Please wait a minute...
Chinese Journal of Engineering Design  2024, Vol. 31 Issue (6): 757-765    DOI: 10.3785/j.issn.1006-754X.2024.03.403
【Special Column】Key Technologies of Design, manufacture, operation and maintenance for New Energy Equipment and Their Applications under the Carbon Peaking and Carbon Neutrality Goals     
Research on power data-driven battery remaining life prediction
Jing JIN1(),Jing WANG1,Yichen ZHOU1,Wenming PAN2
1.Shanghai Municipal Electric Power Company, State Grid Corporation of China, Shanghai 200122, China
2.Anhui Electric Power Co. , Ltd. , State Grid Corporation of China, Hefei 230061, China
Download: HTML     PDF(2594KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

The development of new energy systems increasingly emphasizes the state monitoring and performance prediction of electronic equipment. The battery is an important part of the new energy system, and the accurate monitoring and prediction of its service life and performance is of profound significance to improve the performance of electronic equipment, reduce maintenance costs and enhance energy efficiency. However, due to the influence of various complex factors on the battery performance, predicting its remaining life remains a major challenge. To solve these problems, a new battery remaining life prediction model was proposed. Firstly, the in-depth theoretical research was conducted on residual neural network (ResNet), bidirectional long short-term memory (BiLSTM) network and multi-head self-attention (MHSA) mechanism. Then, based on the above theories, the battery remaining life prediction model based on MHSA-Res-BiLSTM was constructed, and its hyperparameters were optimized. Finally, the battery remaining life prediction experiment was carried out to verify the performance of the proposed MHSA-Res-BiLSTM network. The experimental results showed that the proposed model performed excellently in the prediction of battery remaining life. Compared with other prediction models, the proposed prediction model had lower mean absolute error and root mean square error. The battery remaining life prediction model based on MHSA-Res-BiLSTM has good predictive performance and convergence performance, which can provide theoretical and technical support for the health management of batteries in new energy systems.



Key wordsnew energy system      remaining life prediction      long short-term memory network      multi-head self-attention mechanism     
Received: 15 November 2023      Published: 31 December 2024
CLC:  TM 911  
Cite this article:

Jing JIN,Jing WANG,Yichen ZHOU,Wenming PAN. Research on power data-driven battery remaining life prediction. Chinese Journal of Engineering Design, 2024, 31(6): 757-765.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2024.03.403     OR     https://www.zjujournals.com/gcsjxb/Y2024/V31/I6/757


电力数据驱动的电池剩余寿命预测研究

新型能源系统的发展愈发强调电子设备的状态监测和性能预测。电池作为新型能源系统的重要组成部分,准确监测和预测其使用寿命和性能对提高电子设备性能、降低维护成本和提升能源利用效率具有深远意义。然而,由于电池的性能受到多种复杂因素的影响,预测其剩余寿命仍是一大挑战。针对上述问题,提出了一种新型的电池剩余寿命预测模型。首先,对残差神经网络(residual neural network, ResNet)、双向长短时记忆(bidirectional long short-term memory, BiLSTM)网络和多头自注意力(multi-head self-attention, MHSA)机制进行了深入的理论研究。然后,基于上述理论构建了基于MHSA-Res-BiLSTM的电池剩余寿命预测模型,并对其超参数进行了优化设计。最后,开展电池剩余寿命预测实验,以验证所提出的MHSA-Res-BiLSTM网络的性能。实验结果显示,所提出的模型在电池剩余寿命预测上表现优越;相比于其他几种预测模型,该预测模型具有更低的平均绝对误差和均方根误差。基于MHSA-Res-BiLSTM的电池剩余寿命预测模型具有良好的预测性能和收敛性能,可为新型能源系统中电池的健康管理提供理论技术支撑。


关键词: 新型能源系统,  剩余寿命预测,  长短时记忆网络,  多头自注意力机制 
Fig.1 ResNet structure
Fig.2 Basic structure of LSTM network
Fig.3 Battery remaining life prediction flow based on MHSA-Res-BiLSTM
Fig.4 Variation curves of CS2 battery capacity with discharge cycle period
Fig.5 Convergence curve of training loss for battery remaining life prediction model based on MHSA-Res-BiLSTM
Fig.6 Comparison of battery remaining life prediction results based on different models
模型MAERMSE
MHSA-Res-BiLSTM0.011 280.016 58
Res-BiLSTM0.015 270.020 79
BiLSTM-Attention0.019 600.025 82
BiLSTM-CNN0.031 120.040 07
Table 1 Comparison of MAE and RMSE of different battery remaining life prediction models
Fig.7 Influence of hidden unit quantity on prediction performance of MHSA-Res-BiLSTM network
[1]   唐雁雁. 锂离子电池在电动汽车中的应用现状及发展综述[J]. 环境技术, 2023, 41(7): 94-100.
