Feifan, L.; Zhuoheng, D.; Lei, J.; Chanfei, S.; Caiming, Z.; Yingna, C. Prediction of Bearing RUL Through CNN -Bi-LSTM Based Domain-Adaptation Model. Preprints2024, 2024100128. https://doi.org/10.20944/preprints202410.0128.v1
APA Style
Feifan, L., Zhuoheng, D., Lei, J., Chanfei, S., Caiming, Z., & Yingna, C. (2024). Prediction of Bearing RUL Through CNN -Bi-LSTM Based Domain-Adaptation Model. Preprints. https://doi.org/10.20944/preprints202410.0128.v1
Chicago/Turabian Style
Feifan, L., Zhong Caiming and Chen Yingna. 2024 "Prediction of Bearing RUL Through CNN -Bi-LSTM Based Domain-Adaptation Model" Preprints. https://doi.org/10.20944/preprints202410.0128.v1
Abstract
Predicting the remaining useful life (RUL) of mechanical bearings is crucial in the industry. 1 Estimating the RUL enables the assessment of health bearing, maintenance planning, and signifi- 2 cant cost reduction, thereby fostering industrial development. Existing models rely on traditional 3 feature engineering, with feature changes because operating conditions pose a major challenge to 4 the generalization of RUL prediction models. This study focuses on neural network-based feature 5 engineering and the downstream prediction of the RUL, eliminating the need for specific prior 6 knowledge and simplifying the development and maintenance of models. Initially, a convolutional 7 neural network (CNN) model is employed for feature engineering. Subsequently, a bidirectional 8 long short-term memory network (Bi-LSTM) model is used to capture the time-series degradation 9 characteristics of the engineered features and predict the RUL through regression. Finally, the study 10 examines the influence of operating conditions in the model and integrates domain adaptation to 11 minimize differences in feature distribution, thereby enhancing the model’s generalizability for the 12 RUL prediction.
Keywords
bearing; RUL; CNN; Bi-LSTM; domain adaptation
Subject
Engineering, Industrial and Manufacturing Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.