Performance Evaluation of Concrete Made with Plastic Waste Using Multi-Expression Programming

The immense production of plastic waste due to its non-biodegradable nature has become a major issue for the world. Several researchers have recently tried to incorporate plastic waste in building materials, particularly as a substitute for cement in concrete, using conventional experimental testing. However, it is difficult to examine the optimal mix design in experimental investigations due to time and resource constraints. Therefore, this study aims to provide robust multi-expression programming (MEP) based predictive equations to evaluate the compressive strength (CS) and tensile strength (TS) of concrete containing plastic waste. Based on the literature, a comprehensive data record of 276 and 235 samples of the CS and TS of plastic concrete was generated for model development. The models' prediction capabilities were assessed by evaluating the various statistical indicators and comparing the results with a multi-linear regression (MLR) model. Furthermore, a sensitivity analysis was conducted to find out the contribution of each parameter to the CS and TS of plastic concrete. According to the statistical findings, the MEP model demonstrated higher efficacy in prediction, with an R2 value of 0.87 and 0.89 for the CS and TS models. In addition, MEP generates a simple mathematical formula, which can be employed as a design tool for estimating the CS and TS of plastic concrete. In sensitivity analysis, age demonstrated the highest sensitivity (24.8% and 31%), demonstrating its substantial impact on the model's outputs. Cement (17.63% and 17.3%) and plastic (17.4% and 15.3%) have similar contributions to the CS and TS. These results are consistent with previous research, highlighting the agreement between the results of this study and the literature. Therefore, this study can be employed for sustainable construction practices.