Soft computing approaches for comparative prediction of the mechanical properties of jute fiber reinforced concrete

Abstract The fibers in concrete is necessary to enhance its engineering properties. Different types of fibers are used as a reinforcing material. Due to low cost, availability, and environmentally friendly, in recent years, the use of natural fibers in concrete has increased attention widely. Among all the natural fibers, jute fibers are very cheap and available in tropical countries. This study assesses different soft computing approaches: RSM (Response Surface Methodology), ANN (Artificial Neural Networks) and SVR (Support Vector Regression) for development of nonlinear empirical models that predict the mechanical properties (compressive and tensile strengths) of Jute Fiber Reinforced Concrete Composites (JFRCC). These properties are mainly dependent on water-cement (W/C) ratio, length and volume of jute fiber. The codes for ANN and SVR were written in MATLAB (R-2019a), while Minitab® 18 statistical software was used for generating experimental design matrix via Box-Behnken design (an experimental design for RSM). The data for the properties of JFRCC were obtained based on this design matrix and these data were utilized to develop, compare and evaluate the suggested models. The results indicate that SVR model performs much better than ANN and RSM models with respect to various performance measuring parameters (e.g., correlation coefficient, residual, relative error, mean absolute error, root mean squared error, and fractional bias) for predicting both compressive and tensile strengths.

[1]  E. García-Gonzalo,et al.  Predictive modelling of the higher heating value in biomass torrefaction for the energy treatment process using machine-learning techniques , 2018, Neural Computing and Applications.

[2]  Junjie Li,et al.  Prediction of long-term temperature effect in structural health monitoring of concrete dams using support vector machines with Jaya optimizer and salp swarm algorithms , 2019, Adv. Eng. Softw..

[3]  N. K. Bellam,et al.  Performance of an industrial source complex model: Predicting long‐term concentrations in an urban area , 1999 .

[4]  Hwai Chyuan Ong,et al.  Evaluation of the engine performance and exhaust emissions of biodiesel-bioethanol-diesel blends using kernel-based extreme learning machine , 2018, Energy.

[5]  Md Shah Alam,et al.  An experimental investigation and modeling approach of response surface methodology coupled with crow search algorithm for optimizing the properties of jute fiber reinforced concrete , 2020 .

[6]  Prasenjit Debnath,et al.  Prediction of fresh and hardened properties of self-compacting concrete using support vector regression approach , 2019, Neural Computing and Applications.

[7]  Zaher Mundher Yaseen,et al.  Predicting compressive strength of lightweight foamed concrete using extreme learning machine model , 2018, Adv. Eng. Softw..

[8]  S. Hossain,et al.  Multiobjective optimization of microalgae (Chlorella sp.) growth in a photobioreactor using Box‐Behnken design approach , 2018 .

[9]  Z. Shui,et al.  Understanding the porous aggregates carrier effect on reducing autogenous shrinkage of Ultra-High Performance Concrete (UHPC) based on response surface method , 2019, Construction and Building Materials.

[10]  L. Feo,et al.  Green Concrete: By-Products Utilization and Advanced Approaches , 2019, Sustainability.

[11]  Shad M. Sargand,et al.  Material Properties of Synthetic Fiber–Reinforced Concrete under Freeze-Thaw Conditions , 2018, Journal of Materials in Civil Engineering.

[12]  Taoreed O. Owolabi,et al.  Novel techniques for enhancing the performance of support vector regression chemo-metric in quantitative analysis of LIBS spectra , 2017 .

[13]  Rafat Siddique,et al.  Prediction of compressive strength of self-compacting concrete containing bottom ash using artificial neural networks , 2011, Adv. Eng. Softw..

[14]  Sunday Olusanya Olatunji,et al.  Estimation of surface energies of hexagonal close packed metals using computational intelligence technique , 2015, Appl. Soft Comput..

[15]  Uwe Reuter,et al.  A comparative study of machine learning approaches for modeling concrete failure surfaces , 2018, Adv. Eng. Softw..

[16]  Khandaker M. A. Hossain,et al.  Modeling shear strength of medium- to ultra-high-strength steel fiber-reinforced concrete beams using artificial neural network , 2017, Neural Computing and Applications.

[17]  M. Hoque,et al.  A Comparative Study of the Mechanical Properties of Jute Fiber and Yarn Reinforced Concrete Composites , 2018, Journal of Natural Fibers.

[18]  R. Ferreira,et al.  Optimization of metakaolin-based geopolymer reinforced with sisal fibers using response surface methology , 2019, Industrial Crops and Products.

[19]  N. Aslan,et al.  Application of Box-Behnken design and response surface methodology for modeling of some Turkish coals , 2007 .

[20]  N. Cristelo,et al.  Synthesis of alkaline cements based on fly ash and metallurgic slag: Optimisation of the SiO2/Al2O3 and Na2O/SiO2 molar ratios using the response surface methodology , 2019, Construction and Building Materials.

