基于超声测量及神经网络的锂离子动力电池SOC估算  

SOC Estimation for Lithium Ion Power Batteries Based on Ultrasonic Measurement and Neural Networks

作　　者：周世杰 李顶根[2] ZHOU Shijie;LI Dinggen(China-EU Institute for Clean and Renewable Energy,Huazhong University of Science and Technology,Wuhan 430074,China;School of Energy and Power Engineering,Huazhong University of Science and Technology,Wuhan 430074,China)

机构地区：[1]华中科技大学中欧清洁与可再生能源学院,武汉430074 [2]华中科技大学能源与动力工程学院,武汉430074

出　　处：《汽车工程学报》2021年第1期19-24,共6页Chinese Journal of Automotive Engineering

基　　金：国家重点研发计划资助项目(2018YFB0104100)。

摘　　要：准确地估算电动汽车动力电池的荷电状态(State of Charge,SOC)对电动汽车的安全驾驶和及时充电至关重要。基于超声测量和神经网络提出一种动力电池SOC估算方法。该方法对动力电池施加一个超声波脉冲,超声信号经过电池后得到反馈脉冲波,并以反馈波形的峰峰值作为神经网络的输入来建立模型,从而对动力电池SOC进行估算。试验结果表明,对于放电以及充电过程,SOC估算误差都仅为1%。For electric vehicles,accurately measuring the state of charge of the power battery is essential for safe driving and timely charging.This paper proposed a SOC estimation method based on ultrasonic measurement and neural networks.Initially an ultrasonic pulse was applied to the power battery to obtain a feedback pulse wave.And then the peak-to-peak value of the feedback waveform was used as an input for the neural network to build the model and to estimate the SOC of the power battery.The experimental results show that the SOC estimation error is only 1%for the discharge and charge processes.

关 键 词：锂离子动力电池 超声测量 神经网络 SOC估算 

分 类 号：TM911[电气工程—电力电子与电力传动]