柱

[2021] STRESS-STRAIN MODELING OF CONFINED CONCRETE　USING ARTIFICIAL NEURAL NETWORKS

Mingyang ZHANG¹, Weilun WANG², 秋山充良³ (1.Waseda University 2.Shenzhen University 3.早稲田大学)

キーワード：artificial neural networks, compressive fracture energy, confined concrete, gauge length

A stress-strain model was proposed based on the artificial neural networks (ANN) to predict the behavior of confined concrete columns under concentric compression. A wide range of previous experimental data including 182 samples were collected for establishing ANN model. Gauge length in the compressive test was used in the input layer of ANN model to take into consideration the difference of compressive fracture energy. The proposed stress-strain model provides good agreement with the test results independent of the compressive strength of concrete, yield strength of tie, and gauge length.