To solve the problem of real vehicle fault prediction of electric vehicle battery system, a new algorithm for predicting real vehicle fault using Bayesian algorithm to optimize Long Short-Term Memory neural network (LSTM) was proposed. Firstly, the input and output features of LSTM were determined by Pearson correlation coefficient method, which effectively solved the problem of overfitting or underfitting of deep learning model caused by large amount of existing engineering data and excessive input and output features. Then, Bayes algorithm was used to optimize the hyperparameters of LSTM, it focused on solving the problem of difficult setting of LSTM hyperparameters, which led to false positives. The final combination of hyperparameters was determined after optimization by Bayes algorithm, and the method of establishing a single battery voltage prediction model to predict the vehicle battery voltage was proposed, which saved the model training time. The median of all single battery voltages under each frame time was determined as a new single battery voltage to train the model, and then the single battery voltage prediction model was established. Through the verification of real vehicle data, RMSE, MAE and MRE of the single unit voltage prediction model based on LSTM decreased by 61.59%, 61.31% and 60.94%, respectively, compared with the vehicle voltage prediction model based on LSTM, effectively improving the accuracy of real vehicle voltage prediction. Finally, the superiority, reliability and robustness of the proposed voltage prediction model were verified.
LIUK, PENGQ, CHEY, et al. Transfer learning for battery smarter state estimation and ageing prognostics: Recent progress, challenges, and prospects[J]. Advances in Applied Energy, 2023, 9: 100117.
[2]
WANGQ, YEM, CAIX, et al. Transferable data-driven capacity estimation for lithium-ion batteries with deep learning: A case study from laboratory to field applications[J]. Applied Energy, 2023, 350: 121747.
WANGZhenpo, YUANChanggui, LIXiaoyu. An analysis on challenge and development trend of safety management technologies for traction battery in new energy vehicles[J]. Automotive Engineering, 2020, 42(12): 1606-1620.(in Chinese)
[5]
YANGY, WANGR, SHENZ, et al. Towards a safer lithium-ion batteries: A critical review on cause, characteristics, warning and disposal strategy for thermal runaway[J]. Advances in Applied Energy, 2023, 11: 100146.
WANGZhenpo, LIXiaoyu, YUANChanggui, et al. Challenge and prospects for fault diagnosis of power battery system for electrical vehicles based on big-data[J]. Journal of Mechanical Engineering, 2021, 57(14): 52-63.(in Chinese)
[8]
ZHANGX, CHENS, ZHUJ, et al. A critical review of thermal runaway prediction and early-warning methods for lithium-ion batteries[J]. Energy Material Advances, 2023, 4: 8.
SUNZhenyu, WANGZhenpo, LIUPeng, et al. Overview of fault diagnosis in new energy vehicle power battery system[J].Journal of Mechanical Engineering, 2021, 57(14): 87-104. (in Chinese)
[11]
ZHANGY, JIANGM, ZHOUY, et al. Towards high-safety lithium-ion battery diagnosis methods[J]. Batteries, 2023, 9(1): 63-63.
[12]
XIONGR, SUNW, YUQ, et al. Research progress, challenges and prospects of fault diagnosis on battery system of electric vehicles[J]. Applied Energy, 2020, 279: 115855.
ZHANGYang, LIXiaojie, MAZilin, et al. A review of fault diagnosis algorithms for lithium-ion batteries[J]. Journal of Chongqing University of Technology (Natural Science), 2023, 37(9): 49-61. (in Chinese)
[15]
KUMARAP A, CAHYADIA I, WAHYUNGGOROO. Fault detection algorithm on lithium-polymer (Li-Po) battery based on luenberger observer[C]//2021 International Seminar on Machine Learning, Optimization, and Data Science(ISMODE). Jakarta: Indonesia, 2022: 108-113.
[16]
MARCICKIJ, ONORIS, RIZZONIG. Nonlinear fault detection and isolation for a lithium-ion battery management system[C]//ASME 2010 Dynamic Systems and Control Conference, 2011: 607-614.
HONGJ, WANGZ, YAOY. Fault prognosis of battery system based on accurate voltage abnormity prognosis using long short-term memory neural networks[J]. Applied Energy, 2019, 251: 113381.
ZHANGChaolong, ZHAOShaishai, HEYigang. State-of-health estimate for lithium-ion battery using information entropy and PSO-LSTM[J]. Journal of Mechanical Engineering, 2022, 58(10): 180-190. (in Chinese)
HUJie, YUHai, YANGBowen, et al. Battery safety risk prediction for data-driven electric vehicles.[J]. Automotive Engineering, 2023, 45(5): 814-824. (in Chinese)
[25]
LID, ZHANGZ, LIUP, et al. Battery fault diagnosis for electric vehicles based on voltage abnormality by combining the long short-term memory neural network and the equivalent circuit model[J]. IEEE Transactions on Power Electronics, 2021, 36(2): 1303-1315.
LIUShuxin, GAOShizhen, LIUYang, et al. Residual life prediction of AC contactor based on long short-term memory[J]. High Voltage Engineering, 2022, 48(8): 3210-3220.(in Chinese)
[28]
FELTUSC. Learning algorithm recommendation framework for IS and CPS security: Analysis of the RNN, LSTM, and GRU contributions[J]. International Journal of Systems and Software Security and Protection (IJSSSP), 2022, 13(1): 1-23.