ニューラルネットワークを用いた構造設計における「経験的非明示知識」の知識獲得に関する研究 : 構造特性係数Ds値の推定法を対象として(一般講演)

概要

論文の詳細を見る
This report proposes a knowledge acquisition method of experienced implicit structural design knowhow by neural network. As a structural design target, the structural characteristic coefficient Ds in aseismic structural planning is employed in this paper. Neural network can accurately reason Ds values by using simple information such as structural material types and shapes. 6 input parameters are used on the basis of the first author's structural design experiences. The training and verification data are used from the works that were really designed or planned in FUJITA CORPORATION. From the result of the verification, this system is possible to acquire experienced implicit structural design knowhow by neural network.
一般社団法人日本建築学会の論文
1994-03-15