Zero-shot compound fault diagnosis of gearboxes via fault-coupled semantics

Abstract

Gearboxes with complex structures are key components in rotating machinery, and their failures exhibit both sporadic and coupling characteristics. However, in engineering practice, gearbox fault data are extremely scarce, and the sample size for composite faults is effectively zero. Therefore, it is of great significance to investigate fault diagnosis modeling methods under scarce fault samples and zero composite fault samples. This paper designs a new loss function for single single-fault samples and zero composite fault samples based on the prior knowledge of similarity between time series monitoring signals and the difference between single faults, as well as the prior knowledge that composite faults are composed of single faults. This enables the effective optimization of the feature encoder. On this basis, a diagnostic algorithm for single faults and composite faults of gearboxes is constructed, achieving effective diagnosis of various states of gearboxes. This paper validates the proposed method using two gearbox fault experimental platforms. The results show that the proposed method can construct and obtain the gearbox fault diagnosis model under single single-fault samples and zero composite fault samples.

Keywords

gearboxes / compound fault / zero shot / fault semantics / physical information network / contrastive learning

Acknowledgement

This study was supported by the Natural Science Foundation of Fujian Province (No.2024J08064), the Natural Science Foundation of Xiamen (No.3502Z202471042).

Declaration of conflicting interests

The authors have no conflict of interests related to this publication.

References

[1] YU J B, WANG S Y, WANG L, et al. Gearbox fault diagnosis based on a fusion model of virtual physical model and data-driven method. Mechanical Systems and Signal Processing, 2023, 188: 109980.

[2] XIA J Y, HUANG R Y, CHEN Z Y, et al. A novel digital twin-driven approach based on physical-virtual data fusion for gearbox fault diagnosis. Reliability Engineering & System Safety, 2023, 240: 109542.

[3] ZHOU P, CHEN S Q, HE Q B, et al. Rotating machinery fault-induced vibration signal modulation effects: a review with mechanisms, extraction methods and applications for diagnosis. Mechanical Systems and Signal Processing, 2023, 200: 110489.

[4] JIANG W X, WU J, ZHU H P, et al. Paired ensemble and group knowledge measurement for health evaluation of wind turbine gearbox under compound fault scenarios. Journal of Manufacturing Systems, 2023, 70: 382-394.

[5] YANG H B, WANG Z Y, XU M, et al. Improved deep transfer learning and transmission error based method for gearbox fault diagnosis with limited test samples. Mechanical Systems and Signal Processing, 2025, 230: 112593.

[6] REN Z J, LIN T T, FENG K, et al. A systematic review on imbalanced learning methods in intelligent fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3508535.

[7] PAN T, CHEN J, ZHANG T, et al. Generative adversarial network in mechanical fault diagnosis under small sample: a systematic review on applications and future perspectives. ISA Transactions, 2022, 128: 1-10.

[8] LIU P J, GUO Z C, HE L, et al. Fault diagnosis method of AC motor rolling bearing based on heterogeneous data fusion of current and infrared image. Journal of Measurement Science and Instrumentation, 2024, 15(4): 558-570.

[9] BAI Y H, CHENG W D, WEN W G, et al. Application of time-frequency analysis in rotating machinery fault diagnosis. Shock and Vibration, 2023, 2023: 9878228.

[10] PENG Y Y, QIAO W, CHENG F Z, et al. Wind turbine drivetrain gearbox fault diagnosis using information fusion on vibration and current signals. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3518011.

[11] WANG S B, CHENG C Y, ZHOU J H, et al. Reassignment-enable reweighted sparse time-frequency analysis for sparsity-assisted aeroengine rub-impact fault diagnosis. Mechanical Systems and Signal Processing, 2023, 183: 109602.

[12] CHEN X W, FENG Z P. Iterative generalized time–frequency reassignment for planetary gearbox fault diagnosis under nonstationary conditions. Mechanical Systems and Signal Processing, 2016, 80: 429-444.

[13] SYED S H, MURALIDHARAN V. Feature extraction using Discrete Wavelet Transform for fault classification of planetary gearbox-A comparative study. Applied Acoustics, 2022, 188: 108572.

[14] VASHISHTHA G, CHAUHAN S, KUMAR S, et al. Intelligent fault diagnosis of worm gearbox based on adaptive CNN using amended gorilla troop optimization with quantum gate mutation strategy. Knowledge-Based Systems, 2023, 280: 110984.

[15] ZHANG K, TANG B P, DENG L, et al. A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox. Measurement, 2021, 179: 109491.

[16] ZHANG J B, LI G Y, LIU R J, et al. Compound fault transfer diagnosis of gearboxes based on improved transformer network under small datasets and variable working conditions. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 3543018.

[17] VALLACHIRA S, ORKISZ M, NORRLÖF M, et al. Data-driven gearbox failure detection in industrial robots. IEEE Transactions on Industrial Informatics, 2020, 16(1): 193-201.

[18] CHEN Y G, JIA S L, ZHU J, et al. Fault diagnosis for on-board equipment of train control system based on BERT+CNN_BiLSTM. Journal of Measurement Science and Instrumentation, 2024, 15(1): 120-127.

[19] SINGH V, GANGSAR P, PORWAL R, et al. Artificial intelligence application in fault diagnostics of rotating industrial machines: a state-of-the-art review. Journal of Intelligent Manufacturing, 2023, 34(3): 931-960.

[20] KARNIADAKIS G E, KEVREKIDIS I G, LU L, et al. Physics-informed machine learning. Nature Reviews Physics, 2021, 3(6): 422-440.

[21] NI Q, JI J C, HALKON B, et al. Physics-Informed Residual Network (PIResNet) for rolling element bearing fault diagnostics. Mechanical Systems and Signal Processing, 2023, 200: 110544.

[22] YANG Y K, WANG X F, LI J F, et al. A data-physic driven method for gear fault diagnosis using PINN and pseudo-dynamic features. Measurement, 2024, 236: 115124.

[23] YU Y N, TANG L H, LIU Z P, et al. A novel bearing fault data generation strategy combining physical modeling and CycleGAN variant for fault diagnosis without real samples. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 3505717.

[24] SUN D Y, LI Y B, LIU Z, et al. Physics-inspired multimodal machine learning for adaptive correlation fusion based rotating machinery fault diagnosis. Information Fusion, 2024, 108: 102394.

[25] ZHU P, MA S, HAN Q K, et al. Deep contrastive transfer learning for rotating machinery fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 3501510.

[26] ZHANG S Y, WEI H L, DING J L. An effective zero-shot learning approach for intelligent fault detection using 1D CNN. Applied Intelligence, 2023, 53(12): 16041-16058.

[27] XU J, ZHOU L, ZHAO W H, et al. Zero-shot learning for compound fault diagnosis of bearings. Expert Systems with Applications, 2022, 190: 116197.

[28] LIAO W J, WU L K, XU S H, et al. A novel zero-shot learning method with feature generation for intelligent fault diagnosis. IEEE Transactions on Industrial Informatics, 2025, 21(4): 3386-3395.

[29] YANG J L, WANG C D, WEI C A. A novel Brownian correlation metric prototypical network for rotating machinery fault diagnosis with few and zero shot learners. Advanced Engineering Informatics, 2022, 54: 101815.

[30] MA C Y, WANG X Z, LI Y B, et al. Broad zero-shot diagnosis for rotating machinery with untrained compound faults. Reliability Engineering and System Safety, 2024, 242(C): 109704