Adaptive Neural Backstepping Sliding Mode Heading Control for Underactuated Ships with Drift Angle and Ship-Bank...

Area of Science:

• Marine engineering
• Control systems theory
• Robotics

Background:

• Underactuated ships face challenges in path tracking due to unknown parameters and environmental disturbances.
• Ship-bank interaction and shift angle effects further complicate control.
• Existing control methods may struggle with dynamic and unpredictable conditions.

Purpose of the Study:

• To propose an adaptive backstepping sliding mode control algorithm with a neural estimator for underactuated ships.
• To address unknown ship parameters and environmental disturbances, including ship-bank interaction and shift angle.
• To ensure accurate trajectory tracking and system stability.

Main Methods:

• Utilizing a radial basis function neural network (RBFNN) for estimating unknown ship model parameters and environmental disturbances.
• Implementing an adaptive backstepping sliding mode control strategy.
• Applying Lyapunov stability theory to guarantee system convergence and stability.

Main Results:

• The proposed algorithm effectively reduces trajectory tracking errors, stabilizing sway and surge velocities.
• Compared to basic sliding mode control, the adaptive method shows smaller overshoot and shorter regulation time.
• The RBF neural network observer successfully tracks disturbances in mild (level 3) and severe (level 5) sea states, demonstrating robustness.

Conclusions:

• The adaptive backstepping sliding mode control with a neural estimator provides superior performance for underactuated ship path tracking.
• The system achieves asymptotic stability and accurate convergence to the desired position and attitude.
• The algorithm demonstrates robust performance and accurate disturbance estimation, particularly in challenging maritime environments.