Deep Manifold Transfer Learning Method for Fault Diagnosis of Rotating Machinery Under Different Working Conditions

doi:10.3778/j.issn.1002-8331.2011-0070

Abstract

Abstract: Deep learning has gradually become the mainstream fault diagnosis method of rotating machinery because of its strong feature extraction ability. However, the deep models lack domain adaptation capability, and the performance degrades greatly when the working conditions change. Because transfer learning can learn domain-invariant features to some extent, it provides a new way to solve the problem of fault diagnosis under different conditions. However, most of the existing deep transfer learning methods only align the mean centers of different domain distributions, and do not consider the manifold structure of feature distributions. Thus their adaptive performance is still insufficient to deal with complex mechanical fault signals from different working conditions. To solve this problem, a deep manifold transfer learning method is proposed. Based on stacked auto encoder framework, the source domain and target domain samples are simultaneously used in the unsupervised pre-training to fully explore the features of data. For fine-tuning, a manifold transfer framework is proposed, which adapts the distribution mismatch and maintains the consistency of feature distribution structure among domains simultaneously. The new method has been compared with the existing transfer learning method in rotating machinery fault diagnosis cases. Experimental results show that the new method is superior to the existing transfer learning method and can significantly improve the fault diagnosis accuracy under different working conditions. In addition, by the effectiveness analysis, it is further proved that the unsupervised training using target domain data and fine tuning by manifold regularization are effective to improve the accuracy of cross-condition fault diagnosis tasks.

Key words: deep neural network, transfer learning, manifold learning, rotating machinery, fault diagnosis

摘要： 深度学习因强大的特征提取能力已逐渐成为旋转机械故障诊断的主要方法。但深层模型缺乏领域适应能力，工况变化时性能衰退严重。迁移学习为解决变工况诊断问题提供新的途径。然而现有深度迁移学习方法大多仅对齐不同领域分布的均值中心，未考虑特征分布的流形结构，其适配性能仍难以应对不同工况复杂的机械故障信号。针对该问题，提出一种深度流形迁移学习方法，以堆叠自编码器为框架，在无监督预训练阶段同时利用源域和目标域样本训练，充分挖掘数据本质特征；针对模型微调，提出流行迁移框架，在适配分布差异同时还保持领域间特征分布结构的一致性。将新方法与现有迁移学习方法在旋转机械故障诊断案例进行充分的比较实验，结果表明，新方法优于现有方法，能显著提高变工况故障诊断精度。通过有效性分析在机理上进一步证明了融合目标域数据的无监督预训练策略和流形迁移微调策略对提高变工况故障诊断的有效性。

关键词: 深层神经网络, 迁移学习, 流形学习, 旋转机械, 故障诊断

QIU Yingyu, ZHANG Ke, YANG Xinyi. Deep Manifold Transfer Learning Method for Fault Diagnosis of Rotating Machinery Under Different Working Conditions[J]. Computer Engineering and Applications, 2022, 58(12): 289-298.

邱颖豫, 张柯, 杨欣毅. 面向旋转机械故障诊断的深度流形迁移学习[J]. 计算机工程与应用, 2022, 58(12): 289-298.

