基于改进LightGBM的电动汽车电池剩余使用寿命在线预测

doi:10.19595/j.cnki.1000-6753.tces.211075

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (5287 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要为实现电池剩余使用寿命（RUL）在线预测和降低数据离群值对预测精度影响,提出基于改进轻量型梯度提升机（LightGBM）的RUL在线预测方法。首先,为实现RUL在线预测,通过等压降时间与容量衰减的关系,选取等压降时间为健康因子;然后,为降低数据离群值对预测精度的影响,构建基于LightGBM的预测模型,采用Bagging的学习方式,忽略离群值权重;接着,为进一步降低离群值影响,基于一种兼具自适应性和鲁棒性的损失函数（ARLF）对LightGBM进行改进,通过超参数α限制损失函数一阶导数幅值的饱和值,在残差增长时,限制离群值对梯度的影响;最后,通过行驶工况下电池全生命周期容量测试实验数据,对比基于不同损失函数的RUL在线预测效果,验证所构建健康因子和所提预测方法的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	肖迁
	穆云飞
	焦志鹏
	孟锦豪
	贾宏杰

关键词 ：锂离子电池, 剩余使用寿命, 在线预测, 离群值, 改进轻量型梯度提升机

Abstract：In order to achieve the remaining useful life (RUL) on-line prediction and reduce the impact of outlier value on prediction accuracy, this paper proposes an on-line prediction method based on the improved light gradient boosting machine (LightGBM). Firstly, in order to accomplish RUL on-line prediction, the health indicator is selected according to the relationship between isobaric time series and capacity. Then, in order to reduce the impact of outliers on the prediction accuracy, the prediction model based on LightGBM is built, and Bagging learning method is adopted, which ignores the weights of outliers. The improved LigthGBM based on adaptive robust loss function is established to reduce the impact further. Parameter α is utilized to limit the saturation value for first-order derivative of loss function, so that the influence of residual error on the gradient is reduced. Finally, the effectiveness of the established health indicator and the proposed RUL prediction method is verified by experimental data, and the RUL prediction performance based on different loss functions are compared. The results demonstrate that the proposed method has higher prediction accuracy and better robustness.

Key words： Lithium-ion battery remaining useful life on-line prediction outlier value improved light gradient boosting machine

收稿日期: 2021-07-15

PACS:

TM911

基金资助:国家自然科学基金（52107121, U2066213）和中国博士后科学基金（2020M680880）资助项目

通讯作者: 穆云飞男,1984年生,博士,教授,博士生导师,研究方向为电力系统安全性与稳定性、综合能源集成与应用、电动汽车并网规划与运行控制。E-mail：yunfeimu@tju.edu.cn

作者简介: 肖迁男,1988年生,博士,讲师,博士生导师,研究方向为分布式能源与微电网、直流配电网、电力电子技术及其在智能电网和综合能源系统中的应用、电池储能系统。E-mail：xiaoqian@tju.edu.cn

引用本文:

肖迁, 穆云飞, 焦志鹏, 孟锦豪, 贾宏杰. 基于改进LightGBM的电动汽车电池剩余使用寿命在线预测[J]. 电工技术学报, 2022, 37(17): 4517-4527. Xiao Qian, Mu Yunfei, Jiao Zhipeng, Meng Jinhao, Jia Hongjie. Improved LightGBM Based Remaining Useful Life Prediction of Lithium-Ion Battery under Driving Conditions. Transactions of China Electrotechnical Society, 2022, 37(17): 4517-4527.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.211075 https://dgjsxb.ces-transaction.com/CN/Y2022/V37/I17/4517

