This paper presents an integrated physiconeural network approach for the modeling and optimization of a vertical MOCVD reactor. The basic concept is to utilize the solutions obtained from a physical model to build an accurate neural network (NN) model The resulting model has the attractive features of self-adaptiveness and speed of prediction and is an ideal starting tool for process optimization and control. Following this approach, a first-principles physical model for the reactor was solved numerically using the Fluid Dynamics Analysis Package (FIDAP). This transient model included property variation and thermodiffusion effects. Using software developed in house, neural networks were then trained using FIDAP simulations for combinations of process parameters determined by the statistical Design of Experiments (DOE) methodology. The outputs were the average and local deposition rates. It is shown that the trained NN model predicts the behavior of the reactor accurately. Optimum process conditions to obtain a uniform thickness of the deposited film were determined and tested using the physical model. The results demonstrate the power and robustness of NNs for obtaining fast responses to changing input conditions. A procedure for developing equipment models based on physiconeural network models is also described.
Skip Nav Destination
Article navigation
Research Papers
Real-Time Physiconeural Solutions for MOCVD
A. S. Kelkar,
A. S. Kelkar
Department of Chemical Engineering, University of Colorado at Boulder, Boulder, CO 80309
Search for other works by this author on:
R. L. Mahajan,
R. L. Mahajan
Department of Mechanical Engineering, University of Colorado at Boulder, Boulder, CO 80309
Search for other works by this author on:
R. L. Sani
R. L. Sani
Department of Chemical Engineering, University of Colorado at Boulder, Boulder, CO 80309
Search for other works by this author on:
A. S. Kelkar
Department of Chemical Engineering, University of Colorado at Boulder, Boulder, CO 80309
R. L. Mahajan
Department of Mechanical Engineering, University of Colorado at Boulder, Boulder, CO 80309
R. L. Sani
Department of Chemical Engineering, University of Colorado at Boulder, Boulder, CO 80309
J. Heat Transfer. Nov 1996, 118(4): 814-821 (8 pages)
Published Online: November 1, 1996
Article history
Received:
December 4, 1995
Revised:
August 1, 1996
Online:
December 5, 2007
Citation
Kelkar, A. S., Mahajan, R. L., and Sani, R. L. (November 1, 1996). "Real-Time Physiconeural Solutions for MOCVD." ASME. J. Heat Transfer. November 1996; 118(4): 814–821. https://doi.org/10.1115/1.2822575
Download citation file:
Get Email Alerts
Cited By
Surrogate Modeling-Based Analysis of Concentration Decay in Diffusion-Reaction Mass Transfer Problems
J. Heat Mass Transfer (June 2025)
External Conjugate Boiling On Channels. A Graetz Problem With Multiple Solutions
J. Heat Mass Transfer
Related Articles
Combined Forced and Free Laminar Convection in the Entrance Region of an Inclined Isothermal Tube
J. Heat Transfer (November,1988)
Fluid Flow and Mixed Convection Transport From a Moving Plate in Rolling and Extrusion Processes
J. Heat Transfer (August,1988)
Modeling of Transient Stratified Flow in Vertical Tube Assemblies
J. Heat Transfer (November,1992)
Three-Dimensional Mixed Convection in a Horizontal Chemical Vapor Deposition Reactor
J. Heat Transfer (August,1993)
Related Proceedings Papers
Related Chapters
Advances in the Stochastic Modeling of Constitutive Laws at Small and Finite Strains
Advances in Computers and Information in Engineering Research, Volume 2
Introduction
Introduction to Finite Element, Boundary Element, and Meshless Methods: With Applications to Heat Transfer and Fluid Flow
Analytical and Numerical Methods in Fluid Flow and Heat Transfer
Applications of Mathematical Heat Transfer and Fluid Flow Models in Engineering and Medicine