基于LWOA-LSTM的大容量锂电池SOC估计
SOC Estimation of Large Capacity Lithium Batteries Based on LWOA-LSTM
马宏忠 1宣文婧 1朱沐雨 1陈悦林1
作者信息
- 1. 河海大学电气与动力工程学院,江苏南京 210024
- 折叠
摘要
准确预测锂电池荷电状态(SOC)对电池安全运行至关重要,分析在电网不同模式下的SOC更是锂电池全面推广的基础.提出一种基于莱维飞行的鲸鱼优化算法(LWOA)优化长短时记忆神经网络(LSTM),对调频模式下的大容量锂离子电池SOC进行估计.首先,分析LSTM神经网络和LWOA算法,构建LWOA-LSTM模型,进行参数优化;然后,选取调频模式下大容量锂离子电池组实验数据,对数据进行预处理和模型训练;最后,实现调频模式下锂电池的SOC估计.试验结果表明:所构建模型能准确预测锂电池SOC,较WOA-LSTM模型,评估指标RMSE和MAE分别降低了25.55%、28.71%,R2 上升了0.76%.
Abstract
Accurate prediction of the state of charge(SOC)of lithium batteries is crucial for their safe operation,and analyzing the SOC in different power grid modes is the basis for the comprehensive promotion of lithium batteries.This paper proposes a whale optimization algorithm based on Levy flight(LWOA)to optimize long short-term memory neural network(LSTM)for estimating the SOC of large capacity lithium-ion batteries in frequency modulation mode.Firstly,the LSTM neural network and LWOA algorithm are analyzed,and the LWOA-LSTM model is constructed to optimize the parameters.Then,the experimental data of the large capacity lithium-ion battery pack in frequency modulation mode are selected for data preprocessing and model training.Finally,SOC estimation of lithium batteries in frequency modulation mode is achieved.The experimental results show that the constructed model can accurately predict the SOC of lithium batteries.Compared with the WOA-LSTM model,the evaluation indicators RMSE and MAE are reduced by 25.55% and 28.71%,respectively,while R2 increases by 0.76%.
关键词
荷电状态/锂电池/鲸鱼优化算法/长短时记忆网络/调频模式Key words
state of charge/lithium batteries/whale optimization algorithm/LSTM/frequency modulation mode引用本文复制引用
基金项目
国家自然科学基金(51577050)
国家电网科技项目(J2022158)
出版年
2024
国家科技期刊平台
NSTL
万方数据