Open Collections

Ramezan Khani, Mohammad

University of British Columbia

In recent years, addressing the environmental impact of waste concrete in the construction industry has become increasingly challenging. Additionally, the quantity of discarded tires has significantly increased. Recycled aggregate concrete and rubber have emerged as viable alternatives to natural aggregate in conventional concrete due to their potential to help preserve natural resources in concrete mixtures. While incorporating both recycled aggregate and rubber in concrete mixtures can help produce greener concrete, these materials negatively impact the concrete’s mechanical properties, especially compressive strength. To mitigate these adverse effects and partially recover the losses in mechanical properties, researchers have recently started adding various fibers to concrete mixtures. Extensive engineering tests are essential for determining the mechanical properties of concrete, which are often expensive and time-consuming. To address this challenge, artificial intelligence and machine learning (ML) have been considered as data-driven alternatives. Numerous studies have explored the application of various ML methods in the prediction of concrete’s mechanical properties. However, these methods have some drawbacks. One major limitation is that the ML models are typically trained for one specific type of concrete and thus not applicable to other types, lacking generalizability. Another issue is the absence of sufficient data for training ML models. In real-world scenarios, the available data for novel types of concrete (e.g., fiber-reinforced rubberized recycled aggregate concrete) is painfully limited, which leads to a drastic performance drop in the trained models. This thesis employs a series of data-efficient ML models, namely, continual learning (CL) and transfer learning (TL) to develop a more generalized and adaptable ML framework for concrete mix design applications. Such models leverage the knowledge from related sources of data to improve the prediction performance in low-data regimes. Two types of TL, namely, domain adaptation and inductive TL are investigated. Additionally, a new CL method is proposed by incorporating two separate neural networks (i.e., main and auxiliary networks). The proposed CL framework can serve as a surrogate model in optimization tasks to obtain the optimal mix design for the desired mechanical properties of innovative concrete types.

Text

2025-02-01

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/88922

Civil Engineering

University of British Columbia

UBCO

http://creativecommons.org/licenses/by-nc-nd/4.0/