为了提高锂电池的剩余使用寿命预测的准确性,提出一种多尺度分解和多模型融合的锂电池剩余使用寿命预测模型,以应对容量退化数据中存在噪声和局部波动对电池剩余使用寿命预测的影响。首先,使用自适应噪声的完全集合经验模态分解将原始容量数据分解为若干个分量,其中高频分量包含短期局部变化和噪声,低频分量包含主要退化趋势信息。随后,采用双向长短期记忆网络和高斯过程回归对分解后的高频分量和低频分量分别进行建模,捕捉时间序列数据中的复杂模式和依赖关系,并利用自适应粒子群算法优化模型参数。最后,对预测结果进行叠加融合,并计算锂电池的剩余使用寿命。在公开数据集上通过对比、消融和泛化实验进行分析和测试。实验结果表明,所提模型在锂电池的剩余使用寿命预测任务中AE、MAE 和 RMSE 值最低为0、0.15%和0.18%,具有良好的泛化性和较高的准确性。
Abstract
To enhance the accuracy of RUL predictions, we proposed a novel lithium battery RUL prediction model that integrates multi-scale decomposition with multi-model fusion, effectively addressing noise and local fluctuations in capacity degradation data. Firstly, complete ensemble empirical mode decomposition with adaptive noise （CEEMDAN） is employed to decompose the original capacity data into several components. The high-frequency components primarily reflect short-term local variations and noise, while the low-frequency components capture the long-term degradation trends. Secondly, bidirectional long short-term memory （BiLSTM） networks and Gaussian process regression （GPR） are applied to model the decomposed high-frequency and low-frequency components, respectively, capturing the complex patterns and dependencies in the time series data. To further enhance predictive performance, the model parameters are optimized using an adaptive particle swarm optimization （APSO） algorithm. Finally, the individual predictions from each component are aggregated to compute the overall battery RUL. To evaluation on public datasets includes a comprehensive suite of experiments, such as comparison, ablation, and generalization studies. The results demonstrate that the proposed model achieves minimum AE, MAE and RMSE values of 0, 0.15%, and 0.18%, respectively, for the RUL prediction task. These findings highlight the model’s excellent generalization ability and high prediction accuracy, establishing its effectiveness for lithium battery RUL prediction.
关键词
锂离子电池 /
经验模态分解 /
深度学习 /
机器学习 /
电池剩余使用寿命预测
Key words
lithium-ion batteries /
empirical mode decomposition /
deep learning /
machine learning /
battery remaining useful life prediction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 蔡雨思, 李泽文, 刘萍,等. 基于间接健康特征优化与多模型融合的锂电池SOH-RUL联合预测[J]. 电工技术学报, 2024, 39(18): 5883-5898.
CAI Y S, LI Z W, LIU P, et al.Joint prediction of lithium battery state of health and remaining useful life based on indirect health features optimization and multi-model fusion[J]. Transactions of China Electrotechnical Society, 2024, 39(18): 5883-5898.
[2] 何冰琛, 杨薛明, 王劲松, 等. 基于PCA-GPR的锂离子电池剩余使用寿命预测[J]. 太阳能学报, 2022, 43(05): 484-491.
HE B C, YANG X M, WANG J S, et al.Prediction of remaining useful life of lithiun-ion batteries baesd on PCA-GPR[J]. Acta energiae solaris sinica, 2022, 43(05): 484-491.
[3] 叶鑫, 王海瑞, 李远博, 等. 基于VMD和优化的LSTM锂离子电池寿命预测方法[J]. 电子测量技术, 2022, 45(23): 153-158.
YE X, WANG H R, LI Y B, et al.Remaining useful life prediction method of lithium-ion battery based on variational mode decomposition and optimized LSTM[J]. Electronic measurement technology, 2022, 45(23): 153-158.
[4] 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.
[5] 王志福, 杨忠义,罗崴, 等. 基于数据驱动的锂离子动力电池剩余使用寿命预测方法综述[J]. 科学技术与工程, 2023, 23(15): 6279-6289.
Wang Z F, YANG Z Y, LUO W, et al.Review of remaining useful life prediction for lithium-ion battery based on data-driven[J]. Science technology and engineering, 2023, 23(15): 6279-6289.
