06.2021.102.112

Optimal Control for Ship Fin Stabilizer System Based on Action Dependent Heuristic Dynamic Programming

Author(s):

Thai Duong Nguyen, Quang Duy Nguyen

Affiliation(s):

Vietnam Maritime University

Corresponding Author Email:

nguyenthaiduong@vimaru.edu.vn

This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

In our research, an online learning optimal controller based on the action dependent heuristic dynamic programming (ADHDP) method is proposed for the ship linear fin stabilizer system. Compared with adaptive dynamic programming algorithm (ADP), ADHDP is simpler because no need model network in its structure, therefore, reduces the complexity in controller design and calculations. With the proposed method, the cost function is obtained by using a critic network while the control law is obtained with an action network, it is nonlinear multilayer feedback networks based on the BP network. In the online training process, these two neural networks can use the real-time measurement data, also, the internal model error and the impact of uncertainty disturbances are reduced, thus, improve the control precision and the robustness of the system. The effectiveness of the proposed controller is illustrated by the given simulation results.