Improved CNN-LSTM Bearing Remaining Useful Life Prediction Based on the Weibull Loss Function

Yanping Zhang; Kho Lee Chin; Xiaozheng Li; Mingqiang Zhang; Dongfeng Yuan; Annie Joseph

doi:10.46604/peti.2025.15348

Authors

Yanping Zhang Faculty of Engineering, Universiti Malaysia Sarawak, Kota Samarahan, Sarawak, Malaysia/ Shandong Provincial Key Laboratory of Industrial Big Data and Intelligent Manufacturing, Qilu Institute of Technology, Shandong, China
Kho Lee Chin Faculty of Engineering, Universiti Malaysia Sarawak, Kota Samarahan, Sarawak, Malaysia
Xiaozheng Li School of Information and Electrical Engineering, Shandong Jianzhu University, Shandong, China
Mingqiang Zhang School of Cyber Science and Engineering, Qufu Normal University, Shandong, China
Dongfeng Yuan School of QILU Transportation, Shandong University, Shandong, China
Annie Joseph Faculty of Engineering, Universiti Malaysia Sarawak, Kota Samarahan, Sarawak, Malaysia

DOI:

https://doi.org/10.46604/peti.2025.15348

Keywords:

bearing life prediction, Weibull, CNN, deep learning, predictive maintenance

Abstract

The prediction of the remaining useful life (RUL) of rolling bearings is a critical task in predictive maintenance. This paper presents a deep learning model named knowledge-driven convolutional neural network–long short-term memory (KCNN-LSTM), enhanced by the Weibull-based loss function tailored with historical bearing failure data. By incorporating a probabilistic Weibull modeling mechanism, the model can accurately capture the uncertainty and accelerated degradation trend of bearing failure over time. The prognostics and health management (PHM) 2012 and XJTU-SY bearing datasets are utilized to evaluate the proposed KCNN-LSTM model. The results indicate that the proposed KCNN-LSTM achieves superior performance compared with the conventional CNN-LSTM model, leading to a 10.2% improvement in the score metric and a notable reduction in prediction error. The proposed model offers a practical and effective approach for enhancing predictive maintenance in high-reliability industrial systems.

References

J. Zhuang, M. Jia, Y. Cao, and X. Zhao, “Semi-Supervised Double Attention Guided Assessment Approach for Remaining Useful Life of Rotating Machinery,” Reliability Engineering & System Safety, vol. 226, article no. 108685, 2022.

S. Nandi, H. A. Toliyat, and X. Li, “Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review,” IEEE Transactions on Energy Conversion, vol. 20, no. 4, pp. 719-729, 2005.

S. Gawde, S. Patil, S. Kumar, P. Kamat, K. Kotecha, and A. Abraham, “Multi-Fault Diagnosis of Industrial Rotating Machines Using Data-Driven Approach: A Review of Two Decades of Research,” Engineering Applications of Artificial Intelligence, vol. 123, part A, article no. 106139, 2023.

N. Costa and L. Sánchez, “Variational Encoding Approach for Interpretable Assessment of Remaining Useful Life Estimation,” Reliability Engineering & System Safety, vol. 222, article no. 108353, 2022.

J. Zhang, C. Zhang, S. Xu, G. Liu, H. Fei, and L. Wu, “Remaining Life Prediction of Bearings Based on Improved IF-SCINe,” IEEE Access, vol. 12, pp. 19598-19611, 2024.

L. Li and Q. Jian, “Remaining Useful Life Prediction of Wind Turbine Main-Bearing Based on LSTM Optimized Network,” IEEE Sensors Journal, vol. 24, no. 13, pp. 21143-21156, 2024.

K. You, P. Wang, and Y. Gu, “Toward Efficient and Interpretative Rolling Bearing Fault Diagnosis via Quadratic Neural Network with Bi-LSTM,” IEEE Internet of Things Journal, vol. 11, no. 13, pp. 23002-23019, 2024.

Y. Guo, J. Zhou, Z. Dong, H. She, and W. Xu, “Rolling Bearing RUL Prediction Based on Fusion of Multi-Head Attention and Improved TCN-BiLSTM,” IEEE Access, vol. 12, pp. 95641-95658, 2024.

D. K. B. Kulevome, H. Wang, and X. Wang, “Rolling Bearing Fault Diagnostics Based on Improved Data Augmentation and ConvNet,” Journal of Systems Engineering and Electronics, vol. 34, no. 4, pp. 1074-1084, 2023.

Z. Chen, B. Xu, and Z. Zhang, “Rolling Bearing Fault Diagnosis Based on Recurrence Plot,” IEEE Access, vol. 12, pp. 149710-149721, 2024.

Y. Chang and G. Bao, “Enhancing Rolling Bearing Fault Diagnosis in Motors Using the OCSSA-VMD-CNN-BiLSTM Model: A Novel Approach for Fast and Accurate Identification,” IEEE Access, vol. 12, pp. 78463-78479, 2024.

