The Use of Machine Learning Models in Estimating the Compressive Strength of Recycled Brick Aggregate Concrete

The focus of this study is to investigate the applicability of Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN), and Multiple Linear Regression (MLR) in modeling the compressive strength of Recycled Brick Aggregate Concrete (RBAC). A comparative study on the application of the aforementioned models is developed based on statistical tools such as coefficient of determination, mean absolute error, root mean squared error, and some others, and the application potential of each of these models is investigated. To study the effects of RBAC factors on the performance of representative data-driven models, the Sensitivity Analysis (SA) method is used. The findings revealed that ANN with R2 value of 0.9102 has a great application potential in predicting the compressive strength of concrete. In the absence of ANN, ANFIS with R2 value of 0.8538 is also an excellent substitute for predictions. MLR was shown to be less effective than the preceding models and is only recommended for preliminary estimations. In addition, Subsequent sensitivity analysis on the database indicates the reliability of the prediction models have a strong correlation to the number of input parameters. The application of ANN and ANFIS as a precursor to traditional methods can eliminate the need for old-style tests, thus, constituting a significant reduction in time and expense needed for design and/or repairs.

[1]  Fouad M. Khalaf,et al.  Recycling of Demolished Masonry Rubble as Coarse Aggregate in Concrete: Review , 2004 .

[2]  Ajith Abraham,et al.  Adaptation of Fuzzy Inference System Using Neural Learning , 2005 .

[3]  J. Khatib,et al.  Properties of concrete incorporating fine recycled aggregate , 2005 .

[4]  Chi Sun Poon,et al.  The use of recycled aggregate in concrete in Hong Kong , 2007 .

[5]  A. Öztas,et al.  Appraisal of long-term effects of fly ash and silica fume on compressive strength of concrete by neural networks , 2007 .

[6]  C. Poon,et al.  Effects of contaminants on the properties of concrete paving blocks prepared with recycled concrete aggregates , 2007 .

[7]  I. Topcu,et al.  Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic , 2008 .

[8]  S. Kenai,et al.  The use of coarse and fine crushed bricks as aggregate in concrete , 2008 .

[9]  Ahmed M. Azmy,et al.  Neural networks for predicting compressive strength of structural light weight concrete , 2009 .

[10]  P. Cachim Mechanical properties of brick aggregate concrete , 2009 .

[11]  J. Sobhani,et al.  Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models , 2010 .

[12]  Behrouz Ahmadi-Nedushan,et al.  Prediction of elastic modulus of normal and high strength concrete using ANFIS and optimal nonlinear regression models , 2012 .

[13]  Mônica Batista Leite,et al.  Prediction of compressive strength of concrete containing construction and demolition waste using artificial neural networks , 2013 .

[14]  Ali Sadrmomtazi,et al.  Modeling compressive strength of EPS lightweight concrete using regression, neural network and ANFIS , 2013 .

[15]  C. Poon,et al.  Prediction of compressive strength of recycled aggregate concrete using artificial neural networks , 2013 .

[16]  Xu Ji,et al.  Prediction of concrete compressive strength: Research on hybrid models genetic based algorithms and ANFIS , 2014, Adv. Eng. Softw..

[17]  Faezehossadat Khademi,et al.  Predicting strength of recycled aggregate concrete using Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System and Multiple Linear Regression , 2016 .

[18]  Faezehossadat Khademi,et al.  A COMPREHENSIVE STUDY ON THE CONCRETE COMPRESSIVE STRENGTH ESTIMATION USING ARTIFICIAL NEURAL NETWORK AND ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM , 2017 .

[19]  Hosein Naderpour,et al.  ANN Model for Predicting the Compressive Strength of Circular Steel-Confined Concrete , 2017 .

[20]  Mehdi Nikoo,et al.  Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28 days compressive strength of concrete , 2017, Frontiers of Structural and Civil Engineering.

[21]  Rafat Siddique,et al.  Model for mix design of brick aggregate concrete based on neural network modelling , 2017 .

[22]  Hosein Naderpour,et al.  Shear resistance prediction of concrete beams reinforced by FRP bars using artificial neural networks , 2018, Measurement.

[23]  Amir Hossein Rafiean,et al.  Compressive strength prediction of environmentally friendly concrete using artificial neural networks , 2018 .

[24]  Togay Ozbakkaloglu,et al.  Effect of SnO2, ZrO2, and CaCO3 nanoparticles on water transport and durability properties of self-compacting mortar containing fly ash: Experimental observations and ANFIS predictions , 2018 .

[25]  Swapnasarit Kar,et al.  Prediction of FRP shear contribution for wrapped shear deficient RC beams using adaptive neuro-fuzzy inference system (ANFIS) , 2020 .

[26]  D. R. Eidgahee,et al.  A new and robust hybrid artificial bee colony algorithm – ANN model for FRP-concrete bond strength evaluation , 2020 .

[27]  Amir Hossein Rafiean,et al.  A new proposed approach for moment capacity estimation of ferrocement members using Group Method of Data Handling , 2020 .

[28]  Pouyan Fakharian,et al.  Mechanical properties of roller-compacted concrete pavement containing recycled brick aggregates and silica fume , 2021, Road Materials and Pavement Design.