Artificial Neural Network (ANN) Model for the Prediction of Shear Strength of Exterior RC Beam-Column Joints: A Conceptual Model

One of Machine Learning (ML) techniques that can be used for engineering applications is Artificial Neural Network (ANN). In this paper, Machine Learning (ML) - Artificial Neural Network (ANN) has been utilized to predict the shear capacity of reinforced concrete (RC) beam-column joint (BCJ). In this study, data sets needed for the ANN model have been generated using Finite Element Analysis (FEA) software ABAQUS. ANN prediction model is proposed depending on 4320 total BCJ samples: (70<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>) used for training, (15<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>) for testing, and (15<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>) for validation of the ANN model. The proposed model showed 95.6% accuracy in its prediction for shear capacity of RC BCJ testing data of 648 samples.