结合光纤光栅传感器与特征筛选的锂电池荷电状态估计

doi:10.16628/j.cnki.2095-8188.2025.10.010

摘要/Abstract

摘要：

光纤布拉格光栅(FBG)传感器正逐步成为提升锂电池荷电状态(SOC)估计精度的创新解决方案,而锂电池表面应变的位置和数量均会影响SOC的估计精度,提出一种基于序列前向选择(SFS)算法的多应变特征筛选方法。针对SFS算法在特征选择过程中存在的模型泛化能力波动问题,引入弹性网络(Elastic Net)与留一交叉验证(LOOCV)机制以提升特征筛选稳定性与模型的泛化性能,再利用遗传算法优化反向传播(GA-BP)神经网络对锂电池SOC进行估计。实验结果表明,经特征筛选后,锂电池SOC估计的均方根误差(RMSE)降低至0.635%,平均绝对误差(MAE)为0.419%,拟合优度(R²)达0.999。所提方法为多位置FBG应变信号的特征筛选问题提出了解决思路,对基于光纤传感器的锂电池SOC高精度估计提供了技术参考。

关键词: 光纤布拉格光栅, 应变, 锂离子电池, 荷电状态估计, 特征筛选

Abstract:

Fiber Bragg grating(FBG) sensor is gradually emerging as an innovative solution to enhance the accuracy of state of charge(SOC) estimation for lithium-ion batteries.However, both the positions and the number of strain sensors on the surface of lithium-ion batteries affect the accuracy of SOC estimation.Therefore, a multi-strain feature selection method based on the sequential forward selection(SFS) algorithm is proposed.To address the issue of fluctuations in model generalization ability existing in the SFS algorithm during the feature selection process, the elastic net and leave-one-out cross-validation(LOOCV) mechanisms are introduced to improve the stability of feature selection and the generalization performance of the model.Subsequently, the genetic algorithm-optimized backpropagation neural network(GA-BP) is utilized to estimate the SOC of lithium-ion batteries.Experimental results show that the root mean square error(RMSE) of lithium-ion battery SOC estimation is reduced to 0.635%, the mean absolute error(MAE) is 0.419%, and the coefficient of determination(R²) reaches 0.999 after feature selection.The proposed method provides a solution to the feature selection problem of multi-position FBG strain signals and offers technical reference for high-precision SOC estimation of lithium-ion batteries based on optical fiber sensor.

Key words: fiber Bragg grating(FBG), strain, lithium-ion battery, state of charge(SOC) estimation, feature screening

中图分类号:

TM911

何云, 盛文娟. 结合光纤光栅传感器与特征筛选的锂电池荷电状态估计[J]. 电器与能效管理技术, 2025, 0(10): 72-83.

HE Yun, SHENG Wenjuan. State of Charge Estimation for Lithium-Ion Batteries Combining Fiber Bragg Grating Sensor and Feature Screening[J]. LOW VOLTAGE APPARATUS, 2025, 0(10): 72-83.

