4050 ニューラルネットワークを用いた結合剛性推定法(G03-8 解析・計算技術,G03 材料力学)

Abstract

A rigidity of a part connected by thin-walled box section beams is one of the key factors dominating the basic characteristics of an automobile body structure. In the beginning stage of the body design, it is important to quantitatively evaluate the rigidity of jointed part. Thus it is wished to develop the tool that can quickly and accurately obtain the joint stiffness value for using in the beginning stage of the design. In this paper, the new method that can quickly and accurately estimate the joint stiffness values from the design parameters was proposed. And the structural analysis tool using this method was made. Main flow of this method is as follows. The relation between the design parameters and the joint stiffness values is constructed by neural network. Once the relation was constructed, the joint stiffness values can be obtained by inputting the design parameters to the trained neural network.