拼焊板方盒件拉深成形过程变压边力曲线预测

发布时间：2018-05-13 18:26

本文选题：拼焊板 + 拉深成形　；参考：《塑性工程学报》2017年02期

【摘要】：基于有限元数值模拟软件LS-DYNAFORM,对拼焊板方盒形件拉深成形进行模拟研究。通过改变拉深成形过程中压边力这一最重要且易于控制的工艺参数,寻求拼焊板方盒形件拉深成形时较优的变压边力曲线加载形式。为预测不同工艺参数下拼焊板方盒形件拉深成形时的较优压边力加载曲线,建立了变压边力的BP神经网络预测模型,并将该模型预测的结果与数值模拟得到的结果进行对比分析。研究结果表明,拼焊板薄板采用变压边力、厚板采用恒定压边力、且薄板压边力不小于厚板压边力的加载形式,拼焊板成形件整体质量较好,焊缝移动量较小;神经网络预测模型能较好的预测拼焊板方盒形件拉深成形时的变压边力,与数值模拟结果的最大相对误差在12.3%以内。
[Abstract]:Based on the finite element numerical simulation software LS-DYNAFORM, the drawing of square box part of TWB plate is simulated and studied. By changing the most important and easy to control process parameter of blank holder force in the process of deep drawing, the better loading form of variable blank holding force curve during drawing of square box part of TWFW plate is sought. In order to predict the loading curve of optimum blank holder force in deep drawing of square box part of TWW plate with different process parameters, a BP neural network prediction model of variable blank holder force is established. The results predicted by this model are compared with those obtained by numerical simulation. The results show that the variable blank holder force is used for the TWF sheet and the constant blank holder force is used for the thick plate, and the blank holder force is not less than the loading form of the BHF force of the thick plate. The whole quality of the TWF forming part is better and the welding seam movement is small. The neural network prediction model can better predict the variable blank holder force in the deep drawing of the square box part of the TWB plate, and the maximum relative error with the numerical simulation result is less than 12.3%.
【作者单位】：燕山大学先进锻压成形技术与科学教育部重点实验室;长城汽车股份有限公司;
【基金】：国家自然科学基金资助项目(51275444) 河北省自然科学基金钢铁联合研究基金资助项目(E2014203271) 教育部高等学校博士学科点专项科研基金资助项目(20121333110003)
【分类号】：TG386.3

【参考文献】