Optimized control method and system for boiler soot blower based on reinforcement learning

The invention discloses an optimization control method and system for a boiler soot blower based on reinforcement learning, and relates to the technical field of boiler soot blowing, and the method comprises the steps: obtaining a state value of the boiler soot blower, determining an action value, an action state value and a reward value of the boiler soot blower according to the state value and a strategy network, and building an experience pool; training a value network, a target value network, a target strategy network and the strategy network based on experience data in the experience pool to obtain a soot blower optimization control model; according to the action value and the reverse action value of the boiler soot blower and the soot blower optimization control model, control parameters of the soot blower are determined, and the technical problem that an existing soot blowing control method is insufficient in real-time dynamic control capacity on the soot blower under the multi-working-condition enviro