arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.08049physics.comp-phcs.LG
收藏

基于人工神经网络的喷丸成形图形的有效规划

Efficient planning of peen-forming patterns via artificial neural networks

Polytechnique Montréal(蒙特利尔理工学院);Aluminium Research Centre – REGAL(铝研究中心 – REGAL)

Wassime Siguerdidjane, Farbod Khameneifar, Frédérick P. Gosselin

摘要:

喷丸成形过程的鲁棒自动化需要闭环反馈,其中需要为每次处理迭代实时找到合适的处理模式。在这项工作中,我们提出了一种方法,用于寻找喷丸成形图案,基于神经网络(NN),学习的非线性函数,涉及一个给定的目标形状(输入),其最佳喷丸图案(输出),从有限元模拟产生的数据。训练后的神经网络产生的模式的平均二进制精度为98.8%的地面真理在微秒。

英文摘要:

Robust automation of the shot peen forming process demands a closed-loop feedback in which a suitable treatment pattern needs to be found in real-time for each treatment iteration. In this work, we present a method for finding the peen-forming patterns, based on a neural network (NN), which learns the nonlinear function that relates a given target shape (input) to its optimal peening pattern (output), from data generated by finite element simulations. The trained NN yields patterns with an average binary accuracy of 98.8\% with respect to the ground truth in microseconds.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