Research On Prediction And Intelligent Control For Ship Roll Motion Based On ANFIS

The ship stabilizing fin system is employed as research object,and ANFIS is utilized as theory basis,the ship roll motion prediction and intelligent control for fin stabilizers are systemically investigated in this thesis.Because of the nonlinear and time-variety character of the ship roll motion,predict and control of ship roll motion well and truly play an important role for improving ship seekeeping and navigability.Ship anti-rolling fin is a successful compound of modern bionics and control theory in ship engineering and also one of the most widely used anti-rolling apparatus.Firstly,six degrees of freedom ship motion is introduced and the ship motion equation is established by using the STF method.Through analyzing the wave spectrum get the slop angle of wave of difference speed,the ship roll equation is established.On the base of a great deal of reference literatures,the method using ANFIS theory for the ship roll forecast and the intelligent control are put forward.ANFIS can produce fuzzy rules from sample data directly and is originally combination of fuzzy inference system and neural network.So it is well suitable for some complex process control lacking of expert experience.Because ANFIS can realize the combination of fuzzy quantity and numeric quantity,and both of its parameters and weights adjusted have clear physics meaning.So ANFIS has been great promising for industry application.Then use ANFIS and period fold hybrid arithmetic get the perfect forecast sequence of the certain time. Lastly,a method of inverse mode ANFIS network adaptive control based on ship stability fin system is proposed,the control system can overcome poor adaptability of conventional PID controller and offer better characteristics of fault tolerance and stronger nonlinear adapting ability.In the simulation study,by introducing pseudo random binary signals as simulated input signals of wave slope angle,the built roll model gets better extensive ability for input signals under various sea states.