Regulation experience self-learning-based camber control method

The invention provides a camber control method based on regulation and control experience self-learning, and is suitable for the technical field of hot continuous rolling rough rolling plate shape control. According to the method, the roll gap inclination parameter in rolling of each pass is accurately set, so that the bending amount of the camber is reduced. The specific method comprises the following steps: 1, determining acquired data; 2, preprocessing the data; 3, arranging the processed data according to a time sequence; 4, establishing a data set; 5, establishing a roll gap inclination quantity value regulation and control value prediction model by using a gradient lifting tree algorithm, and training the model to obtain optimal parameters; and 6, verifying the performance on the test set. According to the hot continuous rolling rough rolling camber control method, effective experience in self-learning roll gap inclination regulation and control data is utilized, compared with an existing method only de