作者：赵沁峰, 蔡艳平, 王新军

作者单位：火箭军工程大学，陕西 西安 710025

关键词：锂离子电池;经验模态分解;差分移动自回归;广义回归神经网络;剩余寿命

摘要：

随着锂离子电池的广泛应用，需要现有剩余寿命预测模型适应实际使用工况。针对锂离子电池在循环过程中放电区间对容量衰减影响较大的现象，为解决基于放电性能映射关系建立的剩余寿命预测模型应用范围较窄，提高车用锂电池剩余寿命预测模型适用性能，提出使用经验模态分解将容量分解为波动与趋势分量，并通过建立差分移动自回归模型以及广义回归神经网络分别进行预测，获得锂离子电池剩余寿命。选取 NASA 和 CACEL电池数据集对模型进行验证，并对比基于蚁狮优化的相关向量机的方法，实验结果表明：提出的模型相比蚁狮优化的相关向量机的方法，对容量衰退的跟踪误差平均降低50%，能够实现不同放电区间下的电池老化预测，适用性能好，对电池容量再生现象追踪准确。

Remaining useful life prediction of lithium battery under different discharge intervals
ZHAO Qinfeng, CAI Yanping, WANG Xinjun
Rocket Force University of Engineering, Xi’an 710025, China
Abstract: With the widespread use of lithium batteries, the existing remaining life prediction models need to be adapted to the actual operating conditions. To address the phenomenon that the discharge interval has a large impact on the capacity decay of lithium batteries during cycling, in order to solve the narrow application range of the remaining life prediction model based on the discharge performance mapping relationship and improve the applicability of the remaining life prediction model for automotive lithium batteries, we propose to use empirical modal decomposition to decompose the capacity into fluctuating and trend components, and establish a differential moving autoregressive model and a generalized regression neural network The remaining life of lithium-ion batteries is obtained by building a differential moving autoregressive model and a generalized regression neural network. The model is validated on NASA and CACEL battery datasets and compared with the method based on the correlation vector machine with antlion optimization. The experimental results show that the proposed model reduces the tracking error of capacity decline by 50% on average compared with the method based on the correlation vector machine with antlion optimization, and is capable of predicting battery ageing under different discharge intervals with good applicability and accurate tracking of the battery capacity regeneration phenomenon.
Keywords: lithium battery;empirical modal decomposition;autoregressive integrated moving average model;generalized regression neural network;remaining useful life
2023, 49(3):159-165,180  收稿日期: 2021-07-06;收到修改稿日期: 2021-09-01
基金项目:
作者简介: 赵沁峰(1997-),男,山西晋城市人,硕士研究生,专业方向为锂离子电池健康状态诊断
参考文献
[1] 陈万, 蔡艳平, 苏延召, 姜柯, 黄华. 基于改进粒子滤波的锂离子电池剩余寿命预测[J]. 中国测试, 2021, 47(7): 148-153
[2] CHEN Z, LIU Y, XUE Q, et al. Remaining useful life prediction for lithium-ion batteries based on capacity estimation and Box-Cox transformation[J]. IEEE Transactions on Vehicular Technology, 2020(99): 3039553
[3] ZHANG N, XU A, WANG K, et al. Remaining useful life prediction of lithium batteries based on extended Kalman particle filter[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2021, 16(2): 206-214
[4] OUYANG T, XU P, CHEN J, et al. An online prediction of capacity and remaining useful life of lithium-ion batteries based on simultaneous input and state estimation algorithm[J]. IEEE Transactions on Power Electronics, 2020(99): 1-1
[5] 庞晓琼, 王竹晴, 曾建潮, 等. 基于PCA-NARX的锂离子电池剩余使用寿命预测[J]. 北京理工大学学报, 2019, 39(4): 406-412
[6] 史永胜, 施梦琢, 丁恩松, 等. 基于多退化特征的锂离子电池剩余寿命预测[J]. 电源技术, 2020, 44(6): 836-840
[7] REN L, DONG J, WANG X, et al. A data-driven Auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life[J]. IEEE Transactions on Industrial Informatics, 2021, 17(5): 3478-3487
[8] TANGADE P, HARIHARAN K S, RAMACHANDRAN S, et al. Deep Gaussian process regression for lithium-ion battery health prognosis and degradation mode diagnosis[J]. Journal of Power Sources, 2020, 445: 227281
[9] SU C, CHEN H, WEN Z. Prediction of remaining useful life for lithium-ion battery with multiple health indicators[J]. Eksploatacjai Niezawodnosc - Maintenance and Reliability, 2021, 23(1): 176-183
[10] 何畏, 罗潇, 曾珍等. 利用QPSO改进相关向量机的电池寿命预测[J]. 电子测量与仪器学报, 2020, 34(6): 18-24
[11] 杨战社, 王云浩, 孔晨再. 基于GWO-SVR的锂电池剩余使用寿命预测[J/OL]. 电源学报: 1-13[2021-09-02]. http://kns.cnki.net/kcms/detail/12.1420.TM.20210520.1300.002.html.
[12] 纪常伟, 潘帅, 汪硕峰, 等. 动力锂离子电池老化速率影响因素的实验研究[J]. 北京工业大学学报, 2020, 46(11): 64-74
[13] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings Mathematical Physical & Engineering Sciences, 1998, 454(1971): 903-995
[14] NUNES J C, BOUAOUNE Y, RIC Deléchelle, et al. Image analysis by bidimensional empirical mode decomposition[J]. Image & Vision Computing, 2003, 21: 1019-1026
[15] 王菁, 邓翔天, 王浩然, 等. 考虑温差特征的锂离子电池寿命预测[J]. 电池, 2023, 53(1): 9-13
[16] SPECHT D F. A general regression neural network[J]. IEEE Transactions on Neural Networks, 1991, 2(6): 568-576
[17] 王瀛洲, 倪裕隆, 郑宇清, 等. 基于ALO-SVR的锂离子电池剩余使用寿命预测[J]. 中国电机工程学报, 2021, 41(4): 1445-1457+1550