Based On Adaptive Neuro-Fuzzy Inference Systems Control For Ship Steering

This thesis has systematically researched adaptive neuro-fuzzy inference systems and its application to ship's course steering control.Ship's mathematical model is researched ,in consideration of the forces and moments from the environmental disturbances,such as winds, waves,currents,etc. Aimed at ship linear mathematical motion model ,the model reference adaptive autopilot is first designed based on the analysis of the model reference adaptive control theory, simulation experiments are carried out by using Matlab's Simulink toolbox.Conventional MRAC only used in linearity systems with known structure and parameter time-changed. For the nonlinearity and lag of the ship's movement, and the complexity of the outside interfere make the ship's movement uncertainty. Using adaptive neuro-fuzzy inference system(ANFIS) for the ship steering's nonlinear model to combine the fuzzy logic and ANN properly, so that ANFIS could express FLS by the connection structure of ANN,meanwhile realize the parameter optimization of the FLS rules by the self-learning function of ANN. Then its arithmetic and principle and the realization of ANFIS controller is studied. At last ,the scheme is applied to ship's course steering control and the simulation curves show that the desired results are attained.The ANFIS autopilot is simulated under different conditidns,such as extern disturbances,loadings,etc. The simulation results show the effectiveness and the salient performance of the proposed control scheme. And the comparion between ANFIS scheme and conventional model reference adaptive scheme demonstrates that the performance of the former is better than that of the latter.