[1] 中关村储能产业技术联盟. 储能产业研究白皮书2019[R]. 2019.
[2] Krein P T, Fasugba M A, Vehicle-to-grid power system services with electric and plug-in vehicles based on flexibility in unidirectional charging[J]. CES Transactions on Electrical Machines and Systems, 2017, 1(1): 26-36.
[3] Ng M F, Zhao Jin, Yan Qingyu, et al.Predicting the state of charge and health of batteries using data-driven machine learning[J]. Nature Machine Intelligence, 2020, 2: 161-170.
[4] 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.
Wang Yingzhou, Ni Yulong, Zheng Yuqing, et al.Remaining useful life prediction of lithium-ion batteries based on support vector regression optimized and ant lion optimizations[J]. Proceedings of the CSEE, 2021, 41(4): 1445-1457, 1550.
[5] 李超然, 肖飞, 樊亚翔, 等. 基于卷积神经网络的离子电池SOH估算[J]. 电工技术学报, 2020, 35(19): 4106-4119.
Li Chaoran, Xiao Fei, Fan Yaxiang, et al.An approach to lithium-ion battery SOH estimation based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020, 35(19): 4106-4119.
[6] Wang Junhua, Liu Shiqi, Wang Shuxiao, et al.Multiple indicators-based health diagnostics and prognostics for energy storage technologies using fuzzy comprehensive evaluation and improved multivariate grey model[J]. IEEE Transactions on Power Electronics, 2021, 36(11): 12309-12320.
[7] Adib K M, Caliwag A C, Lim W.Novel SOH estimation of lithium-ion batteries for real-time embedded applications[J]. IEEE Embedded Systems Letters, 2021, 13(4): 206-209.
[8] 陈赐阳, 陈德旺. 基于CNN-LSTM的锂电池剩余寿命(RUL)间接预测研究[J]. 电源技术, 2021, 45(5): 589-594.
Chen Ciyang, Chen Dewang.Research on indirect prediction of lithium battery RUL based on CNN-LSTM[J]. Chinese Journal of Power Sources, 2021, 45(5): 589-594.
[9] Liu Wei, Xu Yan.Data-driven online health estimation of Li-ion batteries using a novel energy-based health indicator[J]. IEEE Transactions on Energy Conversion, 2020, 35(3): 1715-1718.
[10] 郭永芳, 黄凯, 李志刚. 基于短时搁置端电压压降的快速锂离子电池健康状态预测[J]. 电工技术学报, 2019, 34(19): 3968-3978.
Guo Yongfang, Huang Kai, Li Zhigang.Fast state of health prediction of lithium-ion battery based on terminal voltage drop during rest for short time[J]. Transactions of China Electrotechnical Society, 2019, 34(19): 3968-3978.
[11] 史永胜, 王凡, 刘博亲, 等. 基于注意力改进 BiGRU的锂离子电池健康状态估计[J/OL]. 储能科学与技术, DOI: 10.19799/j.cnki.2095-4239.2021. 0099.
Shi Yongsheng, Wang Fan, Liu Boqin, et al.Health state estimation of lithium-ion batteries based on attention augmented BiGRU[J]. Science and Technology of Energy Storage, DOI: 10.19799/j.cnki. 2095-4239.2021.0099.
[12] Cong Xinwei, Zhang Caiping, Jiang Jiuchun, et al.A hybrid method for the prediction of the remaining useful life of lithium-ion batteries with accelerated capacity degradation[J]. IEEE Transactions on Vehicular Technology, 2020, 69(11): 12775-12785.
[13] Sadabadi K K, Jin Xin, Rizzoni G.Prediction of remaining useful life for a composite electrode lithium ion battery cell using an electrochemical model to estimate the state of health[J]. Journal of Power Sources, 2021, 481: 228861.
[14] 卫志农, 原康康, 成乐祥, 等. 基于多新息最小二乘算法的锂电池参数辨识[J]. 电力系统自动化, 2019, 43(15): 139-145.
Wei Zhinong, Yuan Kangkang, Cheng Lexiang, et al.Parameter identification of lithium-ion battery based on multi-innovation least squares algorithm[J]. Automation of Electric Power Systems, 2019, 43(15): 139-145.
[15] 刘芳, 马杰, 苏卫星, 等. 基于自适应回归扩展卡尔曼滤波的电动汽车动力电池全生命周期的荷电状态估算方法[J]. 电工技术学报, 2020, 35(4): 698-707.
Liu Fang, Ma Jie, Su Weixing, et al.State of charge estimation method of electric vehicle power battery life cycle based on auto regression extended Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(4): 698-707.
