A GPU-based prediction and simulation method of grinding surface topography for belt grinding process

Abstract

Rapid simulation of grinding surface topography at different machining conditions can assist users to determine appropriate grinding parameters. Most simulation methods reported so far are time-consuming and can only simulate the surface topography on a micro-scale, which are certainly not effective and intuitive enough. Hence, in this work, a novel GPU-based prediction and simulation method of the grinding surface topography is proposed. With the method, an artificial neural network (ANN) model is first developed to model the grinding surface roughness and fractal dimension. Then, the Cook-Torrance illumination model is introduced to render the color and glossiness of the grinding surface, and a normal map generation method is proposed to render the rugged detail features of grinding surface topography. Finally, a GPU-based prediction and simulation algorithm is developed. A performance evaluation experiment of the ANN model and a comparative experiment between the simulated and actual grinding surface topography are conducted. The experimental results show that the proposed method can achieve fast prediction and photorealistic simulation of the grinding surface topography for the whole part surface, which provides a more intuitive and effective way to evaluate the surface quality under given processing parameters.