Extraction of Bonding Parameter Characterizing Infrared Absorption Intensity of Freon Alternatives by Sensitivity Analysis and Differential Coefficient Analysis of Input Data for Neural Network

Tomoko FUKUDAa, b, Takatoshi MATSUMOTOc, Kazutoshi TANABEc, Umpei NAGASHIMAd* and Tomoo AOYAMAe

aDepartment of Life Arts, Faculty of Home Economics, Japan Women's University
2-8-1 Mejirodai, Bunkyo-ku, Tokyo 112-8681, Japan
bBestsystems Co. Ltd.
4-15-2-1-204 Matsushiro, Tsukuba, Ibaraki 305-0035, Japan
cQuantum Modeling Research Group, Research Institute for Computational Sciences, National Institute for Advanced Industrial Science and Technology
1-1-4 Umezono, Tsukuba, Ibaraki 305-8568 Japan
dTsukuba Advanced Computing Center, National Institute for Advanced Industrial Science and Technology
1-1-4 Higashi, Tsukuba, Ibaraki 305-8562 Japan
eFaculty of Technology, Miyazaki University
Gakuenkihanadai Nishi, Miyazaki 889-2192 Japan

(Received: March 8, 2001; Accepted for publication: October 10, 2001; Published on Web: March 22, 2002)

For molecular design of freon alternatives, we attempted to extract bond parameter characterizing the infrared absorption intensity in the 1500-500 cm-1 region from 44 kinds of fluorine-containing molecules: freon alternatives in gas phase by the analysis of sensitivity and differential coefficients of input parameter for the three layers perceptron type neural network. The analysis of differential coefficients of input parameter for the three layers perceptron type neural network was developed by Aoyama and Ichakawa[3, 4] and was newly equipped into a neural network simulator Neco [2, 5, 8 - 13].
The importance of 8 bond types: C-C, C=C, C-O, C=O, C-H, C-F, C-Cl, O-H were examined using a well educated neural network, where the error of leave-one out test is less than 0.007. The error is acceptable because the value corresponds almost 5% error of intensity and 10% error is usually included in the observed values.
The numbers of C=O and O-H bonds increase the intensity whereas C-O and C-F have less effect. In Figure 2, the sensitivity analysis suggested that the number of C-C bonds is to be unimportant for the intensity. However, the result of the differential coefficients analysis suggested the importance of the number of C-C bonds as shown in Figure 3.
The results of the sensitivity analysis and the differential coefficients suggested that ether type freon alternatives have relatively small infrared absorption intensity in the 1500-500 cm-1 region.

Keywords: Freon Alternatives, Infrared Absorption Intensity, Molecular Design, Sensitivity Analysis, Differential Coefficients Analysis, Neural Network


Abstract in Japanese

Text in Japanese

PDF file(71kB)


Return