Neural Network‐Based Adaptive Dynamic Surface Course Tracking Control of an Unmanned Surface Vehicle With Signal Input Quantization DOI

Qifu Wang,

Yuteng Guan, Jun Ning

et al.

International Journal of Adaptive Control and Signal Processing, Journal Year: 2025, Volume and Issue: unknown

Published: May 14, 2025

ABSTRACT This paper investigates the adaptive neural network‐ controlled course tracking of an unmanned surface vehicle (USV) with quantization signal input. As a first step, characteristics ship's rudder servo system are fully considered and combined mathematical representation heading control system. is done to develop nonlinear third‐order response model. The Radial Basis Function (RBF) network constructed estimate approximate unknown functions within model system, damping terms employed counteract external disturbances. Subsequently, design method for controller proposed. can enable real‐time learning adjustment address performance degradation caused by errors. Based on Lyapunov theorem, designed has been validated its dynamic capability stability, ensuring long‐term reliable stable operation. In addition, semiglobally, uniformly bound signals used in closed‐loop systems. Tracking errors lowered through parameter tuning trim levels arbitrarily. final result, simulation results confirmed effectiveness feasibility RBF network‐based quantification USVs.

Language: Английский

Neural Network‐Based Adaptive Dynamic Surface Course Tracking Control of an Unmanned Surface Vehicle With Signal Input Quantization DOI

Qifu Wang,

Yuteng Guan, Jun Ning

et al.

International Journal of Adaptive Control and Signal Processing, Journal Year: 2025, Volume and Issue: unknown

Published: May 14, 2025

ABSTRACT This paper investigates the adaptive neural network‐ controlled course tracking of an unmanned surface vehicle (USV) with quantization signal input. As a first step, characteristics ship's rudder servo system are fully considered and combined mathematical representation heading control system. is done to develop nonlinear third‐order response model. The Radial Basis Function (RBF) network constructed estimate approximate unknown functions within model system, damping terms employed counteract external disturbances. Subsequently, design method for controller proposed. can enable real‐time learning adjustment address performance degradation caused by errors. Based on Lyapunov theorem, designed has been validated its dynamic capability stability, ensuring long‐term reliable stable operation. In addition, semiglobally, uniformly bound signals used in closed‐loop systems. Tracking errors lowered through parameter tuning trim levels arbitrarily. final result, simulation results confirmed effectiveness feasibility RBF network‐based quantification USVs.

Language: Английский

Citations

0