TANG Y Y. Review on the application status and development of lithium-ion batteries in electric vehicles[J]. Environmental Technology, 2023, 41(7): 94-100.
[2]   吕少茵, 曾维权, 杨洋, 等. 基于相变材料的动力电池热管理研究进展[J]. 新能源进展, 2020, 8(6): 493-501.
LÜ S Y, ZENG W Q, YANG Y, et al. Research progress on power battery thermal management system based on phase change material[J]. Advances in New and Renewable Energy, 2020, 8(6): 493-501.
[3]   尹丽琼, 韦安定, 韦财金. 大数据下电动汽车动力电池故障诊断技术现状与发展趋势[J]. 时代汽车, 2023(13): 154-156.
YIN L Q, WEI A D, WEI C J. Status quo and development trend of electric vehicle power battery fault diagnosis technology under big data[J]. Auto Time, 2023(13): 154-156.
[4]   RAUF H, KHALID M, ARSHAD N. Machine learning in state of health and remaining useful life estimation: theoretical and technological development in battery degradation modelling[J]. Renewable and Sustainable Energy Reviews, 2022, 156: 111903.
[5]   LÜ G Z, ZHANG H, MIAO Q. RUL prediction of lithium-ion battery in early-cycle stage based on similar sample fusion under Lebesgue sampling framework[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3511511.
[6]   邓涛, 李志飞, 陈冰曲, 等. 基于改进型能量守恒SOC估算法的电动汽车三段式智能充电方式研究[J]. 工程设计学报, 2017, 24(3): 273-279.
DENG T, LI Z F, CHEN B Q, et al. Research on three-stage intelligent charging method based on improved energy conservation SOC estimation algorithm for electric vehicle[J]. Chinese Journal of Engineering Design, 2017, 24(3): 273-279.
[7]   李争, 罗晓瑞, 解波, 等. 基于光强感知的太阳能智慧跟踪系统设计[J]. 工程设计学报, 2022, 29(5): 627-633.
LI Z, LUO X R, XIE B, et al. Design of solar intelligent tracking system based on light intensity perception[J]. Chinese Journal of Engineering Design, 2022, 29(5): 627-633.
[8]   黄晓倩, 汪沨, 谭阳红, 等. 考虑V2G模式的电动汽车与可再生能源协同调度[J]. 工程设计学报, 2016, 23(1): 67-73.
HUANG X Q, WANG F, TAN Y H, et al. Coordinated scheduling of electric vehicles and renewable generation considering vehicle-to-grid mode[J]. Chinese Journal of Engineering Design, 2016, 23(1): 67-73.
[9]   周道亮. 基于机器学习的电池剩余使用寿命预测方法综述[J]. 电源技术, 2023, 47(9): 1118-1121.
ZHOU D L. Research progress of prediction methods for remaining useful life of battery based on machine learning[J]. Chinese Journal of Power Sources, 2023, 47(9): 1118-1121.
[10]   ZHONG R R, HU B T, FENG Y X, et al. Lithium-ion battery remaining useful life prediction: a federated learning-based approach[J]. Energy, Ecology and Environment, 2024, 9: 549-562.
[11]   李远博, 王海瑞, 叶鑫, 等. 基于并行CNN-Self attention & LSTM的锂电池RUL间接预测[J]. 化工自动化及仪表, 2023, 50(4): 486-492, 556.
