基于LSTM-NPKDE的锂离子电池SOC预测与不确定分析*

doi:10.16628/j.cnki.2095-8188.2020.05.007

电器与能效管理技术 ›› 2020, Vol. 590 ›› Issue (5): 44-50.doi: 10.16628/j.cnki.2095-8188.2020.05.007

基于LSTM-NPKDE的锂离子电池SOC预测与不确定分析^*

李文启¹, 高东学¹, 李朝晖², 饶宇飞², 顾波³

1.国网河南省电力公司, 河南郑州 450000;
2.国网河南省电力公司电力科学研究院, 河南郑州 450052;
3.华北水利水电大学, 河南郑州 450045

收稿日期:2020-01-15 出版日期:2020-05-30 发布日期:2020-05-29
作者简介:李文启(1963—),男,教授级高级工程师,主要从事电力系统及新能源研究。高东学(1966—),男,教授级高级工程师,主要从事电力系统运行研究。李朝晖(1971—),男,高级工程师,主要从事新能源与储能技术研究。
基金资助:
* 国网河南省电力公司科技项目(5217021600A3)

Forecast and Uncertainty Analysis of Lithium-ion Batteries SOC Based on LSTM-NPKDE

LI Wenqi¹, GAO Dongxue¹, LI Zhaohui², RAO Yufei², GU Bo³

1. State Grid Henan Electric Power Company, Zhengzhou 450000, China;
2. State Grid Henan Electric Power Research Institute, Zhengzhou 450052, China;
3. North China University of Water Resources and Electric Power, Zhengzhou 450045, China

Received:2020-01-15 Online:2020-05-30 Published:2020-05-29

摘要/Abstract

摘要： 提出一种基于长短期记忆(LSTM)网络的锂离子电池荷电状态(SOC)预测方法。以锂离子电池的充放电电流和电压作为模型输入,对锂离子电池SOC进行预测,结果表明LSTM网络的预测精度高于BP神经网络、BP-PSO混合模型和小波神经网络。利用非参数核密度估计方法来计算锂离子电池SOC预测的置信区间,结果表明能够准确计算不同置信水平下锂离子电池SOC预测的不确定性。

关键词: 锂离子电池, 荷电状态, 长短期记忆网络, 预测不确定性, 置信区间

Abstract: A forecast method of the state of charge (SOC) of lithium-ion battery based on the long-short term memory (LSTM) network was proposed.The SOC of lithium-ion battery was forecasted by taking the charge-discharge current and voltage of lithium-ion battery as model inputs.The results show that the forecasting accuracy of LSTM network is higher than that of BP neural network,BP-PSO hybrid model and wavelet neural network (WNN).The nonparametric kernel density estimation (NPKDE) method was used to calculate the confidence interval of the SOC forecast of lithium-ion batteries.The calculation results show that the confidence interval based on NPKDE can accurately calculate the uncertainty of the SOC forecast of lithium-ion batteries at different confidence levels.

Key words: lithium-ion battery, state of charge (SOC), long-short term memory network, forecast uncertainty, confidence interval

中图分类号:

TM910

李文启, 高东学, 李朝晖, 饶宇飞, 顾波. 基于LSTM-NPKDE的锂离子电池SOC预测与不确定分析^*[J]. 电器与能效管理技术, 2020, 590(5): 44-50.

LI Wenqi, GAO Dongxue, LI Zhaohui, RAO Yufei, GU Bo. Forecast and Uncertainty Analysis of Lithium-ion Batteries SOC Based on LSTM-NPKDE[J]. DIANQI YU NENGXIAO GUANLI JISHU, 2020, 590(5): 44-50.

参考文献

[1] 李建林,马会萌,袁晓冬,等.规模化分布式储能的关键应用技术研究综述[J].电网技术,2017,41(10):289-299.
[2] PASCAL M,NGUYENA B H,LEBEL F A,et al.Disturbance observer-based state-of-charge estimation for Li-ion battery used in light electric vehicles[J].Journal of Energy Storage,2020(27):1-15.
[3] 李相俊,王上行,惠东.电池储能系统运行控制与应用方法综述及展望[J].电网技术,2017,41(10):233-243.
[4] 沈佳妮,贺益君,马紫峰.基于模型的锂离子电池SOC及SOH估计方法研究进展[J].化工学报,2018,69(1):309-316.
[5] 刘大同,周建宝,郭力萌,等.锂离子电池健康评估和寿命预测综述术[J].仪器仪表学报,2015,36(1):1-16.
[6] CHEN C,XIONG R,YANG RX,et al.State-of-charge estimation of lithium-ion battery using an improved neural network model and extended Kalman filter[J].Journal of Cleaner Production,2019(234):1153-1164.
[7] 赵泽昆,韩晓娟,马会萌.基于BP神经网络的储能电池衰减容量预测[J].电器与能效管理技术,2016(19):68-72.
[8] DAVID JIMÉNEZ-BERMEJO, JESÚS FRAILE-ARDANUY, CASTAO-SOLIS S,et al.Using dynamic neural networks for battery state of charge estimation in electric vehicles[J].Procedia Computer Science,2018,130:533-540.
[9] 骆秀江,张兵,黄细霞,等.基于SVM的锂电池SOC估算[J].电源技术,2016,40(2):287-290.
[10] 陈健美,钱承,李玉强,等.基于LS-SVM的混合动力镍氢电池组SOC预测[J].中南大学学报(自然科学版),2013,44(1):135-139.
[11] 赵轩,马建,刘瑞,等.基于GGAP-RBF神经网络的多参数纯电动客车蓄电池荷电状态预测[J].中国公路学报,2015,28(4):116-126.
[12] 孙威,修晓青,肖海伟,等.基于MEA-BP神经网络的电池储能系统SOC状态评估[J].电器与能效管理技术,2018(1):58-61,90.
[13] 赵泽昆,韩晓娟,马会萌.基于PSO-BP神经网络的大容量电池储能系统衰减容量预测[J].电器与能效管理技术,2016(14):75-78.
[14] KHAN G M,ZAFARI F,MAHMUD S A.Very short term load forecasting using cartesian genetic programming evolved recurrent neural networks[J].International Conference on Machine Learning & Applications,2013(1):152-155.
[15] HAUSER M,FU Y W,PHOHA S S,et al.Neural probabilistic forecasting of symbolic sequences with long short-term memory[J].Journal of Dynamic Systems Measurement & Control,2018,140(8):084502-1~084502-6.
[16] YANG B,SUN S,LI J,et al.Traffic flow prediction using LSTM with feature enhancement[J].Neurocomputing,2018,332:320-327.
[17] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.

基于LSTM-NPKDE的锂离子电池SOC预测与不确定分析^*

Forecast and Uncertainty Analysis of Lithium-ion Batteries SOC Based on LSTM-NPKDE

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	郑熙东, 江修波. 基于集合经验模态分解的混合储能系统功率分配[J]. 电器与能效管理技术, 2020, 590(5): 21-27.
[2]	彭香园, 唐传雨, 孙金磊, 刘钊. 基于扩展卡尔曼滤波及容量校准的锂电池SOC估计方法研究^*[J]. 电器与能效管理技术, 2020, 590(5): 51-56.
[3]	刘倩倩, 赵言本, 吕超. 磷酸铁锂电池大倍率充放电模型仿真研究[J]. 电器与能效管理技术, 2020, 590(5): 57-61.