Hostname: page-component-7b7567c8c-fvjsw Total loading time: 0 Render date: 2026-11-14T22:33:51.815Z Has data issue: false hasContentIssue false
  • English
  • Français

Artificial Intelligence In Materials Science: Application to Molecular and Particulate Simulations

Published online by Cambridge University Press:  17 March 2011

John F. Maguire,
Mark Benedict,
Leslie V. Woodcock and
Steven R. LeClair
John F. Maguire
Affiliation:
Email address: John.Maguire@afrl.af.mil
Mark Benedict
Affiliation:
Air Force Research Laboratory Materials and Manufacturing Directorate WPAFB, Dayton OH 45433-7746
Leslie V. Woodcock
Affiliation:
Permanent address:, University of Manchester Institute of Science and Technology (UMIST), UK
Steven R. LeClair
Affiliation:
Air Force Research Laboratory Materials and Manufacturing Directorate WPAFB, Dayton OH 45433-7746
Get access

Abstract

We illustrate how emerging methods in artificial intelligence (AI) may be useful in materials science. Historically, these methods were developed in the area of materials process control and, more recently, in the nascent field of materials discovery. However, machine intelligence is of much broader import and our primary objective here is to illustrate how such methods may be used to circumvent some serious roadblocks in the computer simulation of a significant class of computationally hard problems in materials science. This is illustrated by a new approach to solving the dynamics of the N-body problem for large numbers of objects of essentially arbitrarily complex geometry or interaction potential. The approach, based on a particulate artificial neural net dynamics algorithm (PANNDA) is more than two orders of magnitude faster than existing methods when applied to large systems and is only marginally slower (∼10%) than the theoretical lower limiting case of hard spheres. In this method an artificial neural net is trained to predict accurately the time to next collision for binary encounters spanning the Hilbert space of relative positions, orientations and momenta (linear and angular). This approach, which can be extended to soft complex systems, enables construction of exact, albeit numerical, models for the thermodynamic, transport and non-equilibrium properties of very large ensembles of hard or soft objects of arbitrarily complex shape or interaction potential. Our results open up the possibility of immediate application to an usually wide spectrum of contemporary computationally intractable “hard” problems ranging from granular materials with asperities through inclusion of complex many-body terms in the intermolecular interaction in molecular dynamics calculations of complex fluids and polymers.

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

1 Maguire, J.F., Miller, M.A., and Venkatesan, S., Engineering Applications of Artificial Intelligence, 11, 605–618, 1998.Google Scholar
2 Maguire, John F., Talley, Peggy L., Weed, Don, Venkatesen, Sanjeev, Wyatt, Mark and Rose, Tomas, International SAMPE Symposium 39, 164–173, 1994.Google Scholar
3 Maguire, John F. and Talley, Peggy L., Journal of Advanced Materials, p. 27–39, January, 1995.Google Scholar
4 Guessasma, Sofiana, Montavon, Ghidian, Christian Coddet, paper S 8.2, MRS Symposium, Nov. 2001.Google Scholar
5 Schenk, Peter K, Kaiser, Debra L., et al. paper S1.2, MRS Boston 2001.Google Scholar
6 Maguire, John F., Busbee, John D., Liptak, David, Lubbers, David, LeClair, Steve and Biggers, Rand, “Process Control for Pulsed Laser Deposition Using Raman Spectroscopy”, United States Patent 6038525, March 2000.Google Scholar
7 Pao, Y-H, Zhao, Y.H., LeClair, S.R., Neural-Network Based Exploration in the Design and Discovery of Materials, IFAC Symposium on Artificial Inteligence in Real Time Control, Budapest, Hungary, 2001.Google Scholar
8 Pao, Y-H, “Adaptive Pattern Recognition and Neural Networks”, Addison-Wesley, Reading, MA, 1989.Google Scholar
9 Henderson, D., “Fundamentals of Inhomogeneous Fluids”, Marcel Dekker, New York, 1992.Google Scholar
10 Adam, M. et. al., Nature, vol. 393, 1998.Google Scholar
11“Physical Chemistry in the Mesoscopic Regime”, Faraday Discussion 112, 1999.Google Scholar
12 Rowlinson, J. S. and Widom, B., “Molecular Theory of Capillarity,” University Press, Oxford, 1982.Google Scholar
13 Frenkel, D. and Smit, B., “Understanding Molecular Simulations” Academic Press, New York, 1996.Google Scholar
14 Allen, M.P. and Tildesley, D.J., “Computer Simulation of Liquids”, Clarendon Press, Oxford, 1987.Google Scholar
15www.uncwil.edu/peopleGoogle Scholar
16 Cvitanovi, P., “Universitality in Chaos,” Adam Hilger, Bristol, 2nd edition, 1989.Google Scholar
17 Ciccotti, G., Frenkel, D., and McDonald, I.R., “Simulation of Liquids and Solids”, Elsevier, Amsterdam 1989.Google Scholar
18 Alder, B. J. and Wainright, T. E., J. Chem. Phys., 31, 459, 1959.Google Scholar
19 Frenkel, Daan and Maguire, John F., Phys. Rev. Lett., 47, 15, 1025–1028, 1981.Google Scholar
20 Frenkel, D. and Maguire, J.F., Molecular Physics, 49, no.3, 503–541, 1983.Google Scholar
21 Maguire, John F. and Benedict, Mark, to be published.Google Scholar
22 Rowlinson, J. S. and Swinton, F. L., “Liquids and Liquid Mixtures,” 3rd ed., Butterworths, London, 1982.cGoogle Scholar
23www.icall.uni.stuttgart.de/~lui/REFS/references.htmlGoogle Scholar
24 Kadanoff, L. P., Rev. Mod. Phys. 71, 435,1999.Google Scholar
25 Bizon, C., Shattuck, M.D., Swift, J.B., and Swinney, Harry L., Physical Review E, 1–14, 20000.Google Scholar
26 Gennes, P.-G. de, Physica, A 261, 267–293, 1998.Google Scholar
27 Cates, M.E., Wittmer, J. P., Bouchaud, J.-P. and Claudin, P., Phil. Trans. R. Soc. Lond. A 356, 2535, 1998.Google Scholar
28 Brown, R.L. and Richards, J.C., “Principles of Powder Mechanics”, Pergammon, Oxford, 1970.Google Scholar