基于特征优选与改进极限学习机的锂电池SOC估计  

State of charge estimation of lithium battery based on feature optimization and improved extreme learning machine

作　　者：寇发荣[1] 罗希 门浩 郭杨娟 杨天祥 KOU Farong;LUO Xi;MEN Hao;GUO Yangjuan;YANG Tianxiang(School of Mechanical Engineering,Xi'an University of Science and Technology,Xi'an 710054,Shaanxi,China)

机构地区：[1]西安科技大学机械工程学院,陕西西安710054

出　　处：《储能科学与技术》2023年第4期1234-1243,共10页Energy Storage Science and Technology

基　　金：国家自然科学基金项目(51775426);西安市科技计划项目(21XJZZ0039)。

摘　　要：为提高数据驱动方法预测荷电状态(state of charge,SOC)的效率与精度,提出一种基于特征优选与改进极限学习机的SOC估计方法。采用公开数据作为训练集,利用随机森林(random forest,RF)算法判定训练集各特征对SOC的影响程度,选择出最优训练样本,并对优选样本的合理性进行验证;利用极限学习机(extreme learning machine,ELM)对SOC进行预测,针对ELM在预测过程中随机产生的权值及阈值的不稳定性导致SOC估计精度不理想的问题,选取麻雀搜索算法(sparrow search algorithm,SSA)进行参数优化以提高估计精度;随后,通过BJDST工况仿真试验对SSA参数优化的有效性进行验证;在恒流放电与DST工况实验下,分别利用改进极限学习机(SSA-ELM)、ELM、支持向量机(support vector machine,SVM)与BP神经网络(back-propagation neural network,BPNN)对SOC进行预测,结果表明,SSA-ELM算法预测效果最优,预测误差基本保持在1.5%以内,可实现较高精度的SOC预测。In this study,a state of charge(SOC)estimation method is proposed based on a combination of data preprocessing and algorithm optimization in order to improve the efficiency and accuracy of data-driven method in predicting SOC.The open data was selected as the training set,and the random forest(RF)algorithm was used to determine the influence degree of each feature of the training set on SOC.For this,optimal training samples were selected,and the rationality of the optimal samples was verified.Limit learning machine(ELM)was used to predict SOC,aiming at the instability of random weights and thresholds generated by ELM in the prediction process.This leads to the unsatisfactory accuracy of SOC estimation.Sparrow search algorithm(SSA)was selected for optimize parameters and improve estimation accuracy.Subsequently,the effectiveness of SSA parameter optimization was verified using the BJDST simulation test.Under the constant current discharge and DST working conditions,the improved extreme learning machine(SSA-ELM),ELM,support vector machine,and back-propagation neural network were used to predict the SOC.The results show that the SSA-ELM algorithm has the best prediction effect and a prediction error\within 1.5%,thus achieving high-precision SOC prediction.

关 键 词：随机森林(RF) 麻雀搜索算法(SSA) 极限学习机(ELM) 特征优选 荷电状态(SOC) 

分 类 号：TM912[电气工程—电力电子与电力传动]