LI Y B, WANG H R, YE X, et al. Indirect RUL prediction of lithium-ion battery based on parallel CNN-Self attention and LSTM[J]. Control and Instruments in Chemical Industry, 2023, 50(4): 486-492, 556.
[12]   晋殿卫, 顾则宇, 张志宏. 锂电池健康度和剩余寿命预测算法研究[J]. 电力系统保护与控制, 2023, 51(1): 122-130.
JIN D W, GU Z Y, ZHANG Z H. Lithium battery health degree and residual life prediction algorithm[J]. Power System Protection and Control, 2023, 51(1): 122-130.
[13]   赵斐, 郭明, 刘学娟. 基于序列贝叶斯更新的锂电池剩余寿命预测[J]. 计算机集成制造系统, 2024, 30(2): 635-642.
ZHAO F, GUO M, LIU X J. Lithium-ion battery remaining useful life prediction based on sequential Bayesian updating[J]. Computer Integrated Manufacturing Systems, 2024, 30(2): 635-642.
[14]   刘月峰, 张公, 张晨荣, 等. 锂离子电池RUL预测方法综述[J]. 计算机工程, 2020, 46(4): 11-18.
LIU Y F, ZHANG G, ZHANG C R, et al. Review of RUL prediction method for lithium-ion batteries[J]. Computer Engineering, 2020, 46(4): 11-18.
[15]   张若可, 郭永芳, 余湘媛, 等. 基于数据驱动的锂离子电池RUL预测综述[J]. 电源学报, 2023, 21(5): 182-190.
ZHANG R K, GUO Y F, YU X Y, et al. Review of data-driven RUL prediction for lithium-ion batteries[J]. Journal of Power Supply, 2023, 21(5): 182-190.
[16]   舒星, 刘永刚, 申江卫, 等. 基于改进最小二乘支持向量机与Box-Cox变换的锂离子电池容量预测[J]. 机械工程学报, 2021, 57(14): 118-128. doi:10.3901/jme.2021.14.118
SHU X, LIU Y G, SHEN J W, et al. Capacity prediction for lithium-ion batteries based on improved least squares support vector machine and Box-Cox transformation[J]. Journal of Mechanical Engineering, 2021, 57(14): 118-128.
doi: 10.3901/jme.2021.14.118
[17]   张浩, 胡昌华, 杜党波, 等. 多状态影响下基于Bi-LSTM网络的锂电池剩余寿命预测方法[J]. 电子学报, 2022, 50(3): 619-624.
ZHANG H, HU C H, DU D B, et al. Remaining useful life prediction method of lithium-ion battery based on Bi-LSTM network under multi-state influence[J]. Acta Electronica Sinica, 2022, 50(3): 619-624.
[18]   兰凤崇, 陈继开, 陈吉清, 等. 实车数据驱动的锂电池剩余使用寿命预测方法研究[J]. 汽车工程, 2023, 45(2): 175-182.
LAN F C, CHEN J K, CHEN J Q, et al. Research on lithium battery remaining useful life prediction method driven by real vehicle data[J]. Automotive Engineering, 2023, 45(2): 175-182.
[19]   岳家辉, 夏向阳, 蒋戴宇, 等. 基于电压数据片段混合模型的锂离子电池剩余寿命预测与健康状态估计[J]. 中国电力, 2023, 56(7): 163-174.
YUE J H, XIA X Y, JIANG D Y, et al. Remaining useful life prediction and state of health estimation of lithium-ion batteries based on voltage data segment hybrid model[J]. Electric Power, 2023, 56(7): 163-174.
[20]   于沛, 王常乐. 基于局部均值分解和极限学习机的锂电池剩余寿命预测[J]. 电气技术, 2023, 24(1): 23-28.
YU P, WANG C L. Remaining life prediction of lithium-ion battery based on local mean decomposition and extreme learning machine[J]. Electrical Engineering, 2023, 24(1): 23-28.
[21]   刘芊彤, 邢远秀. 基于VMD-PSO-GRU模型的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2023, 12(1): 236-246.