[6] 李浩平, 陈心怡, 朱成彪, 等. 基于健康因子的锂电池剩余寿命预测方法[J]. 电工技术, 2023(6): 47-50.
LI H P, CHEN X Y, ZHU C B, et al.Remaining life prediction method of lithium battery based on health factors[J]. Electric engineering, 2023(6): 47-50.
[7] 熊庆, 邸振国, 汲胜昌. 锂离子电池健康状态估计及寿命预测研究进展综述[J].高电压技术, 2024, 50(3): 1182-1195.
XIONG Q, DI Z G, JI S C.Review on health state estimation and life prediction of lithium-ion batteries[J]. High voltage engineering, 2024, 50(3): 1182-1195.
[8] ASHWIN T R, CHUNG Y M, WANG J.Capacity fade modelling of lithium-ion battery under cyclic loading conditions[J]. Journal of power sources, 2016, 328: 586-598.
[9] HE H, XIONG R, GUO H, et al.Comparison study on the battery models used for the energy management of batteries in electric vehicles[J]. Energy conversion and management, 2012, 64: 113-121.
[10] YANG F, WANG D, XING Y, et al.Prognostics of Li (NiMnCo) O2-based lithium-ion batteries using a novel battery degradation model[J]. Microelectronics reliability, 2017, 70: 70-78.
[11] WANG D, MIAO Q, PECHT M.Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model[J]. Journal of power sources, 2013, 239: 253-264.
[12] LI L, WANG P, CHAO K H, et al.Remaining useful life prediction for lithium-ion batteries based on Gaussian processes mixture[J]. PloS one, 2016, 11(9): 0163004.
[13] PARK K, CHOI Y, CHOI W J, et al.LSTM-based battery remaining useful life prediction with multi-channel charging profiles[J]. IEEE access, 2020, 8: 20786-20798.
[14] SHI Z, CHEHADE A.A dual-LSTM framework combining change point detection and remaining useful life prediction[J]. Reliability engineering & system safety, 2021, 205: 107257.
[15] YAO F, HE W, WU Y, et al.Remaining useful life prediction of lithium-ion batteries using a hybrid model[J]. Energy, 2022, 248: 123622.
[16] PAN D, LI H, WANG S.Transfer learning-based hybrid remaining useful life prediction for lithium-ion batteries under different stresses[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 1-10.
[17] 刘佳, 马志强, 刘广忱, 等. 多尺度分解下GRU-TCN集成的动力电池剩余使用寿命预测方法[J]. 储能科学与技术, 2024, 13(3): 1009-1018.
LIU J, MA Z Q, LIU G C, et al.Predicting the residual useful life of power batteries based on the GRU-TCN ensemble under multiscale decomposition[J]. Energy storage science and technology, 2024, 13(3): 1009-1018.
[18] 李英顺, 阚宏达, 郭占男,等. 基于数据预处理和VMD-LSTM-GPR的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(10): 3244-3258.
LI Y S, KAN H D, GUO Z N, et al.Prediction of remaining useful life of lithium-ion battery based on data preprocessing and VMD-LSTM-GPR[J]. Transactions of China Electrotechnical Society, 2024, 39(10): 3244-3258.
[19] TORRES M E, COLOMINAS M A, Schlotthauer G, et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2011: 4144-4147.
[20] GRAVES A, SCHMIDHUBER J.Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural networks, 2005, 18(5-6): 602-610.
[21] WILLIAMS C K I, RASMUSSEN C E. Gaussian processes for machine learning[M]. Cambridge, MA: MIT press, 2006.
[22] ZHAN Z H, ZHANG J, LI Y, et al.Adaptive particle swarm optimization[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2009, 39(6): 1362-1381.
[23] 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 of the royal society of London. Series A: mathematical, physical and engineering sciences, 1998, 454(1971): 903-995.
[24] WU Z, HUANG N E.Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in adaptive data analysis, 2009, 1(1): 1-41.
[25] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[26] KENNEDY J, EBERHART R.Particle swarm optimization[C]. Proceedings of ICNN'95-International Conference on Neural Networks. IEEE, 1995, 4: 1942-1948.
基金
内蒙古自治区高等学校碳达峰碳中和研究项目（STZX202307）; 内蒙古自治区教育厅项目（JY20220263）; 博士科研启动金项目（DC2200000890）; 校级自然科学基金（ZZ202119）
PDF(1173 KB)
