A chemical reactor selection expert system created by training an artificial neural network
This work investigated the feasibility of using a feed-forward neural network for knowledge acquisition and storage, and subsequent use as a chemical reactor selection expert system. Feed-forward neural networks have the capability of learning heuristics from given examples.
Levenberg-Marquardt method was used to train the network by minimising the sum of squares of residuals. The output of each node was calculated by the logistic activation (sigmoid) function on the weighted sum of inputs to that node. It is shown therein that the number of hidden layers and the number of nodes in the hidden layers are critical, and increase in the number of hidden layers does not always improve the performance of the simulator network. It is possible in certain cases like this one to attribute meanings to the nodes in the hidden layer.
Redundancy in the outputs was considered by having separate output nodes for selecting batch and continuous operations, and for stirred-tank and tubular reactors. The network performance did not significantly change on excluding one of the outputs, although it was not possible to arrive at the converged solution equally easily when four outputs were considered.
This work demonstrated that a selection expert system can be created in a feed-forward neural network. In other words, neural networks can be used for knowledge acquisition and storage for selection expert systems, suitable for convenient retrieval and inferencing. Inspite of covering a wide range (several orders of magnitude) of inputs, the performance was found to be very good.
Keywordsneural networks chemical reactor selection knowledge acquisition
Unable to display preview. Download preview PDF.
- 1.Lippmann, R. P., "An introduction to computing with neural nets", IEEE ASSP Magazine, (April 1987) 4–22.Google Scholar
- 2.Marquardt, D. W., "An algorithm for least-squares estimation of nonlinear parameters", J. Soc. Indust. Appl. Math., 11 (June 1963) 431–441.Google Scholar
- 3.Bulsari, A. and H. Saxén, "Applicability of an artificial neural network as a simulator for a chemical process", The fifth International Symposium on Computer and Information Sciences, Nevsehir, Turkey (October 1990).Google Scholar
- 4.Hoskins, J. C. and D. M. Himmelblau, "Artificial neural network models of knowledge representation in chemical engineering", Computers and Chemical Engineering, 12 (1988) 881–890.Google Scholar
- 5.Venkatasubramanian, V. and K. Chan, "A neural network methodology for process fault diagnosis", AIChE Journal, 35 (1989) 1993–2002.Google Scholar
- 6.Venkatasubramanian, V., R. Vaidyanathan and Y. Yamamoto, "Process fault detection and diagnosis using neural networks I: Steady state processes", Computers and Chemical Engineering, 14 (1990) 699–712.Google Scholar
- 7.Touretzky, D. S. and D. A. Pomerleau, "What's hidden in the hidden layers ?", Byte, 14 (August 1989) 227–233.Google Scholar
- 8.Watanabe, K. et al., "Incipient fault diagnosis of chemical processes via artificial neural networks", AIChE Journal, 35 (1989) 1803–1812.Google Scholar
- 9.Ungar, L. H., B. A. Powell and S. N. Kamens, "Adaptive networks for fault diagnosis and process control", Computers and Chemical Engineering, 14 (1990) 561–572.Google Scholar
- 10.Bhat, N. V., P. A. Minderman, Jr., T. McAvoy and N. S. Wang, "Modeling chemical process systems via neural computation", IEEE Control Systems magazine, (April 1990) 24–30.Google Scholar
- 11.Bhat, N. and T. J. McAvoy, "Use of neural nets for dynamic modeling and control of chemical process systems", Computers and Chemical Engineering, 14 (1990) 573–582.Google Scholar
- 12.Ydstie, B. E., "Forecasting and control using adaptive connectionist networks", Computers and Chemical Engineering, 14 (1990) 583–599.Google Scholar
- 13.Bulsari, A., B. Saxén and H. Saxén, "Programs for feedforward neural networks using the Levenberg-Marquardt method: Documentation and user's manual", Technical report 90-2, Värmeteknik, Äbo Akademi, 1990Google Scholar
- 14.Jones, W. P. and J. Hoskins, "Back-Propagation: A generalized delta learning rule", Byte, (October 1987) 155–162.Google Scholar