http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
균열 정보와 신경망 모델을 이용한 철근콘크리트 보의 전단 성능 예측 연구
권아영(Kwon, Ah-Young),엥 리번듯(Eng Lybundith),김창혁(Kim, Changhyuk) 대한건축학회 2023 대한건축학회논문집 Vol.39 No.10
This study aims to predict how reinforced concrete beams perform under shear stress using Artificial Neural Networks (ANN) and numerical crack data. The shear crack data from reinforced concrete beam specimens through finite element analysis were obtained. Afterward, K-clustering to create an input dataset for the ANN analysis was used. The training and testing of a multi-layer perceptron regression model involved the use of samples that had been analyzed using the Finite Element Method (FEM). The evaluation of the ANN model’s performance considered the Mean Absolute Error (MAE), Adjusted R squared, Coefficient of Correlation, and Coefficient of Variation (CV).