本文關鍵詞：基于遺傳算法優(yōu)化反向傳播神經(jīng)網(wǎng)絡的激光銑削層質量預測，由筆耕文化傳播整理發(fā)布。

摘要

為了有效地控制激光銑削層質量，建立了激光銑削層質量（銑削層深度、銑削層寬度）與銑削層參數(shù)（激光功率、掃描速度和離焦量）之間的反向傳播(BP)神經(jīng)網(wǎng)絡預測模型。利用遺傳算法(GA)優(yōu)化了BP神經(jīng)網(wǎng)絡的權值和閾值，，構建了基于遺傳算法神經(jīng)網(wǎng)絡的質量預測模型。用GA-BP算法對激光銑削層質量進行了仿真預測，并將仿真結果與BP神經(jīng)網(wǎng)絡模型仿真結果進行了對比。仿真結果表明，兩種網(wǎng)絡模型的平均誤差較小，網(wǎng)絡訓練后檢驗精度較高，說明兩種網(wǎng)絡模型用于激光銑削層質量預測是可行的，并且遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡能夠有效地提高網(wǎng)絡的收斂性和預測精度。

關鍵詞

Abstract

In order to control the quality of laser milling layer, back propagation (BP) neural network model of the milling laser quality including milling depth and width, and milling layer parameters including laser power, laser velocity and defocus amount is set up. The weight and threshold of the BP neural network is optimized by genetic algorithm (GA), and a quality prediciton model is constructed based on BP neural network. The quality of the laser milling layer is forecasted by the model of GA-BP neural network. The results from BP neural network are compared with that of GA-BP neural network. The results of simulation show that the errors of the two network models are smaller, and the test accuracy are higher. Therefore, the two network models can be used to predict the quality of the laser milling. It is also shown that both the astringent and prediction accuracies of the GA optimized BP neural network are improved.

補充資料

中圖分類號：TN249

DOI：10.3788/cjl201340.0603004

所屬欄目：激光制造

責任編輯：宋梅梅  信息反饋

基金項目：國家自然科學家（51075173）、江蘇省自然科學基金（BK2010288）、江蘇省高校自然科學重大基礎理論研究（10KJA460004）和江蘇高校優(yōu)勢學科建設工程資助課題。

收稿日期：2013-01-20

修改稿日期：2013-03-01

網(wǎng)絡出版日期：--

作者單位    點擊查看

許兆美：江蘇大學機械工程學院, 江蘇 鎮(zhèn)江 221013淮陰工學院機械工程學院, 江蘇 淮安 223003
周建忠：江蘇大學機械工程學院, 江蘇 鎮(zhèn)江 221013
黃舒：江蘇大學機械工程學院, 江蘇 鎮(zhèn)江 221013
孟憲凱：江蘇大學機械工程學院, 江蘇 鎮(zhèn)江 221013
韓煜航：江蘇大學機械工程學院, 江蘇 鎮(zhèn)江 221013
田清：江蘇大學機械工程學院, 江蘇 鎮(zhèn)江 221013

聯(lián)系人作者：許兆美(fuyun588@163.com)

備注：許兆美（1976—），女，博士研究生，講師，主要從事激光加工脆性材料方面的研究。

【1】S. L. Campanelli, A. D. Ludovico, C. Bonserion. Experimental analysis of the laser milling process parameters［J］. J. Materials Processing Technology, 2007, 191(1-3): 220～223

【2】Zhu Yinbo, Zhou Jianzhong, Huang Shu et al.. Laser application in processing brittle materials [J]. Chinese J. Lasers, 2009, 36(s1): 143～146
朱銀波, 周建忠, 黃舒 等. 激光在脆性材料加工中的應用［J］. 中國激光, 2009, 36(s1): 143～146

【3】Zhu Yinbo, Zhou Jianzhong, Huang Shu et al.. The application of 3D laser milling for ceramic materials [J]. Laser Journal, 2009, 30(6): 59～61
朱銀波, 周建忠, 黃舒 等. 激光三維銑削在陶瓷成形加工中的應用研究 [J]. 激光雜志, 2009, 30(6): 59～61

【4】C. H. Tsai, H. W. Chen. Laser milling of cavity in ceramic substrate by fracturemachining element technique [J]. J. Mater. Processing Technology, 2003, 136(1-3): 158～165

【5】N. Dahotre, S. Harimkar. Laser Fabrication and Machining of Materials [M]. USA: Springer, 2008. 34～37

【6】Huang Shu, Zhou Jianzhong, Sheng Jie et al.. Numerical simulation and experiment on laser milling of Al2O3 ceramic［J］. Transactions of the Chinese Society for Agricultural Machinery, 2011, 42(7): 259～265
黃舒, 周建忠, 盛杰 等. Al2O3陶瓷激光銑削數(shù)值模擬與試驗［J］. 農業(yè)機械學報, 2011, 42(7): 259～265

