Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres

Abstract The study presents a comparative approach between Response Surface Methodology (RSM) and hybridized Genetic Algorithm of Artificial Neural Network (GA-ANN) in predicting the water absorption, compressive strength, flexural strength, split tensile strength and slump for steel fibre reinforced concrete. The effects of process variables such as aspect ratio, water–cement ratio and cement content were investigated using the central composite design of response surface methodology. This same experimental design was used in training the hybrid-training approach of artificial neural network. The predicting ability of both methodologies was compared using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Model Predictive Error (MPE) and Absolute Average Deviation (AAD). The response surface methodology model was found more accurate in being able to predict compared to the hybridized genetic algorithm of the artificial neural network.

[1]  F. Schoefs,et al.  Probabilistic Modelling of Compressive Strength of Concrete Using Response Surface Methodology and Neural Networks , 2014, Arabian Journal for Science and Engineering.

[2]  Weiguo Shen,et al.  Investigation on polymer–rubber aggregate modified porous concrete , 2013 .

[3]  Atoyebi Olumoyewa.  SPLITTING TENSILE STRENGTH ASSESSMENT OF LIGHTWEIGHT FOAMED CONCRETE REINFORCED WITH WASTE TYRE STEEL FIBRES , 2018 .

[4]  Blessen Skariah Thomas,et al.  A comprehensive review on the applications of waste tire rubber in cement concrete , 2016 .

[5]  Bashar S. Mohammed,et al.  Rubbercrete mixture optimization using response surface methodology , 2018 .

[6]  K. E. Alyamaç,et al.  Development of eco-efficient self-compacting concrete with waste marble powder using the response surface method , 2017 .

[7]  Changli Zhang,et al.  Application of Genetic Algorithm (GA) Trained Artificial Neural Network to Identify Tomatoes with Physiological Diseases , 2007, CCTA.

[8]  Tayfun Uygunoğlu,et al.  Analysis of the effects of dioctyl terephthalate obtained from polyethylene terephthalate wastes on concrete mortar: A response surface methodology based desirability function approach application , 2018 .

[9]  J. Maran,et al.  Artificial neural network and response surface methodology modeling in mass transfer parameters predictions during osmotic dehydration of Carica papaya L. , 2013 .

[10]  Rudolf Kruse,et al.  Neuro-fuzzy systems for function approximation , 1999, Fuzzy Sets Syst..

[11]  Mansour Ghaffari Moghaddam,et al.  Comparison of Response Surface Methodology and Artificial Neural Network in Predicting the Microwave-Assisted Extraction Procedure to Determine Zinc in Fish Muscles , 2011 .

[12]  Fernando Pacheco-Torgal,et al.  Properties and durability of concrete containing polymeric wastes (tyre rubber and polyethylene terephthalate bottles): An overview , 2012 .

[13]  O. Atoyebi,et al.  Artificial neural network evaluation of cement-bonded particle board produced from red iron wood (Lophira alata) sawdust and palm kernel shell residues , 2018, Case Studies in Construction Materials.

[14]  G. Najafpour,et al.  Modeling and optimization of ethanol fermentation using Saccharomyces cerevisiae: response surface methodology and artificial neural network. , 2013 .

[15]  A. Dalvand,et al.  Use of silica fume and recycled steel fibers in self-compacting concrete (SCC) , 2016 .

[16]  Rekha S. Singhal,et al.  Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: Case study of fermentative production of scleroglucan , 2008 .

[17]  Özgür Eren,et al.  Effect of cement content and water/cement ratio on fresh concrete properties without admixtures , 2011 .

[18]  S. Kumari,et al.  Adsorptive removal of cyanide from coke oven wastewater onto zero-valent iron: optimization through response surface methodology, isotherm and kinetic studies. , 2018 .

[19]  H Schmidli,et al.  Advantages of Artificial Neural Networks (ANNs) as alternative modelling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage form. , 1998, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[20]  Ronald R. Yager,et al.  Adaptive defuzzification for fuzzy systems modeling , 1992 .

