Online Estimation of Surface Roughness by Recurrent Fuzzy Inference in Grinding Process

Abstract

Grinding is frequently used to make smooth surface in the manufacturing system. In grinding process, a measurement of surface roughness is needed for preserving a whetstone and grinding efficiently. However, it is difficult to measure it in process. To reduce processing time, we have to estimate surface roughness in process by online sensing information. In this paper, we propose a multi-sensor fusion system using Recurrent Fuzzy Inference (RFI) for estimating surface roughness. The membership functions of RFI are expressed by Radial Basis Function (RBF) with insensitive ranges. The learning method of this fuzzy model is based on the steepest descent method and incremental learning which can add new fuzzy rules. We apply proposed multi-sensor fusion system to online estimation of surface roughness in grinding process.