References

[1] LIU R，YANG B，ZIO E，et al.Artificial intelligence for fault diagnosis of rotating machinery：a review[J].Mechanical Systems and Signal Processing，2018，108：33-47.
[2] 雷亚国，贾峰，周昕，等.基于深度学习理论的机械装备大数据健康监测方法[J].机械工程学报，2015，51（11）：49-56.
LEI Y G，JIA F，ZHOU X，et al.A deep learning-based method for machinery health monitoring with big data[J].Journal of Mechanical Engineering，2015，51（11）：49-56.
[3] CHEN Z，LI C，SANCHEZ R V.Multi-layer neural network with deep belief network for gearbox fault diagnosis[J].Journal of Vibroengineering，2015，17（5）：2379-2392.
[4] MENG G，CONG W，ZHU C G.Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings[J].Mechanical Systems and Signal Processing，2016，72-73：92-104.
[5] 唐魏，郑源，潘虹，等.引入动态调节学习率的SAE轴承故障诊断研究[J].计算机工程与应用，2020，56（20）：264-269.
TANG W，ZHENG Y，PAN H，et al.Roller bearing fault diagnosis based on stacked auto-encoder with dynamic learning rate[J].Computer Engineering and Applications，2020，56（20）：264-269.
[6] SHAO H D，JIANG H K，ZHAO H W，et al.A novel deep autoencoder feature learning method for rotating machinery fault diagnosis[J].Mechanical Systems and Signal Processing，2017，95：187-204.
[7] LU C，WANG Z Y，QIN W L，et al.Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification[J].Signal Processing，2017，130：377-388.
[8] SHAO H D，JIANG H K，WANG F，et al.An enhancement deep feature fusion method for rotating machinery fault diagnosis[J].Knowledge-Based Systems，2017，119：200-220.
[9] LU C，WANG Z Y，ZHOU B.Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification[J].Advanced Engineering Informatics，2017，32：739-757.
[10] SADOOGHI M S，KHADEM S E.Improving one class support vector machine novelty detection scheme using nonlinear features[J].Pattern Recognition，2018（83）：14-33.
[11] LU W N，LIANG B，CHENG Y.Deep model based domain adaptation for fault diagnosis[J].IEEE Transactions on Industrial Electronics，2017（64）：2296-2305.
[12] 龙明盛.迁移学习问题与方法研究[D].北京：清华大学，2014.
LONG M S.Transfer learning：problems and methods[D].Beijing：Tsinghua University，2014.
[13] 沈飞，陈超，严如强.奇异值分解与迁移学习在电机故障诊断中的应用[J].振动工程学报，2017，38（1）：118-126.
SHEN F，CHEN C，YAN R Q.Application of SVD and transfer learning strategy on motor fault diagnosis[J].Journal of Vibration Engineering，2017，38（1）：118-126.
[14] 陈超，沈飞，严如强.改进LSSVM迁移学习方法的轴承故障诊断[J].仪器仪表学报，2017，30（1）：33-40.
CHEN C，SHEN F，YAN R Q.Enhanced least squares support vector machine-based transfer learning strategy for bearing fault diagnosis[J].Chinese Journal of Scientific Instrument，2017，30（1）：33-40.
[15] ZHANG L，ZHANG D.Domain adaptation extreme learning machines for drift compensation in e-nose systems[J].IEEE Transactions on Instrumentation and Measurement，2015，64（7）：1790-1801.
[16] GHIFARY M，KLEIJN W B，ZHANG M J.Domain adaptive neural networks for object recognition[C]//Proceedings of the 13th Pacific Rim International Conference on Artificial Intelligence，Gold Coast，Australia，2014：898-904.
[17] LONG M S，WANG J M，CAO Y，et al.Deep learning of transferable representation for scalable domain adaptation[J].IEEE Transactions on Knowledge and Data Engineering，2016，28（8）：2027-2040.
[18] LI X，ZHANG W，DIN Q.A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning[J].Neurocomputing，2018，310（8）：77-95.
[19] SUN M，WANG H，LIU P，et al.A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings[J].Measurement，2019，146：305-314.
[20] SHAO H D，JIANG H K，LIN Y，et al.A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders[J].Mechanical Systems and Signal Processing，2018，102：278-297.
[21] ZHANG Y，LI B W，WANG W，et al.Supervised locally tangent space alignment for machine fault diagnosis[J].Journal of Mechanical Science and Technology，2014，28（8）：2971-2977.
[22] LONG M S，WANG J M，DING G G，et al.Adaptation regularization：a general framework for transfer learning[J].IEEE Transactions on Knowledge and Data Engineering，2014，26（5）：1078-1089.
[23] PENG Y，WANG S H，LONG X Z，et al.Discriminative graph regularized extreme learning machine and its application to face recognition[J].Neurocomputing，2015（149）：340-353.
[24] PANG S，YANG X Y.A cross-domain stacked denoising autoencoders for rotating machinery fault diagnosis under different working conditions[J].IEEE Access，2019，7：77277-77292.