An Intelligent Model for the Prediction of Bond Strength of FRP Bars in Concrete: A Soft Computing Approach

Abstract

Accurate prediction of bond behavior of fiber reinforcement polymer (FRP) concrete has a pivotal role in the construction industry. This paper presents a soft computing method called multi-gene genetic programming (MGGP) to develop an intelligent prediction model for the bond strength of FRP bars in concrete. The main advantage of the MGGP method over other similar methods is that it can formulate the bond strength by combining the capabilities of both standard genetic programming and classical regression. A number of parameters affecting the bond strength of FRP bars were identified and fed into the MGGP algorithm. The algorithm was trained using an experimental database including 223 test results collected from the literature. The proposed MGGP model accurately predicts the bond strength of FRP bars in concrete. The newly defined predictor variables were found to be efficient in characterizing the bond strength. The derived equation has better performance than the widely-used American Concrete Institute (ACI) model.

New Prediction Model for the Ultimate Axial Capacity of Concrete-Filled Steel Tubes: An Evolutionary Approach

“…In GEP the chromosome consist of linear, symbolic strings of genes and each gene in it is a code for object selection while expression tree (ET) is also used for the similar purpose. The parameters that are used by GEP are similar to the ones that were used in GP [52][53][54]. In these algorithms the computer programs consist of the characters of defined length comparing with the expression trees of length which varies in genetic programming.…”

Bridging finite element and deep learning: High-resolution stress distribution prediction in structural components

“…Data-driven approaches that model physical phenomena have been lauded for their significant and growing successes. Most recent works have included design and topology optimization [3][4][5][6], data-driven approaches in fluid dynamics [7][8][9][10], molecular dynamics simulation [11][12][13][14], and material properties prediction [15][16][17][18]. Also, Atalla et al and Levin et al [19,20] have used neural regression for FEA model updating.…”

Predicting Bond Strength between FRP Rebars and Concrete by Deploying Gene Expression Programming Model

“…With the advancement of computer science and the increasing volume of associated experimental datasets, data-driven approaches based on machine learning (ML) algorithms have recently emerged as alternative methods for establishing prediction models using comprehensive experimental data and information [ 35 , 36 , 37 , 38 , 39 ]. Some of the most commonly and successfully deployed ML algorithms for estimating the BS of FRP are artificial neural networks (ANNs), support vector machines (SVMs), multiple linear regression (MLR), genetic and evolutionary algorithms (GEAs), random forest (RF), and ensemble learning (gradient boosted regression trees [GBRT]) [ 18 , 27 , 28 , 35 , 40 , 41 , 42 , 43 , 44 , 45 ]. Thakur et al [ 13 ] proposed a bagged M5P tree regression model out of six different models for the prediction of the bonding strength of FRP bars embedded in concrete.…”

“…A new branch of genetic programming called multigene genetic programming (MGGP) was also proposed, relying on its remarkable prediction capabilities to estimate the BS of FRP bars. Considering its successful implementation and lofty performance in different studies, gene expression programming (GEP) was chosen in this study to estimate the BS of FRP [ 31 , 41 , 42 , 46 , 47 ]. Free from computational issues of slow convergence rates and local minimum convergence, GEP uses a linear constant-length expression tree (ET), a mathematical expression representation arranged in a tree-like the structure of data.…”