Loading...

Artificial neural network aided design of a multi-component catalyst for the steam reforming of methanol

Jooya, Sh ; Sharif University of Technology | 2005

239 Viewed
  1. Type of Document: Article
  2. Publisher: 2005
  3. Abstract:
  4. A neural network based on the feed forward back propagation error has been developed for the design and simulation of the catalytic properties of a multi-component system based on Cu-M-Al2O3 (M=Zn,Cr,Zr) for the steam reforming of methanol. Due to the limited size of the data set, cross validation method has to be used to enhance and also evaluate the prediction ability of the network. The best structural organization has been found to include 4,3,6,3 nodes in the input, two hidden layers and the output layer respectively
  5. Keywords:
  6. Aluminum oxide ; Chromium ; Chromium derivative ; Copper ; Copper derivative ; Methanol ; Zinc ; Zinc derivative ; Zirconium ; Zirconium derivative ; Artificial neural network ; Calculation ; Catalyst ; Prediction ; Simulation ; Validation process ; Water vapor
  7. Source: Indian Journal of Chemistry - Section A Inorganic, Physical, Theoretical and Analytical Chemistry ; Volume 44, Issue 1 , 2005 , Pages 64-66 ; 03764710 (ISSN)
  8. URL: http://nopr.niscair.res.in/handle/123456789/18049