Application of fuzzy reasoning and neural network to feed rate control of a machining robot

Issue title: Proceedings from the 17th International Symposium on Applied Electromagnetics and Mechanics (ISEM 2015)

Guest editors: Fumio Kojima, Futoshi Kobayashi and Hiroyuki Nakamoto

Article type: Research Article

Authors: Nagata, Fusaomi^{a; *} | Hayashi, Shohei^a | Nagatmi, Tomoya^a | Otsuka, Akimasa^a | Watanabe, Keigo^b

Affiliations: [a] Department of Mechanical Engineering, Faculty of Engineering, Tokyo University of Science, Yamaguchi, Japan | [b] Department of Intelligent Mechanical Systems, Graduate School of Natural Science and Technology, Okayama University, Okayama, Japan

Correspondence: [*] Corresponding author: Fusaomi Nagata, Department of Mechanical Engineering, Faculty of Engineering, Tokyo University of Science, Yamaguchi 756-0884, Japan. E-mail:nagata@rs.tus.ac.jp

Abstract: In the previous work, a machining robot based on an industrial robot was developed for foamed polystyrene materials. A robotic CAM system was incorporated in the robot to realize teachingless operation. In this paper, a fuzzy reasoning method processing radius of curvature is designed to skilfully regulate endmill's feed rate. The basic design of the machining robot using the fuzzy feed rate controller is presented for foamed polystyrene materials. Further, it is demonstrated that the mapping obtained by the fuzzy feed rate controller is well replaced by a multi-layered neural network.

Keywords: Machining robot, CAD/CAM, feed rate control, fuzzy control, neural networks

DOI: 10.3233/JAE-162217

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 52, no. 3-4, pp. 897-905, 2016