基于深度学习的工业故障诊断综述

doi:10.13229/j.cnki.jdxbgxb.20260088

摘要/Abstract

摘要：

系统梳理了深度学习应用于工业故障诊断领域的各类研究成果，以填补现有综述未完整梳理方法演进路线、关键技术方向和实际应用方面各类问题的空白。梳理过程中可观察到，深度学习在该领域的发展已经逐渐从搭建基础网络架构延伸到开发混合架构，当前研究方向集中在注意力机制、迁移学习、生成对抗网络等技术方向的创新开发。实际落地过程中，工业场景对模型提出了多重要求，包括数据获取难度大、模型逻辑难解释、运算速度需匹配工业生产节奏等。本文进一步展望了自动化机器学习、多模态融合、物理信息融合等未来方向，可方便后续研究者进行相关工作，促进智能诊断技术融入自主运维模式。

关键词: 机械电子工程, 工业故障诊断, 注意力机制, 迁移学习, 自主机器学习, 生成对抗网络

Abstract:

This paper systematically reviews the various research results of in-depth learning applied in the field of industrial fault diagnosis， in order to fill the gaps in the evolution route， key technology direction and practical application of existing reviews. During the combing process， it can be observed that the development of deep learning in this field has gradually extended from the construction of basic network architecture to the development of hybrid architecture. The current research direction is focused on the innovative development of technology directions such as attention mechanism， transfer learning and generative adversarial networks. In the actual landing process， the industrial scene puts forward multiple requirements for the model， including the difficulty of data acquisition， the difficulty of model logic interpretation， and the need for the calculation speed to match the pace of industrial production. This paper further prospects the future directions of automated machine learning， multimodal fusion， physical information fusion， etc.， which can facilitate the follow-up researchers to carry out related work and promote the integration of intelligent diagnosis technology into the independent operation and maintenance mode.

Key words: mechanical electronics engineering, industrial fault diagnosis, attention mechanism, transfer learning, automated machine learning, generative adversarial networks

中图分类号:

TP181

刘昕晖,陈晫群,吕岩. 基于深度学习的工业故障诊断综述[J]. 吉林大学学报(工学版), 2026, 56(7): 1759-1779.

Xin-hui LIU,Zhuo-qun CHEN,Yan LYU. Review of industrial fault diagnosis based on deep learning[J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(7): 1759-1779.

