State‐of‐health estimation and remaining useful life for lithium‐ion battery based on deep learning with Bayesian hyperparameter optimization. (15th December 2021)

• Record Type: Journal Article
• Authors: Kong, Depeng; Wang, Shuhui; Ping, Ping
• Is Part Of: International journal of energy research. Volume 46:Number 5(2022)
• Page Start: 6081
• Page End: 6098
• Publication Date: 2021-12-15
• Subjects: Bayesian optimization -- deep learning -- Lithium‐ion battery -- remaining useful life -- state‐of‐health; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Power resources -- Research -- Periodicals; 621.042
• DOI: 10.1002/er.7548
• Languages: English
• ISSNs: 0363-907X

Abstract

Summary: Lithium‐ion battery state‐of‐health (SOH) estimation and remaining usable life (RUL) prediction are important for battery prognosis and health management. In this article, a framework‐combined deep convolution neural network (DCNN) with double‐layer long short‐term memory (LSTM) is proposed, which is designed for online health prognosis. Based on the raw data obtained during the constant current charging process, the aging characteristics of the battery can be extracted by DCNN to estimate SOH. The estimation results are then sent to the LSTM for the temporal prediction of the RUL. This framework considers both temporal and spatial characteristics of data, and the powerful spatial feature extraction ability of DCNN and the effectiveness of LSTM for time series problems can ensure the high precision of calculation. At the same time, the hyperparameters of the neural networks, which can highly affect the performance of networks, are obtained by Bayesian optimization to ensure the networks run in the best status. The results show that the proposed method can achieve low root mean square error, which are inferior to 0.0061 and 0.0627 for SOH estimation and RUL prediction, respectively. Abstract : This paper combines deep convolutional neural network and double‐layer long short‐term memory network to perform online battery health estimation and remaining usable life prognosis. This framework takes into account the spatial and temporal characteristics of the battery's raw data, and uses Bayesian optimization to ensure that the networks work in the best state. The calculation results show the usability of the proposed method.