Generator approach to evolutionary optimization of catalysts and its integration with surrogate modeling

This paper presents some unpublished aspects and ongoing developments of the recently elaborated generator approach to the evolutionary optimization of catalytic materials, the purpose of which is to obtain evolutionary algorithms precisely tailored to the problem being solved. It briefly recalls the principles of the approach, and then it describes how the employed evolutionary operations reflect the specificity of the involved mixed constrained optimization tasks, and how the approach tackles checking the feasibility of large polytope systems, frequently resulting from the optimization constraints. Finally, the paper discusses the integration of the approach with surrogate modeling, paying particular attention to surrogate models enhanced with boosting. The usefulness of surrogate modeling in general and of boosted surrogate models in particular is documented on a case study with data from a high-temperature synthesis of hydrocyanic acid.

[1]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[2]  Frédéric Clerc,et al.  Development of an integrated informatics toolbox: HT kinetic and virtual screening. , 2007, Combinatorial chemistry & high throughput screening.

[3]  A. J. Booker,et al.  A rigorous framework for optimization of expensive functions by surrogates , 1998 .

[4]  Gadi Rothenberg,et al.  Data mining in catalysis: Separating knowledge from garbage , 2008 .

[5]  Durga L. Shrestha,et al.  Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression , 2006, Neural Computation.

[6]  Manfred Baerns,et al.  Ethylene and propene by oxidative dehydrogenation of ethane and propane: ‘Performance of rare-earth oxide-based catalysts and development of redox-type catalytic materials by combinatorial methods’ , 2000 .

[7]  J. M. Serra,et al.  Support vector machines for predictive modeling in heterogeneous catalysis: a comprehensive introduction and overfitting investigation based on two real applications. , 2006, Journal of combinatorial chemistry.

[8]  Pierre Collet,et al.  Examination of genetic programming paradigm for high-throughput experimentation and heterogeneous catalysis , 2009 .

[9]  Frédéric Clerc,et al.  Effect of the Genetic Algorithm Parameters on the Optimisation of Heterogeneous Catalysts , 2005 .

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

[11]  Baohui Li,et al.  A simulated annealing study of Si,Al distribution in the omega framework 1 Supported by the National , 1999 .

[12]  Hakan Altinçay,et al.  Optimal resampling and classifier prototype selection in classifier ensembles using genetic algorithms , 2004, Pattern Analysis and Applications.

[13]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[14]  Min-Jea Tahk,et al.  Acceleration of the convergence speed of evolutionary algorithms using multi-layer neural networks , 2003 .

[15]  Claude Mirodatos,et al.  The development of descriptors for solids: teaching "catalytic intuition" to a computer. , 2004, Angewandte Chemie.

[16]  Huang Kai,et al.  Catalyst design for methane oxidative coupling by using artificial neural network and hybrid genetic algorithm , 2003 .

[17]  Claude Mirodatos,et al.  Using Artificial Neural Networks to Boost High‐throughput Discovery in Heterogeneous Catalysis , 2004 .

[18]  Estefania Argente,et al.  DoE framework for catalyst development based on soft computing techniques , 2009, Comput. Chem. Eng..

[19]  Jose Manuel Serra,et al.  Zeolite synthesis modelling with support vector machines: a combinatorial approach. , 2007, Combinatorial chemistry & high throughput screening.

[20]  Martin Holena,et al.  Piecewise-Linear Neural Networks and Their Relationship to Rule Extraction from Data , 2006, Neural Comput..

[21]  Claude Mirodatos,et al.  Combinatorial Approaches to Heterogeneous Catalysis: Strategies and Perspectives for Academic Research , 2001 .

[22]  András Tompos,et al.  Evaluation of catalyst library optimization algorithms: Comparison of the Holographic Research Strategy and the Genetic Algorithm in virtual catalytic experiments , 2006 .

[23]  Bernhard Sendhoff,et al.  A framework for evolutionary optimization with approximate fitness functions , 2002, IEEE Trans. Evol. Comput..

[24]  F. Schüth,et al.  On the suitability of different representations of solid catalysts for combinatorial library design by genetic algorithms. , 2008, Journal of combinatorial chemistry.

