Intelligent Monitoring System for Grinding Process by Recurrent Fuzzy Inference -Evaluation of Inferred Surface Roughness Using Degree of Fuzziness-
Futoshi Kobayashi*, Fumihito Arai*, Toshio Fukuda**, Makoto Onoda*** and Yuzo Hotta***
*Department of Micro System Engineering, Nagoya University, 1, Furo-cho, Chikusa-ku, Nagoya 464-8603, Japan
**Center for Cooperative Research in Advanced Science & Technology, Nagova University, 1, Furo-cho, Chikusa-ku, Nagoya 464-8601, Japan
***Production Machinery R&D Center, NTN Corporation, 1578, Higashi-Kaizuka, Iwata 438-8510, Japan
Grinding process is frequently used to produce a smooth surface in the manufacturing system. Recently, for using a super-abrasive wheel economically, grinding system needs to measure the surface roughness. However, it is difficult to measure surface roughness in process because it takes a long time to measure it. We have to infer the surface roughness in process by online sensor information and evaluate the reliability of inferred surface roughness. We have proposed Recurrent Fuzzy Inference (RFI) for estimating it. But, RFI cannot evaluate the reliability of inferred surface roughness. In this paper, we evaluate the reliability of inferred surface roughness by the degree of fuzziness that shows the lack of difference between the fuzzy set and the fuzzy complement. We show the experimental result of inferring and evaluating the surface roughness in grinding process.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.
Copyright© 1999 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.