图/表 15

图1

表1

图2

图3

图4

图5

图6

图7

图8

图9

表2

图10

图11

表3

表4

参考文献 78

[1]	Minh N Q, Khiem N T, Giang V H. Fault classification and localization in power transmission line based on machine learning and combined CNN-LSTM models[J]. Energy Reports, 2024, 12: 5610-5622.
[2]	Wang Z, Liu Q, Chen H, et al. A deformable CNN-DLSTM based transfer learning method for fault diagnosis of rolling bearing under multiple working conditions[J]. International Journal of Production Research, 2021, 59(16): 4811-4825.
[3]	Ye L, Ma X, Wen C. Rotating machinery fault diagnosis method by combining time-frequency domain features and CNN knowledge transfer[J]. Sensors, 2021, 21(24): No.8168.
[4]	Wang H, Xu J, Yan R, et al. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(5): 2377-2389.
[5]	Dibaj A, Ettefagh M M, Hassannejad R, et al. A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults[J]. Expert Systems with Applications, 2021, 167: No.114094.
[6]	Bu C, Liu T, Wang T, et al. A CNN-architecture-based photovoltaic cell fault classification method using thermographic images[J]. Energies, 2023, 16(9): No.3749.
[7]	Pham M T, Kim J M, Kim C H. 2D CNN-based multi-output diagnosis for compound bearing faults under variable rotational speeds[J]. Machines, 2021, 9(9): No.199.
[8]	Hu P, Zhao C, Huang J, et al. Intelligent and small samples gear fault detection based on wavelet analysis and improved CNN[J]. Processes, 2023, 11(10): No.2969.
[9]	Song X, Cong Y, Song Y, et al. A bearing fault diagnosis model based on CNN with wide convolution kernels[J]. Journal of Ambient Intelligence and Humanized Computing, 2022, 13(8): 4041-4056.
[10]	Zhao K, Xiao J, Li C, et al. Fault diagnosis of rolling bearing using CNN and PCA fractal based feature extraction[J]. Measurement, 2023, 223: 113754.
[11]	Wang X, Zhou P, Peng X, et al. Fault location of transmission line based on CNN-LSTM double-ended combined model[J]. Energy Reports, 2022, 8: 781-791.
[12]	Zhang Y, He L, Cheng G. MLPC-CNN: a multi-sensor vibration signal fault diagnosis method under less computing resources[J]. Measurement, 2022, 188: No.110407.
[13]	Cheng Y, Wang D, Zhou P, et al. A survey of model compression and acceleration for deep neural networks[EB/OL]. [2025-12-19]. .
[14]	Schmidhuber J. Deep learning in neural networks: an overview[J]. Neural Networks, 2015, 61: 85-117.
[15]	Hinton G E, Osindero S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[16]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[17]	Zachariades C, Xavier V. A review of artificial intelligence techniques in fault diagnosis of electric machines[J]. Sensors, 2025, 25: No.5128.
[18]	Choi D J, Han J H, Park S U, et al. Comparative study of CNN and RNN for motor fault diagnosis using deep learning[C]∥2020 IEEE 7th International Conference on Industrial Engineering and Applications, Bangkok, 2020: 693-696.
[19]	Hinton G, Deng L, Yu D, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97.
[20]	Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536.
[21]	Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[22]	Wang J, Joshi G. Cooperative SGD: a unified framework for the design and analysis of local-update SGD algorithms[J]. JMLR, 2021, 22(213): 1-50.
[23]	Zhu Y, Li G, Tang S, et al. Acoustic signal-based fault detection of hydraulic piston pump using a particle swarm optimization enhancement CNN[J]. Applied Acoustics, 2022, 192: No.108718.
[24]	Tang S, Zhu Y, Yuan S. Intelligent fault identification of hydraulic pump using deep adaptive normalized CNN and synchrosqueezed wavelet transform[J]. Reliability Engineering & System Safety, 2022, 224: No.108560.
[25]	Zhang C, Chen P, Jiang F, et al. Fault diagnosis of nuclear power plant based on sparrow search algorithm optimized CNN-LSTM neural network[J]. Energies, 2023, 16(6): No.2934.
[26]	Zhiyi H, Haidong S, Xiang Z, et al. An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE[J]. Advanced Engineering Informatics, 2020, 46: No.101150.
[27]	Chen H, Wei J, Huang H, et al. Novel imbalanced fault diagnosis method based on generative adversarial networks with balancing serial CNN and Transformer (BCTGAN)[J]. Expert Systems with Applications, 2024, 258: No.125171.
[28]	Wang Y, Li D, Li L, et al. A novel deep learning framework for rolling bearing fault diagnosis enhancement using VAE-augmented CNN model[J]. Heliyon, 2024, 10(15): No.e35407.
