Estimation of the mechanical properties of oil palm shell aggregate concrete by novel AO-XGB model

Due to the steadily declining supply of natural coarse aggregates, the concrete industry has shifted to substituting coarse aggregates generated from byproducts and industrial waste. Oil palm shell is a substantial waste product created during the production of palm oil (𝑂𝑃𝑆). When considering the usage of 𝑂𝑃𝑆𝐶, building engineers must consider its uniaxial compressive strength (𝑈𝐶𝑆). Obtaining 𝑈𝐶𝑆 is expensive and time-consuming, machine learning may help. This research established five innovative hybrid 𝐴𝐼 algorithms to predict 𝑈𝐶𝑆. Aquila optimizer (𝐴𝑂) is used with methods to discover optimum model parameters. Considered models are artificial neural network (𝐴𝑂 − 𝐴𝑁𝑁), adaptive neuro-fuzzy inference system (𝐴𝑂 − 𝐴𝑁𝐹𝐼𝑆), support vector regression (𝐴𝑂 − 𝑆𝑉𝑅), random forest (𝐴𝑂 − 𝑅𝐹), and extreme gradient boosting (𝐴𝑂 − 𝑋𝐺𝐵). To achieve this goal, a dataset of 𝑂𝑃𝑆-produced concrete specimens was compiled. The outputs depict that all five developed models have justifiable accuracy in 𝑈𝐶𝑆 estimation process, showing the remarkable correlation between measured and estimated 𝑈𝐶𝑆 and models' usefulness. All in all, findings depict that the proposed 𝐴𝑂 − 𝑋𝐺𝐵 model performed more suitable than others in predicting 𝑈𝐶𝑆 of 𝑂𝑃𝑆𝐶 (with 𝑅 2 , 𝑅𝑀𝑆𝐸, 𝑀𝐴𝐸, 𝑉𝐴𝐹 and 𝐴15−index at 0.9678, 1.4595, 1.1527, 97.6469, and 0.9077). The proposed model could be utilized in construction engineering to ensure enough mechanical workability of lightweight concrete and permit its safe usage for construction aims.