Bulletin of the Korean Chemical Society

Korean Chemical Society (대한화학회)
권호 표지
DOI QR코드

DOI QR Code

Optimization of Neural Networks Architecture for Impact Sensitivity of Energetic Molecules

  • Published : 2005.03.20
Download PDF
⟨ Previous Next ⟩

Abstract

We have utilized neural network (NN) studies to predict impact sensitivities of various types of explosive molecules. Two hundreds and thirty four explosive molecules have been taken from a single database, and thirty nine molecular descriptors were computed for each explosive molecule. Optimization of NN architecture has been carried out by examining seven different sets of molecular descriptors and varying the number of hidden neurons. For the optimized NN architecture, we have utilized 17 molecular descriptors which were composed of compositional and topological descriptors in an input layer, and 2 hidden neurons in a hidden layer.

Keywords

References

  1. Perssen, P.-A.; Holmberg, R.; Lee, J. Rock Blasting and Explosives Engineering; CRC Press: Baca Raton, FL, 1993
  2. Koehler, J.; Meyer, R. Explosives, 4th ed.; VCH: Weinheim, Germany, 1993
  3. Coffey, C. S.; DeVost, V. F. Propel. Explos. Pyrotech. 1995, 20, 105 https://doi.org/10.1002/prep.19950200302
  4. Brill, T. B.; James, K. J. Chem. Rev. 1993, 2667
  5. Zeman, S.; Krupka, M. Propel. Explos. Pyrotech. 2003, 28, 301 https://doi.org/10.1002/prep.200300018
  6. Zeman, S. Propel. Explos. Pyrotech. 2003, 28, 308 https://doi.org/10.1002/prep.200300021
  7. Zeman, S.; Krupka, M. Propel. Explos. Pyrotech. 2003, 28, 249 https://doi.org/10.1002/prep.200300012
  8. Zeman, S. Propel. Explos. Pyrotech. 2000, 25, 66 https://doi.org/10.1002/(SICI)1521-4087(200004)25:2<66::AID-PREP66>3.0.CO;2-Q
  9. Politzer, P.; Murray, J. S.; Lane, P.; Sjoberg, P.; Adolph, H. G. Chem. Phys. Lett. 1991, 181, 78 https://doi.org/10.1016/0009-2614(91)90225-X
  10. Politzer, P.; Murray, J. S. Mol. Phys. 1995, 86, 251 https://doi.org/10.1080/00268979500101981
  11. Rice, B.; Hare, J. J. J. Phys. Chem. A 2002, 106, 1770 https://doi.org/10.1021/jp012602q
  12. Storm, C. B.; Stine, J. R.; Kramer, J. F. Sensitivity Relationship in Energetic Materials; Los Alamos National Laboratory, LAUR-89-2936, 1989
  13. Storm, C. B.; Stine, J. R.; Kramer, J. F. In Chemistry and Physics of Energetic Materials; Bulusu, S. N., Ed.; Kluwer Academic Press: Dordrecht, Netherlands, 1990; p 605
  14. Nefati, H.; Cense, J.-M.; Legendre, J.-J. J. Chem. Inf. Comput. Sci. 1996, 36, 804 https://doi.org/10.1021/ci950223m
  15. Cerius Modeling Environment, Relaese 4.0; Accelrys Inc.: San Diego, 1999
  16. Dewar, M. J. S.; Zoebisch, E. G.; Healy, E. F.; Stewart, J. J. P. J. Am. Chem. Soc. 1985, 107, 3902 https://doi.org/10.1021/ja00299a024
  17. Ghose, A. K.; Viswanadhan, V. N.; Wendoloski, J. J. J. Phys. Chem. A 1998, 102, 3762 https://doi.org/10.1021/jp980230o
  18. Zupan, J.; Gasteiger, J. Neural Networks in Chemistry and Drug Design, 2nd ed.; Wiley-VCH: Weinheim, Germany, 1999
  19. Neural Networks in QSAR and Drug Design; Devillers, J., Ed.; Academic Press: London, 1996
  20. Wold, S.; Johansson, E.; Cocchi, M. In 3D-QSAR in Drug Design. Theory Methods and Applications; Kubynyi, H., Ed.; ESCOM: Leiden, Netherlands, 1993; pp 523-550
  21. Myers, R. H. Classical and Modern Regression with Applications, 2nd ed.; Duxbury Press: Belmont, CA, 1990
  22. Cho, D. H.; Lee S. K.; Kim, B. T.; No, K. T. Bull. Korean Chem. Soc. 2001, 22, 388
  23. Karelson, M.; Lobonov, V. S. Chem. Rev. 1996, 96, 1027 https://doi.org/10.1021/cr950202r
  24. Lee, K. W.; Kwon, S. Y.; Hwang, S.; Lee, J.-U.; Kim, H. Bull. Korean Chem. Soc. 1996, 17, 147

