Mechanical behaviour of E-waste aggregate concrete using a novel machine learning algorithm: Multi expression programming (MEP)

Abstract

Technological advancement encourages the usage of electronic appliances in daily life and makes it possible for users to switch to more advanced devices very easily and at a reasonable cost. As new devices are produced and manufactured at an alarming rate around the world, outdated old devices become e-waste. This research work aims at using a popular machine learning (ML) method known as Multi-expression programming (MEP) to examine the compressive strength (CS) and tensile strength (TS) of E-waste aggregate-based concrete (EWAC). 279 and 105 scientific entries for CS and TS, respectively, were culled from reputable literature. The ten convincing input parameters selected based on multicollinearity analysis (correlation matrix and variance inflation factor) were E-waste coarse aggregate (ECA%), E-waste fine aggregate (EFA%), water-cement ratio (w/c), age of concrete (A in days), fine aggregate water-absorption (WAF%), coarse aggregate water-absorption (WAC%), E-waste aggregate water-absorption (WAE%), E-waste aggregate specific-gravity (SGE), coarse aggregate specific-gravity (SGC), and fine aggregate specific-gravity (SGF). To estimate the functioning of the projected models, root-squared-error (RSE), mean-absolute error (MAE), mean-absolute-percent error (MAPE), Nash-Sutcliffe-efficiency (NSE), root-mean-squared error (RMSE), objective-function (OF), coefficient-of-correlation (R), root-mean-squared-logarithmic error (RMSLE), and performance-index (PI) were used. The R-value for both MEP models exceeds 0.9, showing “excellent” with MAPE values in the testing stage equals to 6.68% and 6.78% for the CS-MEP and TS-MEP models, respectively. While for non-linear regression (NLR) models, the MAPE exceeds 20% and 30%, respectively, making them unsuitable for future prediction. Moreover, the sensitivity analysis carried out to evaluate the MEP equations' consistency with the observed physical phenomena, indicates that for both CS and TS, the w/c, ECA%, and EFA% remain the most sensitive parameters with a sensitivity index greater than 0.60. Due to the accuracy and viability of developed models, they can be used to reduce the time needed for laborious laboratory tests.

Keywords

• Electronic waste
• Sustainability
• Artificial intelligence (AI)
• Machine learning (ML)
• Mechanical behaviour