SOC Prediction of Pure Electric Vehicle Battery Based on Cnn-lstm

Pure electric vehicles will gradually replace traditional cars because of their green, environmental protection, safety and reliability. During the operation of pure electric vehicle, SOC is an important parameter in the driving process of electric vehicle.Taking the battery data of pure electric vehicle as the research object, this paper studies the SOC prediction of pure electric vehicle battery. Firstly, this paper briefly describes the data involved in this paper, then processes the missing values, abnormal values and invalid data in the data set, and extracts the charging data of pure electric vehicles. Then, through the analysis of data features and the extraction of features through Pearson correlation coefficient, cnn-lstm model is established to predict SOC. Finally, with CNN RNN and LSTM models are compared and analyzed. The analysis results show that cnn-lstm has a good effect on SOC prediction of pure electric vehicles. Compared with other algorithms, cnn-lstm has high accuracy and small error.