DRNN-MIMO-PID control strategy for multi-point mooring system

A dynamic recurrent neural network (DRNN)- multi-input-multi-output (MIMO)-PID control scheme for multi-point mooring system (MPMS) is proposed in this paper. MPMS has complex characteristics for the large geometric nonlinearity of the platform hull and the impact of marine circumstances. The parallel winch motor of MPMS is controlled by MIMO PID, which is composed of position loop, speed loop and torque loop in series. The positive and inverse solutions of MPMS model are established, the relationship between MPMS position and mooring cable is determined, MPMS positioning control is achieved by DRNN-MIMO-PID, DRNN connection weight coefficients are optimised iteratively by the steepest gradient descent method to ensure MPMS position tracks the desired trajectory. The proposed scheme has been mathematically simulated, verified by four-point mooring hardware-in-the-loop system and applied to four-point mooring dredger, the results show the DRNN-MIMO-PID strategy has the advantages of collaborative optimisation and anti-interference ability.

• Record URL:
  • https://doi.org/10.1504/IJVD.2023.131055
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/14775360
• Supplemental Notes:
  • Copyright © 2023 Inderscience Enterprises Ltd.
• Authors:
  • Zhang, Guichen
  • Lu, Run
  • Chen, Mengwei
• Publication Date: 2023

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 138-160
• Serial:
  • International Journal of Vehicle Design
  • Volume: 91
  • Issue Number: 1-3
  • Publisher: Inderscience Enterprises Limited
  • ISSN: 1477-5360
  • Serial URL: http://www.inderscience.com/jhome.php?jcode=IJVD

Subject/Index Terms

• TRT Terms: Machine learning; Mooring; Neural networks; Optimization; Ships
• Subject Areas: Data and Information Technology; Marine Transportation; Vehicles and Equipment;

Filing Info

• Accession Number: 01900109
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 20 2023 9:12AM