【7】I. E. Saklakoglu, S. Kasman. Investigation of micro-milling process parameters for surface roughness and milling depth [J]. Int. J. Adv. Manuf. Technol., 2011, 54(5-8): 567～578

【8】Wang Xuyue, Xu Wenji, Lei Mingkai et al.. An experimental study of laser milling based on deteriorative layer on Al2O3 ceramic [J]. J. Dalian University of Technolgy, 2009, 49(2): 211～215
王續(xù)躍, 徐文驥, 雷明凱 等. 基于變質層的Al2O3陶瓷激光銑削實驗研究［J］. 大連理工大學學報, 2009, 49(2): 211～215

【9】J. P. Davim, C. Oliveira, N. Barricas et al.. Some experimental studies on CO2 laser cutting quality of polymeric materials [J]. J. Mater Process Technol., 2007, 198(1-3): 99～104

【10】Zhang Jixian, Mi Xia. BP Neural Networks and Its Use in the Engineering［M］. Beijing: China Machine Press, 1996. 68～71
張際先, 宓霞. 神經(jīng)網(wǎng)絡及其在工程中的應用［M］. 北京: 機械工業(yè)出版社, 1996. 68～71

【11】Yang Donghui, Ma Liang, Huang Weidong. Component′s surface quality predictions by laser rapid forming based on artificial neural networks［J］. Chinese J. Lasers, 2011, 38(8): 0803004
楊東輝, 馬良, 黃衛(wèi)東. 基于人工神經(jīng)網(wǎng)絡的激光立體成形件成形表面質量預測［J］. 中國激光, 2011, 38(8): 0803004

【12】S. L. Campanelli, G. Casalino, A. D. Ludovico et al.. An artificial neural network approach for the control of the laser milling process [J]. Int. J. Adv. Manuf. Technol., 2012, Doi 10.1007/s00170-012-4457-9

【13】C. K. Desai, A. Shaikh. Prediction of depth of cut for single-pass laser micro-milling process using semi-analytical, ANN and GP approaches [J]. Int. J. Adv. Manuf. Technol., 2012, 60(9-12): 865～882

【14】Xia Kewen, Li Changbiao, Shen Junyi. An optimization algorithm on the number of hidden layer modes in feed-forward neural network ［J］. Computer Science, 2005, 32(10): 143～145
夏克文, 李昌彪, 沈鈞毅. 前向神經(jīng)網(wǎng)絡隱含層節(jié)點數(shù)的一種優(yōu)化算法［J］. 計算機科學, 2005, 32(10): 143～145

【15】Xu Dapeng, Zhou Jianzhong, Guo Huafeng. Application for laser cladding forming using evolutionary neural networks［J］. Applied Laser, 2006, 26(5): 303～306
徐大鵬, 周建忠, 郭華鋒. 進化神經(jīng)網(wǎng)絡在激光熔覆成形中的應用研究［J］. 應用激光, 2006, 36(5): 303～306

【16】Yan Pingfan, Zhang Changshui. Atrificial Neural Networks and Evolutionary Computing [M]. Beijing: Tsinghua University Press, 2005. 161～166
閻平凡, 張長水. 人工神經(jīng)網(wǎng)絡與模擬進化計算［M］. 北京: 清華大學出版社, 2005. 161～166

引用該論文

Xu Zhaomei,Zhou Jianzhong,Huang Shu,Meng Xiankai,Han Yuhang,Tian Qing. Quality Prediction of Laser Milling Based on Optimized Back Propagation Networks by Genetic Algorithms[J]. Chinese Journal of Lasers, 2013, 40(6): 0603004

許兆美,周建忠,黃舒,孟憲凱,韓煜航,田清. 基于遺傳算法優(yōu)化反向傳播神經(jīng)網(wǎng)絡的激光銑削層質量預測[J]. 中國激光, 2013, 40(6): 0603004

被引情況

【1】王書濤,王興龍,陳東營,魏蒙,王志芳. GA-BP神經(jīng)網(wǎng)絡在檢測微量磷酸鹽中的應用. 中國激光, 2015, 42(5): 515001--1

【2】王書濤,陳東營,魏蒙,王興龍,王志芳,王佳亮. 熒光光譜法和PSO-BP神經(jīng)網(wǎng)絡在山梨酸鉀濃度檢測中的應用. 中國激光, 2015, 42(5): 515004--1

【3】王書濤,陳東營,王興龍,韓歡歡,王佳亮. 熒光分析法和ABC-BP 神經(jīng)網(wǎng)絡相結合的多環(huán)芳烴的檢測. 中國激光, 2015, 42(11): 1115001--1

【4】李歡歡,盧偉,杜昌文,馬菲,羅慧. 基于光聲光譜結合LS-SVR 的稻種活力快速無損檢測方法研究. 中國激光, 2015, 42(11): 1115003--1

  本文關鍵詞：基于遺傳算法優(yōu)化反向傳播神經(jīng)網(wǎng)絡的激光銑削層質量預測，由筆耕文化傳播整理發(fā)布。