[10] G Liu, H Li, W Liu. Bearing fault detection in varying operational conditions based on empirical mode decomposition and random forest. 2018 Prognostics and System Health Management Conference (PHM-Chongqing 2018), 2018: 851-854, https://doi.org/10.1109/PHM-Chongqing.2018.00152.
[11] Y Hu, S Thang, A Jiang, et al. A new method of wind turbine bearing fault diagnosis based on multi-masking empirical mode decomposition and fuzzy C-means clustering. Chinese J. Mech. Eng., 2019, 32: 46, https://doi.org/10.1186/s10033-019-0356-4.
[12] P Baraldi, F Cannarile, F Di Maio, et al. Hierarchical k-nearest neighbours classification and binary differential evolution for fault diagnostics of automotive bearings operating under variable conditions. Eng. Appl. Artif. Intell., 2016, 56: 1-13, https://doi.org/10.1016/j.engappai.2016.08.011.
[13] J Yu, M Bai, G Wang, et al. Fault diagnosis of planetary gearbox with incomplete information using assignment reduction and flexible naive Bayesian classifier. J. Mech. Sci. Technol., 2018, 32(1): 37-47, https://doi.org/10.1007/s12206-017-1205-y.
[14] A Yang, Y Wang, Y Zi, et al. An enhanced trace ratio linear discriminant analysis for fault diagnosis: An illustrated example using HDD data. IEEE Trans. Instrum. Meas., 2019, 68(12): 4629-4639, https://doi.org/10.1109/TIM.2019.2900885.
[15] M Tan, J Li, X Chen, et al. Power grid fault diagnosis method using intuitionistic fuzzy Petri nets based on time series matching. Complexity, 2019, https://doi.org/10.1155/2019/7890652.
[16] K Li, L Su, J Wu, et al. A rolling bearing fault diagnosis method based on variational mode decomposition and an improved kernel extreme learning machine. Appl. Sci., 2017, https://doi.org/10.3390/app7101004.
[17] S Khan, T Yairi. A review on the application of deep learning in system health management. Mech. Syst. Signal Process., 2018, 107: 241-265, https://doi.org/10.1016/j.ymssp.2017.11.024.
[18] R Zhao, R Yan, Z Chen, et al. Deep learning and its applications to machine health monitoring. Mech. Syst. Signal Process., 2019, 115: 213-237, https://doi.org/10.1016/j.ymssp.2018.05.050.
[19] C Li, S Zhang, Y Qin, et al. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing, 2020, 407: 121-135, https://doi.org/10.1016/j.neucom.2020.04.045.
[20] R Yan, F Shen, C Sun, et al. Knowledge transfer for rotary machine fault diagnosis. IEEE Sens. J., 2020, 20(15): 8374-8393, https://doi.org/10.1109/JSEN.2019.2949057.
[21] Y LeCun, Y Bengio, G Hinton. Deep learning. Nature, 2015, 521(7553): 436-444, https://doi.org/10.1038/nature14539.
[22] J Dai, J Tang, S Huang, et al. Signal-based intelligent hydraulic fault diagnosis methods: Review and prospects. Chinese J. Mech. Eng., 2019, https://doi.org/10.1186/s10033-019-0388-9.
[23] F Jia, Y Lei, J Lin, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech. Syst. Signal Process., 2016, 72-73: 303-315, https://doi.org/10.1016/j.ymssp.2015.10.025.
[24] Z Chen, W Li. Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network. IEEE Trans. Instrum. Meas., 2017, 66(7): 1693-1702, https://doi.org/10.1109/TIM.2017.2669947.
[25] 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, https://doi.org/10.1016/j.sigpro.2016.07.028.
[26] S-Y Shao, W-J Sun, R-Q Yan, et al. A deep learning approach for fault diagnosis of induction motors in manufacturing. Chinese J. Mech. Eng., 2017, 30(6): 1347-1356, https://doi.org/10.1007/s10033-017-0189-y.
[27] L-H Wang, X-P Zhao, J-X Wu, et al. Motor fault diagnosis based on short-time fourier transform and convolutional neural network. Chinese J. Mech. Eng., 2017, 30(6): 1357-1368, https://doi.org/10.1007/s10033-017-0190-5.
[28] G Jiang, H He, J Yan, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox. IEEE Trans. Ind. Electron., 2019, 66(4): 3196-3207, https://doi.org/10.1109/TIE.2018.2844805.
[29] Y Chang, J Chen, C Qu, et al. Intelligent fault diagnosis of Wind Turbines via a deep learning network using parallel convolution layers with multi-scale kernels. Renew. Energy, 2020, 153: 205-213, https://doi.org/10.1016/j.renene.2020.02.004.
[30] M Yuan, Y Wu, L Lin. Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network. 2016 IEEE/CSAA International Conference on Aircraft Utility Systems (AUS), 2016: 135-140.
