...
首页> 外文期刊>Optics and Lasers in Engineering >Laser forming of a dome shaped surface: Experimental investigations, statistical analysis and neural network modeling
【24h】

Laser forming of a dome shaped surface: Experimental investigations, statistical analysis and neural network modeling

机译:圆顶形表面的激光成型:实验研究,统计分析和神经网络建模

获取原文
获取原文并翻译 | 示例

摘要

Forming a 3D shape from a flat sheet metal using a laser beam requires multiple irradiations along different paths with necessary heating parameters. In this article, investigations on forming a dome shaped surface from a square metal sheet were carried out using laser forming under temperature gradient mechanism. Experiments were conducted to study the effects of various process parameters, considering laser power, scan speed and spot diameter as inputs and the dome height as the output. Statistical regression analysis was performed based on the experimental data collected according to a design of experiments. All the input variables were found to have significant effects on the dome height. Dome height increased with the laser power and decreased with the spot diameter, but it was found to initially increase and then decrease with the scan speed. Optimization was done to obtain the maximum dome height and the corresponding set of optimal input parameters. Neural network-based models were also developed to predict the dome height and carry out the process synthesis, i.e., to predict the process parameters for obtaining a particular dome height. These methods were able to predict the dome height and process parameters with reasonable accuracy. The effects of sample size, scan pitch, number of scans and Fourier number on dome height were further investigated experimentally. The dome height was found to increase with the increase of work piece size and number of laser scans, and decrease with the scan pitch and Fourier number.
机译:使用激光束由平板金属形成3D形状需要沿着不同的路径进行多次辐射,并具有必要的加热参数。在本文中,研究了在温度梯度机制下使用激光成形由方形金属板形成圆顶形表面的方法。进行实验以研究各种工艺参数的影响,并以激光功率,扫描速度和光斑直径为输入,并以圆顶高度为输出。基于根据实验设计收集的实验数据进行统计回归分析。发现所有输入变量都对球顶高度有重大影响。圆顶高度随激光功率而增加,而随光斑直径而减小,但发现其高度最初随扫描速度而增加,然后减小。进行了优化以获得最大圆顶高度和相应的一组最佳输入参数。还开发了基于神经网络的模型来预测圆顶高度并进行过程综合,即预测用于获得特定圆顶高度的过程参数。这些方法能够以合理的精度预测球顶高度和过程参数。通过实验进一步研究了样本大小,扫描间距,扫描次数和傅立叶数对球顶高度的影响。发现圆顶高度随着工件尺寸和激光扫描次数的增加而增加,并且随着扫描间距和傅里叶数的增加而降低。

著录项

  • 来源
    《Optics and Lasers in Engineering 》 |2014年第2期| 31-42| 共12页
  • 作者单位

    Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur-721 302, West Bengal, India;

    Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur-721 302, West Bengal, India;

    Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur-721 302, West Bengal, India;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    3D Laser forming; Statistical analysis; Neural networks; Process synthesis;

    机译:3D激光成型;统计分析;神经网络;工艺综合;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号