Understanding Complex Chemo-Physical Distress and Mitigation Mechanisms of Structural Concrete Using a Physics-Informed Machine Learning Method

Author

Md Asif Rahman, Boise State UniversityFollow

Publication Date

12-2023

Date of Final Oral Examination (Defense)

11-3-2023

Type of Culminating Activity

Dissertation - Boise State University Access Only

Degree Title

Doctor of Philosophy in Computing

Department Filter

Computer Science

Department

Computer Science

Supervisory Committee Chair

Yang Lu, Ph.D.

Supervisory Committee Member

Tim Andersen, Ph.D.

Supervisory Committee Member

Edoardo Serra, Ph.D.

Abstract

Concrete is a widely utilized construction material globally, composed of a mixture of cement, water, and aggregates. It possesses exceptional strength and durability, making it an ideal choice for various construction projects. Nonetheless, concrete structures undergo degradation over time, necessitating a deeper understanding of the underlying chemical and physical processes. One crucial chemical process in concrete formation is cement hydration, which involves intricate reactions and physical transformations, resulting in a solid and enduring material. This exothermic process yields calcium hydroxide (CH) and releases heat, contributing to temperature fluctuations that can impact the early-age performance of concrete. It also plays a role in energy production and carbon emissions. To address these challenges, the use of supplementary materials is a prudent strategy. Selecting appropriate supplementary cementitious materials (SCMs) can reduce carbon emissions and enhance the overall strength of concrete. On the other hand, a sulfate attack arises from harmful chemical reactions that lead to the formation of ettringite and undesirable expansion within concrete. This issue can occur when pyrrhotite-rich aggregates react with the hydrated products of the cement paste, resulting in a series of chemical reactions that impact the long-term performance of concrete. To tackle these challenges, there is a pressing need for a robust model that can predict the chemo-physical behavior of cement-concrete. This research delves into the application of physics-informed machine learning (PIML), an interdisciplinary approach that combines physics and machine learning (ML) to improve model performance and interpretability. The primary emphasis of this study lies in the creation of physics-informed neural network (PINN) models aimed at quantifying and mitigating distress issues in cement-concrete. The outcomes of this research are documented in three individual chapters, each corresponding to a separate journal manuscript.

In the first manuscript, the focus lies on the introduction of PINN-CHK, a physics-informed neural network model designed to predict cement hydration kinetics. Its primary objective is to explore temperature variations during the initial phases of cement paste hydration. PINN-CHK harnesses data-driven methodologies to construct an accurate predictive model, incorporating material characteristics and maturity functions associated with cement hydration. It adeptly aligns with both empirical findings and the fundamental principles of physics, resulting in a simulation that operates without the need for traditional mesh structures.

The second manuscript is dedicated to the development of EcoBlendNet, an innovative physics-informed neural network, designed to scrutinize carbon emissions during the enhancement of cement hydration with supplementary cementitious materials. EcoBlendNet amalgamates empirical data with the chemical and physical facets of cement hydration in a heated cement paste, providing precise predictions of concrete maturity and compressive strength. It accomplishes this by accurately capturing the temperature increases during the early stages of hydration for various mixtures, including Portland cement, cement-fly ash blends, and cement-slag blends. Notably, SCMs prove effective in mitigating temperature rises while maintaining strength development.

The third manuscript addresses PyrrhotiteNet, a pioneering sequential structure based on a physics-informed neural network. PyrrhotiteNet aims to handle coupled differential equations conjugating both pyrrhotite oxidation and sulfate attack in concrete. By leveraging experimental data and incorporating physical insights, PyrrhotiteNet allows the model to quantify sulfate ion concentration and concrete expansion, facilitating the assessment and prediction of sulfate attack's extent, distribution, and progression. The validated PyrrhotiteNet aligns with real dam measurements and can predict future structural displacement with minimal training data. In essence, the developed PyrrhotiteNet represents a mesh-free, data-driven platform for accurate predictions of concrete expansion and displacement, rivaling traditional finite element solvers.

Hence, the ultimate result of this study reveals a groundbreaking physics-informed modeling approach that effectively bridges the gap between theoretical principles and real-world applications. This approach offers an enticing departure from traditional finite element solvers and machine learning techniques, fostering a deeper comprehension of cement hydration, use of SCMs, and sulfate attack in concrete, to precisely predict maturity, strength development, and overall concrete performance. When integrated into infrastructure asset management methodologies, it carries the potential to enhance the design of durable concrete structures, facilitating prompt maintenance as well as eco-friendly solution.

DOI

https://doi.org/10.18122/td.2193.boisestate

Recommended Citation

Rahman, Md Asif, "Understanding Complex Chemo-Physical Distress and Mitigation Mechanisms of Structural Concrete Using a Physics-Informed Machine Learning Method" (2023). Boise State University Theses and Dissertations. 2193.
https://doi.org/10.18122/td.2193.boisestate