Bio-inspired based meta-heuristic approach for predicting the strength of fiber-reinforced based strain hardening cementitious composites

Yasar Khan; Adeel Zafar; Muhammad Faisal Rehman; Muhammad Faisal Javed; Bawar Iftikhar; Yaser Gamil

doi:10.1016/j.heliyon.2023.e21601

Bio-inspired based meta-heuristic approach for predicting the strength of fiber-reinforced based strain hardening cementitious composites

Heliyon. 2023 Nov 2;9(11):e21601. doi: 10.1016/j.heliyon.2023.e21601. eCollection 2023 Nov.

Authors

Yasar Khan¹, Adeel Zafar¹, Muhammad Faisal Rehman², Muhammad Faisal Javed³, Bawar Iftikhar³, Yaser Gamil^{4

5}

Affiliations

¹ Department of Structural Engineering, Military College of Engineering (MCE), National University of Science and Technology (NUST), Islamabad 44000, Pakistan.
² University of Engineering and Technology Peshawar, Abbottabad Campus, Pakistan.
³ Department of Civil Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, 22060, Pakistan.
⁴ Department of Civil, Environmental and Natural Resources Engineering, Luleå University of Technology, Sweden.
⁵ Department of Civil Engineering, School of Engineering, Monash University Malaysia, Jalan Lagoon Selatan, 47500 Bandar Sunway, Selangor, Malaysia.

Abstract

A recently introduced bendable concrete having hundred times greater strain capacity provides promising results in repair of engineering structures, known as strain hardening cementitious composites (SHHCs). The current research creates new empirical prediction models to assess the mechanical properties of strain-hardening cementitious composites (SHCCs) i.e., compressive strength (CS), first crack tensile stress (TS), and first crack flexural stress (FS), using gene expression programming (GEP). Wide-ranging records were considered with twelve variables i.e., cement percentage by weight (C%), fine aggregate percentage by weight (F_agg%), fly-ash percentage by weight (FA%), Water-to-binder ratio (W/B), super-plasticizer percentage by weight (SP%), fiber amount percentage by weight (F_ib%), length to diameter ratio (L/D), fiber tensile strength (F_TS), fiber elastic modulus (F_EM), environment temperature (ET), and curing time (CT). The performance of the models was deduced using correlation coefficient (R) and slope of regression line. The established models were also assessed using relative root mean square error (RRMSE), Mean absolute error (MAE), Root squared error (RSE), root mean square error (RMSE), objective function (OBF), performance index (PI) and Nash-Sutcliffe efficiency (NSE). The resulting mathematical GP-based equations are easy to understand and are consistent disclosing the originality of GEP model with R in the testing phase equals to 0.8623, 0.9269, and 0.8645 for CS, TS and FS respectively. The PI and OBF are both less than 0.2 and are in line with the literature, showing that the models are free from overfitting. Consequently, all proposed models have high generalization with less error measures. The sensitivity analysis showed that C%, F_agg%, and ET are the most significant variables for all three models developed with sensitiveness index higher than 10 %. The result of the research can assist researchers, practitioners, and designers to assess SHCC and will lead to sustainable, faster, and safer construction from environment-friendly waste management point of view.

Keywords: Compressive strength; Engineering cementitious composites (ECC); Flexural stress; Gene expression programming (GEP); Machine learning (ML); Tensile stress.