Dynamically Positioned Ship Steering Making Use of Backstepping Method and Artificial Neural Networks

Abstract

The article discusses the issue of designing a dynamic ship positioning system making use of the adaptive vectorial backstepping method and RBF type artificial neural networks. In the article, the backstepping controller is used to determine control laws and neural network weight adaptation laws. The artificial neural network is applied at each time instant to approximate nonlinear functions containing parametric uncertainties. The proposed control system does not require precise knowledge of the model of ship dynamics and external disturbances, it also eliminates the problem of analytical determination of the regression matrix when designing the control law with the aid of the adaptive backstepping procedure.

Analysis of Impact of Ship Model Parameters on Changes of Control Quality Index in Ship Dynamic Positioning System

“…And, the stabilizing functions vector will be determined during designing the control rule. Based on the model kinematics and dynamics equations (1)-(2), derivatives of the control errors were determined as follows [25]:…”

“…In order to determine the adaptation rule for the parameters of the matrices M, D, C and the vector b it is necessary to represent the function f in the form of a regression model and proceed further in compliance with the backstepping procedure. The components of the function were approximated by three artificial neural networks NN i of RBF type [25] whose outputs were defined in the form of the following regression model:…”

“…Control over nonlinear systems with uncertainties still constitutes rather a not recognized field. The adaptive control method such as disturbance rejection control (ADSC), backstepping [ 10,24,25] as well as its modifications either of DSC (dynamic surface control) type [20,26,27] or other adaptive methods based on artificial intelligence theory [1,3,12,16], make it possible to design a dynamically varying feedback loop. The fundamental idea of the adaptive designing of control rule consists first of all in the assessing of value of an unknown parameter as well as the determining of its estimate.…”

“…For this reason, there was carried out a susceptibility analysis of changes in values of control quality index for the ship dynamic positioning system designed with the application of the backstepping adaptive controller [10,24,6]. Such system was already proposed by these authors in the paper [25].…”

Control of Dynamic Positioning System with Disturbance Observer for Autonomous Marine Surface Vessels

“…The dynamic positioning systems presented in some works applied tools used for modeling artificial intelligence, such as fuzzy systems [91][92][93][94][95][96][97], artificial neural networks [98][99][100][101][102][103] and neuro-fuzzy systems [104,105]. An overview of selected research works related to the technological progress in the design of dynamic positioning control systems was presented in [19,21].…”