关键词: 二次开发, 神经网络, 板料起皱失稳, Python, 统一起皱判定

Abstract: Aiming at the low efficiency of establishing uniform wrinkling determination line of sheet plastic forming based on a shear wrinkling test of sheet metal of four typical shapes. With the help of the secondary development function provided by ABAQUS, the python scripting language was used to write the plug-in registration script and plug-in GUI script, establish the user interface, and develop the kernel execution script. Parameterization, automatic modeling, and automatic output of wrinkling judgment line are realized., and the cost of manual operation time is saved. On this basis, to further save the time required by numerical simulation, a BP neural network prediction model was established to predict the uniform wrinkling decision line of the thin plate by using the decision line data output from secondary development. By comparing the prediction results with the finite element simulation results, the results show that the prediction results of the two methods are the same, but the neural network has a more efficient prediction ability, the required time is reduced by thousands of times, and it can realize the rapid output of the unified wrinkle determination line of different materials, providing a convenient, effective, efficient and accurate new method for the wrinkle prediction of metal sheets of different materials.

Key words: secondary development, BP neural network, plate wrinkling instability, Python, unified wrinkle judgment