On-line identification of an electronic component placement process using a potential fuzzy clustering scheme

This paper presents an evolutionary potential fuzzy clustering approach for on-line identification of an electronic component placement process in the pick-and-place machines. The main idea is to identify a global nonlinear fuzzy model of the component placement process. In the proposed approach, the fuzzy clustering method utilizes an on-line potential clustering scheme to form the antecedent part of fuzzy rule-based models using an evolving Takagi-Sugeno (eTS) structure adaptation algorithm. A new on-line approach is proposed to control the rate of rule creation mechanism. The effectiveness of the proposed approach is evaluated by comparing the achieved results with some well-known approaches.