Direct Adaptive Neural Network Control for Ship Manoeuvring Modelling Group Model-Based Uncertain Nonlinear Systems in Non-Affine Pure-Feedback Form

Xin Wang,Carlos Guedes Soares

doi:10.1109/access.2019.2962604

Xin Wang, Carlos Guedes Soares

Open Access

https://doi.org/10.1109/access.2019.2962604

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 8	License type: CC BY 4.0

Affiliation: Dalian Maritime University, University of Lisbon

Abstract

In this article, a direct neural network based adaptive backstepping control approach is proposed for a class of uncertain non-affine ship manoeuvring pure-feedback nonlinear systems. To carry out the backstepping design, the high fidelity 3 degrees of freedom Manoeuvring Modelling Group (MMG) model with external disturbances is transformed into the ship manoeuvring systems in non-affine pure-feedback form. Then, by combing the Implicit Function Theorem, Mean Value Theorem and dynamic surface control technique, the proposed approach is able to avoid completely the circularity problem and complexity growing problem exist in the adaptive neural network controller. During the controller design, the uncertain nonlinear functions are approximated by neural networks. Following this control approach, it is worth noting that the direct adaptive backstepping control for the high fidelity MMG model based ship manoeuvring nonlinear systems is achieved firstly, and the controller structure is simpler. Furthermore, it is shown via stability analysis that all signals in the closed-loop system are uniformly ultimately bounded. At last, two reference signals consist of a constant and a realistic performance requirement of ship are applied to simulation studies to illustrate the utility and merits of the proposed control scheme.

Highlights

Since the world’s first mechanical ship autopilot was constructed in 1910s, the control problem of ship manoeuvring has been an active research subject in the field of both marine engineering as well as automation and control system [1]
The simulation results are encouraging, and indicate that the control performance of the proposed adaptive neural network (NN) control scheme for 3 degrees of freedom (DOF) Manoeuvring Modelling Group (MMG) manoeuvring system is excellent, which means that the direct backstepping control design for high fidelity non-affine ship manoeuvring system is feasible and successful via the proposed adaptive NN control scheme
Thereby, comparing with the controller designed based on the simplified ship manoeuvring system, the proposed adaptive NN control scheme is able to realize good control performance for most of ship manoeuvres

Summary

INTRODUCTION

Since the world’s first mechanical ship autopilot was constructed in 1910s, the control problem of ship manoeuvring has been an active research subject in the field of both marine engineering as well as automation and control system [1]. In this article, a direct adaptive NN control scheme is developed for non-affine MMG model based ship manoeuvring nonlinear systems via backstepping firstly. Thereby, to carry out the adaptive backstepping design for ship manoeuvring system, the control system (23) is considered to be a class of non-affine pure-feedback nonlinear system with uncertainties . Theorem are used to show the existence of desired feedback control α3∗ and u∗, as well as design the stabilizing function, which the RBF NN is employed to approximate the desired feedback control α3∗ and u∗ Following this approach, the circularity problem during adaptive backstepping design for system (24) is avoided with less restrictive assumptions.

SIMULATION STUDIES

CONCLUSION