Intelligent self-decision molten pool monitoring system

The utility model discloses an intelligent self-decision molten pool monitoring system which comprises a front-end sensing module, a molten pool image processing module, a molten pool state analysis module, a decision learning module and a control module. According to the utility model, a hardware image acquisition device for synchronously acquiring a high dynamic range image of a molten pool image is designed, a method for reconstructing an image from a gradient based on Fourier transformation is integrated, the molten pool state and welding parameters represented by the depth characteristics of the molten pool are utilized, the molten pool state is used as signal feedback, SAC reinforcement learning is carried out, and the welding quality of the molten pool is improved. The optimal welding strategy learning of interaction between the welding operation strategy and the molten pool state environment can be carried out by imitating trial and error experience learning of manual welding with the target of maximi