About

Oguzhan Bayrak is a professor in the Fariborz Maseeh Department of Civil, Architectural and Environmental Engineering at The University of Texas at Austin. He serves as the director of the Ferguson Structural Engineering Laboratory and holds the Cockrell Family Chair in Engineering. His research interests include the behavior, analysis, and design of reinforced and prestressed concrete structures, bridge engineering, evaluation of structures in distress, use of fiber reinforced polymers for structural repair, and earthquake engineering. Bayrak received his B.S. in civil engineering from the Middle East Technical University and his M.S. and Ph.D. in civil engineering/structures from the University of Toronto. He has been recognized with numerous awards, including the Regents' Outstanding Teaching Award, the Joe J. King Professional Engineering Achievement Award, the Chester Paul Siess Award from the American Concrete Institute, and membership in the Academy of Distinguished Teachers at The University of Texas at Austin.

Research topics

• Computer Science
• Engineering
• Structural engineering
• Composite material
• Materials science
• Algorithm
• Geotechnical engineering
• Forensic engineering

Selected publications

• Explainable Boosting Machine for Structural Health Assessment: An Interpretable Approach to Data-Driven Structural Assessment

  2025-09-09

  articleOpen access

  Machine learning models used in structural health monitoring often act as "black boxes," offering predictions without justifying their logic. This lack of transparency undermines trust in safety-critical infrastructure assessments. To solve this, we propose the Explainable Boosting Machine, an interpretable method that explicitly links input variables (e.g., sensor data, and structural parameters) to predictions, enabling engineers to validate results against engineering principles. Real-world structural health monitoring and assessment struggles with sparse data, structural complexity, and hidden biases. Explainable Boosting Machine addresses these challenges by prioritizing transparency and physically meaningful insights. We apply it to predict the shear load- carrying capacity as a percentage of the ultimate load, based on the maximum diagonal crack widths observed on the surface of reinforced concrete beams—a critical metric for shear failure risk. Our results show that the model achieves an RMSE of 10.40% on the test dataset while identifying the influence of key predictors (e.g., beam depth, shear and skin reinforcement ratios). For instance, the model reveals that, for the same maximum diagonal crack width observed in two beams, a structure with a larger depth is farther from failure compared to the one with a smaller depth, enabling engineers to audit model logic and enhance structural assessment. This work advances trustworthy AI in structural health monitoring by bridging data-driven innovation and engineering accountability. Interpretability of explainable boosting machine ensures models remain consistent with physical laws, actionable for decision-making, and adaptable to realworld constraints. We advocate for machine learning frameworks that prioritize transparency as rigorously as predictive performance.

  PublisherOA PDFDOI

• Relaxing Shear Stress Limit for the End Region of Prestressed Concrete Girders

  Journal of Structural Engineering · 2025-10-13

  articleSenior author

  This paper investigates the potential for relaxing the 0.18fc′ shear stress limit imposed by AASHTO load-and-resistance factor design (LRFD) in the end regions of prestressed concrete girders with relatively large bottom flanges, which often exceed this limit based on an analysis of experimental data. Extreme scenarios involving key characteristics of prestressed girders, such as total prestress loss, strut angle, strand pattern, skewed end block, and inclined web, are proposed to evaluate maximum shear stress. The shear evaluation method, which is based on the strut-and-tie method (STM), is applied to predict maximum shear stresses under these extreme conditions. An analysis of the shear capacity in the end regions of girders with large bottom flanges, such as Texas standard prestressed girders and decked slab beams, indicates that such girders commonly exceed the 0.18fc′ limit, with ratios reaching up to 0.22fc′ depending on their size. These findings suggest that the shear stress limit could potentially be relaxed, providing a rational basis for more economical design considerations.

  PublisherDOI

• Direct tension behavior of concrete reinforced with high-chromium steel exhibiting continuous strain hardening

  Construction and Building Materials · 2025-10-17

  articleSenior author
  PublisherDOI

• Shear behavior in the end region of prestressed box girders: Influence of support configurations and reinforcement strengths

  Engineering Structures · 2025-02-28 · 4 citations

  articleSenior author
  PublisherDOI

• Evaluation method for shear strength of pretensioned concrete girder based on refined strut-and-tie model

  Structures · 2025-07-15 · 1 citations

  articleSenior author
  PublisherDOI

• Data-Driven Machine Learning for Predicting the Strength of Pretensioned Concrete Girders Considering Shear Failure Mode

  Journal of Structural Engineering · 2025-06-09 · 3 citations

  articleSenior author
  PublisherDOI

• Behavior of Reinforced Concrete Beams with Large-Diameter High-Strength Tension-Spliced Bars

  ACI Structural Journal · 2025-03-12 · 1 citations

  articleSenior author

  The American Concrete Institute (ACI) is a leading authority and resource worldwide for the development and distribution of consensus-based standards, technical resources, educational programs, certification programs, and proven expertise for individuals and organizations involved in concrete design, construction, and materials, who share a commitment to pursuing the best use of concrete.

