Prediction of Spherical Sheet Springback Based on a Sparrow-Search-Algorithm-Optimized BP Neural Network

Springback is an unavoidable problem in cold-forming processes and affects the efficiency quality of processing outer sheets for ships. Therefore, effective control prediction sheet-forming springback particularly important field cold-bending processes. To this end, paper presents research on based a study multipoint process combined with intelligent algorithms, as well production ship-hull plates. The forming spherical was simulated by finite element simulation. amount under different studied, state were briefly analyzed. Then in-depth machine learning carried out, sparrow search algorithm (SSA) introduced back-propagation neural network (BPNN). purpose integration to prevent BP model from falling into local optimal solution problems. simulation data obtained help build backpropagation model, which optimized algorithm, training tests conducted. results compared verify that accuracy performance sparrow-search-algorithm-optimized BPNN improved. Finally, SSA–BPNN models showed outperformed other algorithms speed; its error within 4%, meets on-site requirements. sparrow-search-algorithm-based optimization confirmed have strong applicability prediction.