Abstract: Overcharging is an important safety issue in the charging process of electric vehicle power batteries, and can easily lead to accelerated battery aging and serious safety accidents. It is necessary to accurately predict the vehicle's charging time to effectively prevent the battery from overcharging. Due to the complex structure of the battery pack and various charging modes, the traditional charging time prediction method often encounters modeling difficulties and low accuracy. In response to the above problems, data drivers and machine learning theories are applied. On the basis of fully considering the different electric vehicle battery management system (BMS) charging modes, a charging time prediction method with charging mode recognition is proposed. First, an intelligent algorithm based on dynamic weighted density peak clustering (DWDPC) and random forest fusion is proposed to classify vehicle charging modes. Then, on the basis of an improved simplified particle swarm optimization (ISPSO) algorithm, a high-performance charging time prediction method is constructed by fully integrating long short-term memory (LSTM) and a strong tracking filter. Finally, the data run by the actual engineering system are verified for the proposed charging time prediction algorithm. Experimental results show that the new method can effectively distinguish the charging modes of different vehicles, identify the charging characteristics of different electric vehicles, and achieve high prediction accuracy.

一种基于充电模式识别的电动汽车充电时间预测方法

[1]Altché F, de la Fortelle A, 2017. An LSTM network for highway trajectory prediction. Proc IEEE 20^th Int Conf on Intelligent Transportation Systems, p.353-359.

[2]Chang XQ, Song ZX, Wang JH, 2020. Electric vehicle charging load prediction and system development based on Monte Carlo algorithm. High Volt Appar, 56(8):1-5 (in Chinese).

[3]Cheng SY, Lin PC, Lin PJ, 2019. New method of predict remaining charging time for lithium-ion batteries. Chin J Power Sources, 43(1):99-102, 135 (in Chinese).

[4]Du MJ, Ding SF, Jia HJ, 2016. Study on density peaks clustering based on k-nearest neighbors and principal component analysis. Knowl-Based Syst, 99:135-145.

[5]Frendo O, Graf J, Gaertner N, et al., 2020. Data-driven smart charging for heterogeneous electric vehicle fleets. Energy AI, 1:100007.

[6]Ge QB, Guo C, Jiang HY, et al., 2022. Industrial power load forecasting method based on reinforcement learning and PSO-LSSVM. IEEE Trans Cybern, 52(2):1112-1124.

[7]Han T, Xu M, Lu YF, 2014. Charging Remaining Time Estimation Method, Device and Mobile Equipment. CN Patent 201210297383.4 (in Chinese).

[8]Hu W, Li ZS, 2007. A simpler and more effective particle swarm optimization algorithm. J Softw, 18(4):861-868 (in Chinese).

[9]Huang TS, Wu SY, 2005. Enhanced particle swarm optimization algorithm based on Kalman filter principle. Comput Eng Appl, 41(35):56-58 (in Chinese).

[10]Li B, Han R, He YG, et al., 2020. Applications of the improved random forest algorithm in fault diagnosis of motor bearings. Proc CSEE, 40(4):1310-1319 (in Chinese). doi:

[11]Li CX, Fu YY, Zhang JM, et al., 2020. Evaluation methods on charging safety for EV power battery. Proc 35^th Youth Academic Annual Conf of Chinese Association of Automation, p.318-323.

[12]Li YY, 2020. Engineering Intelligent Kalman Filtering Method. MS Thesis, Hangzhou Dianzi University, Hangzhou, China (in Chinese). doi:

[13]Lin PC, 2018. Tri-section SVR model for predicting charging time of lithium-ion batteries. Chin J Power Sources, 42(8):1155-1157, 1232 (in Chinese).

[14]Liu B, 2020. Research of Short-Term Power Load Forecasting Based on PSO-LSTM Algorithm. MS Thesis, Jilin University, Jilin, China (in Chinese). doi:

[15]Liu WW, Sang SB, Zhang HP, 2022. Study on improved heart sound classification model based on CNN+LSTM. Electron Des Eng, 30(2):38-42 (in Chinese).

[16]Liu X, 2020. Prediction of Lithium Battery's Remaining Charging Time Based on IndyLSTM. MS Thesis, Xi’an University of Science and Technology, Xi’an, China (in Chinese). doi:

[17]Liu YY, 2018. Research on modeling and simulation of detailed model of photovoltaic power generation system. Comput Knowl Technol, 14(10):221-224, 228 (in Chinese).

[18]Rodriguez A, Laio A, 2014. Clustering by fast search and find of density peaks. Science, 344(6191):1492-1496.

[19]Roondiwala M, Patel H, Varma S, 2017. Predicting stock prices using LSTM. Int J Sci Res, 6(4):1754-1756.

[20]Sun J, Chen SB, You PC, et al., 2021. Battery-assisted online operation of distributed data centers with uncertain workload and electricity prices. IEEE Trans Cloud Comput, early access.

[21]Wang ZL, Li J, Song YF, 2020. Improved K-means algorithm based on distance and weight. Comput Eng Appl, 56(23):87-94 (in Chinese).

[22]Xu ZY, Kang Y, Cao Y, et al., 2019. Man-machine verification of mouse trajectory based on the random forest model. Front Inform Technol Electron Eng, 20(7):925-929.

[23]Yang QM, Liu GL, Bao YN, et al., 2022. Fault detection of wind turbine generator bearing using attention-based neural networks and voting-based strategy. IEEE/ASME Trans Mechatron, 27(5):3008-3018.

[24]Zhang QS, Zhao QC, 2020. Effects of overcharge cycling on the aging and safety of lithium ion batteries. High Volt Eng, 46(10):3390-3397 (in Chinese).

[25]Zhang YF, Zhao ZD, Deng YJ, et al., 2021. ECGID: a human identification method based on adaptive particle swarm optimization and the bidirectional LSTM model. Front Inform Technol Electron Eng, 22(12):1641-1654.

[26]Zhou D, Song XH, Lu WB, et al., 2019. Real-time SOH estimation algorithm for lithium-ion batteries based on daily segment charging data. Proc CSEE, 39(1):105-111 (in Chinese). doi:

[27]Zhu XQ, Wang ZP, Wang C, et al., 2019. An experimental study on overcharge behaviors of lithium-ion power battery with LiNi_0.6Co_0.2Mn_0.2O₂ cathode. Automot Eng, 41(5):582-589 (in Chinese).

[28]Zhu ZC, Zheng YJ, 2017. Prediction method of rechargeable electricity of vehicle battery at different temperature. Agric Equip Veh Eng, 55(8):1-5.