Image encoding-based bearing fault diagnosis: Review and challenges for high-speed trains

Abstract

High-Speed Trains (HSTs) have emerged as a mainstream mode of transportation in China, owing to their exceptional safety and efficiency. Ensuring the reliable operation of HSTs is of paramount economic and societal importance. As critical rotating mechanical components of the transmission system, bearings make their fault diagnosis a topic of extensive attention. This paper provides a systematic review of image encoding-based bearing fault diagnosis methods tailored to the condition monitoring of HSTs. First, it categorizes the image encoding techniques applied in the field of bearing fault diagnosis. Then, a review of state-of-the-art studies has been presented, encompassing both monomodal image conversion and multimodal image fusion approaches. Finally, it highlights current challenges and proposes future research directions to advance intelligent fault diagnosis in HSTs, aiming to provide a valuable reference for researchers and engineers in the field of intelligent operation and maintenance.

Keywords

High-speed trains / Image encoding / Fault diagnosis / Rotating machinery / Condition monitoring

CRediT authorship contribution statement

Bin Liu: Writing – review & editing. Lingfeng Li: Writing – review & editing. Huimin Li: Writing – original draft. Ge Xin: Writing – review & editing, Supervision, Conceptualization.

Declaration of Competing Interest

The authors declare the following personal relationships which may be considered as potential competing interests: Bin Liu is currently employed by Division of Car-Body, CRRC Tangshan CO., LTD.

Acknowledgements

This work is supported by the Fundamental Research Funds for the Central Universities (No. 2024JBZX027), the National Natural Science Foundation of China (No. 52375078).

References

[1] E. Zio. Advances in reliability analysis and risk assessment for enhanced safety. J. Reliab. Sci. Eng., 1 (2025) 013002.

[2] W. Hu, G. Xin, J. Wu, et al., Vibration-based bearing fault diagnosis of high-speed trains: A literature review. High-speed Rail., 1(4)(2023), pp. 219-223.

[3] Y. Li, S. Wang, J. Xie, et al., A lightweight dual-compression fault diagnosis framework for high-speed train bogie bearing. IEEE Trans. Instrum. Meas., 73 (2024), pp. 1-14.

[4] B. Han, Z. Yang, Z. Zhang, et al., A novel rolling bearing fault diagnosis method based on generalized nonlinear spectral sparsity. Measurement, 198 (2022) 111131.

[5] Z. Zhang, W. Huang, Y. Liao, et al., Bearing fault diagnosis via generalized logarithm sparse regularization. Mech. Syst. Signal Proc., 167 (2022) 108576.

[6] J. Wu, Y. Li, L. Jia, et al., Semi-supervised fault diagnosis of wheelset bearings in high-speed trains using autocorrelation and improved flow Gaussian mixture model. Eng. Appl. Artif. Intell., 132 (2024) 107861.

[7] A. Rai, S. Upadhyay. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol. Int., 96 (2016), pp. 289-306.

[8] A. Soomro, B. Muhammad, A. Mokhtar, et al., Insights into modern machine learning approaches for bearing fault classification: A systematic literature review. Res. Eng., 23 (2024) 102700.

[9] Z. Zhu, Y. Lei, G. Qi, et al., A review of the application of deep learning in intelligent fault diagnosis of rotating machinery. Measurement, 206 (2023) 112346.

[10] Y. Zhang, C. Li, Y. Tang, et al., A novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder and transfer learning. Manuf. Syst., 76 (2024), pp. 443-456.

[11] X. Zhang, T. Wang, L. Ma, et al., Reliability engineering, risk management, and trustworthiness assurance for AI systems. J. Reliab. Sci. Eng., 1(2)(2025) 022001.

[12] T. Ince. Real-time broken rotor bar fault detection and classification by shallow 1D convolutional neural networks. Electr. Eng., 101(2)(2019), pp. 599-608.

