Research for an on-line diagnostic system for intelligent roll grinding

Although work has been carried out on fault diagnosis of general computer numerical control system, there have been few papers which focus on fault diagnosis of special computer numerical control system of roll grinder. In order to satisfy higher grinding accuracy and roll shape lower error of roll grinder. In this paper, Rough Set and Dempster-Shafer Theory as a new fault-diagnosing tool is used to identify the roll grinding fault. This method overcomes the shortcoming of conventional methods where each method of fault diagnosis on roll grinding can only provide one corresponding fault category. By the analysis of the final reducts generated using Rough Set Theory, it is shown that this new method is effective for roll grinding fault diagnosis and it is a new powerful tool that can be applied in this field.