Explainable Ensemble Learning and Multilayer Perceptron Modeling for Compressive Strength Prediction of Ultra-High-Performance Concrete

Abstract

first_pagesettingsOrder Article Reprints Open AccessArticle Explainable Ensemble Learning and Multilayer Perceptron Modeling for Compressive Strength Prediction of Ultra-High-Performance Concrete by Yaren Aydın 1ORCID,Celal Cakiroglu 2ORCID,Gebrail Bekdaş 1,*ORCID andZong Woo Geem 3,*ORCID 1 Department of Civil Engineering, Istanbul University-Cerrahpaşa, 34320 Istanbul, Turkey 2 Department of Civil Engineering, Turkish-German University, 34820 Istanbul, Turkey 3 Department of Smart City, Gachon University, Seongnam 13120, Republic of Korea * Authors to whom correspondence should be addressed. Biomimetics 2024, 9(9), 544; https://doi.org/10.3390/biomimetics9090544 Submission received: 27 June 2024 / Revised: 23 August 2024 / Accepted: 5 September 2024 / Published: 9 September 2024 (This article belongs to the Special Issue Bionic Design & Lightweight Engineering) Downloadkeyboard_arrow_down Browse Figures Versions Notes

Abstract The performance of ultra-high-performance concrete (UHPC) allows for the design and creation of thinner elements with superior overall durability. The compressive strength of UHPC is a value that can be reached after a certain period of time through a series of tests and cures. However, this value can be estimated by machine-learning methods. In this study, multilayer perceptron (MLP) and Stacking Regressor, an ensemble machine-learning models, is used to predict the compressive strength of high-performance concrete. Then, the ML model’s performance is explained with a feature importance analysis and Shapley additive explanations (SHAPs), and the developed models are interpreted. The effect of using different random splits for the training and test sets has been investigated. It was observed that the stacking regressor, which combined the outputs of Extreme Gradient Boosting (XGBoost), Category Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), and Extra Trees regressors using random forest as the final estimator, performed significantly better than the MLP regressor. It was shown that the compressive strength was predicted by the stacking regressor with an average R2 score of 0.971 on the test set. On the other hand, the average R2 score of the MLP model was 0.909. The results of the SHAP analysis showed that the age of concrete and the amounts of silica fume, fiber, superplasticizer, cement, aggregate, and water have the greatest impact on the model predictions.