基于反向传播神经网络的激光弱化残余厚度预测

丁华; 殷潇

应用激光, 2018, 38 (4): 649, 网络出版: 2018-10-06

基于反向传播神经网络的激光弱化残余厚度预测

Residual Thickness Prediction of Laser Weakening Based on Back-propagation Neural Network

论文大纲

丁华 ^*殷潇

作者单位

江苏大学汽车与交通工程学院, 江苏镇江212013

激光弱化弱化线残余厚度 BP神经网络预测模型 laser weakening weakening line residual thickness BP neural network prediction model

摘要

激光弱化加工是目前的新兴技术, 弱化后残余厚度的大小是其关键问题。将残余厚度与各项激光加工工艺参数结合起来, 建立相应的预测模型。首先对汽车仪表板常用材料PC(聚碳酸酯)硬塑进行弱化加工, 沿弱化孔中心线将试件剖开并通过影像测量系统测得残余厚度值。建立激光脉冲宽度、离焦量和加工速率这三个工艺参数与残余厚度之间的BP(反向传播)神经网络预测模型, 使用大量试验数据训练网络, 并使用试验样本中的部分数据检验所建网络。最终得到了最大误差率不超过3%, 收敛速率及预测准确性高的预测模型。使用该模型, 可以精确地预测残余厚度的大小, 缩短了激光弱化加工作业的准备时间。

Abstract

Laser weakening processing is the current emerging technology. The residual thickness after weakening is the key issue. The residual thickness and the laser processing parameters were combined to establish a corresponding prediction model. First of all, the material PC (polycarbonate) hard plastic common used in automobile dashboard was weakened. The specimen was cut along the weakened hole center line and the residual thickness value was measured by an video measuring system. The BP(back-propagation)neural network prediction model was established between the three process parameters of laser pulse width, defocusing and processing rate and the residual thickness. Use a large amount of test data to train the network and use the data in the test sample to test the network. Finally, a prediction model with maximum error rate less than 3%, high convergence rate and high prediction accuracy is obtained. Using this model, the size of the residual thickness can be accurately predicted and the preparation time for laser weakening process can be reduced.

参考文献

[1] 卞春雷, 安慧, 于善平, 等.无缝安全气囊仪表板气囊区弱化线的加工工艺［J］.汽车工艺与材料, 2014(5): 31-36.

BIAN C L, AN H, YU S P, et al.Processing technology for weak line in airbag zone of seamless airbag dashboard［J］.Automobile Technology & Material, 2014(5): 31-36.

[2] 苟刚.YAG固体激光小孔加工实验及工艺仿真研究［D］.成都: 西华大学, 2015.

GOU G.Study of the experiment and process simulation on YAG solid-state laser drilling［D］.Chengdu: Xihua University, 2015.

[3] KIM M J, ZHANG J.Finite element analysis of evaporative cutting with a moving high energy pulsed laser［J］.Applied Mathematical Modelling, 2001, 25(3): 203-220.

[4] KIM M J, CHEN Z H, MAJUMDAR P.Finite element modelling of the laser cutting process［J］.Computers & Structures, 1993, 49(2): 231-241.

[5] KIM M J, MAJUMDAR P.A computational model for high energy laser cutting process［J］.Numerical Heat Transfer, 1995, 27(6): 717-733.

[6] KAEBERNICK H, BICLEANU D, BRANDT M.Theoretical and experimental investigation of pulsed laser cutting［J］.CIRP Annals-Manufacturing Technology, 1999, 48(1): 163-166.

[7] TTH G J, SZAKCS T, LRINCZ A.Simulation of pulsed laser material processing controlled by an extended self-organizing Kohonen feature map［J］.Springer London, 1993, 18(3): 281-288.

[8] PRAKASH S, KUMAR S.Profile and depth prediction in single-pass and two-pass CO2 laser microchanneling processes［J］.Journal of Micromechanics & Microengineering, 2015, 25(3): 035010.

[9] 钱晓忠, 王琪琪, 任乃飞.基于正交实验的SUS304不锈钢激光打孔过程参量优化［J］.激光技术, 2017, 41(4): 578-581.

QIAN X Z, WANG Q Q, REN N F.Optimization of laser drilling parameters of SUS304 stainless steel based on orthogonal experiment ［J］. Laser Technology, 2017, 41 (4): 578-581.

[10] 许兆美, 周建忠, 黄舒, 等.基于遗传算法优化反向传播神经网络的激光铣削层质量预测［J］.中国激光, 2013, 40(6): 167-171.

XU Z M, ZHOU J Z, HUANG S, et al.Quality prediction of laser milling based on optimize back propagation networks by genetic algorithms［J］.Chinese Journal of Lasers, 2013, 40(6): 167-171.

[11] FRANCO A, RASHED C A A, ROMOLI L.Analysis of energy consumption in micro-drilling processes［J］.Journal of Cleaner Production, 2016(137): 1260-1269.

[12] 刘韧, 王忠雷, 季忠.基于人工神经网络的板料激光成形工艺优化［J］.锻压技术, 2005, 30(1): 26-29.

LIU R, WANG Z L, JI Z.ANN based process optimization of metal sheet laser forming［J］.Forging & Stamping Technology, 2005, 30(1): 26-29.

丁华, 殷潇. 基于反向传播神经网络的激光弱化残余厚度预测[J]. 应用激光, 2018, 38(4): 649. Ding Hua, Yin Xiao. Residual Thickness Prediction of Laser Weakening Based on Back-propagation Neural Network[J]. APPLIED LASER, 2018, 38(4): 649.

基于反向传播神经网络的激光弱化残余厚度预测

关于本站 Cookie 的使用提示

全站搜索

基于反向传播神经网络的激光弱化残余厚度预测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索