图/表 16

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

表2

图10

表3

图11

图12

表4

参考文献 26

[1]	饶宇飞, 司学振, 谷青发, 等. 储能技术发展趋势及技术现状分析[J]. 电器与能效管理技术, 2020(10):7-15.
[2]	曹梓泉, 李雅欣, 马凌怡, 等. 基于锂电池的电氢混合储能系统研究[J]. 电器与能效管理技术, 2022(5):29-34.
[3]	李晓宇, 陈炫锴, 李嘉栩, 等. 基于机器学习的电动汽车续航里程预测[J]. 电器与能效管理技术, 2021(10):78-82.
[4]	GABBAR H, OTHMAN A, ABDUSSAMI M. Review of battery management systems(BMS)development and industrial standards[J]. Technologies, 2021, 9(2):28. doi: 10.3390/technologies9020028
[5]	MOVASSAGH K, RAIHAN A, BALASINGAM B, et al. A critical look at coulomb counting approach for state of charge estimation in batteries[J]. Energies, 2021, 14(14):1-33. doi: 10.3390/en14010001
[6]	CHEN X, LEI H, XIONG R, et al. A novel approach to reconstruct open circuit voltage for state of charge estimation of lithium ion batteries in electric vehicles[J]. Applied Energy, 2019, 255:113758.1-113758.14.
[7]	EE Y J, TEY K S, LIM K S, et al. Lithium-ion battery state of charge(SOC)estimation with non-electrical parameter using uniform fiber Bragg grating(FBG)[J]. Journal of Energy Storage, 2021, 40:102704.1-102704.9.
[8]	ZHANG L, LIU X, LI K, et al. Real-time battery temperature monitoring using FBG sensors:A data-driven calibration method[J]. IEEE Sensors Journal, 2022, 22(19):18639-18648. doi: 10.1109/JSEN.2022.3200589
[9]	CHEN D, ZHAO Q, ZHENG Y, et al. Recent progress in lithium-ion battery safety monitoring based on fiber bragg grating sensors[J]. Sensors, 2023, 23(12):5609. doi: 10.3390/s23125609
[10]	许守平, 胡娟, 徐翀, 等. 一种基于光纤光栅传感的锂离子电池温度测量方法[J]. 电器与能效管理技术, 2020(12):85-88.
[11]	BANDYOPADHYAY S, FABIAN M, LI K, et al. Fiber-Bragg-grating-based sensor system to measure battery state of charge based on a machine learning model[J]. Batteries, 2023, 9(10):508. doi: 10.3390/batteries9100508
[12]	PENG J, JIA S, YU H, et al. Design and experiment of FBG sensors for temperature monitoring on external electrode of lithium-ion batteries[J]. IEEE Sensors Journal, 2020, 21(4):4628-4634. doi: 10.1109/JSEN.7361
[13]	SOMMER L W, KIESEL P, GANGULI A, et al. Fast and slow ion diffusion processes in lithium ion pouch cells during cycling observed with fiber optic strain sensors[J]. Journal of Power Sources, 2015, 296:46-52. doi: 10.1016/j.jpowsour.2015.07.025
[14]	史雯慧, 王浩, 曹慧, 等. 基于光纤布拉格光栅传感的锂电池内部状态原位监测[J]. 光子学报, 2023, 52(9):156-164.
[15]	LI Y, LI K, LIU X, et al. A hybrid machine learning framework for joint SOC and SOH estimation of lithium-ion batteries assisted with fiber sensor measurements[J]. Applied Energy, 2022, 325:1-12.
[16]	PENG J, JIA S, YANG S, et al. State estimation of lithium-ion batteries based on strain parameter monitored by fiber Bragg grating sensors[J]. Journal of Energy Storage, 2022, 52:104950.1-104950.10.
[17]	XIA X, WU W, LI Z, et al. State of charge estimation for commercial Li-ion battery based on simultaneously strain and temperature monitoring over optical fiber sensors[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73:2516411.1-2516411.11.
[18]	RAO Y. In-fibre Bragg grating sensors[J]. Measurement Science and Technology, 1997, 8(4):355. doi: 10.1088/0957-0233/8/4/002
[19]	GANGULI A, SAHA B, RAGHAVAN A, et al. Embedded fiber-optic sensing for accurate internal monitoring of cell state in advanced battery management systems part 2:Internal cell signals and utility for state estimation[J]. Journal of Power Sources, 2017, 341:474-482. doi: 10.1016/j.jpowsour.2016.11.103
[20]	SUN Z, BEBIS G, MILLER R. Object detection using feature subset selection[J]. Pattern Recognition, 2004, 37(11):2165-2176. doi: 10.1016/j.patcog.2004.03.013
[21]	SEVERSON K A, ATTIA P M, JIN N, et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nature Energy, 2019, 4(5):383-391. doi: 10.1038/s41560-019-0356-8
[22]	高书豫, 刘树鑫, 邹嫣然, 等. 基于 GA-SVR 的交流接触器剩余电寿命预测[J]. 电器与能效管理技术, 2023(5):9-14.
[23]	LIM K S, ONG Z C, LEE Y S, et al. Pseudohigh-resolution spectral interrogation scheme for small signals from FBG sensors[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68(8):2964-2970. doi: 10.1109/TIM.19
[24]	DONOHO D L, JOHNSTONE J M. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika, 1994, 81(3):425-455. doi: 10.1093/biomet/81.3.425
[25]	WANG C, WANG Y, DONG L, et al. SOC estimation of lithium battery based on the combination of electrical parameters and FBG non-electrical parameters and using NGO-BP model[J]. Optical Fiber Technology, 2023, 81:1.1-1.10.
[26]	BHATTACHARJEE A, VERMA A, MISHRA S, et al. Estimating state of charge for xEV batteries using 1D convolutional neural networks and transfer learning[J]. IEEE Transactions on Vehicular Technology, 2021, 70(4):3123-3135. doi: 10.1109/TVT.2021.3064287

FBG	特征波长/nm
FBG0	1 539.700
FBG1	1 531.788
FBG2	1 535.892
FBG3	1 543.723
FBG4	1 551.844

小波	SNR/dB	RMSE/%
Haar	19.659	2.236
Coif4	19.739	2.195
Coif5	19.731	2.197
Db4	19.784	2.136
Db5	19.742	2.192
Sym5	19.764	2.157
Sym8	19.799	2.104

模型	输入	RMSE/%	MAE/%	R²
BP	电参数+FBG1	3.377	2.618	0.988
	电参数+FBG2、FBG4	2.448	1.996	0.994
	电参数+经特征筛选后的应变	2.276	1.663	0.995
	电参数+四位置应变	2.795	2.091	0.992
GA-BP	电参数+FBG1	1.502	1.177	0.997
	电参数+FBG2、FBG4	0.719	0.480	0.999
	电参数+经特征筛选后的应变	0.635	0.419	0.999
	电参数+四位置应变	1.077	0.793	0.998

文献	模型	RMSE/%	MAE/%
文献[7]	DNN	1.02	—
文献[16]	NN	—	0.84
文献[17]	NN	0.76	0.59
文献[25]	NGO-BP	2.01	1.54
文献[26]	CNN	—	0.89
本文	GA-BP	0.64	0.42