企画セッション（数値解析の検証と妥当性確認（V&V)、不確かさ評価）②

[22013-19-06] DEVELOPMENT OF COORDINATE SYSTEM INDEPENDENT NEURAL NETWORK (Proceedings of Symposium on Applied Mechanics)

*Siwei Zhang¹, Muneo Hori¹ (1. University of Tokyo)

Keywords:coordinate system independent, neural network, synthesized rotation, structural response analysis

A neural network is required to be coordinate system independent when it is applied to solve physical problems. Instead of training, this paper develops a post-processing which is applicable for any arbitrary neural network. The essence of the post-processing is synthesized rotation that generates a set of rotated input data, applies the neural network to each of the set, re-rotates the output, and extracts a coordinate system independent solution from the output. Numerical experiments of the post-processing are carried for structural response analysis. It is shown that the post-processing works as designed. Discussions are made for further use of the post-processing of neural networks to make them coordinate system independent.