融合算法在蓄电池SOC估算中的研究综述

Summary of Fusing Algorithm Research in Estimation for State of Charge of Battery

摘要:

蓄电池的荷电状态（state of charge，SOC）是电池管理系统（Battery Management System，BMS）中的重要参数之一，准确估算电池SOC对生产运行具有重要意义。首先阐释了SOC的定义；其次分析了传统单一SOC估算法的不足；然后，论述了近几年蓄电池SOC融合估算方法：神经网络、卡尔曼滤波法和综合法的研究进展，并分析了各种方法存在的优缺点；最后，给出总结与展望。提出充分利用数据挖掘和深度学习技术，将BMS记录的历史数据用于蓄电池SOC的估算，有助于提高计算精度和应用范围。

Abstract:

The state of charge (SOC) of battery is one of the important parameters in battery management system (BMS). Accurate estimation of SOC is of great significance for production and operation. Firstly, the definition of SOC is explained. Secondly, the shortcomings of traditional single SOC estimation method are analyzed, and then, the research progress of SOC fusion estimation methods for battery in recent years, including neural network, Kalman filter and synthesis method, is discussed, and the advantages and disadvantages of each method are analyzed. Finally, the summary and prospect are given. It is proposed to make full use of data mining and deep learning technology and use the historical data recorded by BMS to estimate the SOC of battery, which is helpful to improve the calculation accuracy and application range.