[21]  P. Mativenga,et al.  A Benchmark Study of Waste Tyre Recycling in South Africa to European Union Practice , 2018 .

[22]  V. Balasubramanian,et al.  Comparison of RSM with ANN in predicting tensile strength of friction stir welded AA7039 aluminium alloy joints , 2009 .

[23]  A. Ghaffari,et al.  Performance comparison of neural network training algorithms in modeling of bimodal drug delivery. , 2006, International journal of pharmaceutics.

[24]  I. S. Ibrahim,et al.  Mechanical Properties of Recycled Steel Tire Fibres in Concrete , 2013 .

[25]  Samir Dirar,et al.  Properties of concrete prepared with waste tyre rubber particles of uniform and varying sizes , 2015 .

[26]  Amin Hamed Mashhadzadeh,et al.  Using response surface methodology for modeling and optimizing tensile and impact strength properties of fiber orientated quaternary hybrid nano composite , 2015 .

[27]  Michele Notarnicola,et al.  Surface and bulk hydrophobic cement composites by tyre rubber addition , 2018 .

[28]  G. Mucsi,et al.  Fiber reinforced geopolymer from synergetic utilization of fly ash and waste tire , 2018 .

[29]  Joel Oliveira,et al.  Use of a warm mix asphalt additive to reduce the production temperatures and to improve the performance of asphalt rubber mixtures , 2013 .

[30]  K. Pilakoutas,et al.  Design Issues for Concrete Reinforced with Steel Fibers, Including Fibers Recovered from used Tires , 2006 .

[31]  T. Awolusi,et al.  Application of response surface methodology: Predicting and optimizing the properties of concrete containing steel fibre extracted from waste tires with limestone powder as filler , 2019, Case Studies in Construction Materials.

[32]  M. Basri,et al.  A modeling study by response surface methodology and artificial neural network on culture parameters optimization for thermostable lipase production from a newly isolated thermophilic Geobacillus sp. strain ARM , 2008, BMC biotechnology.

[33]  T. Awolusi,et al.  Performance comparison of neural network training algorithms in the modeling properties of steel fiber reinforced concrete , 2019, Heliyon.

[34]  K. Pilakoutas,et al.  Reuse of tyre steel fibres as concrete reinforcement , 2004 .

[35]  Peter A. Claisse,et al.  Absorption and Sorptivity of Cover Concrete , 1997 .

[36]  Chengqing Qi.  Quantitative assessment of plastic shrinkage cracking and its impact on the corrosion of steel reinforcement , 2003 .

[37]  Rudolf Kruse,et al.  A neuro-fuzzy method to learn fuzzy classification rules from data , 1997, Fuzzy Sets Syst..

[38]  Rajendra Kumar Sharma,et al.  Artificial Neural Networks for the Prediction of Compressive Strength of Concrete , 2015 .

[39]  Mpanyana Lucas Mahlangu.  Waste tyre management problems in South Africa and the possible opportunities that can be created through the recycling thereof , 2009 .

[40]  Rajarathinam Ravikumar,et al.  Response surface methodology and artificial neural network for modelling and optimization of distillery spent wash treatment using Phormidium valderianum BDU 140441 , 2013 .

[41]  R. Gomes,et al.  Comparison of response surface methodology (RSM) and artificial neural networks (ANN) towards efficient extraction of artemisinin from Artemisia annua , 2014 .

[42]  N. Bedewi.  Steel Fiber Reinforced Concrete Made With Fibers Extracted from Used Tyres , 2009 .

[43]  Bing Chen,et al.  Contribution Of Hybrid Fibers On The Properties Of The High-Strength Lightweight Concrete Having Good Workability , 2005 .

[44]  Blessen Skariah Thomas,et al.  Recycling of waste tire rubber as aggregate in concrete: durability-related performance , 2016 .

[45]  Eduardo Júlio,et al.  Influence of fibres on the mechanical behaviour of fibre reinforced concrete matrixes , 2017 .