Modeling and optimization of the growth rate for ZnO thin films using neural networks and genetic algorithms

被引：38

作者：

Ko, Young-Don ^{[1
]}

Moon, Pyung ^{[1
]}

Kim, Chang Eun ^{[1
]}

Ham, Moon-Ho ^{[2
]}

Myoung, Jae-Min ^{[2
]}

Yun, Ilgu ^{[1
]}

机构：

[1] Yonsei Univ, Dept Elect & Elect Engn, Seoul 120749, South Korea

[2] Yonsei Univ, Dept Met Syst Engn, Seoul 120749, South Korea

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2009年 / 36卷 / 02期

关键词：

Process modeling; Neural networks; Genetic algorithms; ZnO; PLD; ELECTRICAL-PROPERTIES; DESIGN;

D O I：

10.1016/j.eswa.2008.03.010

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The process modeling for the growth rate in pulsed laser deposition (PLD)-grown ZnO thin films was investigated using neural networks (NNets) based on the back-propagation (BP) algorithm and the process recipes was optimized via genetic algorithms (GAs). Two input factors were examined with respect to the growth rate as the response factor. D-optimal experimental design technique was performed and the growth rate was characterized by NNets based on the BP algorithm. GAs was then used to search the desired recipes for the desired growth rate on the process. The statistical analysis for those results was then used to verify the fitness of the nonlinear process model. Based on the results, this modeling methodology can explain the characteristics of the thin Him growth mechanism varying with process conditions. (C) 2008 Elsevier Ltd. All rights reserved.

引用

页码：4061 / 4066

页数：6

共 28 条

[1] ZnO diode fabricated by excimer-laser doping [J].

Aoki, T ;

Hatanaka, Y ;

Look, DC .

APPLIED PHYSICS LETTERS, 2000, 76 (22) :3257-3258

[2]

BAC SH, 2001, APPL SURF SCI, P525

[3] D-optimal experimental design applied to a linear magnetostatic inverse problem [J].

Bégot, S ;

Voisin, E ;

Hiebel, P ;

Artioukhine, E ;

Kauffmann, JM .

IEEE TRANSACTIONS ON MAGNETICS, 2002, 38 (02) :1065-1068

[4] Hybrid neural network modeling of anion exchange at the interfaces of mixed anion III-V heterostructures grown by molecular beam epitaxy [J].

Brown, TD ;

May, GS .

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2005, 18 (04) :614-621

[5]

Chen C.H., 1996, The Fuzzy Logic and Neural Network handbook. ISBN

[6] Fairly pure ultraviolet electroluminescence from ZnO-based light-emitting devices [J].

Chen, Peiliang ;

Ma, Xiangyang ;

Yang, Deren .

APPLIED PHYSICS LETTERS, 2006, 89 (11)

[7] Parametric modeling of a microaccelerometer: Comparing I- and D-Optimal design of experiments for finite-element analysis [J].

Gianchandani, YB ;

Crary, SB .

JOURNAL OF MICROELECTROMECHANICAL SYSTEMS, 1998, 7 (02) :274-282

[8]

Goldberg D. E., 1989, Genetic algorithms in machine learning, search and optimization

[9] Optimization of neural network structure and learning parameters using genetic algorithms [J].

Han, SS ;

May, GS .

EIGHTH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1996, :200-206

[10] Using neural network process models to perform PECVD silicon dioxide recipe synthesis via genetic algorithms [J].

Han, SS ;

May, GS .

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 1997, 10 (02) :279-287

← 1 2 3 →