Design of Electroceramic Materials Using Artificial Neural Networks and Multiobjective Evolutionary Algorithms

We describe the computational design of electroceramic materials with optimal permittivity for application as electronic components. Given the difficulty of large-scale manufacture and characterization of these materials, including the theoretical prediction of their materials properties by conventional means, our approach is based on a recently established database containing composition and property information for a wide range of ceramic compounds. The electroceramic materials composition-function relationship is encapsulated by an artificial neural network which is used as one of the objectives in a multiobjective evolutionary algorithm. Evolutionary algorithms are stochastic optimization techniques which we employ to search for optimal materials based on chemical composition. The other objectives optimized include the reliability of the neural network prediction and the overall electrostatic charge of the material. The evolutionary algorithm searches for materials which simultaneously have high relative permittivity, minimum overall charge, and good prediction reliability. We find that we are able to predict a range of new electroceramic materials with varying degrees of reliability. In some cases the materials are similar to those contained in the database; in others, completely new materials are predicted.

[1]  J. Kato,et al.  Dielectric Properties of (PbCa)(MeNb)O3 at Microwave Frequencies , 1992 .

[2]  Taho Yang,et al.  Metamodeling approach in solving the machine parameters optimization problem using neural network and genetic algorithms: A case study , 2006 .

[3]  Peter V. Coveney,et al.  Using Artificial Neural Networks to Predict the Quality and Performance of Oilfield Cements , 1996, AAAI/IAAI, Vol. 2.

[4]  R C A Laboratories,et al.  The "Multiple-Sample Concept" in Materials Research: Synthesis, Compositional Analysis and Testing of Entire Multicomponent Systems , 1970 .

[5]  Venkat Venkatasubramanian,et al.  Catalyst design: knowledge extraction from high-throughput experimentation , 2003 .

[6]  Johann Gasteiger,et al.  A novel workflow for the inverse QSPR problem using multiobjective optimization , 2006, J. Comput. Aided Mol. Des..

[7]  P. V. Coveney,et al.  Prediction of the functional properties of ceramic materials from composition using artificial neural networks , 2007 .

[8]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001, Statistical Science.

[9]  Abraham I. Beltzer,et al.  Neural computing of effective properties of random composite materials , 2001 .

[10]  P. Coveney,et al.  Combinatorial searches of inorganic materials using the ink-jet printer: science, philosophy and technology , 2001 .

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

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

[13]  Peter V Coveney,et al.  Modelling biological complexity: a physical scientist's perspective , 2005, Journal of The Royal Society Interface.

[14]  Johann Gasteiger,et al.  Neural networks and genetic algorithms in drug design , 2001 .

[15]  Amit Kumar,et al.  Feasibility of using neural networks and genetic algorithms to predict and optimize coated paper and board brightness , 2000 .

[16]  John Evans,et al.  Control of particle segregation during drying of ceramic suspension droplets , 2007 .

[17]  A. Belous,et al.  Temperature compensated microwave dielectrics based on lithium containing titanates , 2003 .

[18]  Peter J. Fleming,et al.  Combinatorial Library Design Using a Multiobjective Genetic Algorithm , 2002, J. Chem. Inf. Comput. Sci..

[19]  D. K. Kim,et al.  Mechanical properties and structural stability of perovskite-type, oxygen-permeable, dense membranes , 2006 .

[20]  Musbah M. Aqel,et al.  Pattern recognition using multilayer neural-genetic algorithm , 2003, Neurocomputing.

[21]  Wolfram Wersing,et al.  Microwave ceramics for resonators and filters , 1996 .

[22]  T. Ikeda,et al.  Dielectric Characteristics of Several Complex Oxide Ceramics at Microwave Frequencies , 1987 .

[23]  David A. Winkler,et al.  Predicting maximum bioactivity by effective inversion of neural networks using genetic algorithms , 1997 .

[24]  Lothar Thiele,et al.  Comparison of Multiobjective Evolutionary Algorithms on Test Functions of Different Difficulty , 1999 .

[25]  G. Stoica,et al.  Transitions of barium strontium titanate ferroelectric ceramics for different strontium content , 2007 .

[26]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[27]  X. M. Chen,et al.  Characterization of CaTiO3-modified Pb(Mg1/3Nb2/3)O3 dielectrics , 2000 .

[28]  D. J. Scott,et al.  An Integrated Instrument Control and Informatics System for Combinatorial Materials Research , 2006, J. Chem. Inf. Model..

[29]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[30]  Kalyanmoy Deb,et al.  Simulated Binary Crossover for Continuous Search Space , 1995, Complex Syst..

[31]  Nava Setter,et al.  Electroceramics: looking ahead , 2001 .

[32]  Hong Wang,et al.  Low-Temperature Firing and Microwave Dielectric , 2008 .

[33]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[34]  Y. Zhang,et al.  Functional Ceramic Materials Database: An Online Resource for Materials Research , 2008, J. Chem. Inf. Model..