基于ANN的不同材料统一起皱判定线的高效建立方法  

An Efficient Method for Establishing Unified Wrinkling Judgment Lines of Different Materials Based on ANN

作　　者：杜冰[1] 万宇凡 陈星池 王绪辰 DU Bing;WAN Yufan;CHEN Xingchi;WANG Xuchen(Key Laboratory of Advanced Forging Stamping Technology and Science,Ministry of Education of China,Yanshan University,Qinhuangdao 066004)

机构地区：[1]燕山大学先进锻压成形技术与科学教育部重点实验室,秦皇岛066004

出　　处：《机械工程学报》2025年第2期106-119,共14页Journal of Mechanical Engineering

基　　金：国家自然科学基金(52175367);河北省科技计划(236Z1011G);河北省青年科学基金(E2022203050)资助项目。

摘　　要：针对基于四种典型形状板料的剪切起皱试验的板料塑性成形统一起皱判定线建立效率过低的问题,借助ABAOUS提供的二次开发功能,利用Pvthon脚本语言编写插件注册脚本和插件程序GU脚本,建立用户界面,实现了参数化、自动化建模和板料统一起皱判定线自动输出,省去了人工操作时间成本。在此基础上,为进一步省去数值模拟所需时间,利用二次开发输出的判定线数据建立了预测薄板统一起皱判定线的BP神经网络预测模型。将预测结果与有限元仿真结果进行比较,结果表明两种方法的预测结果基本一致,但神经网络具备更加高效的预测能力,所需时间缩短了上千倍,能够实现不同材料统一起皱判定线的快速输出,对为不同材料金属板料的起皱预测提供了便捷有效、高效、准确的新方法。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.

关 键 词：二次开发 神经网络 板料起皱失稳 PYTHON 统一起皱判定 

分 类 号：TG386[金属学及工艺—金属压力加工]