Document Type : Regular Paper

**Authors**

Department of Civil Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran

10.22075/jrce.2020.19043.1358

**Abstract**

Artificial neural networks (ANNs) as a powerful approach have been widely utilized to demonstrate some of the engineering problems. A three-layer ANN including three neurons in the hidden layer is considered to produce a verified pattern for assessing the compressive strength of concrete incorporating metakaolin (MK). For this purpose, an extensive database including 469 experimental specimens was obtained from the literature. Next, novel equations utilizing the developed ANN approach were developed to measure the compressive strength of concrete mixtures incorporating MK. To examine the model accuracy a comparison between the proposed formulas based ANN and an empirical formula based nonlinear least-squares regression (NLSR) was carried out. The results show that the proposed formula based on the ANN yields a higher correlation coefficient and fewer errors compared to the NLSR method. An analysis based weights incorporating was utilized to show the significance of input variables. Accordingly, the ratio of fine aggregate to coarse aggregate exerts a dominant influence on the compressive strength of the concretes containing MK.

**Keywords**

- Artificial neural network
- Compressive strength of concrete
- Metakaolin
- Garson’s algorithm
- Nonlinear least squares regression

**Main Subjects**

[1] Y Sharifi, I Afshoon, Z Firoozjaei, M Momeni (2016). Utilization of Waste Glass Micro-particles in Producing Self-Consolidating Concrete Mixtures. International Journal of Concrete Structures and Materials 10 (3): 337–353.

[2] Y Sharifi, I Afshoon, Z Firoozjaie (2015). Fresh properties of self-compacting concrete containing ground waste glass microparticles as cementing material. Journal of Advanced Concrete Technology 13 (2): 50-66.

[3] I Afshoon, Y Sharifi (2014). Ground copper slag as a supplementary cementing material and its influence on the fresh properties of self-consolidating concrete. The IES Journal Part A: Civil & Structural Engineering 7 (4): 229-242.

[4] Gleize, PJP. Cyr, M. Escadeillas, G. (2007). Effects of metakaolin on autogenous shrinkage of cement pastes. Cement Concrete Compos; 29(2):80-7.

[5] Sabir, B.B. Wild, S. Bai, J. (2001). Metakaolin and calcined clays as pozzolans for concrete: a review. Cement Concrete Compos; 23(6): 441-54.

[6] Heidari A, Hashempour M, Chermahini MD. (2019) Influence of reactive MgO hydration and cement content on C&DW aggregate concrete characteristics. International Journal of Civil Engineering. 1;17(7):1095-106.

[7] Shakiba M, Rahgozar P, Elahi AR, Rahgozar (2018) R. Effect of Activated Pozzolan with Ca (OH) 2 and nano-SiO2 on Microstructure and Hydration of High-Volume Natural Pozzolan Paste. Civ Eng J. 30; 4(10):2437-49.

[8] Sharifi YA, Maghsoudi AA, Rahgozar RE. (2010) Ductility of Self-Consolidating Reinforced Concrete Beams. Civil Engineering Infrastructures Journal. 1;44(4):497-506.

[9] Kakvand, P., Rahgozar, R., Ghalehnovi, M. and Irandegani, M.A. (2014) ‘Experimentally analysing compressive and tensile strengths of concrete containing steel waste fibers’, Int. J. Structural Engineering, Vol. 5, No. 2, pp.132–141.

[10] Wild, S. Khatib, J.M. Jones, A. (1996). Relative strength, pozzolanic activity and cement hydration in superplasticised metakaolin concrete. Cement and Concrete Research, Vol. 26, No. 10, pp. 1537-1544.

[11] Vu, D.D. Stroeven, P. Bui, V.B. (2001). Strength and durability aspects of calcined kaolin-blended Portland cement mortar and concrete. Cement Concrete Compos; 23 (6):471-8.

[12] Parande, A.K. Babu, B.R. Karthik, M.A. (2008) Deepak Kumaar KK, Palaniswamy N. Study on strength and corrosion performance for steel embedded in metakaolin blended. concrete/mortar. Constr Build Mater; 22(3): 127-34.

[13] Li, Q. Geng, H. Shui, Zh. Huang, Y. (2015). Effect of metakaolin addition and seawater mixing on the properties and hydration of concrete. Applied Clay Science 115 - 51–60.

[14] Safarzadegan Gilan, S. Bahrami Jovein, H. Ramezanianpour, A. (2012). Hybrid support vector regression – Particle swarm optimization for prediction of compressive strength and RCPT of concretes containing metakaolin. Construction and Building Materials 34 -321–329.

[15] Wong, H.S, Abdul Razak, H. (2005). Efficiency of calcined kaolin and silica fume as cement replacement material for strength performance. Cement and Concrete Research 35 - 696– 702.

