Research on federated learning method for fault diagnosis in multiple working conditions

Abstract

As one of the critical components of rotating machinery, fault diagnosis of rolling bearings has great significance. Although deep learning is useful in diagnosing rolling bearing faults, it is difficult to diagnose the faults of bearings under multiple operating conditions. To overcome the above-mentioned problem, this paper designs a modular federated learning network for fault diagnosis in multiple working conditions by using dynamic routing technology as the federation strategy for federated learning of the multiple modular neural network. First, according to different working conditions, the collected multi-working condition data are divided into different groups for feeding of modular network to extract the local features under different working conditions. Then, an additional deep neural network is constructed to extract the feature involved in data without working condition division. Finally, the global adaptive feature extraction of each working condition can be obtained by designing a federated strategy based on dynamic routing technology to achieve the weights allocation scheme of the modular neural network. The bearing dataset of Case Western Reserve University is taken as a benchmark dataset to verify the effectiveness of the proposed method.

Keywords

Fault diagnosis / neural network / federated learning

References

[1] Djelloul I,Sidibe IDB.Fault diagnosis based on the quality effect of learning algorithm for manufacturing systems..Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering2019;233:801-14

[2] Li J,Wang X,Zhang Y.Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis..Measurement2020;153:107419

[3] Xu X,Xu X.Machine learning-based wear fault diagnosis for marine diesel engine by fusing multiple data-driven models..Knowledge-Based Systems2020;190:105324

[4] Hoang D.A survey on Deep Learning based bearing fault diagnosis..Neurocomputing2019;335:327-35

[5] Xu Z,Yang Y.Fault diagnosis of rolling bearing of wind turbines based on the Variational Mode Decomposition and Deep Convolutional Neural Networks..Applied Soft Computing2020;95:106515

[6] Zhou F,Chen D.Real-time fault diagnosis using deep fusion of features extracted by parallel long short-term memory with peephole and convolutional neural network..Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering2021;235:1873-97

[7] Li C,Li L.Exploring temporal representations by leveraging attention-based bidirectional LSTM-RNNs for multi-modal emotion recognition..2020;57:102185

[8] Kong X,Wang Q,Yang W.A multi-ensemble method based on deep auto-encoders for fault diagnosis of rolling bearings..Measurement2020;151:107132

[9] Liu H,Gao L.Characterization of a Bacillus subtilis surfactin synthetase knockout and antimicrobial activity analysis..J Biotechnol2016;237:1-12

[10] Shao H,Wang F.An enhancement deep feature fusion method for rotating machinery fault diagnosis..Knowledge-Based Systems2017;119:200-20

[11] Sun W,Li J.Decision tree and PCA-based fault diagnosis of rotating machinery..Mech Syst Signal Process2007;21:1300-17

[12] Song B,Shi H.Key principal components with recursive local outlier factor for multimode chemical process monitoring..Journal of Process Control2016;47:136-49

[13] Liu H,Ma J.Rolling bearing fault diagnosis based on STFT-deep learning and sound signals..Shock and Vibration2016;2016:1-12

[14] Zhou F,Wen C.A novel multimode fault classification method based on deep learning..Journal of Control Science and Engineering2017;2017:1-14

[15] Chen X,Gao D.Bearing fault diagnosis base on multi-scale CNN and LSTM model..J Intell Manuf2021;32:971-87

[16] Gu X.Multimodal industrial process fault detection based on LNS-DEWKECA..Control and Decision2020;35:1879-86

[17] Che C,Ni X.Domain adaptive deep belief network for rolling bearing fault diagnosis..2020;143:106427

[18] Qiao H,Wang P,Xu M.An adaptive weighted multiscale convolutional neural network for rotating machinery fault diagnosis under variable operating conditions..IEEE Access2019;7:118954-64

[19] Zhao B,Zhan Z.Deep multi-scale convolutional transfer learning network: a novel method for intelligent fault diagnosis of rolling bearings under variable working conditions and domains..Neurocomputing2020;407:24-38

[20] Han S,Tang T.Measurement of weld pool oscillation for pulsed GTAW based on laser vision..Microcomputer Applications2019;35:8-13

[21] Jacobs RA,Nowlan SJ.Adaptive mixtures of local experts..Neural Comput1991;3:79-87

[22] Andreas J,Darrell T.Neural module networks..Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016;39-48

[23] Zhang W,Peng G,Zhang Z.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load..Mech Syst Signal Process2018;100:439-53

[24] Zhao X.Fault diagnosis of nonlinear systems based on modular fuzzy neural networks..Control Theory and Applications2001;18:395-400

[25] Bo YC,Yang G.A Modular Neural Networks ensembling method based on fuzzy decision-making. 2011 International Conference on Electric Information and Control Engineering2011;2011 Apr 15-17Wuhan, China. IEEE1030-4

[26] Yan Z,Piramuthu R.HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. Proceedings of the IEEE International Conference on Computer Vision (ICCV)2015;2740-8

[27] Geng Z,Han Y.Fault diagnosis of converter based on wavelet decomposition and BP neural network. 2019 Chinese Automation Congress (CAC)2020;2019 Nov 22-24Hangzhou, China. IEEE1273-6

[28] Sabour S,Hinton GE.Dynamic routing between capsules..arXiv preprint arXiv:1710.098292017;

[29] Chen T,Yang X.A deep capsule neural network with stochastic delta rule for bearing fault diagnosis on raw vibration signals..Measurement2019;148:106857

[30] Li L,Wang K.A fault diagnostic scheme based on capsule network for rolling bearing under different rotational speeds..Sensors (Basel)2020;20:1841 PMCID:PMC7181279

[31] Zhu Z,Chen Y.A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis..Neurocomputing2019;323:62-75

[32] Rumelhart DE,Williams RJ.Learning representations by back-propagating errors..Nature1986;323:533-6

[33] Ioffe S.Batch normalization: accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning2015;448-56

[34] Wang J,An Z,Qian W.Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines..Neurocomputing2019;329:53-65

[35] Bearingdata Centre. Case Western Reserve University. Available: http://csegroups.case.edu/bearingdatacenter/home. [Last accessed on 15 Oct 2021]