Optimizing membership function of fuzzy logic controller via orthogonal array: A case study on temperature control
Gunawan Dewantoro · 2017
Fuzzy logic controller (FLC) is one of popular approach to control any process variables which mimics human inference mechanisms. Due to their intelligent nature and simplicity, FLC has become very common among any intelligent control schemes. One of the challenges in implementing FLC is regarding to the tuning method of the membership functions. The fixed points along the universe of discourse, on which the border of fuzzy sets are defined, need to be determined properly to achieve the desired behavior. This study proposes a design of experiments using orthogonal array for optimizing the membership function for both inputs and outputs. The temperature control case was utilized to show the effectiveness of such method. Four control factors were chosen to conduct the experiments, where the objective is to diminish the integral absolute error of the step response. Analysis of means was used to determine the optimum membership function and analysis of variance (ANOVA) was used to find out the most significant control factors. The results show that the performance of the fine-tuned membership function is better than that of default membership function. The controller also shows robustness against variation and works properly within input full range.