Fuzzy-Neural Control Based On Genetic Algorithms

The objects controlled become more and more complex with the development of epoch and the progress of technology. The objects controlled have a lot of unclear things, it leads the tradition control methods based on math model is not successful, Fuzzy logic control and neural net control is an effective way to solve these problems. Both of them are intelligent control with no model. They can be used for uncertain complex system, but fuzzy control can't adjust membership function and fuzzy rule. Neural net has the ability of learning, but its inner mechanism isn't clear. It is difficulty to present the knowledge.This paper put forward fuzzy control based on neural net, it influxes the advantage of fuzzy logic and neural net, gathers learning, association and self-adaptation together. Tradition learning method has disadvantages such as long leaning and slow convergence speed. This paper use advanced GA adjust fuzzy rules get the initial values, using these optimized parameters as the initial weight values of neural net. Aiming at the structure characters of fuzzy neural control, using fuzzy-GA training the weights of fuzzy neural control, the compound control has good characteristic.Using fuzzy neural control based on GA in single pendulum system, the results of simulation manifests the new compound intelligent control has quick response speed and good robust.