[29]	Cao H, Shao H, Zhong X, et al. Unsupervised domain-share CNN for machine fault transfer diagnosis from steady speeds to time-varying speeds[J]. Journal of Manufacturing Systems, 2022, 62: 186-198.
[30]	Yu G, Wu P, Lv Z, et al. Few-shot fault diagnosis method of rotating machinery using novel MCGM based CNN[J]. IEEE Transactions on Industrial Informatics, 2023, 19(11): 10944-10955.
[31]	Jia W, Dong Z, Shi H, et al. A zero-shot bearing fault diagnosis framework utilizing spatial relationships among primary features under variable working conditions[J]. Mechanical Systems and Signal Processing, 2025, 238: No.113103.
[32]	Lv Y, Qi X, Zheng X, et al. Unsupervised quantitative judgment of furnace combustion state with CBAM-SCAE-based flame feature extraction[J]. Journal of the Energy Institute, 2024, 116: No.101733.
[33]	Meng Z, Cao W, Sun D, et al. Research on fault diagnosis method of MS-CNN rolling bearing based on local central moment discrepancy[J]. Advanced Engineering Informatics, 2022, 54: No.101797.
[34]	Wang C, Li H, Zhang K, et al. Intelligent fault diagnosis of planetary gearbox based on adaptive normalized CNN under complex variable working conditions and data imbalance[J]. Measurement, 2021, 180: No.109565.
[35]	Gu Y, Zhang Y, Yang M, et al. Motor on-line fault diagnosis method research based on 1D-CNN and multi-sensor information[J]. Applied Sciences, 2023, 13(7): No.4192.
[36]	Peng D, Liu Z, Wang H, et al. A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains[J]. IEEE Access, 2019, 7: 10278-10293.
[37]	Li X, Li P, Zhang Z, et al. CNN-LSTM-based fault diagnosis and adaptive multichannel fusion calibration of filament current sensor for mass spectrometer[J]. IEEE Sensors Journal, 2024, 24(2): 2255-2269.
[38]	Chen J, Jiang J, Guo X, et al. An efficient CNN with tunable input-size for bearing fault diagnosis[J]. International Journal of Computational Intelligence Systems, 2021, 14(1): No.625.
[39]	Yuan Z, Zhang L, Duan L, et al. Intelligent fault diagnosis of rolling element bearings based on HHT and CNN[C]∥IEEE 2018 Prognostics and System Health Management Conference, Chongqing, China, 2018: 292-296.
[40]	Yu Z, Zhang C, Liu J, et al. SKND-TSACNN: a novel time-scale adaptive CNN framework for fault diagnosis of rotating machinery[J]. Knowledge-Based Systems, 2023, 275: No.110682.
[41]	Chen X, Zhang B, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021, 32(4): 971-987.
[42]	Luo R, Li Y, Guo H, et al. Cross-operating-condition fault diagnosis of a small module reactor based on CNN-LSTM transfer learning with limited data[J]. Energy, 2024, 313: No.133901.
[43]	Kang J, Zhu X, Shen L, et al. Fault diagnosis of a wave energy converter gearbox based on an Adam optimized CNN-LSTM algorithm[J]. Renewable Energy, 2024, 231: No.121022.
[44]	Snyder Q, Jiang Q, TRIPP E. Integrating self-attention mechanisms in deep learning: a novel dual-head ensemble transformer with its application to bearing fault diagnosis[J]. Signal Processing, 2025, 227: No.109683.
[45]	Zhu Q X, Qian Y S, Zhang N, et al. Multi-scale Transformer-CNN domain adaptation network for complex processes fault diagnosis[J]. Journal of Process Control, 2023, 130: No.103069.
[46]	Cheng D, Liu L, Yu Z. CNN-based intelligent fault-tolerant control design for turbofan engines with actuator faults[J]. IEEE Access, 2021, 9: 28122-28139.
[47]	Jiang T, Gradus J L, Rosellini A J. Supervised machine learning: a brief primer[J]. Behavior Therapy, 2020, 51(5): 675-687.
[48]	Li Y F, Liang D M. Safe semi-supervised learning: a brief introduction[J]. Frontiers of Computer Science, 2019, 13(4): 669-676.
[49]	Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
[50]	冯志刚,王颖,王宇.基于多通道融合的齿轮箱故障诊断方法[J/OL]. [2025-12-19]. .
[51]	Wang K, Gou C, Duan Y, et al. Generative adversarial networks: introduction and outlook[J]. IEEE/CAA Journal of Automatica Sinica, 2017, 4(4): 588-598.
[52]	Peng D, Wang H, Desmet W, et al. RMA-CNN: a residual mixed-domain attention CNN for bearings fault diagnosis and its time-frequency domain interpretability[J]. Journal of Dynamics, Monitoring and Diagnostics, 2023, 2: 115-132.
[53]	Huang Y, Zhang J, Liu R, et al. Improving accuracy and interpretability of CNN-based fault diagnosis through an attention mechanism[J]. Processes, 2023, 11(11): No. 3233.