[25]  Alain Ratle,et al.  Kriging as a surrogate fitness landscape in evolutionary optimization , 2001, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[26]  Thomas Bartz-Beielstein,et al.  Experimental research in evolutionary computation , 2007, GECCO '07.

[27]  Mato Baotic,et al.  Multi-Parametric Toolbox (MPT) , 2004, HSCC.

[28]  Frédéric Clerc,et al.  Library design using genetic algorithms for catalyst discovery and optimization , 2005 .

[29]  Martin Holena,et al.  Optimization of Catalysts Using Specific, Description-Based Genetic Algorithms , 2008, J. Chem. Inf. Model..

[30]  Arne Ohrenberg,et al.  Application of Data Mining and Evolutionary Optimization in Catalyst Discovery and High-Throughput Experimentation – Techniques, Strategies, and Software , 2005 .

[31]  Nicolas Lachiche,et al.  Using Genetic Programming for an Advanced Performance Assessment of Industrially Relevant Heterogeneous Catalysts , 2009 .

[32]  Julian F. Miller,et al.  Genetic and Evolutionary Computation — GECCO 2003 , 2003, Lecture Notes in Computer Science.

[33]  W. Maier,et al.  Strategies for the discovery of new catalysts with combinatorial chemistry , 2004 .

[34]  L. Gladden,et al.  Development of a Genetic Algorithm for Molecular Scale Catalyst Design , 1997 .

[35]  András Tompos,et al.  Holographic research strategy for catalyst library design: Description of a new powerful optimisation method , 2003 .

[36]  Claude Mirodatos,et al.  Design of Discovery Libraries for Solids Based on QSAR Models , 2005 .

[37]  Andy J. Keane,et al.  Combining Global and Local Surrogate Models to Accelerate Evolutionary Optimization , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[38]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[39]  Ferdi Schüth,et al.  Multi-objective optimization in combinatorial chemistry applied to the selective catalytic reduction of NO with C3H6 , 2007 .

[40]  R. Kraehnert,et al.  The influence of preparation variables on the performance of Pd/Al2O3 catalyst in the hydrogenation of 1,3-butadiene: Building a basis for reproducible catalyst synthesis , 2007 .

[41]  L. F. Gladden,et al.  Heterogeneous Catalyst Design Using Stochastic Optimization Algorithms , 2000, J. Chem. Inf. Comput. Sci..

[42]  G. Ertl,et al.  Handbook of Heterogeneous Catalysis , 1997 .

[43]  Lakhmi C. Jain,et al.  Knowledge-Based Intelligent Information and Engineering Systems , 2004, Lecture Notes in Computer Science.

[44]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[45]  Jaume Giralt,et al.  Kinetic modelling of catalytic wet air oxidation of phenol by simulated annealing , 2001 .

[46]  Peter Claus,et al.  High-throughput synthesis and screening of catalytic materials: Case study on the search for a low-temperature catalyst for the oxidation of low-concentration propane , 2001 .

[47]  Kohji Omata,et al.  Optimization of Cu oxide catalysts for methanol synthesis by combinatorial tools using 96 well microplates, artificial neural network and genetic algorithm , 2004 .

[48]  Pedro Serna,et al.  Combining high-throughput experimentation, advanced data modeling and fundamental knowledge to develop catalysts for the epoxidation of large olefins and fatty esters , 2008 .

[49]  José M. Serra,et al.  Development of a low temperature light paraffin isomerization catalysts with improved resistance to water and sulphur by combinatorial methods , 2003 .

[50]  Martin Holena,et al.  New catalytic materials for the high-temperature synthesis of hydrocyanic acid from methane and ammonia by high-throughput approach , 2008 .

[51]  Yaochu Jin,et al.  Knowledge incorporation in evolutionary computation , 2005 .

[52]  J. M. Serra,et al.  Discovery of new paraffin isomerization catalysts based on SO42−/ZrO2 and WOx/ZrO2 applying combinatorial techniques , 2003 .

[53]  M. Baerns,et al.  Application of a genetic algorithm and a neural network for the discovery and optimization of new solid catalytic materials , 2004 .

[54]  Martin Holeňa,et al.  Feedforward neural networks in catalysis: A tool for the approximation of the dependency of yield on catalyst composition, and for knowledge extraction , 2003 .