SOC Prediction of Lead-acid Battery based on EEMD-LSTM Network

Xinwei Zhang ； Zhanying Li

《International Core Journal of Engineering》 9卷4期 (2023/04) Pp. 205-211

https://doi.org/10.6919/ICJE.202304_9(4).0028

摘要

Lead‐acid battery is widely used because of its reliable safety. The state of charge (SOC) of the battery is the most direct reflection of the battery's use status. Its accurate estimation helps users to formulate a reasonable battery management plan and maximize the safe use of the battery. In this paper, a data‐driven method is proposed to predict the SOC of the battery. The real‐time online data of the lead‐acid battery cloud data management system of a technology limited company is used, and the isolated forest algorithm is used to deal with the abnormal data. It is proposed to build a deep learning model combining the set empirical mode decomposition (EEMD) and the short‐term memory neural network (LSTM), and compare with various models. At the same time, this paper uses the EEMD algorithm to decompose the time series into several subsequences, which enlarges the details of the time series data, making the fluctuation of the subsequences more stable than the original sequence, and solving the prediction lag problem of LSTM network. Through experimental analysis, the EEMD‐LSTM model used in this paper has the best prediction effect and the highest prediction accuracy.

關鍵字

Lead Acid Battery ； EEMD ； Long‐term and Short‐term Memory Network (LSTM) ； Life Prediction ； Neural Network

參考文獻

Dhundhara, Sandeep, Yajvender Pal Verma, and Arthur Williams. "Techno-economic analysis of the lithium-ion and lead-acid battery in microgrid systems. "Energy Conversion and Management 177 (2018): 122-142.

Xia, B.; Zhang, G.; Chen, H.; Li, Y.; Yu, Z.; Chen, Y. Verification Platform of SOC Estimation Algorithm for Lithium-Ion Batteries of Electric Vehicles. Energies (2022):15, 3221.

Zhang, R., Xia, B., Li, B., Cao, L., Zhang R, Xia B, Li B, Cao L, Lai Y, Zheng W, Wang H, Wang W. State of the Art of Lithium-Ion Battery SOC Estimation for Electrical Vehicles. Energies. 2018; 11(7):1820.

Chen, Xu-Dong, et al. "Life estimation of lithium-ion battery based on a hybrid model."Energy Exploration & Exploitation38.5 (2020): 1854-1878.

Zhao, R.; Kollmeyer, P.J.; Lorenz, R.D.; Jahns, T.M. A compact methodology via a recurrent neural network for accurate equivalent circuit type modeling of lithiumion batteries. IEEE Trans. Ind. Appl. 2019, 55, 1922–1931.