本文關(guān)鍵詞：基于神經(jīng)網(wǎng)絡(luò)和遺傳算法的激光多層熔覆厚納米陶瓷涂層工藝優(yōu)化，由筆耕文化傳播整理發(fā)布。

摘要

為了有效地控制激光熔覆層質(zhì)量，采用反向傳播(BP)算法建立了激光熔覆層質(zhì)量(熔覆層寬度、熔覆層深度和稀釋率)隨激光功率、光斑直徑和掃描速度變化的進(jìn)化神經(jīng)網(wǎng)絡(luò)預(yù)測模型。針對BP算法存在收斂速度慢、容易陷入局部極小值及全局搜索能力弱等缺陷，采用遺傳算法訓(xùn)練BP神經(jīng)網(wǎng)絡(luò)，取代了一些傳統(tǒng)的學(xué)習(xí)算法，設(shè)計了基于進(jìn)化神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)算法。經(jīng)過理論分析和實驗驗證，在神經(jīng)網(wǎng)絡(luò)的輸出端得到期望的線性輸出，并在訓(xùn)練樣本之外，選取了5組工藝參數(shù)檢驗神經(jīng)網(wǎng)絡(luò)模型的可靠性，預(yù)測結(jié)果與相應(yīng)的實驗結(jié)果的最大相對誤差為2．14%。結(jié)果表明，運(yùn)用該模型可以方便、準(zhǔn)確地選擇激光工藝參數(shù)，提高激光熔覆層的加工質(zhì)量。

關(guān)鍵詞

Abstract

Artificial neural networks were introduced in the area of laser cladding forming. The prediction model of surface quality in laser cladding parts,including the width,depth of cladding layer and dilution,was proposed based on the improved learned arithmetic. The model combined the global optimization searching performance of the genetic algorithm and the localization of the back propagation(BP)neural networks. Five technical parameters were selected to test the reliability of the model. The simulation and experimental results show that the evolutionary neural network based on genetic algorithm can effectively overcome the problem of falling into local minimum point. This method can get higher accuracy of prediction. It improves the measurement precision with the maximum relative error 2.14% between the predicted content and the real value.

補(bǔ)充資料

中圖分類號：TG156．9;TP183

所屬欄目：激光與光電子技術(shù)應(yīng)用

收稿日期：2006-07-26

修改稿日期：2006-09-06

網(wǎng)絡(luò)出版日期：0001-01-01

作者單位    點(diǎn)擊查看

徐大鵬：江蘇大學(xué) 機(jī)械工程學(xué)院，鎮(zhèn)江 212013
周建忠：江蘇大學(xué) 機(jī)械工程學(xué)院，鎮(zhèn)江 212013
郭華鋒：江蘇大學(xué) 機(jī)械工程學(xué)院，鎮(zhèn)江 212013
季霞：江蘇大學(xué) 機(jī)械工程學(xué)院，，鎮(zhèn)江 212013

聯(lián)系人作者：周建忠(zhoujz@ujs.edu.cn)

備注：徐大鵬|男|碩士研究生|主要從事基于激光熔覆的金屬零件快速制造技術(shù)的研究|(1979－)

【1】LIU X M,GUAN Z Z. The relationship between the process parameter of laser cladding by powder feeding method and the laser layer parameters [J].Transactions of Metal Heat Treatment,1998,A26(5):29～34.

【2】van ACKER K,VANHOYWEGHEN D,PERSOONS R et al. Influence of tungsten carbide particle size and distribution on the wear resistance of laser clad WC/Ni coatings [J].Wear,2005,258(1～4):194～202.

【3】SONG J L,DENG Q L,CHEN Ch Y et al. Rebuilding of metal components with laser cladding forming [J].Applied Surface Science,2006,252(22):7934～7940.

【4】WU X W,ZHU B D,ZENG X Y et al. Critical state of laser cladding with power auto-feeding [J].Surface and Coatings Technology,1996,79(l～3):200～204.

【5】JI S Q,LI P,ZENG X Y. Microstructure and mechanical property analyses of the metal parts direct fabricated by laser cladding [J].Laser Technology,2006,30(2):130～133(in Chinese).

【6】YAN P F,ZHANG C S. Artificial neural network and simulated evolutionary computing [M].Beijing: Tsinghua University Press,2000.15～22(in Chinese).

【7】LEI Y J,ZHANG S W,LI X W et al. MATLAB genetic algorithm toolbox and application [M].Xi''an : University of Electronic Science and Technology of China Press,2005.15～33(in Chinese).

【8】STEEN W M,WEERASINGHE V M,MONSON P. Some aspects of the formation of laser clad tracks [J].SPIE,1996,650:226～234.

【9】LIU J C,LIU L J. Experimental study on fabrication of thin-wall metallic features by laser cladding [J].Chinese Journal of Mechanical Engineering,2004,40(10):185～188(in Chinese).

【10】ZHU B D,ZENG X Y,TAO C Y et al. Effect of laser processing parameters on dilution of the cladded coating [J].Chinese Journal of Materials Research,1994,8(4):315～319(in Chinese).

引用該論文

XU Da-peng,ZHOU Jian-zhong,GUO Hua-feng,JI Xia. Quality prediction of laser cladding layer based on improved neural network[J]. Laser Technology, 2007, 31(5): 0511

徐大鵬,周建忠,郭華鋒,季霞. 基于進(jìn)化神經(jīng)網(wǎng)絡(luò)的激光熔覆層質(zhì)量預(yù)測[J]. 激光技術(shù), 2007, 31(5): 0511

被引情況

【1】邵珺,華文深,周中亮,高鴻啟. 神經(jīng)網(wǎng)絡(luò)和遺傳算法在相關(guān)峰判讀中的應(yīng)用. 激光技術(shù), 2009, 33(4): 422-425

【2】張毅,姚建華,胡曉冬,陳智君. 激光再制造粉末輸送流量檢測系統(tǒng)設(shè)計. 激光技術(shù), 2009, 33(6): 568-570

【3】王東生,楊友文,田宗軍,沈理達(dá),黃因慧. 基于神經(jīng)網(wǎng)絡(luò)和遺傳算法的激光多層熔覆厚納米陶瓷涂層工藝優(yōu)化. 中國激光, 2013, 40(9): 903001--1

  本文關(guān)鍵詞：基于神經(jīng)網(wǎng)絡(luò)和遺傳算法的激光多層熔覆厚納米陶瓷涂層工藝優(yōu)化，由筆耕文化傳播整理發(fā)布。