The application of neuron fuzzy network for assessing the impact of cutting regime parameters on part’s surface roughness, part’s oval level and grinding wheel’s wear in profile grinding for ball bearing’s inner ring groove ☆

The paper presents the results of research and application of adaptive neuro-fuzzy inference system (ANFIT) to predict the value of part’s surface roughness and the amount of grinding stone’s wear when grinding profile ball bearing's inner ring groove according to parameters such as normal feet rate, the speed of part, the depth of cut and the number of grinding parts in a grinding cycle. On that basis, the impact of cutting mode on part’s surface roughness, part’s oval level and grinding wheel’s wear is assessed. The comparison of ANFIT predictions, BPNN predictions and experimental data values indicates that results predicted by ANFIT model are more accurate than those predicted by BPNN method. This demonstrates the reliability and applicability in reality of the neurons fuzzy network tool.