Shear Strength Prediction of Unusual Interior Reinforced Concrete Beam-Column Joint Using Multi-Layer Neural Network: a Data Collection by Digital 3D Finite Element Simulation

One of the controversial topics in the literature on structural engineering is retrofitting existing substandard interior reinforced concrete beam-column joints. However, these retrofitting methods gave an unusual shape to the joints, causing the unpredictability of their strength. A machine learning application was developed to predict the shear strength of unusual joint, farther finite element analysis was utilized to generate 3D samples as a training dataset. The paper presented detailed methodologies and discussions of the two disciplines. Powerful digital technologies and computer systems shown dominance by presenting the performance and regression analysis through different trained neural network models. Sensitivity analysis was conducted utilizing connection weights algorithm to determine the relative importance factor.

I. Introduction

Because of its numerous advantages, reinforced concrete (RC) has been the most extensively used structural material nowadays. Using this material with a moment-resisting frame (MRF) has been famous for economic and architectural reasons. MRF requires rigid beam-column joints (BCJs) to disperse earthquake energy and prevent brittle failure that could cause catastrophic building collapse. However, some RC MRF constructions were poor or lacked transverse reinforcement in the BCJ. Many researchers recommend various ways to improve these weak joints. One of the literature’s most recent and robust ways is to extend the inner joint area by forming an unsymmetrical chamfer with fiber mortar material [1], to resist the governing joint shear failure [2]. Envision what will be happened to poor RC buildings with no transverse reinforcement in the joint and has high shear stresses, a dangerous event will have occurred, killing the inhabitant, so retrofitting and constructing a larger BCJ is required to avoid unwillingness. Nevertheless, strengthening the RC BCJs could create a new issue by changing the joints’ regular shape to irregular. The product’s unusual shape precludes the application of theoretical, analytical, and empirical models in the literature, which cannot forecast shear strength. Because models are seen and evolved from conventional ones, predicting the unconventional structural component shape was difficult. Even though the joint was strengthened, it is still essential to assess the strength considering other structural components affected, global structure analysis, and user cost.