Abstract: A fuzzy neural network controller based on the optimization of defuzzification is presented.A fuzzy neural network optimal control by genetic algorithm is put forward based on the ideal of optimal control.Through simulating the process of the control system, the structure and the parameters of the fuzzy neural network are optimized off-line using GAs by optimizing an index of the controller performance.The trained fuzzy neural network is then introduced into the fuzzy nerual network intelligent control system.The computer simulation results demonstrate that the system has high control precise and small overshoot, possesses strong robustness and results show good control performance.