Vessel steering autopilot (VSA) is the core system that realizes the course tracking maneuvering. It ensures that the ship navigates in the predefined course by providing appropriate control signals. This article is concerned with the adaptive inertia weight-based particle swarm optimization (PSO) control problem for VSA system. Firstly, the improved belief rule construction and inference are proposed by combining expert knowledge and data. Then, the adaptive inertia weight-based particle swarm optimization (AIWPSO) is designed to adaptively update the inertia weight in PSO via the belief rule inference. Subsequently, the AIWPSO is utilized for the adaptive proportional-integral-derivative (PID) controller design of the VSA system. Consequently, the AIWPSO-based adaptive PID (AIWPSO-APID) controller is designed and the controller parameters are optimized in real-time via AIWPSO, which realizes the adaptive control of VSA system. Finally, performance comparison experiments with other course tracking controllers under both undisturbed and disturbed situations are conducted to demonstrate the effectiveness and robustness of the AIWPSO-APID controller.
Adaptive Inertia Weight-Based Particle Swarm Optimization Control Design for Vessel Steering Autopilot
Lect. Notes Electrical Eng.
International Conference on Artificial Intelligence and Autonomous Transportation ; 2024 ; Beijing, China December 06, 2024 - December 08, 2024
The Proceedings of 2024 International Conference on Artificial Intelligence and Autonomous Transportation ; Chapter : 47 ; 476-488
2025-04-19
13 pages
Article/Chapter (Book)
Electronic Resource
English
Adaptive Particle Swarm Algorithm with Dynamically Changing Inertia Weight
British Library Online Contents | 2005
|AUTOPILOT SYSTEM FOR VESSEL, VESSEL, AND AUTOPILOT METHOD FOR VESSEL
European Patent Office | 2018
|AUTOPILOT SYSTEM FOR VESSEL, VESSEL, AND AUTOPILOT METHOD FOR VESSEL
European Patent Office | 2018
|A Particle Swarm Optimization Algorithm with Initialized Adaptive Inertia Weights
British Library Online Contents | 2012
|