  PublisherDOI

• Explainable boosting machine for structural health assessment of reinforced concrete beams using crack width measurements

  Automation in Construction · 2025-11-20 · 3 citations

  article
  PublisherDOI

• Shear Performance of RC Deep Beams with High-Strength Reinforcing Steel

  Journal of Structural Engineering · 2025-08-06

  articleSenior author

  With the increased need to construct megastructures such as long-span bridges and skyscrapers, there has been significant development in high-strength reinforcement for these structures. In line with this trend, specific provisions in design specifications such as ACI 318-19 and the 2020 AASHTO Load and Resistance Factor Design (LRFD) have allowed the application of high-strength reinforcing bars with yield strength reaching 689 MPa (100 ksi). However, high-strength reinforcing bars are restricted in discontinuity regions of a member, which are designed using the strut-and-tie method. This study aims to evaluate the application of high-strength steel bars in concrete beams following the current design codes. For this purpose, four large-scale rectangular deep beam shear tests were carried out on concrete beams reinforced with high-strength longitudinal and web reinforcement. The high-strength longitudinal reinforcement was reduced in proportion to the strength ratio between normal- and high-strength reinforcement, and its load-carrying capacity was evaluated under these conditions. Additionally, high-strength web reinforcement was utilized to evaluate the adequacy of the current web reinforcement ratio for crack control. The shear capacity and cracks width were monitored to assess the effect of high-strength steel on deep beam behavior and the applicability of current design codes such as ACI 318-19 and AASHTO LRFD (2020). The results demonstrate that the strut-and-tie method in current design codes effectively estimate the shear capacity of deep beams reinforced with high-strength steel for both longitudinal and web reinforcement. Furthermore, the design provisions for the web reinforcement ratio for crack control are also valid.

  PublisherDOI

• Evaluation and Proposal of Strut-and-Tie Method for the Design of Drilled Shaft Footings

  Journal of Structural Engineering · 2025-05-07 · 2 citations

  articleOpen accessSenior author

  This paper presents a practical, accurate, and reasonably conservative procedure for the design and analysis of drilled shaft footings, also referred to as pile caps. A database of drilled shaft footing tests was compiled from the literature to evaluate the accuracy of an existing design guide based on the three-dimensional (3D) strut-and-tie method (STM). It was concluded that strength estimations obtained with the existing 3D STM-based design guidelines were excessively conservative, and the accuracy of the method varied with key design parameters such as strut inclination and drilled shaft size. Key enhancements to the 3D STM are proposed to resolve existing limitations and ambiguities, including the definition of tie area for bottom mat reinforcement, 3D nodal geometry, nodal strength, concrete efficiency factor, and tie anchorage checks. These recommendations are supported by experimental evidence, including data from large-scale footing tests recently conducted by the authors, and are consistent with current design code provisions. The proposed method provides more accurate (less conservative) and less scattered (more reliable) strength estimations as compared to the existing recommendation. Lastly, a complete design example of a drilled shaft footing subjected to different loading scenarios is provided in the Supplemental Materials.

  PublisherOA PDFDOI

Recent grants

• Punching Shear Upgrade of Reinforced Concrete Flat Plates

  NSF · $232k · 2003–2007

• Use of Carbon Fiber Materials to Provide Alternate Load Paths in RC Structures Vulnerable to Progressive Collapse

  NSF · $321k · 2005–2009

Frequent coauthors

• James O. Jirsa

  42 shared

• Trevor D. Hrynyk

  University of Waterloo

  24 shared

• Robin Tuchscherer

  Northern Arizona University

  15 shared

• Michael D. Brown

  Bruker (United States)

  15 shared

• David B. Birrcher

  14 shared

• Shamim A. Sheikh

  13 shared

• Hossein Yousefpour

  Babol Noshirvani University of Technology

  12 shared

• Dean Deschenes

  12 shared

Awards & honors

• Joe J. King Professional Engineering Achievement Award – The…
• Academy of Distinguished Teachers member – The University of…
• Chester Paul Siess Award – American Concrete Institute (2014…
• Regents’ Outstanding Teaching Award – The University of Texa…
• Dean’s Award for Outstanding Engineering Teaching by an Assi…