Physical properties prediction

R. Banares-Alcantara, A. W. Westerberg, and M. D. Rychener, Development of an Expert System for Physical Property Predictions, Technical Keport, Carnegie Mellon University, Design Research Center and Robotics Institute, Pittsburgh, Pa., 1983. 

C. Jochum, M. G. Hicks, and J. Sunkel, eds.. Physical Property Prediction in Organic Chemistry, Proceedings of the Beilstein Workshop, May 16—20, 1988, Schloss Korb, Italy, Springer-Vedag, Berlin and New York, 1988. 

Artificial Neural Networks as a Semi-Empirical Modeling Tool for Physical Property Predictions in Polymer Science... 

Recently, a new approach called artificial neural networks (ANNs) is assisting engineers and scientists in their assessment of fuzzy information, Polymer scientists often face a situation where the rules governing the particular system are unknown or difficult to use. It also frequently becomes an arduous task to develop functional forms/empirical equations to describe a phenomena. Most of these complexities can be overcome with an ANN approach because of its ability to build an internal model based solely on the exposure in a training environment. Fault tolerance of ANNs has been found to be very advantageous in physical property predictions of polymers. This chapter presents a few such cases where the authors have successfully implemented an ANN-based approach for purpose of empirical modeling. These are not exhaustive by any means. 

These capabilities of ANNs make them a unique tool for a large number of industrial applications. In this chapter, the authors demonstrate, with case studies, the advantages of using this approach to physical property predictions in polymer science. 

Physical property prediction in polymer science has evolved from the original basic group contribution meth-... 

DeWitte, R., Gorohov, F., Kolovanov, E. Using targeted measurements to improve the accuracy of physical property prediction. Presented at ADMET-1 Conference 2004, San Diego, 2004. 

Example of a three-layer back-propagation network describing the application of physical property prediction. 

OPTIMIZATION ROUTINES DIFFERENTIAL EQUATION SOLVERS PHYSICAL PROPERTY PREDICTIONS DATA BASE MANAGEMENT... 

Gasteiger, J. (1988). Empirical Methods for the Calculation of Physicochemical Data of Organic Compounds. In Physical Property Prediction in Organic Chemistry (Jochum, C, Hicks, M.G. and Sunkel, J., eds.). Springer-Verlag, Berlin (Germany), pp. 119-138. 

Physical Property Prediction in Organic Chemistry, Springer-Verlag, Berlin, Germany, p. 554. 

Willett, P. (1988) Ranking and clustering of chemical structure databases, in Physical Property Prediction in Organic Chemistry (eds C. Jochum, M.G. Hicks and J. Sunkel), Springer-Verlag, Berhn, Germany, pp. 191-207. 

O Donnell, T.J. 2006. Using relational databases for physical property prediction. The 232nd ACS National Meeting, San Francisco, CA, September 10-14, 2006. 

Kubinyi H. Current problems in quantitative structure-activity relationships. In Jochum C, Hicks MG, Sunkel J, eds. Physical Property Prediction in Organic Chemistry. Berlin Springer-Verlag, 1988 235-247. 

The physical properties predict whether the spin number is equal to zero, a half integer, or a whole integer, but the actual spin number— for example, 1 /2 or 3/2 or 1 or 2— must be determined experimentally. All elements in the first six rows of the periodic table have at least one stable isotope with a nonzero spin quantum number, except Ar, Tc, Ce, Pm, Bi, and Po. It can be seen from Table 3.1 and Appendix 10.1 that many of the most abundant isotopes of common elements in the periodic table cannot be measured by NMR, notably those of C, O, Si, and S, which are very important components of many organic molecules of interest in biology, the pharmaceutical industry, the polymer industry, and the chemical manufacturing industry. Some of the more important elements that can be determined by NMR and their spin quantum numbers are shown in Table 3.2. The two nuclei of most importance to organic chemists and biochemists, and H, both have a spin quanmm number =1/2. 

---