PCA-Based Neural Network Modeling Using the Photoluminescence Data for Growth Rate of ZnO Thin Films Fabricated by Pulsed Laser Deposition
The process modeling for the growth rate of pulsed laser deposition (PLD)-grown ZnO thin films was investigated using neural networks (NNets) based on the back-propagation (BP) algorithm and PCA-based NNets using photoluminescence (PL) data. D-optimal experimental design was performed and the growth rate was characterized by NNets. PCA-based NNets were then carried out in order to build the model by PL data. 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 film growth mechanism varying with process conditions and the model can be analyzed and predicted by the multivariate data.
KeywordsPulse Laser Deposition Latin Hypercube Sampling Vary Process Condition Model Growth Rate Pulse Laser Deposition Process
Unable to display preview. Download preview PDF.
- 5.Triplett, G., May, G.S., Brown, A.: Modeling Electron Mobility in MBE-Grown InAs/AlSb Thin Films for HEMT Applications Using Neural Networks. Solid-State Electron, 1519–1524 (2002)Google Scholar
- 6.Kim, B., May, G.S.: An Optimal Neural Network Process Model for Plasma Etching. IEEE Trans. Semiconduct Manufact., 12–21 (1994)Google Scholar
- 7.Hong, S.J., May, G.S., Park, D.C.: Neural Network Modeling of Reactive Ion Etching Using Optical Emission Spectroscopy Data. IEEE Trans. Semiconduct Manufact., 598–608 (2003)Google Scholar