[16] Poon, C.S. Kou S.C. Lam, L. (2006). Compressive strength, chloride diffusivity and pore structure of high performance metakaolin and silica fume concrete. Construction and Building Materials 20-858–865.

[17] Ramezanianpour, A.A. Bahrami Jovein, H. (2012). Influence of metakaolin as supplementary cementing material on strength and durability of concretes. Construction and Building Materials 30- 470–479.

[18] Guneyisi, E. Gesog˘lu, M. Karaog˘lu, S. Mermerdaş, K. (2012). Strength, permeability and shrinkage cracking of silica fume and metakaolin concretes. Construction and Building Materials 34-120–130.

[19] Mohammadi, M. Mir Moghtadaei, R. Ashraf Samani, N. (2014). Influence of silica fume and metakaolin with two different types of interfacial adhesives on the bond strength of repaired concrete. Construction and Building Materials 51-141–150.

[20] Khatib, J.M. (2008). Metakaolin concrete at a low water to binder ratio. Construction and Building Materials 22 -1691–1700.

[21] Duana, P. Shuia, Z.h. Chena, W. Shenb, C.h. (2013). Enhancing microstructure and durability of concrete from ground granulated blast furnace slag and metakaolin as cement replacement materials. J. Mater. Res. Technol; 2(1):52-59.

[22] Khatib, M.J. Hibbert, J.J. (2005). Selected engineering properties of concrete incorporating slag and metakaolin. Construction and Building Materials 19-460–472.

[23] Naderpour H, Eidgahee DR, Fakharian P, Rafiean AH, Kalantari SM. (2019). A new proposed approach for moment capacity estimation of ferrocement members using Group Method of Data Handling. Engineering Science and Technology, an International Journal. 23 (2), 382-391.

[24] Rezazadeh Eidgahee D, Haddad A, Naderpour H. (2018). Evaluation of shear strength parameters of granulated waste rubber using artificial neural networks and group method of data handling. Scientia Iranica.

[25] Naderpour H, Nagai K, Fakharian P, Haji M. (2019). Innovative models for prediction of compressive strength of FRP-confined circular reinforced concrete columns using soft computing methods. Composite Structures. 215: 69-84.

[26] Tohidi S. and Sharifi Y. (2015). Empirical modeling of distortional buckling strength of half-through bridge girders via stepwise regression method. Advances in Structural Engineering, Vol. 18, No. 9, pp. 1383-1397.

[27] Hosseinpour M., Sharifi H. and Sharifi Y. (2018). Stepwise regression modeling for compressive strength assessment of mortar containing metakaolin. International Journal of Modelling and Simulation, Vol. 38, No. 4, pp. 207-215.

[28] Sharifi Y. and Moghbeli A. (2019). Stepwise Regression for shear capacity assessment of steel fiber reinforced concrete beams. Journal of Rehabilitation in Civil Engineering, Vol. 7, No. 2, pp. 95-108.

[29] Eidgahee DR, Rafiean AH, Haddad A. A (2019). Novel Formulation for the Compressive Strength of IBP-Based Geopolymer Stabilized Clayey Soils Using ANN and GMDH-NN Approaches. Iranian Journal of Science and Technology, Transactions of Civil Engineering.

[30] Sharifi, Y. Hosseinpour, M. (2019). Adaptive neuro-fuzzy inference system and stepwise regression for compressive strength assessment of concrete containing metakaolin. International Journal of Optimization in Civil Engineering; 9 (2):251-272.

[31] Naderpour H, Rafiean AH, Fakharian P. Compressive strength prediction of environmentally friendly concrete using artificial neural networks. Journal of Building Engineering 16: 213–219.

[32] Naderpour H, Nagai K, Haji M, Mirrashid M. Adaptive neuro‐fuzzy inference modelling and sensitivity analysis for capacity estimation of fiber reinforced polymer‐strengthened circular reinforced concrete columns. Expert Systems. 2019:e12410.

[33] Naderpour H, Kheyroddin A, Amiri GG. Prediction of FRP-confined compressive strength of concrete using artificial neural networks. Composite Structures. 2010 Nov 1;92(12):2817-29.

[34] Naderpour H, Alavi SA. A proposed model to estimate shear contribution of FRP in strengthened RC beams in terms of Adaptive Neuro-Fuzzy Inference System. Composite Structures. 2017 Jun 15;170:215-27.

[35] Sharifi Y., Lotfi F. and Moghbeli A. Compressive strength prediction by ANN formulation approach for FRP confined rectangular concrete columns. Journal of Rehabilitation in Civil Engineering, 2019, Vol. 7, No. 3, pp. 182-203.

[36] Sharifi Y., Moghbeli A., Hosseinpour M. and Sharifi H. Neural networks for lateral torsional buckling strength assessment of cellular steel I-beams. Advances in Structural Engineering, 2019, Vol. 22, No. 9, pp. 2192-2202.