[13] L. Deng, C. Zhao, X. Yan, et al., A novel approach for bearing fault diagnosis in complex environments using PSO-CWT and SA-FPN. Measurement, 249 (2025) 117027.

[14] S. Liu, Z. Ji, Z. Zhang, et al., An improved deep transfer learning method for rotating machinery fault diagnosis based on time frequency diagram and pretraining model. IEEE Trans. Instrum. Meas., 73 (2024), pp. 1-12.

[15] G. Xin, Z. Li, L. Jia, et al., Fault diagnosis of wheelset bearings in high-speed trains using logarithmic short-time Fourier transform and modified self-calibrated residual network. IEEE Trans. Ind. Inf., 18(10)(2022), pp. 7285-7295.

[16] G. Hamzaoui, N. Hamzaoui, J. Antoni. Semi-automated diagnosis of bearing faults based on a hidden Markov model of the vibration signals. Measurement, 127 (2018), pp. 141-166.

[17] Y. Xu, Z. Li, S. Wang, et al., A hybrid deep-learning model for fault diagnosis of rolling bearings. Measurement, 169 (2021) 108502.

[18] Y. Li, X. Liu, J. Hu, et al., Graph optimization algorithm enhanced by dual-scale spectral features with contrastive learning for robust bearing fault diagnosis. Knowl.-based Syst., 315 (2025) 113275.

[19] Z. Zhang, Y. Qin, L. Jia, et al., Visibility graph feature model of vibration signals: A novel bearing fault diagnosis approach. Materials, 11(11)(2018), p. 2262.

[20] P. Yin, J. Nie, X. Liang, et al., A multiscale graph convolutional neural network framework for fault diagnosis of rolling bearing. IEEE Trans. Instrum. Meas., 72 (2023), pp. 1-13.

[21] L. Ou, D. Yu, H. Yang. A new rolling bearing fault diagnosis method based on GFT impulse component extraction. Mech. Syst. Signal Proc., 81 (2016), pp. 162-182.

[22] Y. Liu, S. Dou, Y. Du, et al., Gearbox fault diagnosis based on gramian angular field and CSKD-ResNeXt. Electronics, 12(11)(2023), p. 2475.

[23] S. Ding, Z. Rui, C. Lei, et al., A rolling bearing fault diagnosis method based on Markov transition field and multi-scale Runge-Kutta residual network. Meas. Sci. Technol., 34 (12) (2023).

[24] X. Li, T. Zhou, S. Qiu. Alzheimer’s disease analysis algorithm based on no-threshold recurrence plot convolution network. Front. Aging Neurosci., 14 (2022) 888577.

[25] M. Stender, S. Oberst, M. Tiedemann, et al., Complex machine dynamics: Systematic recurrence quantification analysis of disk brake vibration data. Nonlinear Dyn., 97(4)(2019), pp. 2483-2497.

[26] L. Ji, Z. Wei, J. Hao, et al., An intelligent diagnostic method of ECG signal based on Markov transition field and a ResNet. Comput. Methods Prog. Biomed., 242 (2023) 107784.

[27] J. Xie, J. Xu, Z. Wei, et al., Fault isolating and grading for Li-ion battery packs based on pseudo images and convolutional neural network. Energy, 263 (2023) 125867.

[28] Y. Liu, K. Wang, G. Li, et al., Semantics-aware adaptive knowledge distillation for sensor-to-vision action recognition. IEEE Trans. Image Process., 30 (2021), pp. 5573-5588.

[29] L. Zhang, S. Zhang. Gas/liquid two-phase flow pattern identification method using Gramian angular field and densely connected network. IEEE Sens. J., 23(4)(2023), pp. 4022-4032.

[30] F. Liu, C. Liang, Z. Guo, et al., Fault diagnosis of rolling bearings under varying speeds based on gray level co-occurrence matrix and DCCNN. Measurement, 235 (2024) 114955.

