基于改进BPNN⁃MPF算法的锂离子电池SoE估计

doi:10.13229/j.cnki.jdxbgxb20210556

摘要/Abstract

摘要：

为了提高锂离子电池能量状态（SoE）估计的准确性，考虑到电流或电压传感器噪声会累积误差，提出了一种基于改进反向传播神经网络（BPNN）与模型预测滤波（MPF）相结合的SoE估计方法。基于一阶RC等效电路模型，采用MPF算法估计电池的SoE，并使用改进BPNN对MPF算法的估计结果进行误差补偿。在NEDC工况下验证了本文方法的准确性。结果表明，与传统MPF算法和BPNN-MPF算法相比，本文方法的SoE估计值能较好地收敛到真实值，且最大绝对误差和均方根误差均在1%以内。

关键词: 控制理论与控制工程, 锂离子电池, 能量状态估计, 改进BP神经网络, 模型预测滤波

Abstract:

The State of Energy （SoE） of lithium-ion battery is an important evaluation index for the energy optimization and management of electric vehicles. In order to improve the accuracy and reliability of battery SoE estimation， a SoE estimation method based on the combination of improved Back Propagation Neural Network （BPNN） and Model Predictive Filtering （MPF） was proposed in this paper. Considering the accumulated errors of current or voltage sensor noise， a first-order RC equivalent circuit model was established in this paper. Based on this model， the MPF algorithm was used to estimate the battery SoE. In order to make the estimated results more accurate， the improved BPNN was used to compensate the errors of the estimated results of MPF algorithm. Finally， the accuracy of the proposed method was verified under New European Driving Conditions （NEDC）. The results show that the SoE estimate based on the improved BPNN-MPF algorithm well converges to the real SoE value， compared with traditional MPF algorithm and BPNN-MPF algorithm. The Maximum Absolute Error （MAE） and Root-Mean-Square Error （RMSE） of the estimated values are all within 1%.

Key words: control theory and control engineering, lithium-ion batteries, state of energy, improved bp neural network, model predictive filtering

中图分类号:

U463.63

马彦,郭则宣. 基于改进BPNN⁃MPF算法的锂离子电池SoE估计[J]. 吉林大学学报(工学版), 2023, 53(1): 263-272.

Yan MA,Ze-xuan GUO. SoE estimation of lithium-ion batteries based on improved BPNN-MPF algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(1): 263-272.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

图12

表2

参考文献 14

1	Lin C, Mu H, Xiong R, et al. Multi-model probabilities based state fusion estimation method of lithium-ion battery for electric vehicles: state-of-energy[J]. Applied Energy, 2016, 194(15): 560-568.
2	Chang J Q, Chi M S, Shen T. Model based state‑of‑energy estimation for LiFePO₄ batteries using unscented particle filter[J]. Journal of Power Electronics, 2020(20): 624-633.
3	刘伟龙, 王丽芳, 王立业. 基于电动汽车工况识别预测的锂离子电池SOE估计[J]. 电工技术学报, 2018, 33(1): 17-25.
	Liu Wei-long, Wang Li-fang, Wang Li-ye. Estimation of state-of-energy for electric vehicles based on the identification and prediction of driving condition[J]. Transactions of China Electrotechnical Society, 2018, 33(1): 17-25.
4	Liu X T, Wu J, Zhang C B, et al. A method for state of energy estimation of lithium-ion batteries at dynamic currents and temperatures[J]. Journal of Power Sources, 2014(270): 151-157.
5	He H W, Zhang Y Z, Xiong R, et al. A novel gaussian model based battery state estimation approach: state-of-energy[J]. Applied Energy, 2015(151): 41-48.
6	Wang Y J, Zhang C B, Chen Z H. A method for joint estimation of state-of-charge and available energy of LiFePO₄ batteries[J]. Applied Energy, 2014(135): 81-87.
7	Zhang W G, Shi W, Ma Z Y. Adaptive unscented kalman filter based state of energy and power capability estimation approach for lithium-ion battery[J]. Journal of Power Sources, 2015(289): 50-62.
8	Dong G Z, Chen Z H, Wei J W, et al. An online model-based method for state of energy estimation of lithium-ion batteries using dual filters[J]. Journal of Power Sources, 2016(301): 277-286.
9	赵琳, 王小旭, 丁继成, 等. 组合导航系统非线性滤波算法综述[J].中国惯性技术学报, 2009, 17(1): 46-52.
	Zhao Lin, Wang Xiao-xu, Ding Ji-cheng, et al. Overview of nonlinear filter methods applied in integrated navigation system[J]. Journal of Chinese Inertial Technology, 2009, 17(1): 46-52.
10	Mook D J, Junkins J L. Minimum model error estimation for poorly modeled dynamic systems[J]. Journal of Guidance, Control and Dynamics, 1988, 11(3): 256-261.
11	Crassidis J L, Markley F L. Predictive filtering for nonlinear systems[J]. Journal of Guidance, Control and Dynamics, 1997, 20(3): 566-572.
12	杨一. 神经网络优化方法及其在组合导航中的应用研究[D]. 西安: 西北工业大学自动化学院, 2016.
	Yang Yi. Research on the optimization of neural networks method and its application for integrated navigation[D]. Xi'an: College of Automation, Northwestern Polytechnical University, 2016.
13	华寅, 许敏. 基于双非线性预测滤波法的锂离子电池SOH估计[J]. 电源技术, 2018, 42(9): 1321-1324.
	Hua Yin, Xu Min. State of health estimation of lithium-ion battery by dual nonlinear predictive filter for electric vehicles[J]. Chinese Journal of Power Sources, 2018, 42(9): 1321-1324.
14	田冬冬, 李立伟, 杨玉新. 基于改进BP-EKF算法的SoC估算[J]. 电源技术, 2020, 44(9): 1274-1278.
	Tian Dong-dong, Li Li-wei, Yang Yu-xin. Research on SoC estimation based on improved BP-EKF algorithm[J]. Chinese Journal of Power Sources, 2020, 44(9): 1274-1278.

