Tuning of a neuro-fuzzy controller by genetic algorithm

Due to their powerful optimization property, genetic algorithms (GA's) are currently being investigated for the development of adaptive or self-tuning fuzzy logic control systems. This paper presents a neuro-fuzzy logic contr oller (NFLC) where all of its parameters can be tuned simultaneously by GA. The structure of the controller is based on the radial basis function neur al network (RBF) with Gaussian membership functions. The NFLC tuned by GA c an somewhat eliminate laborious design steps such as manual tuning of the m embership functions and selection of the fuzzy rules. The GA implementation incorporates dynamic crossover and mutation probabilistic rates for faster convergence. A flexible position coding strategy of the NFLC parameters is also implemented to obtain near optimal solutions. The performance of the proposed controller is compared with a conventional fuzzy controller and a PLD controller tuned by GA. Simulation results show that the proposed contr oller offers encouraging advantages and has better performance.