Flexural Capacity Prediction of RC Beams Strengthened in Terms of NSM System Using Soft Computing

Abstract

In recent years, there has been a notable increase in the application of near-surface mounted fiber-reinforced polymer (FRP) reinforcement in reinforced concrete structures. Nevertheless, there is a discernible disparity in the accessibility of accurate and customize measures for augmenting flexural strength through the use of near-surface mounted (NSM) reinforcement techniques. Although several basic models have been proposed to predict the flexural capacity achievable with this technology, established codes have not yet provided mathematical equations for this specific purpose. This study presents two separate methodologies with the objective of enhancing the development of suitable code provisions. In the first stage, A comprehensive and reliable database has been developed to leverage the predictive accuracy of neural networks in the computation of the flexural capacity of reinforced beams that utilize near-surface mounted reinforcement. Following this, the results obtained from the neural network are employed to construct a linear equation using the group method of data handling (GMDH) technique. The presented equation has been carefully formulated to produce a concise and simple mathematical expression that enables the determination of the flexural strength of a beam on the field. The evaluation of the accuracy and effectiveness of both the neural network and the suggested equation is conducted in accordance with the requirements specified in ACI 440.R2 for externally bonded reinforcements. The neural network's prediction has a mean absolute error of just 5% in comparison to the experimental results and the GMDH equations exhibit a noteworthy level of concurrence with the experimental outcomes, as they display a mean absolute error of 16%.

Keywords

• machine learning
• artificial neural network
• predictive model
• near-surface mounted (nsm)
• frp
• flexural strength