[54]	Zhang J, Liang J, Liu J. Fault diagnosis in reactor coolant pump with an automatic CNN-based mixed model[J]. Progress in Nuclear Energy, 2024, 175: No.105294.
[55]	He C, Ge D, Yang M, et al. A data-driven adaptive fault diagnosis methodology for nuclear power systems based on NSGAII-CNN[J]. Annals of Nuclear Energy, 2021, 159: No. 108326.
[56]	Dembczyński K, Waegeman W, Cheng W, et al. On label dependence and loss minimization in multi-label classification[J]. Machine Learning, 2012, 88(1/2): 5-45.
[57]	Nam J, Kim J, Mencía E L, et al. Large-scale multi-label text classification-revisiting neural networks[J]. Lecture Notes in Computer Science, 2014, 8725: 437-452.
[58]	Zhang Z. Graph neural network-based bearing fault diagnosis using Granger causality test[J]. Expert Systems with Applications, 2024, 242: No.122827.
[59]	Weiss K, Khoshgoftaar T M, Wang D. A survey of transfer learning[J]. Journal of Big Data, 2016, 3(1): No.9.
[60]	CHEN Q, ZHANG F, WANG Y, et al. Bearing fault diagnosis based on efficient cross space multiscale CNN transformer parallelism[J]. Scientific Reports, 2025, 15(1): No.12344.
[61]	Zhao X, Yin F, Durrett G. Understanding synthetic context extension via retrieval heads[EB/OL]. [2025-12-19]. .
[62]	Liao Y L, Smidt T. EQUIFORMER: Equivariant graph attention transformer for 3D atomistic graphs[EB/OL]. [2025-12-19]. .
[63]	Ali M, Ali M, Hussain M, et al. Generative adversarial networks (GANs) for medical image processing: recent advancements[J]. Archives of Computational Methods in Engineering, 2025, 32(2): 1185-1198.
[64]	Baratchi M, Wang C, Limmer S, et al. Automated machine learning: past, present and future[J]. Artificial Intelligence Review, 2024, 57(5): No.122.
[65]	Alvarez-melis D, Jaakkola T S. On the robustness of interpretability methods[EB/OL]. [2025-12-19]. .
[66]	Siddique N I. Fault classification and location of a PMU-equipped active distribution network using deep convolution neural network (CNN)[J]. Electric Power Systems Research, 2024, 229: No. 110178.
[67]	He X, Zhao K, Chu X. AutoML: a survey of the state-of-the-art[J]. Knowledge-Based Systems, 2021, 212: No.106622.
[68]	Zhao X, Zhu X, Zhang R, et al. Imbalanced fault diagnosis of a conditional variational auto-encoder with transfer and adversarial structures[J]. Advanced Engineering Informatics, 2025, 64: No. 103032.
[69]	Shang Z, Wang Z, Pan C, et al. Physics-informed auto-encoder based on digital twin for rolling bearing fault diagnosis under imbalanced sample conditions[J]. Engineering Applications of Artificial Intelligence, 2026, 163: No.113017.
[70]	Lu Z, Chu Z, Zhu M, et al. Unsupervised feature learning using locality-preserved auto-encoder with complexity-invariant distance for intelligent fault diagnosis of machinery[J]. Applied Intelligence, 2025, 55(6): 379.
[71]	Bayoudh K. A survey of multimodal hybrid deep learning for computer vision: architectures, applications, trends, and challenges[J]. Information Fusion, 2024, 105: No.102217.
[72]	Yun T, Li J, Ma L, et al. Status, advancements and prospects of deep learning methods applied in forest studies[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 131: 103938.
[73]	Chen C, Wang T, Mao D, et al. A multi-scale graph pyramid attention network with knowledge distillation towards edge computing robotic fault diagnosis[J]. Expert Systems with Applications, 2025, 260: No.125469.
[74]	Yu Z, Wang Y, Zong X, et al. GRUDMU-DSCNN: an edge computing method for fault diagnosis with missing data[J]. Applied Intelligence, 2025, 55(2): No.140.
[75]	Zaman W, Siddique M F, Ullah S, et al. Hybrid deep learning model for fault diagnosis in centrifugal pumps: a comparative study of VGG16, ResNet50, and wavelet coherence analysis[J]. Machines, 2024, 12(12): No.905.
[76]	Wang X, Jiang H, Mu M, et al. A trackable multi-domain collaborative generative adversarial network for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2025, 224: No.111950.
[77]	Wang X, Jiang H, Zeng T, et al. An adaptive fused domain-cycling variational generative adversarial network for machine fault diagnosis under data scarcity[J]. Information Fusion, 2026, 126: No.103616.
[78]	Fan C, Zhang Y, Ma H, et al. A novel lightweight DDPM-based data augmentation method for rotating machinery fault diagnosis with small sample[J]. Mechanical Systems and Signal Processing, 2025, 232: No.112741.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

