Affiliation:
1. School of Information Engineering, China University of Geosciences, Beijing 100083, China
Abstract
Traditional methods for predicting remaining useful life (RUL) ignore the correlation between physical world data and virtual world data, leading to the low prediction accuracy of RUL and affecting the normal working of rolling element bearing (REB). To solve the above problem, we propose a hybrid method based on digital twin (DT) and long short-term memory (LSTM). The hybrid method combines the high simulation capabilities of DT and the strong data processing capabilities of LSTM. Firstly, we develop a DT system for the life characteristics analysis of an REB. When the DT system is implemented, we can obtain the theoretical value of RUL. Then, the experimental data is used to train the LSTM model. The output of LSTM is the actual value of RUL. Finally, the particle swarm optimization (PSO) algorithm fuses the theoretical values of DT with the actual values of LSTM. The case study demonstrates that the prediction accuracy of the hybrid method is greater than 97.5%, which improves the prediction performance and robustness of RUL. Therefore, the hybrid method is an important technology of REB prediction and health management (PHM). It realizes the early intervention and maintenance of mechanical equipment and ensures the safety of enterprises’ production.
Funder
Hebei University Science and technology research project
2023 Graduate Innovation Fund Project of China University of Geosciences, Beijing
Subject
Electrical and Electronic Engineering,Industrial and Manufacturing Engineering,Control and Optimization,Mechanical Engineering,Computer Science (miscellaneous),Control and Systems Engineering
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献