Recycled powder (RP) serves as a potential and prospective substitute for cementitious materials in concrete. The compressive strength of RP mortar is a pivotal factor affecting the mechanical properties of RP concrete. The application of machine learning (ML) approaches in the engineering problems, particularly for predicting the mechanical properties of construction materials, leads to high prediction accuracy and low experimental costs. In this study, 204 groups of RP mortar compression experimental data are collected from the literature to establish a dataset for ML, including 163 groups in the training set and 41 groups in the test set. Four ensemble ML models, namely eXtreme Gradient-Boosting (XGBoost), Random Forest (RF), Light Gradient-Boosting Machine (LightGBM) and Adaptive Boosting (AdaBoost), were selected to predict the compressive strength of RP mortar. The comparative results demonstrate that XGBoost has the highest prediction accuracy when the a10-index, MAE, RMSE and R2 of the training set are 0.926, 1.596, 2.155 and 0.950 and the a10-index, MAE, RMSE and R2 of the test set are 0.659, 3.182, 4.285 and 0.842, respectively. SHapley Additive exPlanation (SHAP) is adopted to interpret the prediction process of XGBoost and explain the influence of influencing factors on the compressive strength of RP mortar. According to the importance of influencing factors, the order is the mass replacement rate of RP, the size of RP, the kind of RP and the water binder ratio of RP. The compressive strength of RP mortar decreases with the increase in the RP mass replacement rate. The compressive strength of RBP mortar is slightly higher than that of RCP mortar. Machine learning technologies will benefit the construction industry by facilitating the rapid and cost-effective evaluation of RP material properties.
Multi-objective optimization problems (MOPs) in structural engineering arise as a significant challenge in achieving a balance between prediction accuracy and efficiency of the surrogate models, which are conventionally adopted as mechanics-driven models or numerical models. Data-driven models, such as machine learning models, can be instrumental in resolving intricate structural engineering issues that cannot be tackled through mechanics-driven models. This study aims to address the challenges of multi-objective optimization punching shear design of fiber-reinforced polymer (FRP) reinforced flat slabs by using a data-driven surrogate model. Firstly, this study employs an advanced machine learning model, namely Natural Gradient Boosting (NGBoost), to predict the punching shear resistance of FRP reinforced flat slabs. The comparisons with other machine learning models, design provisions and empirical theory models illustrate that the NGBoost model has higher accuracy in predicting the punching shear resistance. Additionally, the NGBoost model is explained with Shapley Additive Explanation (SHAP), revealing that the slab’s effective depth is the primary factor affecting the punching shear resistance. Then, the formulated NGBoost model is adopted as a surrogate model in conjunction with the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) algorithm for multi-objective optimization design of FRP reinforced flat slabs subjected to punching shear. Through a case study, it is demonstrated that the Pareto-optimal set of the punching shear resistance and cost of the FRP reinforced flat slabs can be successfully obtained. By discussing the effects of design parameter changes on the results, it is also shown that increasing the slab’s effective depth is a relatively effective way to achieve higher punching shear resistance of FRP reinforced flat slabs.
19 March 2024 in Case Studies in Construction Materials