Drivability evaluation of engine start based on principal component analysis and support vector regression 2019-01-0932
Reasonable calibration can improve vehicle drivability. Aiming at the problem that subjective evaluation method is used to evaluate the drivability is likely to cause poor stability of the evaluation results. In this paper, a drivability evaluation model combined with principal component analysis and support vector regression is proposed. In the evaluation model, the principal component analysis is adapted to determine the input index of evaluation model, and the drivability evaluation model is built on the basis of support vector regression. Compared the evaluation model in this paper with the evaluation model using the BP neural network, the experimental results show that the drivability evaluation model using principal component analysis and support vector regression has higher accuracy and stability than the model using the BP neural network. This method can be as well extended to other evaluation models, with higher theoretical guidance and application value in practical issues.