Bulbul Abdulrahman Mohamad Radwan, Khan Kaffayatullah, Nafees Afnan, Amin Muhammad Nasir, Ahmad Waqas, Usman Muhammad, Nazar Sohaib, Arab Abdullah Mohammad Abu
Department of Civil and Environmental Engineering, College of Engineering, King Faisal University, Al-Ahsa 31982, Saudi Arabia.
Department of Civil Engineering, COMSATS University Islamabad, Abbottabad 22060, Pakistan.
Materials (Basel). 2022 Nov 3;15(21):7764. doi: 10.3390/ma15217764.
In recent decades, a variety of organizational sectors have demanded and researched green structural materials. Concrete is the most extensively used manmade material. Given the adverse environmental effect of cement manufacturing, research has focused on minimizing environmental impact and cement-based product costs. Metakaolin (MK) as an additive or partial cement replacement is a key subject of concrete research. Developing predictive machine learning (ML) models is crucial as environmental challenges rise. Since cement-based materials have few ML approaches, it is important to develop strategies to enhance their mechanical properties. This article analyses ML techniques for forecasting MK concrete compressive strength (fc'). Three different individual and ensemble ML predictive models are presented in detail, namely decision tree (DT), multilayer perceptron neural network (MLPNN), and random forest (RF), along with the most effective factors, allowing for efficient investigation and prediction of the fc' of MK concrete. The authors used a database of MK concrete mechanical features for model generalization, a key aspect of any prediction or simulation effort. The database includes 551 data points with relevant model parameters for computing MK concrete's fc'. The database contains cement, metakaolin, coarse and fine aggregate, water, silica fume, superplasticizer, and age, which affect concrete's fc' but were seldom considered critical input characteristics in the past. Finally, the performance of the models is assessed to pick and deploy the best predicted model for MK concrete mechanical characteristics. K-fold cross validation was employed to avoid overfitting issues of the models. Additionally, ML approaches were utilized to combine SHapley Additive exPlanations (SHAP) data to better understand the MK mix design non-linear behaviour and how each input parameter's weighting influences the total contribution. Results depict that DT AdaBoost and modified bagging are the best ML algorithms for predicting MK concrete fc' with R = 0.92. Moreover, according to SHAP analysis, age impacts MK concrete fc' the most, followed by coarse aggregate and superplasticizer. Silica fume affects MK concrete's fc' least. ML algorithms estimate MK concrete's mechanical characteristics to promote sustainability.
近几十年来，各个组织部门都对绿色结构材料提出了需求并进行了研究。混凝土是使用最广泛的人造材料。鉴于水泥生产对环境的不利影响，研究主要集中在将环境影响和水泥基产品成本降至最低。偏高岭土（MK）作为一种添加剂或部分水泥替代品，是混凝土研究的一个关键课题。随着环境挑战的增加，开发预测性机器学习（ML）模型至关重要。由于基于水泥的材料很少有机器学习方法，因此制定提高其力学性能的策略很重要。本文分析了用于预测MK混凝土抗压强度（fc'）的机器学习技术。详细介绍了三种不同的个体和集成ML预测模型，即决策树（DT）、多层感知器神经网络（MLPNN）和随机森林（RF），以及最有效的因素，以便对MK混凝土的fc'进行高效的研究和预测。作者使用了一个MK混凝土力学特性数据库进行模型泛化，这是任何预测或模拟工作的一个关键方面。该数据库包括551个数据点以及用于计算MK混凝土fc'的相关模型参数。数据库包含水泥、偏高岭土、粗骨料和细骨料、水、硅灰、高效减水剂和龄期，这些因素会影响混凝土的fc'，但在过去很少被视为关键输入特性。最后，对模型的性能进行评估，以挑选和部署用于MK混凝土力学特性的最佳预测模型。采用K折交叉验证来避免模型的过拟合问题。此外，利用机器学习方法结合SHapley加性解释（SHAP）数据，以更好地理解MK配合比设计的非线性行为以及每个输入参数的权重如何影响总贡献。结果表明，DT AdaBoost和改进的装袋法是预测MK混凝土fc'的最佳机器学习算法，相关系数R = 0.92。此外，根据SHAP分析，龄期对MK混凝土fc'的影响最大，其次是粗骨料和高效减水剂。硅灰对MK混凝土fc'的影响最小。机器学习算法估计MK混凝土的力学特性以促进可持续性。
