Remaining Fatigue Life Assessment of Electric Drive Axles Based on Data Augmentation and BiLSTM

Xiuyang Huang

doi:10.47297/taposatWSP2633-456905.20260702

PDF
Export
Share
Collection
Album

Remaining Fatigue Life Assessment of Electric Drive Axles Based on Data Augmentation and BiLSTM

Volume 7, Issue 2

Views: 0 Downloads: 0

Remaining Fatigue Life Assessment of Electric Drive Axles Based on Data Augmentation and BiLSTM
Remaining Fatigue Life Assessment of Electric Drive Axles Based on Data Augmentation and BiLSTM
University of Shanghai for Science and Technology, Shanghai, 20093, China
Vol. 7, Issue 2, Pages: 22-29(2026)
Published：28 February 2026
DOI：10.47297/taposatWSP2633-456905.20260702
Accepted：

Scan QR Code

Huang Xiuyang.Remaining Fatigue Life Assessment of Electric Drive Axles Based on Data Augmentation and BiLSTM[J].Theory and Practice of Science and Technology,2026,07(02):22-29.
DOI：

Huang Xiuyang.Remaining Fatigue Life Assessment of Electric Drive Axles Based on Data Augmentation and BiLSTM[J].Theory and Practice of Science and Technology,2026,07(02):22-29. DOI： 10.47297/taposatWSP2633-456905.20260702.

摘要

Abstract

The prognosis of remaining fatigue life (RFL) for drive axles is paramount in mechanical engineering; however

the scarcity of empirical fatigue monitoring data

particularly within the electric vehicle (EV) sector

presents a formidable obstacle to accurate durability assessment. This research introduces an innovative two-stage methodology designed for RFL estimation. In the initial phase

a Bidirectional Generative Adversarial Network (BiGAN) is implemented to synthesize degradation trajectories from limited samples and derive corresponding high-dimensional Health Indices (HI). During the subsequent phase

a Bidirectional Long Short-Term Memory (BiLSTM) network is utilized to map multi-channel sensor observations onto these HIs

facilitating regression-based remaining life prediction. Empirical evaluations across diverse drive axle datasets demonstrate robust predictive performance

yielding a mean Root Mean Square Error (RMSE) of 0.0723 and a Mean Absolute Error (MAE) of 0.0375. Furthermore

a 3D-printed drive axle surrogate model was employed to conduct physical bench tests under simulated operating conditions

generating a stress-induced failure dataset. These physical experiments substantiated both the predictive precision and the physical fidelity of the proposed network. The proposed framework significantly bolsters predictive maintenance capabilities within the automotive industry

effectively minimizing downtime

mitigating safety risks

and curtailing operational costs in engineering applications.

关键词

Keywords

references

D. Ronanki, S. A. Singh, and S. S. Williamson, "Comprehensive Topological Overview of Rolling Stock Architectures and Recent Trends in Electric Railway Traction Systems," IEEE Transactions on Transportation Electrification, vol. 3 , no. 3 , pp. 724 - 738 , 2017 .

Y. Chen, W. Men, Z. Yuan et al., "Nonlinear Damage Accumulation Rule for Solder Life Prediction Under Combined Temperature Profile With Varying Amplitude," IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 9 , no. 1 , pp. 39 - 50 , 2019 .

J. Zhang, Y. Yan, S. Jin et al., "Fatigue tests and design of welded hollow spherical joints in grid structures," Structures, vol. 65 , pp. 106590 , 2024/07/01/, 2024.

F. Zhao, Z. Tian, and Y. Zeng, "Uncertainty Quantification in Gear Remaining Useful Life Prediction Through an Integrated Prognostics Method," IEEE Transactions on Reliability, vol. 62 , no. 1 , pp. 146 - 159 , 2013 .

Y. Zhang, L. Fang, Z. Qi et al., "A Review of Remaining Useful Life Prediction Approaches for Mechanical Equipment," IEEE Sensors Journal, vol. 23 , no. 24 , pp. 29991 - 30006 , 2023 .

H. Zhang, X. Xi, and R. Pan, "A two-stage data-driven approach to remaining useful life prediction via long short-term memory networks," Reliability Engineering and System Safety, vol. 237 , 2023.

S. Wang, H. Ma, Y. Zhang et al., "Remaining useful life prediction method of lithium-ion batteries is based on variational modal decomposition and deep learning integrated approach," Energy, vol. 282 , 2023.

J. Bi, X. Zhang, H. Yuan et al., "A Hybrid Prediction Method for Realistic Network Traffic With Temporal Convolutional Network and LSTM," IEEE Transactions on Automation Science and Engineering, vol. 19 , no. 3 , pp. 1869 - 1879 , 2022 .

X. Li, C. Ye, B. Huang et al., "A Shortcut Enhanced LSTM-GCN Network for Multi-Sensor Based Human Motion Tracking," IEEE Transactions on Automation Science and Engineering, vol. 21 , no. 4 , pp. 5078 - 5087 , 2024 .

Z. Wang, J. Cheng, H. Zheng et al., "Multistage Convolutional Autoencoder and BCM-LSTM Networks for RUL Prediction of Rolling Bearings," IEEE Transactions on Instrumentation and Measurement, vol. 72 , pp. 1 - 13 , 2023 .

Y. Wei, J. Jang-Jaccard, W. Xu et al., "LSTM-Autoencoder-Based Anomaly Detection for Indoor Air Quality Time-Series Data," IEEE Sensors Journal, vol. 23 , no. 4 , pp. 3787 - 3800 , 2023 .

X. Yang, D. Chen, J. Huang et al., "Remaining Useful Life Prediction Under Multiple Operating Conditions Based on a Novel Dual-Layer Temporal Convolutional Network," IEEE Sensors Journal, vol. 25 , no. 1 , pp. 1900 - 1911 , 2025 .

Z. Yang, Y. Wang, Y. Yang et al., "Remaining Useful Life Prediction Approach for Aviation Bearings Based on Multigenerator Generative Adversarial Network and CBAM," IEEE Transactions on Instrumentation and Measurement, vol. 74 , pp. 1 - 9 , 2025 .

W. Luo, W. Yang, J. He et al., "Fault Diagnosis Method Based on Two-Stage GAN for Data Imbalance," IEEE Sensors Journal, vol. 22 , no. 22 , pp. 21961 - 21973 , 2022 .

Y. Zou, L. Yu, and K. He, "Forecasting crude oil risk: A multiscale bidirectional generative adversarial network based approach," Expert Systems with Applications, vol. 212 , 2023.

Y. Xiao, J. Yu, G. X. Xu et al., "An improved bidirectional generative adversarial network model for multivariate estimation of correlated and imbalanced tunnel construction parameters," JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING, vol. 15 , no. 7 , pp. 1797 - 1809 , JUL, 2023.

Q. Su, B. Tian, H. Wan et al., "Anomaly Detection Under Contaminated Data With Contamination-Immune Bidirectional GANs," IEEE Transactions on Knowledge and Data Engineering, vol. 36 , no. 11 , pp. 5605 - 5620 , 2024 .

Alert me when the article has been cited

Submit

No data

Related Author

No data

Related Institution

No data

⁰