Prediction of Tire Rolling Resistance with Regression Model and Artificial Neural Network (ANN)

In this study, a single tire tester was used to study the effects of vertical load, inflation pressure and moisture content on tire rolling resistance in a soil bin. A Goodyear 12.4-28, 6 ply tractor drive tire was employed and the soil texture was a clay loam. The experimental design was a completely randomized with factorial layout at three replications. A multivariate regression model was obtained with the correlation coefficient of R2=0.85 to predict the tire rolling resistance based on vertical load, inflation pressure, and moisture content. A multilayer feed-forward ANN (artificial neural network) with standard BP (back propagation) algorithm and LM (Levenberg-Marquardt) training function by using of two hidden layer in the network architecture was employed. RMSE (root mean squared error) and R2 was used as modeling performance criteria. Tire inflation pressure was identified as the controller parameter of tire rolling resistance at low moisture content and also moisture content was the most effective parameter on changing of rolling resistance in regression model. Also the obtained R2=0.977 from ANN model showed that ANN data were more close to actual data than the regression model.