School of Mechanical and Electrial Engineering, University of Electronic Science and Technology of China. Qingshuihe Campus, No.2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu 611731, Sichuan, China
Dr. Yu Liu
School of Mechanical and Electrial Engineering, University of Electronic Science and Technology of China. Qingshuihe Campus, No.2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu 611731, Sichuan, China
The remaining useful lifetime (RUL) and state of charge (SoC) of rechargeable lithium-ion batteries (LIBs) are two integral parts to ensure LIBs working reliably and safely for transportation electrification systems. The two together reflect the state of a battery in use. However, existing capacity estimation approaches focus on separately modeling one of them, and no one has proposed a unified estimation model that is applicable to both RUL and SoC estimation yet. In this article, we propose a unified deep learning method that can be implemented for both RUL and SoC estimation. The proposed method leverages long short-term memory recurrent neural networks to achieve state-of-the-art accurate capacity estimation for LIBs under complex operating conditions. Notably, the unified method can perform not only one-step-ahead prediction but also multistep-ahead estimation with high accuracy, achieving RUL estimation error within ten cycles and SoC estimation error within 0.13%. Experimental data collected from battery testing systems with simulated complex operating conditions are used to train the method. A series of comparative experiments are conducted to compare our method with other existing methods. The experimental results show that our method can increase estimation accuracy and robustness for LIBs estimation problems via capturing the long-term dependencies among battery degradation data.
22 May 2024 in Reliability Engineering & System Safety
In this article, we develop a mixture of Gaussians-evidential hidden Markov model (MoG-EHMM) to fuse expert knowledge and condition monitoring information for remaining useful life (RUL) prediction under the belief function theory framework. The evidential expectation-maximization algorithm is implemented in the offline phase to train the MoG-EHMM based on historical data. In the online phase, the trained model is used to recursively update the health state and reliability of a particular individual system. The predicted RUL is, then, represented in the form of its probability mass function. A numerical metric is defined based on the Bhattacharyya distance to measure the RUL prediction accuracy of the developed methods. We applied the developed methods on a simulation experiment and a real-world dataset from a bearing degradation test. The results demonstrate that despite imprecisions in expert knowledge, the performance of RUL prediction can be substantially improved by fusing expert knowledge with condition monitoring information.
28 July 2024 in Reliability Engineering & System Safety