A design methodology of intelligent neuro-fuzzy system model using an improved max-min CRI method

The max-min CRI (conditional rule of inference) method, a traditional fuzzy inference method, has three problems: subjective formulation of membership functions, error-prone weighting strategy, and inefficient compositional rule of inference. Because of these problems, there are insurmountable error regions between desired output and inferred output. To overcome these problems, we propose an intelligent neuro-fuzzy system (INFS) based on inference functions of fuzzy theory and learning functions of neural networks. INFS makes use of neural network (error back propagation) to solve the first problem, and NCRI (new max-min CRI) method for the second. With a proposed similarity measure, NCRI method is an improved method compared to the traditional max-min CRI method. For the last problem, we propose a new defuzzification method which combines only the appropriate rules produced by the rule selection level. Applying INFS to a DC series motor, we can conclude that error regions are removed completely and NCRI method performs better than max-min CRI method