Correlation Model of Subjective and Objective Evaluation Based on Grey GM(0,N) for Automobile Sound Quality

Correlation analysis of subjective and objective evaluation for automobile sound quality is an important topic in automobile technology fields. In view of the deficiency of multi-dimensional linear regression analysis and the theoretical merits of grey system method, grey comprehensive relational degree was calculated to analyze the contribution of objective evaluation data to subjective evaluation. The main objective variables affecting the subjective feeling were determined. The variables include loudness, sharpness and shaking degrees. Grey GM(0,4) model was established as a quantitative expression for describing the subjective and objective evaluation correlation. The results of residual test and posterior-variance-test show that the established model was accurate and the model can be used to analyze and predict subjective and objective evaluation data of automobile sound quality.