摘要 : Due to their powerful optimization property, genetic algorithms(GAs) are currently being investigated for the development of adaptiveor self-tuning fuzzy logic control systems. This paper presents aneuro-fuzzy logic controller (NF... 展开 Due to their powerful optimization property, genetic algorithms(GAs) are currently being investigated for the development of adaptiveor self-tuning fuzzy logic control systems. This paper presents aneuro-fuzzy logic controller (NFLC) where all of its parameters can betuned simultaneously by GA. The structure of the controller is based onthe radial basis function neural network (RBF) with Gaussian membershipfunctions. The NFLC tuned by GA can somewhat eliminate laborious designsteps such as manual tuning of the membership functions and selection ofthe fuzzy rules. The GA implementation incorporates dynamic crossoverand mutation probabilistic rates for faster convergence. A flexibleposition coding strategy of the NFLC parameters is also implemented toobtain near optimal solutions. The performance of the proposedcontroller is compared with a conventional fuzzy controller and a PIDcontroller tuned by GA. Simulation results show that the proposedcontroller offers encouraging advantages and has betterperformance 收起