可充电锂电池剩余电量预测方法

来源期刊:中南大学学报(自然科学版)2018年第9期

论文作者:方正 陈思媛 胡伟锋 余杰 王倩 王涵博 王禹昕

文章页码:2121 - 2129

关键词:锂离子电池;SOC预测;BP;RBF

Key words:lithium ion battery; SOC prediction; BP; RBF

摘    要:为了对锂离子电池剩余电量(SOC)进行准确测量,以2 200 mA·h的聚合物锂电池为研究对象,利用Hyperion平衡充放电设备采集6个不同放电电流下(0.7,1.1,1.7,2.2,2.7和3.3 A)的放电电压和放电倍率;采取误差反向传播(BP)和径向基函数(RBF) 2个原理不同的神经网络算法进行SOC预测;把采集的样本数据分为训练组和测试组,采用不同的神经网络算法对训练组进行训练后,选择合适的参数构建神经网络,并用测试组数据进行测试;最终比较2种算法的预测效果和误差。研究结果表明:RBF预测结果的相对误差比BP的低,且预测速度更快,RBF较BP更适合于锂离子电池剩余电量的预测。

Abstract: In order to accurately measure SOC (state of charge) of lithium ion batteries, the discharge voltage and discharge rate of 6 different discharge currents (0.7, 1.1, 1.7, 2.2, 2.7 and 3.3 A) were collected by using Hyperion balanced charge and discharge equipment with 2 200 mA·h polymer lithium battery as the research object. The neural network algorithm based on backpropagation (BP) and radial basis function (RBF) was used. Collected sample data was divided into training group and test group. After training the training group with different neural network algorithms, appropriate parameters were selected to construct the neural network and the test group data were tested. Finally, predicted results and errors of the two algorithms were compared. The results show that the average relative error of RBF prediction is lower than that of BP, and the prediction speed is faster, therefore, RBF is more suitable for the prediction of residual capacity of lithium-ion batteries than BP.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号