相关文章 15

[1]	齐国元,李阔,王琨. 基于补偿函数观测器的四旋翼无人机姿态受限控制[J]. 吉林大学学报(工学版), 2023, 53(3): 853-862.
[2]	郭洪艳,于文雅,刘俊,戴启坤. 复杂场景智能车辆车道与速度一体化滚动优化决策[J]. 吉林大学学报(工学版), 2023, 53(3): 693-703.
[3]	王德军,张凯然,徐鹏,顾添骠,于文雅. 基于车辆执行驱动能力的复杂路况速度规划及控制[J]. 吉林大学学报(工学版), 2023, 53(3): 643-652.
[4]	徐卓君,王耀祥,黄兴,彭程. 多无人机地面移动目标搜寻和定位[J]. 吉林大学学报(工学版), 2023, 53(3): 832-840.
[5]	何德峰,周丹,罗捷. 跟随式车辆队列高效协同弦稳定预测控制[J]. 吉林大学学报(工学版), 2023, 53(3): 726-734.
[6]	陈珑茏,冯天宇,吕宗阳,吴玉虎. 共轴倾转旋翼无人机有限时间滑模姿态控制[J]. 吉林大学学报(工学版), 2023, 53(3): 883-890.
[7]	齐国元,陈浩. 基于观测器的四旋翼控制-抗扰-避障一体化[J]. 吉林大学学报(工学版), 2023, 53(3): 810-822.
[8]	魏素凤,平昕,李春霖,王国勇. 氮掺杂Co/Co₃O₄@C核壳纳米粒子作为锂电池负极材料的性能[J]. 吉林大学学报(工学版), 2023, 53(2): 376-384.
[9]	刘兴涛,刘晓剑,武骥,何耀,刘新天. 基于曲线压缩和极限梯度提升算法的锂离子电池健康状态估计[J]. 吉林大学学报(工学版), 2022, 52(6): 1273-1280.
[10]	王宏志,王婷婷,胡黄水,鲁晓帆. 基于Q学习优化BP神经网络的BLDCM转速PID控制[J]. 吉林大学学报(工学版), 2021, 51(6): 2280-2286.
[11]	冯建鑫,王强,王雅雷,胥彪. 基于改进量子遗传算法的超声电机模糊PID控制[J]. 吉林大学学报(工学版), 2021, 51(6): 1990-1996.
[12]	潘凤文,弓栋梁,高莹,徐明伟,麻斌. 基于锂离子电池线性化模型的电流传感器故障诊断[J]. 吉林大学学报(工学版), 2021, 51(2): 435-441.
[13]	高菲,肖阳,张文华,祁锦轩,李子樵,马骁远. 高温和荷电状态对锂离子电池单体力学响应的耦合影响[J]. 吉林大学学报(工学版), 2020, 50(5): 1574-1583.
[14]	马彦,黄健飞,赵海艳. 基于车间通信的车辆编队控制方法设计[J]. 吉林大学学报(工学版), 2020, 50(2): 711-718.
[15]	邓丽飞, 石要武, 朱兰香, 于丁力. SI发动机闭环系统故障检测[J]. 吉林大学学报(工学版), 2017, 47(2): 577-582.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

估计对象	最大误差	平均误差（MAE）	均方根误差（RMSE）
电压/mV	1.7	1.4	1.4
SoE（MPF）/%	0.62	0.52	0.52
SoE（BPNN-MPF）/%	0.61	0.51	0.51
SoE（改进BPNN-MPF）/%	0.1	0.02	0.02

估计对象	最大误差	平均误差（MAE）	均方根误差（RMSE）
电压/mV	2.1	1.5	1.5
SoE（MPF）/%	1.46	1.05	1.05
SoE（BPNN-MPF）/%	1.45	1.03	1.04
SoE（改进BPNN-MPF）/%	0.95	0.53	0.54