Development of a Neural Network Simulator for Structure-Activity Correlation of Molecules: Neco (6)
- Estimation of Mechanical Properties of Cr-Mo Steel, Ni Steel, Ni-Cr Steel and Ni-Cr-Mo Steel -

Tomoko FUKUDAa,b, Sumie TAJIMAc, Takatoshi MATSUMOTOd, Umpei NAGASHIMAe*, Haruo HOSOYAc and Tomoo AOYAMAf

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
cDepartment of Human Culture and Sciences, Graduate School of Ochanomizu University
2-1-1 Otsuka, Bunkyo-ku, Tokyo 112-8610, Japan
dNational Institute of Materials and Chemical Research
1-1 Higashi, Tsukuba, Ibaraki 305-8565, Japan
eNational Institute for Advanced Interdisciplinary Research
1-1-4 Higashi, Tsukuba, Ibaraki 305-8562, Japan
fFaculty of Technology, Miyazaki University
Gakuenkihanadai Nishi, Miyazaki 889-2192, Japan

(Received: September 22, 2000; Accepted for publication: January 10, 2001; Published on Web: August 20, 2001)

In order to estimate mechanical properties of high tension steels for machine tools: Cr-Mo steel, Ni steel, Ni-Cr steel and Ni-Cr-Mo steel, we applied property prediction by a perceptron type neural network. It was found that six mechanical properties: yield point, tensile strength, diaphragm, impulsive force and hardness are predictable within experimental error, almost 20%, using only the amount of C, Mn, Ni, Cr and Mo in the steels.

Keywords: Yield Point, Tensile Strength, Elongation Percentage, Diaphragm, Impulsive Force, Hardness, Cr-Mo Steel, Ni Steel, Ni-Cr Steel, Ni-Cr-Mo Steel, Property Estimation, Neural Network

Abstract in Japanese

Text in Japanese

PDF file(74kB)

Author Index
Keyword Index