LIU Q T, XING Y X. Remaining life prediction of lithium-ion battery based on VMD-PSO-GRU model[J]. Energy Storage Science and Technology, 2023, 12(1): 236-246.
[22]   刘泽, 张闯, 齐磊, 等. 基于CNN-BiLSTM的锂电池剩余使用寿命概率密度预测[J]. 电源技术, 2023, 47(1): 57-61.
LIU Z, ZHANG C, QI L, et al. Prediction of probability density of remaining useful life of lithium ion battery based on CNN-BiLSTM[J]. Chinese Journal of Power Sources, 2023, 47(1): 57-61.
[23]   武明虎, 岳程鹏, 张凡, 等. 多尺度分解下GRU-MLR组合的锂电池剩余使用寿命预测方法[J]. 储能科学与技术, 2023, 12(7): 2220-2228.
WU M H, YUE C P, ZHANG F, et al. Combined GRU-MLR method for predicting the remaining useful life of lithium batteries via multiscale decomposition[J]. Energy Storage Science and Technology, 2023, 12(7): 2220-2228.
[24]   吴忠强, 胡晓宇, 马博岩, 等. 基于PF-LSTM的锂电池剩余使用寿命预测[J]. 计量学报, 2023, 44(6): 939-947.
WU Z Q, HU X Y, MA B Y, et al. Prediction of the remaining useful life of lithium-ion batteries based on PF-LSTM[J]. Acta Metrologica Sinica, 2023, 44(6): 939-947.
[25]   王升晖, 田庆, 刘力豪, 等. 融合注意力机制的CNN-GRU动车组蓄电池SOC估算方法[J]. 控制与信息技术, 2023(5): 83-90.
WANG S H, TIAN Q, LIU L H, et al. CNN-GRU battery SOC estimation method fused with attention mechanism for electric multiple units[J]. Control and Information Technology, 2023(5): 83-90.
[26]   耿鑫月, 胡昌华, 郑建飞, 等. 双时间尺度下基于Transformer的锂电池剩余寿命预测[J]. 空间控制技术与应用, 2023, 49(4): 119-126.
GENG X Y, HU C H, ZHENG J F, et al. Remaining useful life prediction of lithium batteries based on Transformer under the dual time scales[J]. Aerospace Control and Application, 2023, 49(4): 119-126.
[27]   王朋凯, 张新燕, 张光昊. 基于ResNet-Bi-LSTM-Attention的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2023, 12(4): 1215-1222.
WANG P K, ZHANG X Y, ZHANG G H. Remaining useful life prediction of lithium-ion batteries based on ResNet-Bi-LSTM-Attention model[J]. Energy Storage Science and Technology, 2023, 12(4): 1215-1222.
[28]   梁海峰, 袁芃, 高亚静. 基于CNN-Bi-LSTM网络的锂离子电池剩余使用寿命预测[J]. 电力自动化设备, 2021, 41(10): 213-219.
LIANG H F, YUAN P, GAO Y J. Remaining useful life prediction of lithium-ion battery based on CNN-Bi-LSTM network[J]. Electric Power Automation Equipment, 2021, 41(10): 213-219.
[29]   高德欣, 刘欣, 杨清. 基于卷积神经网络与双向长短时融合的锂离子电池剩余使用寿命预测[J]. 信息与控制, 2022, 51(3): 318-329, 360.
GAO D X, LIU X, YANG Q. Remaining useful life prediction of lithium-ion battery based on CNN and BiLSTM fusion[J]. Information and Control, 2022, 51(3): 318-329, 360.
[30]   周雅夫, 史宏宇. 面向实车数据的电动汽车电池退役轨迹预测[J]. 太阳能学报, 2022, 43(5): 510-517.
ZHOU Y F, SHI H Y. Battery retirement trajectory prediction of electric vehicle based on real vehicle data[J]. Acta Energiae Solaris Sinica, 2022, 43(5): 510-517.
[31]   HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, Jun. 27-30, 2016.
[32]   GUO X F, WANG K Z, YAO S, et al. RUL prediction of lithium ion battery based on CEEMDAN-CNN BiLSTM model[J]. Energy Reports, 2023, 9(): 1299-1306.
No related articles found!