[31] H. Wang, J. Xu, R. Yan, et al., Intelligent bearing fault diagnosis using multi-head attention-based CNN. Proc. Manuf., 49 (2020), pp. 112-118.

[32] Y. Cheng, B. Zhou, C. Lu, et al., Fault diagnosis for rolling bearings under variable conditions based on visual cognition. Materials, 10(6)(2017), p. 582.

[33] C. Lei, C. Miao, H. Wan, et al., Rolling bearing fault diagnosis method based on MTF-MFACNN. Meas. Sci. Technol., 35(3)(2024) 035007.

[34] D. Ding, J. Li, H. Wang, et al., ApplianceFilter: Targeted electrical appliance disaggregation with prior knowledge fusion. Appl. Energy, 365 (2024) 123157.

[35] Z. Zhou, Q. Ai, P. Lou, et al., A novel method for rolling bearing fault diagnosis based on gramian angular field and CNN-ViT. Sensors, 24(12)(2024), p. 3967.

[36] Y. Chen, D. Zhang, C. Deng, et al., Integrated learning method of gramian angular field and optimal feature channel adaptive selection for bearing fault diagnosis. 2022 8th International Conference on Control, Automation and Robotics (ICCAR), IEEE, Xiamen (2022), pp. 209-217.

[37] Z. Liu, H. Yu, K. Xu, et al., RMCW: An improved residual network with multi-channel weighting for machinery fault diagnosis. IEEE Access, 11 (2023), pp. 124472-124483.

[38] J. Liu, Y. Tan, N. Yang, et al., An anti-noise bearing’s fault diagnosis method using adaptive deconvolution and mobile ViT. IEEE Sens. J., 25(11)(2024), pp. 19563-19575.

[39] Z. Huang, X. Song, Z. Liao, et al., Bearing fault feature enhancement and diagnosis based on Savitzky–Golay filtering Gramian angular field. IEEE Access, 12 (2024), pp. 87991-88005.

[40] A. Nath, S. Udmale, D. Raghuwanshi, et al., Improved structural rotor fault diagnosis using multi-sensor fuzzy recurrence plots and classifier fusion. IEEE Sens. J., 21(19)(2021), pp. 21705-21717.

[41] Y. Sun, G. Yu, W. Wang. Image texture feature fusion enhancement for bearing fault diagnosis based on maximum gradient. Reliab. Eng. Syst. Saf., 260 (2025) 111009.

[42] B. Han, H. Zhang, M. Sun, et al., A new bearing fault diagnosis method based on capsule network and Markov transition field/Gramian angular field. Sensors, 21(22)(2021), p. 7762.

[43] Q. Yang, B. Tang, Y. Shen, et al., Self-attention parallel fusion network for wind turbine gearboxes fault diagnosis. IEEE Sens. J., 23(19)(2023), pp. 23210-23220.

[44] P. Liu, S. Zhao, L. Kang, et al., CNN intelligent diagnosis method for bearing incipient faint faults based on adaptive stochastic resonance-wave peak cross correlation sliding sampling. Digit. Signal Process., 156 (2025) 104871.

[45] W. Jia, H. Shi, Z. Dong, et al., A rolling bearing fault diagnosis framework under variable working conditions considers dynamic feature extraction. Eng. Appl. Artif. Intell., 146 (2025) 110255.

[46] G. Xin, Q. Zhong, Y. Jin, et al., Autonomous bearing fault diagnosis based on Fault-Induced envelope spectrum and moving peaks-over-threshold approach. IEEE Trans. Instrum. Meas., 73 (2024), pp. 1-12.

[47] G. Xin, Y. Chen, L. Li, et al., Complex symplectic geometry mode decomposition and a novel time–frequency fault feature extraction method. IEEE Trans. Instrum. Meas., 74 (2025), pp. 1-10.

[48] Y. Zhou, R. Zhu, H. Zhao, et al., Influence of noise on wear fault diagnosis based on recurrence plot. Measurement, 205 (2022) 112158.

