AUV Fuzzy Neural Network Hybrid Learning Algorithm Control

Up to now, intelligent control has been applied widely in the uncertain and nonlinear system .Fuzzy neural network control, which is suitable for the control of strong nonlinear system with strong coupling ,is widely used in the field of the intelligent control. In this thesis, we aimed at the application of the fuzzy neural network control in the motion control and try to design a good control system for the underwater vehicle.The dynamic model of six degrees of freedom motions of the AUV is constructed, and is simplified according to practical demands. A novel controller based on the fuzzy B -spline neural network is presented, which combines the advantages of qualitative defining capability of fuzzy logic, quantitative learning ability of neural networks and excellent local controlling ability of B-spline basis functions, which are being used as membership of fuzzy functions. Simultaneously, a hybrid learning algorithm of the controller is proposed as well, in which immune genetic algorithm is used offline first for optimizing, followed by online Back Propagation algorithm.The simulation results show that it is feasible to design the fuzzy neural network control of AUV by the hybrid learning algorithm.