基于IPSO-BP神经网络的激光打孔表面粗糙度预测
DOI:
CSTR:
作者:
作者单位:

沈阳航空航天大学 工程训练中心

作者简介:

通讯作者:

中图分类号:

基金项目:

槽定位弧面凸轮转位机构的设计仿真与实物模型验证(辽宁省科技攻关计划)(项目编号:JYT2020073)


Prediction of Surface Roughness in Laser Drilling Based on IPSO-BP Neural Network
Author:
Affiliation:

Shenyang Aerospace University Engineering Training Centre,Shenyang

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对激光加工钛合金TC4微孔过程中表面粗糙度难以实时、准确预测的问题,提出一种基于改进粒子群算法优化BP神经网络(IPSO-BP)的表面粗糙度预测方法。以激光功率、脉冲频率及焦点位置偏差三个关键工艺参数作为输入特征,以微孔表面粗糙度作为输出,建立了IPSO-BP预测模型。模型基于27组仿真样本进行训练与验证,其中22组用于训练,5组用于独立测试。仿真测试结果表明,预测模型在测试集上的最大相对误差为6.89%。为进一步验证模型的有效性,开展了三组激光打孔验证试验,实测粗糙度与模型预测值的最大相对误差为8.50%。结果显示,所构建的IPSO-BP神经网络模型能够以较高精度预测激光打孔的表面粗糙度,该方法可为工艺参数优化提供有效指导,减少实验试错,降低加工成本。

    Abstract:

    To address the difficulty in real-time and accurate prediction of surface roughness during laser drilling of titanium alloy micro-holes, a prediction method based on an Improved Particle Swarm Optimization algorithm optimized Backpropagation (IPSO-BP) neural network is proposed. Taking three key process parameters—laser power, pulse frequency, and focal position deviation—as input features and the surface roughness of micro-holes as the output, an IPSO-BP prediction model was established. The model was trained and validated using 27 sets of simulation data, with 22 sets for training and 5 sets for independent testing. Simulation test results show that the maximum relative error of the prediction model on the test set is 6.89%. To further validate the model"s effectiveness, three sets of laser drilling verification experiments were conducted. The maximum relative error between the measured roughness and the model"s predicted values is 8.50%. The results indicate that the constructed IPSO-BP neural network model can predict the surface roughness of laser-drilled holes with high accuracy. This method can provide effective guidance for process parameter optimization, reduce experimental trial and error, and lower processing costs.

    参考文献
    相似文献
    引证文献
引用本文
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2026-02-07
  • 最后修改日期:2026-03-11
  • 录用日期:2026-03-23
  • 在线发布日期:
  • 出版日期:
文章二维码