Drivability evaluation model using principal component analysis and optimized extreme learning machine

Abstract

The accuracy of the evaluation method is essential to optimize the control system and improve a vehicle’s drivability quality. This study aimed at exploring a more effective drivability evaluation method and a drivability evaluation model was proposed on the basis of principal component analysis and optimization of an extreme learning machine. The drivability evaluation model was built using an extreme learning machine. The input of the model was determined by the principal component analysis method, and the optimal number of neurons in the hidden layer of the drivability evaluation model was obtained by a particle swarm optimization algorithm. The experimental results show that considering the evaluation index coupling factors can improve the prediction accuracy of the evaluation model. The R correlation between the score predicted by the drivability evaluation model proposed in this paper and the actual score reached 0.979, and the predicted pass rate also reached 95%, which indicate the model was more accurate and stable than others. The evaluation model can be extended to fuel economy and handling stability. It also has theoretical guidance and application value in practical problems.