Feedforward neural networks in catalysis: A tool for the approximation of the dependency of yield on catalyst composition, and for knowledge extraction

Abstract Artificial neural networks are distributed computing systems implementing the functionality characterizing biological neural networks. This way of computing has become quite successful in practical applications as a tool for solving several traditional mathematical and data-analysis tasks, such as classification, clustering, approximation and prediction. In this paper, main principles of employing multilayer perceptrons for the approximation of unknown functions are outlined, and another possible use of multilayer perceptrons in combinatorial catalysis is indicated—their use for the extraction of knowledge from experimental catalytic input and output data. To counterbalance the abstractness of the subject, the method is illustrated by applying multilayer perceptrons to data on catalyst composition and catalytic results in the oxidative dehydrogenation of propane to propene.

[1]  Gerrit Kateman,et al.  Using artificial neural networks for solving chemical problems Part I. Multi-layer feed-forward networks , 1994 .

[2]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[3]  E. A. Mamedov,et al.  Oxidative dehydrogenation of lower alkanes on vanadium oxide-based catalysts. The present state of the art and outlooks , 1995 .

[4]  Tadashi Hattori,et al.  Neural network as a tool for catalyst development , 1995 .

[5]  Martin T. Hagan,et al.  Neural network design , 1995 .

[6]  Philip E. Gill,et al.  Practical optimization , 1981 .

[7]  John W. Clark,et al.  Scientific Applications of Neural Nets , 1999 .

[8]  F. Cavani,et al.  The oxidative dehydrogenation of ethane and propane as an alternative way for the production of light olefins , 1995 .

[9]  Michael A. Henson,et al.  Nonlinear model predictive control: current status and future directions , 1998 .

[10]  M. Baerns,et al.  Oxidative functionalization of ethane and propane , 2002 .

[11]  Tadashi Hattori,et al.  Estimation of the acid strength of mixed oxides by a neural network , 1992 .

[12]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[13]  Tadashi Hattori,et al.  Estimation of catalytic performance by neural network — product distribution in oxidative dehydrogenation of ethylbenzene , 1994 .

[14]  Joachim Diederich,et al.  The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks , 1998, IEEE Trans. Neural Networks.

[15]  Fischer–Tropsch synthesis with Co/SiO2–Al2O3 catalyst and steady-state modeling using artificial neural networks , 1998 .

[16]  Motoi Sasaki,et al.  Application of a neural network to the analysis of catalytic reactions Analysis of NO decomposition over Cu/ZSM-5 zeolite , 1995 .

[17]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[18]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[19]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[20]  Joachim Diederich,et al.  Survey and critique of techniques for extracting rules from trained artificial neural networks , 1995, Knowl. Based Syst..

[21]  Manfred Baerns,et al.  Fundamental and combinatorial approaches in the search for and optimisation of catalytic materials for the oxidative dehydrogenation of propane to propene , 2001 .

[22]  P. G. J. Lisboa.  Neural Networks: Current Applications , 1992 .

[23]  Manfred Baerns,et al.  An evolutionary approach in the combinatorial selection and optimization of catalytic materials , 2000 .

[24]  Alan F. Murray.  Applications of Neural Networks , 1994 .

[25]  Huang Kai,et al.  Artificial neural network-aided design of a multi-component catalyst for methane oxidative coupling , 2001 .

[26]  Kishan G. Mehrotra,et al.  Elements of artificial neural networks , 1996 .

[27]  K. Schittkowski.  NLPQL: A fortran subroutine solving constrained nonlinear programming problems , 1986 .

[28]  Gerrit Kateman,et al.  USING ARTIFICIAL NEURAL NETWORKS FOR SOLVING CHEMICAL PROBLEMS .2. KOHONEN SELF-ORGANIZING FEATURE MAPS AND HOPFIELD NETWORKS , 1994 .

[29]  Sushmita Mitra,et al.  Neuro-fuzzy rule generation: survey in soft computing framework , 2000, IEEE Trans. Neural Networks Learn. Syst..

[30]  Xiaoqun Wu,et al.  Artificial neural network aided design of catalyst for propane ammoxidation , 1997 .