Intelligent Motion Control Of Autonomous Underwater Vehicle

Intelligent control is the pivot of Underwater Vehicle's control in recent years, and it is the research direction in the future to a great extent. Underwater vehicle, the precise kinetic equations of which are usually hard to acquire, is a nonlinear system with strong coupling motions of each freedom, so intelligent control is widely used in the motion control of underwater vehicles. This paper aims at the application of intelligent control techniques to motion control of AUVs, and trying to design a control system with nice performance for a certain Underwater Vehicle.Based on the space motion equations of six DOF of the MAUV(multifunctional AUV), a four DOF dynamic simulation model of the MAUV is constructed combined with the engineering demands.In this paper, fuzzy control theory is used to tune S plane controller's parameters k₁ and k₂ ,to make the controller adapt the changes of MAUV's hydrodynamic characteristic in different motion states. And also a RBF fuzzy neural network controller based on amelioration of Resource Assign Net is designed in this paper. This controller which combines the fuzzy control theory with RBF fuzzy neural network, uses the improved Resource Assign Net algorithm. It makes the number of hide nodes in the rule layer can adjust itself on line, and makes the center of the network data can adjust themselves on line too. Thus the precision and realtime requirement of the control system can be satisfied by a less structure fuzzy neural network.Based on the simulation platform of the plant------MAUV, simulationexperiments are conducted for the proposed controllers and the rusults show that the presented controllers are feasible in application to AUV.