当前位置: X-MOL 学术Int. J. Mater. Form. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Closed-loop control of product geometry by using an artificial neural network in incremental sheet forming with active medium
International Journal of Material Forming ( IF 2.6 ) Pub Date : 2020-11-13 , DOI: 10.1007/s12289-020-01598-1
S. Thiery , M. Zein El Abdine , J. Heger , N. Ben Khalifa

A strategy to adjust the product geometry autonomously through an online control of the manufacturing process in incremental sheet forming with active medium is presented. An axial force sensor and a laser distance sensor are integrated into the process setup to measure the forming force and the product height, respectively. Experiments are conducted to estimate the bulging behavior for different pre-determined tool paths. An artificial neural network is consequently trained based on the experimental data to continuously predict the pressure levels required to control the final product height. The predicted pressure is part of a closed-loop control to improve the geometrical accuracy of formed parts. Finally, experiments were conducted to verify the results, where truncated cones with different dimensions were formed with and without the closed-loop control. The results indicate that this strategy enhances the geometrical accuracy of the parts and can potentially be expanded to be implemented for different types of material and geometries.



中文翻译:

主动介质在增量板材成形中使用人工神经网络对产品几何形状进行闭环控制

提出了一种通过在线控制具有活性介质的增量片材成型过程中制造过程的在线控制来自动调整产品几何形状的策略。轴向力传感器和激光距离传感器集成到过程设置中,分别测量成形力和产品高度。进行实验以估计不同预定刀具路径的凸起行为。因此,根据实验数据对人工神经网络进行训练,以连续预测控制最终产品高度所需的压力水平。预测压力是闭环控制的一部分,可提高成形零件的几何精度。最后,进行了实验以验证结果,在有和没有闭环控制的情况下,形成了不同尺寸的截锥。结果表明,该策略提高了零件的几何精度,并且可以潜在地扩展为针对不同类型的材料和几何形状实施。

更新日期:2020-11-13
down
wechat
bug