A new continuous t-norm and its application in fuzzy control

• Published in: Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393) Vol. 3; pp. 1795 - 1798 vol.3
• Main Authors: Dan Chen, Huacan He, Yuqin Ji, Hui Wang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2000
• Subjects: Application software; Boundary conditions; Computer science; Fuzzy control; Fuzzy sets; Fuzzy systems; Genetic algorithms; Logic; Optimization methods; Testing
• DOI: 10.1109/WCICA.2000.862783
• ISBN: 078035995X; 9780780359956

In conventional fuzzy control, MAX and MIN operators are usually adopted, but MIN and MAX operations only consider the extreme elements and ignore the contributions of other elements, which will inevitably affect the control performance. To solve this problem, we presented a new kind of t-norm and t-conorm, which can vary through Lukasiewicz operators, probability operators, and Zadeh operators with a correlation coefficient h ranging from [-1, 1]. On this basis we present simplified AND and OR operators to replace MAX and MIN operators in fuzzy control. In the simulation we use genetic algorithms to optimize the correlation coefficients and the simulation result shows that our method is better than the conventional one.