Cited by

  1. Simple Relationship for Predicting Impact Sensitivity of Nitroaromatics, Nitramines, and Nitroaliphatics vol.35, pp.2, 2009, https://doi.org/10.1002/prep.200800078
  2. Computational design and structure–property relationship studies on heptazines vol.17, pp.11, 2011, https://doi.org/10.1007/s00894-011-0959-x
  3. A Predictive Study on Molecular and Explosive Properties of 1-Aminoimidazole Derivatives vol.32, pp.7, 2011, https://doi.org/10.5012/bkcs.2011.32.7.2319
  4. Theoretical evaluation of sensitivity and thermal stability for high explosives based on quantum chemistry methods: A brief review vol.113, pp.8, 2013, https://doi.org/10.1002/qua.24209
  5. Theoretical Shock Sensitivity Index for Explosives vol.116, pp.7, 2012, https://doi.org/10.1021/jp209730a
  6. Prediction of Impact Sensitivity of Nonheterocyclic Nitroenergetic Compounds Using Genetic Algorithm and Artificial Neural Network vol.30, pp.2, 2012, https://doi.org/10.1080/07370652.2010.550598
  7. Global and local quantitative structure-property relationship models to predict the impact sensitivity of nitro compounds vol.31, pp.3, 2012, https://doi.org/10.1002/prs.11499
  8. Review of Existing QSAR/QSPR Models Developed for Properties Used in Hazardous Chemicals Classification System vol.51, pp.49, 2012, https://doi.org/10.1021/ie301079r
  9. Toward a Physically Based Quantitative Modeling of Impact Sensitivities vol.117, pp.10, 2013, https://doi.org/10.1021/jp311677s
  10. QSPR prediction of physico-chemical properties for REACH vol.24, pp.4, 2013, https://doi.org/10.1080/1062936X.2013.773372
  11. A New General Correlation for Predicting Impact Sensitivity of Energetic Compounds vol.38, pp.6, 2013, https://doi.org/10.1002/prep.201200128
  12. Predicting Impact Sensitivities of Nitro Compounds on the Basis of a Semi-empirical Rate Constant vol.118, pp.41, 2014, https://doi.org/10.1021/jp507057r
  13. A General Guidebook for the Theoretical Prediction of Physicochemical Properties of Chemicals for Regulatory Purposes vol.115, pp.24, 2015, https://doi.org/10.1021/acs.chemrev.5b00215
  14. Two dimensional analysis between the performance and the sensitivity of methylnitroimidazole derivatives vol.28, pp.6, 2015, https://doi.org/10.5806/AST.2015.28.6.430
  15. Kriging models for forecasting crude unit overhead corrosion vol.33, pp.7, 2016, https://doi.org/10.1007/s11814-016-0083-9
  16. Analysis of air blast effect for explosives in a large scale detonation pp.1975-7220, 2017, https://doi.org/10.1007/s11814-017-0227-6
  17. Prediction of Detonation Pressure of Aluminized Explosive by Artificial Neural Network vol.641-642, pp.1662-8985, 2013, https://doi.org/10.4028/www.scientific.net/AMR.641-642.460
  18. -phenyl-pyrazoles and Indazoles: Mononitro, Dinitro, and Trinitro Derivatives vol.55, pp.1, 2018, https://doi.org/10.1002/jhet.3026
  19. Neural networks study on the correlation between impact sensitivity and molecular structures for nitramine explosives vol.17, pp.5, 2006, https://doi.org/10.1007/s11224-006-9101-6
  20. Energetic mono and dibasic 5-dinitromethyltetrazolates: synthesis, properties, and particle processing vol.17, pp.36, 2007, https://doi.org/10.1039/b708041g
  21. Novel correlation for predicting impact sensitivity of nitroheterocyclic energetic molecules vol.141, pp.3, 2005, https://doi.org/10.1016/j.jhazmat.2006.07.046
  22. Prediction of shock sensitivity of explosives based on small-scale gap test vol.145, pp.1, 2005, https://doi.org/10.1016/j.jhazmat.2006.10.091
  23. Synthesis, characterization, thermal and explosive properties of potassium salts of trinitrophloroglucinol vol.147, pp.1, 2005, https://doi.org/10.1016/j.jhazmat.2007.01.043
  24. Prediction of impact sensitivity of nitroaliphatic, nitroaliphatic containing other functional groups and nitrate explosives vol.148, pp.3, 2005, https://doi.org/10.1016/j.jhazmat.2007.03.022
  25. Physical Chemistry Research Articles Published in the Bulletin of the Korean Chemical Society: 2003-2007 vol.29, pp.2, 2008, https://doi.org/10.5012/bkcs.2008.29.2.450
  26. Development of quantitative structure-property relationships for predictive modeling and design of energetic materials vol.27, pp.3, 2005, https://doi.org/10.1016/j.jmgm.2008.06.003
  27. A simple approach for predicting impact sensitivity of polynitroheteroarenes vol.166, pp.2, 2005, https://doi.org/10.1016/j.jhazmat.2008.12.022
  28. New Correlations for Predicting Impact Sensitivities of Nitro Energetic Compounds vol.28, pp.1, 2005, https://doi.org/10.1080/07370650903193281
  29. MATEO: A software package for the molecular design of energetic materials vol.176, pp.1, 2005, https://doi.org/10.1016/j.jhazmat.2009.11.030
  30. MS-HEMs: An On-line Management System for High-Energy Molecules at ADD and BMDRC in Korea vol.33, pp.3, 2005, https://doi.org/10.5012/bkcs.2012.33.3.855
  31. QSPR studies of impact sensitivity of nitro energetic compounds using three-dimensional descriptors vol.36, pp.None, 2005, https://doi.org/10.1016/j.jmgm.2012.03.002
  32. Prediction of Detonation Velocity of Aluminized Explosive by Artificial Neural Network vol.790, pp.None, 2013, https://doi.org/10.4028/www.scientific.net/amr.790.673
  33. 트리나이트로이미다졸 치환체들의 화약성능 및 감도 예측 분석 vol.20, pp.4, 2005, https://doi.org/10.9766/kimst.2017.20.4.543
  34. Applying machine learning to balance performance and stability of high energy density materials vol.24, pp.3, 2005, https://doi.org/10.1016/j.isci.2021.102240
  35. Artificial Neural Networks for Pyrolysis, Thermal Analysis, and Thermokinetic Studies: The Status Quo vol.26, pp.12, 2005, https://doi.org/10.3390/molecules26123727