J. Tong, C. Liu, J. Bao, H. Pan, and J. Zheng, “A Novel Ensemble Learning-Based Multisensor Information Fusion Method for Rolling Bearing Fault Diagnosis,” IEEE Transactions on Instrumentation and Measurement, vol. 72, article no. 9501712, 2022.

J. Mi, M. Chu, Y. Hou, J. Jin, W. Huang, T. Xiang, et al., “A Fault Diagnosis Method for Rolling Bearing Based on Deep Adversarial Transfer Learning with Transferability Measurement,” IEEE Sensors Journal, vol. 24, no. 1, pp. 984-994, 2024.

J. Zheng, S. Cao, K. Feng, and Q. Liu, “Zero-Phase Filter-Based Adaptive Fourier Decomposition and Its Application to Fault Diagnosis of Rolling Bearing,” IEEE Transactions on Instrumentation and Measurement, vol. 73, article no. 3512111, 2023.

M. Sun, X. Xiao, T. Chen, Q. He, Z. Long, and L. Li, “A Novel Domain Incremental Learning Method for Bearing Fault Diagnosis Based on F&K,” IEEE Transactions on Industrial Informatics, vol. 21, no. 1, pp. 980-989, 2025.

H. Liu, R. Yuan, Y. Lv, X. Yang, H. Li, and G. Song, “Degradation Tracking of Rolling Bearings Based on Local Polynomial Phase Space Warping,” IEEE Transactions on Reliability, vol. 73, no. 2, pp. 1380-1392, 2024.

C. Peng, Y. Sheng, W. Gui, Z. Tang, and C. Li, “A Rolling Bearing Fault Diagnosis Method Based on Multimodal Knowledge Graph,” IEEE Transactions on Industrial Informatics, vol. 20, no. 11, pp. 13047-13057, 2024.

C. Wang, X. Wang, and C. Zeng, “Saw Blade Wear Identification Based on Data Enhancement and Feature Fusion,” IEEE Access, vol. 11, pp. 123677-123687, 2023.

C. Li, Y. Tang, N. Lei, and X. Wang, “An Intelligent Fault Diagnosis Method Based on Optimized Parallel Convolutional Neural Network,” IEEE Sensors Journal, vol. 25, no. 4, pp. 6160-6175, 2025.

Y. Chen and L. Xiao, “A Multisource–Multitarget Domain Adaptation Method for Rolling Bearing Fault Diagnosis,” IEEE Sensors Journal, vol. 24, no. 3, pp. 3406-3419, 2024.

X. Zhao, L. Wang, M. Yang, Y. Chen, and J. Xiang, “A Novel Small-Sample Fault Diagnosis Method for Rolling Bearings via Continuous Wavelet Transform and Siamese Neural Network,” IEEE Sensors Journal, vol. 24, no. 15, pp. 24988-24996, 2024.

Z. Cao, J. Dai, W. Xu, and C. Chang, “Sparse Bayesian Learning Approach for Compound Bearing Fault Diagnosis,” IEEE Transactions on Industrial Informatics, vol. 20, no. 2, pp. 1562-1574, 2024.

Z. Meng, T. Shao, J. Liu, J. Li, L. Cao, and F. Fan, “Scale-Demodulation Adaptive Chirp Mode Decomposition with Application to Rolling Bearing Fault Diagnosis,” IEEE Sensors Journal, vol. 24, no. 20, pp. 32554-32565, 2024.

J. Feng, Y. Xing, Y. Yao, and B. Wang, “Artificial Feature Bias Rectified by Self-Supervised Learning for Rolling Bearings Fault Diagnosis Under Limited Labeled Vibration Signals,” IEEE Transactions on Instrumentation and Measurement, vol. 74, article no. 3502812, 2024.

B. Chang, X. Zhao, D. Guo, S. Zhao, and J. Fei, “Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE,” IEEE Access, vol. 12, pp. 130746-130762, 2024.

A. Yan, Y. Zhao, Z. Lu, Y. Pang, S. Jin, Z. Liu, et al., “An Online Fault Detection and Remaining Life Prediction Method Based on SVDD for Rolling Bearings,” IEEE Transactions on Instrumentation and Measurement, vol. 73, article no. 3516112, 2024.

C. Gao, Z. Wang, Y. Guo, H. Wang, and H. Yi, “MPINe: Multiscale Physics-Informed Network for Bearing Fault Diagnosis with Small Samples,” IEEE Transactions on Industrial Informatics, vol. 20, no. 12, pp. 14371-14380, 2024.

P. Nectoux, R. Gouriveau, K. Medjaher, E. Ramasso, B. Morello, N. Zerhouni, et al., “PRONOSTIA: An Experimental Platform for Bearings Accelerated Degradation Tests,” IEEE International Conference on Prognostics and Health Management, pp. 1-8, 2012.

T. von Hahn and C. K. Mechefske, “Knowledge Informed Machine Learning Using a Weibull-Based Loss Function,” https://doi.org/10.48550/arXiv.2201.01769, 2022.