Bending Prediction Of Bulb Flat Steel By Neural Network Algorithm Based On SSA-BP

facing the increasing demand for high-precision bending processing production in modern shipyards, the traditional control method of CNC rib Steel bending machine can not accurately control the angle of profile bending. This deficiency leads to increased processing errors and affects product quality. For this reason, this paper introduces a machine learning predictive control method and constructs a BP neural network (SSA-BP) prediction model based on the sparrow optimization algorithm. Firstly, the method of calculating the target bending point using the secant method is introduced, and then the bending data of bulb flat steel is obtained through experiments, from which the SSA-BP model is constructed and trained. The experimental results show that the sparrow algorithm can optimize the BP neural network model to improve the prediction accuracy and achieve effective bulb flat steel bending prediction.