[16] Feng Hailin, Song Dandan.A health indicator extraction based on surface temperature for lithium-ion batteries remaining useful life prediction[J]. Journal of Energy Storage, 2021, 34: 102118.
[17] 刘昊天, 王萍, 程泽. 一种编解码器模型的锂离子电池健康状态估算[J]. 中国电机工程学报, 2021, 41(5): 1851-1860.
Liu Haotian, Wang Ping, Cheng Ze.A novel method based on encoder-decoder framework for Li-ion battery state of health estimation[J]. Proceedings of the CSEE, 2021, 41(5): 1851-1860.
[18] Li Wenhua, Jiao Zhipeng, Du Le, et al.An indirect RUL prognosis for lithium-ion battery under vibration stress using Elman neural network[J]. International Journal of Hydrogen Energy, 2019, 44(23): 12270-12276.
[19] 张婷婷, 于明, 李宾, 等. 基于Wavelet降噪和支持向量机的锂离子电池容量预测研究[J]. 电工技术学报, 2020, 35(14): 3126-3136.
Zhang Tingting, Yu Ming, Li Bin, et al.Capacity prediction of lithium-ion batteries based on Wavelet noise reduction and support vector machine[J]. Transactions of China Electrotechnical Society, 2020, 35(14): 3126-3136.
[20] Bai Lu, Cui Lixin, Zhang Zhihong, et al.Entropic dynamic time warping kernels for co-evolving financial time series analysis[J/OL]. IEEE Transactions on Neural Networks and Learning Systems, 2020, DOI: 10.1109/TNNLS.2020.3006738.
[21] Kang Weijie, Xiao Jiyang, Xiao Mingqing, et al.Research on remaining useful life prognostics based on fuzzy evaluation-Gaussian process regression method[J]. IEEE Access, 2020, 8: 71965-71973.
[22] Zhang Yongzhi, Xiong Rui, He Hongwen, et al.Lithium-ion battery remaining useful life prediction with Box-Cox transformation and monte carlo simulation[J]. IEEE Transactions on Industrial Electronics, 2018, 66(2): 1585-1597.
[23] 李奇, 刘嘉蔚, 陈维荣. 质子交换膜燃料电池剩余使用寿命预测方法综述及展望[J]. 中国电机工程学报, 2019, 39(8): 2365-2375.
Li Qi, Liu Jiawei, Chen Weirong.Review and prospect of remaining useful life prediction methods for proton exchange membrane fuel cell[J]. Proceedings of the CSEE, 2019, 39(8): 2365-2375.
[24] Liang Jialin, Gan Yunhua, Song Weifeng, et al.Thermal-electrochemical simulation of electro- chemical characteristics and temperature difference for a battery module under two-stage fast charging[J]. Journal of Energy Storage, 2020, 29: 101307.
[25] Li Xiaoyu, Zhang Lei, Wang Zhenpo, et al.Remaining useful life prognosis for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks[J]. Journal of Energy Storage, 2019, 21: 510-518.
[26] 魏子茹, 卢延辉, 王鹏宇, 等. 基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用[J]. 机械工程学报, 2021, 51(12): 99-108.
Wei Ziru, Lu Yanhui, Wang Pengyu, et al.Application of grey correlation theory based on CRITIC method in autonomous vehicles test and evaluation[J]. Journal of Mechanical Engineering, 2021, 51(12): 99-108.
[27] 肖迁, 焦志鹏, 穆云飞, 等. 基于LightGBM的电动汽车行驶工况下电池剩余使用寿命预测[J/OL]. 电工技术学报, 1-10[2021-12-27]. DOI: 10.19595/ j.cnki.1000-6753.tces.201653.
Xiao Qian, Jiao Zhipeng, Mu Yunfei, et al.LightGBM based remaining useful life prediction of electric vehicle lithium-ion battery under driving conditions[J/OL]. Transactions of China Electrotechnical Society, 1-10[2021-12-27]. DOI: 10.19595/j.cnki.1000-6753.tces.201653.
[28] 颜诗旋, 朱平, 刘钊. 基于改进LightGBM模型的汽车故障预测方法研究[J]. 汽车工程, 2020, 42(6): 815-819, 825.
Yan Shixuan, Zhu Ping, Liu Zhao.Research on vehicle fault prediction scheme based on improved LightGBM model[J]. Automotive Engineering, 2020, 42(6): 815-819, 825.
[29] Jonathan T Barron.A general and adaptive robust loss function[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019: 4326-4334.
[30] 韦海燕, 陈静, 王惠民, 等. 新陈代谢灰色粒子滤波实现电池剩余寿命预测[J]. 电工技术学报, 2020, 35(6): 1181-1188.
Wei Haiyan, Chen Jing, Wang Huimin, et al.Remaining useful life prediction of battery using metabolic grey particle filter[J]. Transactions of China Electrotechnical Society, 2020, 35(6): 1181-1188.