基于自适应灾变遗传-循环神经网络的锂离子电池SOC估计  

State of Charge Estimation with Adaptive Cataclysm Genetic Algorithm-recurrent Neural Network for Li-ion Batteries

作　　者：陈诚 皮志勇 赵英龙 廖玄 张明敏 李勇[2] CHEN Cheng;PI Zhiyong;ZHAO Yinglong;LIAO Xuan;ZHANG Mingmin;LI Yong(Jingmen Power Supply Company of Hubei Electric Power Company,Jingmen 448000;College of Electrical and Information Engineering,Hunan University,Changsha 410000)

机构地区：[1]国网湖北省电力公司荆门供电公司,荆门448000 [2]湖南大学电气与信息工程学院,长沙410000

出　　处：《电气工程学报》2022年第1期86-94,共9页Journal of Electrical Engineering

基　　金：国网湖北电力“基于新型防火防爆磷酸铁锂电池智能直流系统研究”资助项目(5215G021000D)。

摘　　要：锂离子荷电状态(State of charge,SOC)的精准估计是锂离子电池安全稳定运行的基础。传统的误差反向传播(Back propagation,BP)神经网络估计SOC的精度不高,而循环神经网络(Recurrent neural network,RNN)也容易陷入局部最优。针对这些问题,提出了自适应灾变遗传-循环神经网络(ACGA-RNN)联合算法,将自适应灾变遗传算法(Adaptive cataclysm genetic algorithm,ACGA)用于优化RNN的初始权值和阈值,提高了最优权值和阈值的全局搜索能力,从而有效提升锂离子电池SOC的估计精度。基于锂离子电池充放电的试验数据,将所提ACGA-RNN联合算法与RNN、GA-RNN算法分别用于锂离子电池的SOC估计。测试结果显示,相较于传统的RNN算法与GA-RNN算法,提出的ACGA-RNN联合算法获得了最佳的SOC估计精度,在DST工况下的估计平均绝对误差为1.74%,低于传统RNN和GA-RNN的估计精度3.68%和2.49%;另外,在45℃和0℃条件下,ACGA-RNN联合算法估计的平均绝对值误差分别为1.75%和2.05%,符合国家标准要求。因此,提出的ACGA-RNN联合算法在锂电池的SOC估计方面具有良好的应用价值。Accurate estimation of the state of charge(SOC) of lithium batteries is the basis for safe and stable operation of lithium batteries. The traditional back propagation(BP) neural network has low accuracy in estimating SOC, and the recurrent neural network(RNN) is easy to fall into local optimization. To work out these problems, a recurrent neural network(ACGA-RNN) combined algorithm based on an adaptive catastrophe genetic algorithm is proposed. The adaptive catastrophe genetic algorithm(ACGA) is utilized to optimize the initial weight and threshold of RNN and improve the global search ability of the optimal value, which effectively improves the estimation preciseness of the state of charge of lithium battery. Based on the experimental data from the charge and discharge test, the proposed ACGA-RNN combined algorithm, RNN algorithm, and GA-RNN algorithm are applied for SOC estimation of the lithium-ion battery respectively. The experimental results show that the estimation mean absolute error of ACGA-RNN combined algorithm obtains the best accuracy of SOC estimation compared with the traditional RNN and GA-RNN algorithms. The mean absolute error under the DST condition is 1.74%, which is lower than the estimation accuracy of traditional RNN(3.68%) and GA-RNN(2.49%). In addition, at 45 ℃ and 0 ℃, the mean absolute error of the ACGA-RNN combined algorithm is 1.75% and 2.05%, respectively, which meets the requirements of national standards. Therefore, the proposed ACGA-RNN combined algorithm has a good application value in SOC estimation of lithium batteries.

关 键 词：锂离子电池 荷电状态 循环神经网络 自适应灾变遗传算法 

分 类 号：TM912[电气工程—电力电子与电力传动]