[21]  R. Haddad,et al.  Predicting fiber‐reinforced polymer–concrete bond strength using artificial neural networks: A comparative analysis study , 2020, Structural Concrete.

[22]  M. Hoque,et al.  Effect of jute yarn on the mechanical behavior of concrete composites , 2015, SpringerPlus.

[23]  M. S. Liew,et al.  Bond behaviour of nano-silica-modified self-compacting engineered cementitious composite using response surface methodology , 2019, Construction and Building Materials.

[24]  B. Cai,et al.  Shear Resistance Prediction of Post-fire Reinforced Concrete Beams Using Artificial Neural Network , 2019, International Journal of Concrete Structures and Materials.

[25]  Tianqi Liu,et al.  Using response surface regression method to evaluate the influence of window types on ventilation performance of Hong Kong residential buildings , 2019, Building and Environment.

[26]  Guowei Ma,et al.  Prediction of permeability and unconfined compressive strength of pervious concrete using evolved support vector regression , 2019, Construction and Building Materials.

[27]  Sunday O. Olatunji,et al.  Modeling thermal conductivity enhancement of metal and metallic oxide nanofluids using support vector regression , 2018 .

[28]  G. Bennett,et al.  Statistical evaluation of Lower Flammability Distance (LFD) using four hazardous release models , 1993 .

[29]  Tao Yu,et al.  A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems , 2019, International Journal of Energy Research.

[30]  Giovanni Plizzari,et al.  Influence of Steel and Macro-Synthetic Fibers on Concrete Properties , 2018, Fibers.

[31]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[32]  Xiao Ling Zhao,et al.  Fatigue behavior of concrete beams reinforced with glass- and carbon-fiber reinforced polymer (GFRP/CFRP) bars after exposure to elevated temperatures , 2019 .

[33]  Ahmed El-Shafie,et al.  Adaptive neuro-fuzzy inference system–based model for elevation–surface area–storage interrelationships , 2011, Neural Computing and Applications.

[34]  Mohammad S. Islam,et al.  Influence of jute fiber on concrete properties , 2018, Construction and Building Materials.

[35]  Sandip Kumar Lahiri,et al.  Development of a hybrid support vector machine and genetic algorithm model for regime identification of slurry transport in pipelines , 2010 .

[36]  Z. Ahmad,et al.  Hybrid Intelligent Modelling of the Viscoelastic Moduli of Coal Fly Ash Based Polymer Gel System for Water Shutoff Treatment in Oil and Gas Wells , 2019, The Canadian Journal of Chemical Engineering.

[37]  Mehmet Polat Saka,et al.  Optimum design of tied-arch bridges under code requirements using enhanced artificial bee colony algorithm , 2019, Adv. Eng. Softw..

[38]  Xiaofeng Li,et al.  Response-surface-model based on influencing factor analysis of subway tunnel temperature , 2019, Building and Environment.

[39]  Wei Xu,et al.  Modeling of ammonia conversion rate in ammonia synthesis based on a hybrid algorithm and least squares support vector regression , 2012 .

[40]  Pijush Samui,et al.  Support vector regression based models to predict fracture characteristics of high strength and ultra high strength concrete beams , 2013 .

[41]  Mohammad S. Islam,et al.  Principal Component and Multiple Regression Analysis for Steel Fiber Reinforced Concrete (SFRC) Beams , 2013 .

[42]  P. Akpinar,et al.  Investigation of the parameters influencing progress of concrete carbonation depth by using artificial neural networks , 2020 .

[43]  S. Agatonovic-Kustrin,et al.  Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. , 2000, Journal of pharmaceutical and biomedical analysis.

[44]  G. Murali,et al.  Influence of Treated Natural Jute Fiber on Flexural Properties of Reinforced Concrete Beams , 2018, International Journal of Engineering & Technology.

[45]  S. Hossain,et al.  Optimization of Biodiesel Production from Spent Palm Cooking Oil Using Fractional Factorial Design Combined with the Response Surface Methodology , 2016 .

[46]  Sunday O. Olatunji,et al.  Development and validation of surface energies estimator (SEE) using computational intelligence technique , 2015 .

[47]  Pak Kin Wong,et al.  Modeling and optimization of biodiesel engine performance using advanced machine learning methods , 2013 .

[48]  Junbin Gao,et al.  A Probabilistic Framework for SVM Regression and Error Bar Estimation , 2002, Machine Learning.

[49]  Jonas Mockus,et al.  Global Optimization and the Bayesian Approach , 1989 .

[50]  Uneb Gazder,et al.  Shear strength prediction of FRP reinforced concrete members using generalized regression neural network , 2019, Neural Computing and Applications.

[51]  B. Ali,et al.  Influence of glass fibers on mechanical and durability performance of concrete with recycled aggregates , 2019 .

[52]  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.