Sliding Mode PID Path Following Control And Optimization Of Underactuated Ship

Aiming at the inherent nonlinearity,complexity,susceptibility to external wind,wave,and current interference of conventional underactuated ships,and the difficulty of adjusting control parameters,this paper designs an RBF neural network sliding mode variable structure PID controller based on improved particle swarm optimization.The controller improves the performance of the ship’s autopilot.The algorithm does not need to estimate external disturbances such as wind,waves,currents,etc.It can effectively solve the problem of the ship’s lateral deviation caused by external disturbances and the difficulty of parameter adjustment.It has a better adaptive control effect under marine environmental conditions.This paper directly constructs the desired course angle based on the ship’s track deviation,and turns the track control problem into a course tracking control problem.Since PID control parameters are difficult to adjust and its overshoot is inevitable,this paper first adds a differential compensation term to the integral term of PID control to reduce or even eliminate the overshoot value caused by the PID control integral term,and then combines the variable structure characteristics of PID control to design Sliding mode PID controller is conducive to its parameter tuning and optimization.Finally,combining with the identification function of RBF neural network,the on-line adjustment and adaptive control of ship control parameters are realized.Aiming at the shortcomings of the particle swarm algorithm,the inertia weight value and the learning factor value that can be adjusted adaptively and dynamically are designed to improve the optimization ability of the algorithm,and the chaotic motion is applied to the structure of the particle swarm algorithm to improve the algorithm convergence speed and accuracy.Aiming at the problem that the initial value of the RBF neural network and the controller parameters are difficult to determine,the improved particle swarm algorithm is used to optimize the tuning.The optimization is mainly divided into two parts: 1)Sliding mode PID control parameters are optimized and set as the initial values of RBF neural network.2)Optimize and set the initial values of the learning rate and momentum factor in the RBF neural network.Using the Simulink module of MATLAB software to simulate the container ship "MV KOTA SEGAR" MMG model,the results show that the designed RBF neural network sliding mode PID controller can effectively eliminate the ship’s lateral deviation caused by external interference such as wind,waves,and currents.It has better control effect,strong robustness and adaptive ability.The improved particle swarm algorithm has better optimization effect,faster convergence speed,higher accuracy,and effectively solves the difficult problem of controller parameters and neural network parameters that are difficult to adjust and tune.