Layered optimization control method for ventilation system of ocean platform

The invention belongs to the technical field of ocean engineering, and provides a layered optimization control method for an ocean platform ventilation system. Each cabin air valve is defined as an intelligent agent; a control target of the ocean platform ventilation system is determined, and intelligent agent reinforcement learning elements are designed; learning elements are reinforced according to a set ocean platform ventilation system control target; based on an SAC algorithm, training a cabin air valve intelligent body to obtain the required air volume of each cabin of the ocean platform ventilation system; based on the cabin ventilation quantity control target, proportional balance control is conducted on the air quantity of the ocean platform ventilation system, the proportional error of the actual air quantity and the required air quantity of all cabins is controlled to be minimum, and the optimal cabin air valve angle consistent with the required air quantity proportion is obtained through solving;