[31] X Chen, B Zhang, D Gao. Bearing fault diagnosis base on multi-scale CNN and LSTM model. J. Intell. Manuf. (2021), 32: 971-987. https://doi.org/10.1007/s10845-020-01600-2.
[32] J Long, S Zhang, C Li. Evolving deep echo state networks for intelligent fault diagnosis. IEEE Trans. Ind. Informatics, 2020, 16(7): 4928-4937, https://doi.org/10.1109/TⅡ.2019.2938884.
[33] J Long, Z Sun, C Li, et al. A novel sparse echo autoencoder network for data-driven fault diagnosis of delta 3-D printers. IEEE Trans. Instrum. Meas., 2020, 69(3): 683-692, https://doi.org/10.1109/TIM.2019.2905752.
[34] S Zhang, Z Sun, C Li, et al. Deep hybrid state network with feature reinforcement for intelligent fault diagnosis of delta 3-D printers. IEEE Trans. Ind. Informatics, 2020, 16(2): 779-789, https://doi.org/10.1109/TⅡ.2019.2920661.
[35] Y Bengio, A Courville, P Vincent. Representation learning: A review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35(8): 1798-1828, https://doi.org/10.1109/TPAMI.2013.50.
[36] B Gao, W L Woo, Y He, et al. Unsupervised sparse pattern diagnostic of defects with inductive thermography imaging system. IEEE Trans. Ind. Informatics, 2016, 12(1): 371-383, https://doi.org/10.1109/TⅡ.2015.2492925.
[37] A Ng. Sparse autoencoder. CS294A Lect. Notes, 2011, 72: 1-19.
[38] J Long, J Mou, L Zhang, et al. Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots. J. Manuf. Syst., 2020, https://doi.org/10.1016/j.jmsy.2020.08.010.
[39] E Principi, D Rossetti, S Squartini, et al. Unsupervised electric motor fault detection by using deep autoencoders. IEEE-CAA J. Autom. Sin., 2019, 6(2): 441-451, https://doi.org/10.1109/JAS.2019.1911393.
[40] Y Qi, C Shen, D Wang, et al. Stacked sparse autoencoder-based deep network for fault diagnosis of rotating machinery. IEEE Access, 2017, 5: 15066-15079, https://doi.org/10.1109/ACCESS.2017.2728010.
[41] Y Qu, M He, J Deutsch, et al. Detection of pitting in gears using a deep sparse autoencoder. Appl. Sci. (Switzerland), 2017, 7(5): 515. https://doi.org/10.3390/app7050515.
[42] M Sohaib, J-M Kim. Reliable fault diagnosis of rotary machine bearings using a stacked sparse autoencoder-based deep neural network. Shock Vib., 2018, https://doi.org/10.1155/2018/2919637.
[43] H O A Ahmed, M L D Wong, A K Nandi. Intelligent condition monitoring method for bearing faults from highly compressed measurements using sparse over-complete features. Mech. Syst. Signal Process., 2018, 99: 459-477, https://doi.org/10.1016/j.ymssp.2017.06.027.
[44] H Zhu, J Cheng, C Zhang, et al. Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings. Appl. Soft Comput., 2020, 88, 106060, https://doi.org/10.1016/j.asoc.2019.106060.
[45] L Xu, M Cao, B Song, et al. Open-circuit fault diagnosis of power rectifier using sparse autoencoder based deep neural network. Neurocomputing, 2018, 311: 1-10, https://doi.org/10.1016/j.neucom.2018.05.040.
[46] Y Zheng, T Wang, B Xin, et al. A sparse autoencoder and softmax regression based diagnosis method for the attachment on the blades of marine current turbine. Sensors, 2019, 19(4): 826, https://doi.org/10.3390/s19040826.
[47] B A Olshausen, D J Field. Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Res., 1997, 37(23): 3311-3325.
[48] D F Williamson, R A Parker, J S Kendrick. The box plot: a simple visual method to interpret data. Ann. Intern. Med., 1989, 110(11): 916-921.
[49] X Lou, K A Loparo. Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mech. Syst. Signal Process., 2004, 18(5): 1077-1095, https://doi.org/10.1016/S0888-3270(03)00077-3.
[50] K Yan, Z Ji, W Shen. Online fault detection methods for chillers combining extended kalman filter and recursive one-class SVM. Neurocomputing, 2017, 228: 205-212.
[51] S Amraee, A Vafaei, K Jamshidi, et al. Abnormal event detection in crowded scenes using one-class SVM. Signal, Image Video Process., 2018, 12(6): 1115-1123.
[52] S Zhang, Z Sun, J Long, et al. Dynamic condition monitoring for 3D printers by using error fusion of multiple sparse auto-encoders. Comput. Ind., 2019, 105: 164-176, https://doi.org/10.1016/j.compind.2018.12.004.
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