Neural network based modeling of PL intensity in PLD-grown ZnO thin films

Abstract The process modeling of ZnO thin films grown by pulsed laser deposition (PLD) was investigated using neural networks based on radial basis function networks (RBFN) and multi-layer perceptron (MLP). Two input factors were examined with respect to the response factor, photoluminescence (PL), which is one of the main factors to determine the optical characteristic of the structure. In order to minimize the joint confidence region of fabrication process with varying the conditions, D-optimal experimental design technique was performed and PL intensity was characterized by neural networks. The statistical results were then used to verify the fitness of the nonlinear process model. Based on the results, this modeling methodology can optimize the process conditions for semiconductor manufacturing.

[1]  Sang Yeol Lee,et al.  Effect of the variation of film thickness on the structural and optical properties of ZnO thin films deposited on sapphire substrate using PLD , 2002 .

[2]  Ilgu Yun,et al.  Zinc diffusion process investigation of InP-based test structures for high-speed avalanche photodiode fabrication , 2000 .

[3]  Yogesh B. Gianchandani,et al.  Parametric modeling of a microaccelerometer: comparing I- and D-optimal design of experiments for finite-element analysis , 1998 .

[4]  In-Beum Lee,et al.  Nonlinear regression using RBFN with linear submodels , 2003 .

[5]  Gary S. May,et al.  An optimal neural network process model for plasma etching , 1994 .

[6]  R. H. Myers,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[7]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[8]  G. May,et al.  Modeling and optimization of integral capacitor fabrication using neural networks , 2000, Twenty Sixth IEEE/CPMT International Electronics Manufacturing Technology Symposium (Cat. No.00CH37146).

[9]  Guido Bugmann,et al.  NEURAL NETWORK DESIGN FOR ENGINEERING APPLICATIONS , 2001 .

[10]  M. S. Khots,et al.  D-optimal designs , 1995 .

[11]  Boudewijn P. F. Lelieveldt,et al.  Optimal design of radial basis function neural networks for fuzzy-rule extraction in high dimensional data , 2002, Pattern Recognit..

[12]  R. H. Myers.  Classical and modern regression with applications , 1986 .

[13]  George W. Irwin,et al.  Multi-layer perceptron based modelling of nonlinear systems , 1996, Fuzzy Sets Syst..