基于参数分层辨识的RMA-UKF算法SOC估计  

SOC estimation of RMA-UKF algorithm based on parameters hierarchical identification

作　　者：寇发荣[1] 王甜甜 王思俊 门浩 KOU Fa-rong;WANG Tian-tian;WANG Si-jun;MEN Hao(School of Mechanical Engineering,Xi’an University of Science and Technology,Xi’an,Shaanxi 710054,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：《电池》2021年第6期553-557,共5页Battery Bimonthly

基　　金：国家自然科学基金项目(51775426);陕西省重点研发计划项目(2020GY-128);西安市科技计划项目(21XJZZ0039);咸阳市重点研发计划项目(2021ZDYF-GY-0027)。

摘　　要：针对荷电状态(SOC)估计时模型参数抗干扰性差及噪声干扰下全生命周期SOC适应性差的问题,在建立二阶RC等效模型的基础上,提出参数分层辨识架构,以提高辨识精度。在获得精确模型参数的基础上,利用鲁棒似然估计的自适应无迹卡尔曼滤波(RMA-UKF)算法进行SOC在线估计,用修正因子修正噪声协方差矩阵的权重,改善全生命周期SOC适应性差的问题。模拟不同实车道路工况,利用实时系统对噪声干扰下的SOC估计算法,实现快速控制原型(RCP)在线验证。在附加噪声干扰情况下,RMA-UKF算法的SOC估计误差约为1%,与传统UKF算法相比精度更高、收敛性较快。Aiming at the problem of the poor anti-interference of model parameters and the poor adaptability of the full life cycle state of charge(SOC)under noise interference in SOC estimation,based on the establishment of second-order RC equivalent model,a layered parameter identification framework was proposed to improve the identification accuracy.On the basis of obtaining accurate model parameters,the adaptive unscented Kalman filter(RMA-UKF)algorithm of robust likelihood estimation was used to estimate the SOC online,the weight of the noise covariance matrix was corrected by correction factor to change poor adaptability of SOC under whole life cycle.Simulating different real-vehicle road conditions,the real-time system was used to realize the rapid control prototype(RCP)online verification of the SOC estimation algorithm under noise interference.In the case of additional noise interference,the SOC estimation error of RMA-UKF algorithm was about 1%,which had higher accuracy and faster convergence,compared with the traditional UKF algorithm.

关 键 词：锂离子电池 荷电状态(SOC) 参数分层辨识 鲁棒似然法 无迹卡尔曼滤波 快速控制原型(RCP) 

分 类 号：TM912.9[电气工程—电力电子与电力传动]