Wavelet neural network applied for prognostication of contact pressure between soil and driving wheel

This paper describes the measurement of contact pressure in the context of wheel–terrain interaction as affected by wheel load and tire inflation pressure when fusion of the wavelet transform with the back-propagation (BP) neural network is applied to construct the wavelet neural network contact pressure prediction model. To this aim, a controlled soil bin testing facility equipped with single-wheel tester was utilized while three levels of velocity, three levels of slippage and three levels of wheel load were applied. Using image processing technique, contact area values were determined which were subsequently used for quantification of contact pressure. Performances of the different predictor models incorporated of various mother wavelets were evaluated using standard statistical evaluation criteria. Root mean square error and coefficient of determination values of 0.1382 and 0.9864 achieved by the optimal wavelet neural network are better than that of BP neural network. The proposed tool typifies a high learning speed, enhanced predicting accuracy, and strong robustness.