[49] B. Wang, W. Qiu, X. Hu, et al., A rolling bearing fault diagnosis technique based on recurrence quantification analysis and Bayesian optimization SVM. Appl. Soft Comput., 156 (2024) 111506.

[50] T. Jian, J. Cao, W. Liu, et al., A novel wind turbine fault diagnosis method based on compressive sensing and lightweight SqueezeNet model. Expert Syst. Appl., 260 (2025) 125440.

[51] K. Shao, Y. He, X. He, et al., Distribution recurrence plots and measures: effective signal analysis tools for fault diagnosis of wind turbine drivetrain system. Adv. Eng. Inf., 56 (2023) 101985.

[52] A. Tong, J. Zhang, L. Xie. Intelligent fault diagnosis of rolling bearing based on gramian angular difference field and improved dual attention residual network. Sensors, 24(7)(2024), p. 2156.

[53] Y. Cui, R. Wang, Y. Si, et al., T-type inverter fault diagnosis based on GASF and improved AlexNet. Energy Rep., 9 (2023), pp. 92718-92731.

[54] H. Tang, Y. Tang, Y. Su, et al., Feature extraction of multi-sensors for early bearing fault diagnosis using deep learning based on minimum unscented kalman filter. Eng. Appl. Artif. Intell., 127 (2024) 107138.

[55] H. Tang, K. Zhang, B. Wang, et al., Early bearing fault diagnosis for imbalanced data in offshore wind turbine using improved deep learning based on scaled minimum unscented kalman filter. Ocean Eng., 300 (2024) 117392.

[56] J. Lu, J. Chen, D. Yang, et al., Two-dimensional small leak detection of pipeline based on time sequence coding. Flow Meas. Instrum., 97 (2024) 102572.

[57] Z. Wang, J. Shen, X. Zhang, et al., Gear fault diagnosis research based on GAF-TFR-2DCV with small sample size. Ain Shams Eng. J., 16(5)(2025) 103344.

[58] J. Wang, H. Shao, J. He, et al., A novel interpretable fault diagnosis method using multi-image feature extraction and attention fusion. Pattern Recognit. Lett., 189 (2025), pp. 38-47.

[59] G. Li, J. Ao, J. Hu, et al., Dual-source gramian angular field method and its application on fault diagnosis of drilling pump fluid end. Expert Syst. Appl., 237 (2024) 121521.

[60] Y. Hong, R. Pula. Diagnosis of PV faults using digital twin and convolutional mixer with LoRa notification system. Energy Rep., 9 (2023), pp. 1963-1976.

[61] V. Christian, L. Iraklis. Development of a time series imaging approach for fault classification of marine systems. Ocean Eng., 263 (2022) 112297.

[62] C. Cai, T. Xu, J. Ren, et al., Bearing fault diagnosis based on the Markov transition field and SE-IShufflenetV2 model. Struct. Durab. Health Monit., 19(1)(2024), pp. 125-144.

[63] J. Song, X. Wu, L. Qian, et al., PMSLM eccentricity fault diagnosis based on deep feature fusion of stray magnetic field signals. IEEE Trans. Instrum. Meas., 73 (2024), pp. 1-12.

[64] J. Zhang, J. Chen, H. Deng, et al., A novel framework based on adaptive multi-task learning for bearing fault diagnosis. Energy Rep., 9(S8)(2023), pp. 522-531.

[65] H. Huang, H. Li, Y. Shi, et al., Theory and application of possibility and evidence in reliability analysis and design optimization. J. Reliab. Sci. Eng., 1 (2025) 015007.

[66] Y. Shi, L. Niu, M. Beer. Adaptive artificial neural network for uncertainty propagation. J. Reliab. Sci. Eng., 1 (2025) 015002.

[67] M. Compare, E. Zio. Opportunities and risks of artificial intelligence for industry 5.0 in the context ofreliability and maintenance engineering. J. Reliab. Sci. Eng., 1 (2025) 015001.