Research on Battery Capacity Decline Prediction Based on Improved Algorithm of Traceless Particle Filtering
GUO Ruijun1,XIN Yongqiang1,YANG Jianfeng2
1. Gansu Measurement Research Institute, Lanzhou, Gansu 730070, China
2. School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
Abstract：In order to improve the accuracy and applicability of battery capacity prediction, an improved algorithm based on traceless particle filtering is proposed. In order to reduce the observation error of the filtering iteration process, a support vector regression algorithm is introduced to improve it. Since the kernel function and penalty factor in the support vector regression algorithm are difficult to determine, it is proposed to use the optimization ability of the genetic algorithm to solve it, forming a model improved by the genetic algorithm and support vector regression. The performance of this fusion model is evaluated and compared with UPF-SVR and UPF-RVR, and the experimental results show that the mean absolute error EMAand root mean square error SRMSE of the fusion model prediction results are lower than 2.0% and 2.5%, respectively, and the prediction accuracy is higher compared with the other models, and at the same time, the prediction level and convergence are significantly better than other models, which is more effective and feasible.
WU Z Q, HU X Y, MA B Y, et al. Remaining service life prediction of lithium batteries based on PF-LSTM［J］. Acta Metrologica Sinica, 2023, 44(6): 939-947.
ZHANG Z Q, MA S L, JIANG X Y, et al. SOC estimation method for lithium battery based on local model network［J］. Chinese Journal of Scientific Instrument, 2023, 44(7): 161-171.
XI J N, NI Y L, ZHU C B. Remaining life prediction of lithium battery based on improved support vector regression ［J］. Transactions of China Electrotechnical Society, 2021, 36(17): 3693-3704.
［7］
WEI M, GU H, YE M, et al. Remaining useful life prediction of lithium-ion batteries based on Monte Carlo Dropout and gated recurrent unit［J］. Energy Reports, 2021, 7: 2862-2871.
WANG F K, AMOGNE Z E, TSENG C, et al. A hybrid method for online cycle life prediction of lithium‐ion batteries［J］. International Journal of Energy Research, 2022, 46(7): 9080-9096.
LI C R, XIAO F, FAN Y X, et al. Estimation of lithium-ion battery charge state based on the fusion of gated recurrent unit neural network and Uber-M estimation robust Kalman filtering method by Chaoran Li［J］. Journal of Electrotechnology, 2020, 35(9): 2051-2062.
LIU Q, ZHANG B. Remaining service life prediction of lithium battery based on GBDT algorithm ［J］. Journal of Electronic Measurement and Instrumentation, 2022, 36(10): 166-172.
ZHAO Q F, CAI Y P, WANG X J. Residual life prediction of lithium batteries under different discharge intervals ［J］. China Measurement & Test, 2023, 49(3): 159-165.
HAO K Q, L Z Q, DI R H, et al. Residual life prediction of lithium battery based on whale algorithm optimized long and short-term memory neural network［J］. Science Technology and Engineering, 2022, 22(29): 12900-12908.
HUANG K, DING H, GUO Y F, et al. Lithium-ion battery life prediction based on data preprocessing and long and short-term memory neural networks ［J］. Transactions of China Electrotechnical Society, 2022, 37(15): 3753-3766.
ZHANG X, FENG H L. Remaining life prediction of lithium battery based on discharge process information ［J］. Acta Metrologica Sinica, 2022, 43(11): 1492-1500.
WANG Q T, QI W. Nonlinear degradation model and multi-objective energy storage optimization for lithium batteries［J］. Control Engineering of China, 2022, 29(8): 1360-1369.
JIN D W, GU Z Y, ZHANG Z H. Research on lithium battery healthiness and remaining life prediction algorithms ［J］. Power System Protection and Control, 2023, 51(1): 122-130.
［17］
JIANG B, GENT W E, MOHR F, et al. Bayesian learning for rapid prediction of lithium-ion battery-cycling protocols［J］. Joule, 2021, 5(12): 3187-3203.
DING G, WANGW, ZHU T. Remaining useful life prediction for lithium-ion batteries based on CS-VMD and GRU［J］. IEEE Access, 2022, 10: 89402-89413.
ZHANG H, HU C H, DU D B, et al. Residual life prediction of lithium battery based on Bi-LSTM network under multi-state influence ［J］. Acta Electronica Sinica, 2022, 50(3): 619-624.
HE Y J, LIU Y F, BIAN H D, et al. Informer-based battery charge state estimation and its sparse optimization method［J］. Acta Electronica Sinica, 2023, 51(1): 50-56.
［4］
XUE Q, SHEN S Q, LI G, 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, 69 (12): 14765 - 14779.
WU Z Q, HU X Y. STPF-based SOC estimation and its application in multi-lithium battery equalization［J］. Journal of Electronic Measurement and Instrumentation, 2022, 36(2): 235-244.
ZHAO Z, PANG X Q, DONG Y C. Prediction of recession interval of lithium battery remaining use capacity with multiple health indicators［J］. Journal of North University of China: Natural Science Edition, 2023, 44(3): 263-271.
2024, Vol. 45 
