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

Authors: Guichen Zhang; Run Lu; Mengwei Chen

Addresses: Merchant Marine College, Shanghai Maritime University, Shanghai, 201306, China ' Merchant Marine College, Shanghai Maritime University, Shanghai, 201306, China ' Merchant Marine College, Shanghai Maritime University, Shanghai, 201306, China

Abstract: 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.

Keywords: multi-point mooring; MIMO-PID; DRNN; dynamic recurrent neural network; optimal control.

DOI: 10.1504/IJVD.2023.131055

International Journal of Vehicle Design, 2023 Vol.91 No.1/2/3, pp.138 - 160

Received: 13 Sep 2021
Received in revised form: 23 May 2022
Accepted: 13 Jul 2022
Published online: 22 May 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article