Recurrent ANN-based modelling of the dynamic evolution of the surface roughness in grinding

Grinding is critical in modern manufacturing due to its capacity for producing high surface quality and high-precision parts. One of the most important parameters that indicate the grinding quality is the surface roughness (R-a). Analytical models developed to predict surface finish are not easy to apply in the industry. Therefore, many researchers have made use of artificial neural networks. However, all the approaches provide a particular solution for a wheel-workpiece pair, not generalizing to new grinding wheels. Besides, these solutions do not give surface roughness values related to the grinding wheel status. Therefore, in this work the modelling of the dynamic evolution of the surface roughness (R-a) based on recurrent neural networks is presented with the capability to generalize to new grinding wheels and conditions taking into account the wheel wear. Results show excellent prediction of the surface finish dynamic evolution. The absolute maximum error is below 0.49 mu m, being the average error around 0.32 mu m. Besides, the analysis of the relative importance of the inputs shows that the grinding conditions have higher influence than the wheel characteristics over the prediction of the surface roughness confirming experimental knowledge of grinding technology users.