文献	主要贡献	局限性
［47］	系统梳理了监督学习的基本原理及其在健康监测中的应用	未深入探讨数据稀缺、工况多变等工业现实问题下的模型适应性
［48］	指出了在半监督学习中标注不足时盲目引入无标签数据的风险	未充分扩展到深度学习在故障诊断中的实际应用场景
［49］	强调了迁移学习在跨工况、跨设备诊断中的潜力	对其与深度学习的深度融合机制缺乏系统性总结
［50］	提出的Transformer架构及其自注意力机制在自然语言处理领域取得突破	在故障诊断时序信号建模中的适用性与局限性有待探讨
［51］	为故障数据增强提供了新思路	实际效能与工程落地路径不明确

评估指标	基线CNN（不平衡）	注意力CNN	迁移学习
最终训练准确率	0.974 7	0.934 0	0.995 8（源域）/0.875 0（目标域）
最终验证准确率	0.961 5	0.760 4	1.000 0（源域）/0.958 3（目标域）
训练轮次	80	80	80+80
训练稳定性	中等（波动较大）	良好	优秀
小样本适应性	差	中等	优秀

类别	具体表现	影响
数据稀缺与不平衡	故障样本极少，不同故障发生率差异较大	模型对罕见故障的识别能力差，整体性能下降
模型可解释性较差	深度学习作为“黑箱”，决策依据不明确	在关键场景难以被信任与采纳
实时性与边缘部署困难	模型计算复杂，难以满足毫秒级别的响应	可能导致故障的漏报、误报
跨域泛化能力不足	在训练分布外的工况下的性能有所下降	在新设备、新环境中需要对模型进行重新训练
多模态数据融合复杂	异构传感器数据在时序、语义上存在一定差异	信息未能做到有效互补，系统的鲁棒性较低

发展趋势	核心技术	可解决的问题
AutoML驱动的自适应诊断	NAS、超参数优化、动态资源分配	跨域泛化能力不足
多模态混合深度学习	跨模态注意力、知识迁移、多尺度融合	多模态数据融合复杂
物理信息融合的因果诊断	物理约束网络、因果推理、数字孪生	模型可解释性较差
边缘-云协同的分布式智能诊断	轻量化模型、联邦学习、5G/IoT	实时性与边缘部署困难
生成式人工智能驱动的数据增强与故障预测	扩散模型、条件GAN、时序生成模型	数据稀缺与不平衡