Method for predicting wind resistance coefficient of side contour of car body

The invention relates to a method for predicting the wind resistance coefficient of the side profile of a car body, which comprises the following steps of: S1, acquiring data parameters of the side profile of the car body, and determining a Bezier curve of the side profile of the car body; s2, extracting a wind resistance coefficient characteristic value of the Bezier curve of the side contour of the car body, and obtaining a characteristic parameter by using LASSO regression; s3, training feature parameters by using an LSTM deep learning model; and S4, constructing a car body side contour prediction model as an LASSO-LSTM wind resistance coefficient prediction model, and realizing wind resistance coefficient prediction. According to the method, the problems that the vehicle body contour features are not obvious and cannot be extracted under the condition that the data size is small are solved, the cognition degree of the model for the vehicle body contour is improved, the error value of the prediction wind r