[37] Sharifi Y., Moghbeli A., Hosseinpour M. and Sharifi H. Study of Neural Network Models for the Ultimate Capacities of Cellular Steel Beams. Iran J Sci Technol Trans Civ Eng, (2020) 44:579–589.

[38] Sharifi Y., Hosseinpour M., Moghbeli A., and Sharifi H. Lateral Torsional Buckling Capacity Assessment of Castellated Steel Beams Using Artificial Neural Networks. Int J Steel Struct, 2019, Vol. 19, 1408–1420.

[39] Sharifi Y., Mohammadi N., and Moghbeli A. Shear capacity assessment of reinforced concrete deep beams using artificial neural network. Journal of Concrete Structures and Materials, 2018, Vol. 3, No. 5, pp. 30-43.

[40] Tohidi, S. and Sharifi, Y. (2015). Neural networks for inelastic distortional buckling capacity assessment of steel I-beams. Thin-Walled Structures, Vol. 94, No. 9, pp. 359-371.

[41] Tohidi, S. and Sharifi, Y. (2014). Inelastic lateral-torsional buckling capacity of corroded web opening steel beams using artificial neural networks. The IES Journal Part A: Civil & Structural Engineering, Vol. 8, No. 1, pp. 24-40.

[42] Sharifi, Y. and Tohidi, S. (2014). Lateral-torsional buckling capacity assessment of web opening steel girders by artificial neural networks–elastic investigation. Frontiers of Structural and Civil Engineering, Vol. 8, No. 2, pp. 167–177.

[43] Sharifi Y, Tohidi S. (2014). Ultimate Capacity Assessment of Web Plate Beams with Pitting Corrosion Subjected to Patch Loading by Artificial Neural Networks. Advanced Steel Construction, Vol. 10, No. 3, pp. 325-350.

[44] Tohidi, S. and Sharifi, Y. (2014). A new predictive model for restrained distortional buckling strength of half-through bridge girders using artificial neural network. KSCE Journal of Civil Engineering, Vol. 10, No. 3, pp. 325–350.

[45] Tohidi, S. and Sharifi, Y. (2014). Load-carrying capacity of locally corroded steel plate girder ends using artificial neural network. Thin-Walled Structures, Vol. 100, No. 1, pp. 48–61.

[46] Sharifi Y., Moghbeli A. Rahmatian M. and Moghbeli K. (2020). Shear Strength Assessment of Slender Reinforced Normal Concrete Beams using Artificial Neural Networks. Journal of Concrete Structures and Materials, Vol. 4, No. 8, pp. 173-190.

[47] Ghoddousi, P., Abbasi, A. M., Shahrokhinasab, E., Abedin, M. (2019). Prediction of Plastic Shrinkage Cracking of Self-Compacting Concrete. Advances in Civil Engineering, 2019.

[48] Cybenko, J. (1989), Approximations by super positions of a sigmoidal function, Math Control Signal Syst, 2, 303–14.

[49] Marquardt, D. (1963). An algorithm for least squares estimation of non-linear parameters. J Soc Ind Appl Math, Vol. 11, pp. 431–41.

[50] Hagan, M.T. Menhaj, M.B. (1994). Training feed forward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, Vol. 5, No. 6, pp. 861-867.

[51] Hristev R.M. (1998). The ANN book. GNU public license.

[52] Gandomi, A.H. Tabatabaei, S.M. Moradian, M.H. Radfar, A. Alavi, A.H. (2011). A New Prediction Model for the Load Capacity of Castellated Steel Beams. Journal of Constructional Steel Research, Vol. 67, pp. 1096-1105.

[53] Frank, IE. Todeschini, R. (1994). The data analysis handbook, Amsterdam: Elsevier.

[54] Gandomi, A.H. Mohammadzadeh, S. Pérez-Ordó˜nezc, J.L. Alavi A.H. (2014). Linear genetic programming for shear strength prediction of reinforced concrete beams without stirrups. Applied Soft Computing, Vol. 19, pp. 112–120.

[55] Smith, G.N. (1986). Probability and Statistics in Civil Engineering. Collins, London.

[56] Garson, G. D. (1991). Interpreting neural-network connection weights. AI Expert, Vol. 6, pp. 47–51.

[57] Gandomi, A.H. Alavi, A.H. Mousavi, M. Tabatabaei, S.M. (2011). A hybrid computational approach to derive new ground-motion prediction equations. Eng. Appl. Artif. Intell. Vol. 24, No. 4, pp. 717–732.

[58] Gandomi, A.H. Alavi, A.H. Sadegh Kazemi C. Gandomi, M. (2014). Formulation of shear strength of slender RC beams using gene expression programming, part I: Without shear reinforcement. Automation in Construction, Vol. 42, pp. 112–121.

Autumn 2020

Pages 15-27

**Receive Date:**01 November 2019**Revise Date:**09 May 2020**Accept Date:**11 May 2020