Control method of mooring auxiliary dynamic positioning system based on reinforcement learning

Abstract

The present invention proposes a control method for mooring assisted dynamic positioning system based on reinforcement learning, including: first constructing a Markov decision model of the optimal point selection problem, constructing a state space and a behavior space; using a neural network to construct a reinforcement learning model Q function, Based on the current state of the mooring-assisted dynamic positioning system measured in real time, the control system uses the ε-greedy algorithm to select behaviors, and observes the system state s' and feedback rewards after the behavior a is selected; the state, behavior, obtained rewards and The new state is stored in the memory bank as label data, and the neural network is trained; by repeating the above process, the mooring-assisted dynamic positioning system can obtain the behavior selection strategy that maximizes the reward function, and obtains the power consumption of the pusher under the anchor point control mode. The lowest sweet spot.

Description

technical field [0001] The invention relates to a control method for combined use of anchoring and dynamic positioning of marine structures, in particular to a control method for an anchoring auxiliary dynamic positioning system based on reinforcement learning. Background technique [0002] With the gradual expansion of the scale of human development of marine resources, the development of positioning systems for marine structures operating in harsh sea conditions has become one of the important topics in the research and development of high-tech equipment for marine engineering. In addition to the traditional positioning method using the mooring system, more and more offshore platforms and engineering ships are beginning to be equipped with dynamic positioning systems to complete more accurate heading and position control in complex marine environments, so that they can safely and efficiently Carry out various fixed-point marine engineering operations. The joint use method...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the technical problem of selecting the anchor point with the lowest power consumption of the thruster in the anchor point control mode of the anchoring auxiliary power positioning system, the present invention proposes a control method for the anchoring auxiliary power system based on reinforcement learning, so that the control computer can control the anchoring auxiliary power system according to the mooring auxiliary The operating state of the dynamic positioning system, the optimal positioning point is calculated independently, so as to avoid the mutual interference between the mooring system and the propeller in the positioning function, give full play to the main role of the mooring system in resisting the average environmental load, and reduce the power consumption of the propeller

Images