Prediction of concrete coefficient of thermal expansion and other properties using machine learning. (30th September 2019)

• Record Type: Journal Article
• Authors: Nilsen, Vanessa; Pham, Le T.; Hibbard, Michael; Klager, Adam; Cramer, Steven M.; Morgan, Dane
• Is Part Of: Construction & building materials. Volume 220(2019)
• Page Start: 587
• Page End: 595
• Publication Date: 2019-09-30
• Subjects: Concrete -- Coefficient of thermal expansion -- Machine learning -- Random forest -- Compressive strength; Building materials -- Periodicals; 624.18
• DOI: 10.1016/j.conbuildmat.2019.05.006
• Languages: English
• ISSNs: 0950-0618

Abstract

Highlights: A machine learning model effectively predicted concrete coefficient of thermal expansion. The model was more accurate than level-2 and level-3 predictions. The model was also effective in predicting other concrete properties. Abstract: The coefficient of thermal expansion (CTE) significantly influences the performance of concrete. However, CTE measurements are both time consuming and expensive; therefore, CTE is often predicted from empirical equations based on historical data and concrete composition. In this work we demonstrate the application of linear regression and random forest machine learning methods to predict CTE and other properties from a database of Wisconsin concrete mixes. The random forest model accuracy, as assessed by cross-validation, is found to be significantly better than the American Association of State Highway and Transportation Officials (AASHTO) recommended prediction methods for CTE, denoted as level-2 and level-3.