Browsing by Author "Ciftcioglu, AO"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Causal discovery and inference for evaluating fire resistance of structural members through causal learning and domain knowledge
    Naser, MZ; Ciftcioglu, AO
    Experiments remain the gold standard to establish an understanding of fire-related phenomena. A primary goal in designing tests is to uncover the data generating process (i.e., the how and why the observations we see come to be); or simply what causes such observations. Uncovering such a process not only advances our knowledge but also provides us with the capability to be able to predict phenomena accurately. This paper presents an approach that leverages causal discovery and causal inference to evaluate the fire resistance of structural members. In this approach, causal discovery algorithms are adopted to uncover the causal structure between key variables pertaining to the fire resistance of reinforced concrete columns. Then, companion inference algorithms are applied to infer (estimate) the influence of each variable on the fire resistance given a specific intervention. Finally, this study ends by contrasting the algorithmic causal discovery with that obtained from domain knowledge and traditional machine learning. Our findings clearly show the potential and merit of adopting causality into our domain.
  • No Thumbnail Available
    Item
    Taguchi-enhanced Grey Wolf Optimizer for robust design of cellular beams
    Ciftcioglu, AO; Ustuner, B; Dogan, E; Arafat, S; Hussain, A
    This research presents a comprehensive comparative analysis of optimization techniques for achieving the optimal design of cellular beams. The incorporation of gaps within cellular beams reduces the weight of the beam and increases section height, resulting in the production of lighter and stronger sections. The Taguchi method is employed to fine-tune the parameters of the Grey Wolf Optimizer, enabling the achievement of a robust design. The performance of each algorithm is evaluated through three design examples, facilitating comprehensive comparisons among the seven algorithms. Moreover, the study encompasses the modeling and analysis of optimally designed cellular beams using finite element software.
  • No Thumbnail Available
    Item
    Hiding in plain sight: What can interpretable unsupervised machine learning and clustering analysis tell us about the fire behavior of reinforced concrete columns?
    Ciftcioglu, AO; Naser, MZ
    The role of machine learning (ML) continues to rise in the structural fire engineering area. Noting the widespread of supervised ML approaches, such methods are being heavily utilized nowadays. On the other hand, little in-terest has been dedicated to unsupervised ML. Unlike supervised learning, unsupervised learning algorithms are trained using data that is neither classified nor labeled, thus, allowing the algorithm , without guidance, to identify unseen patterns , decode hidden structures of complex phenomena residing in data. In this pursuit, this study presents findings obtained from one of the earliest investigations aimed to explore the potential of unsupervised and interpretable machine learning (ML) clustering analysis to investigate the response of rein-forced concrete (RC) columns under fire conditions. We used four algorithms (namely, K-Means, Hierarchical, Fuzzy C-Means, and DBSCAN) to cluster over 140 fire-exposed RC columns. Results from our clustering analysis show that the performance of such columns can be distinctly grouped into unique clusters. Our findings allow structural fire engineers to 1) identify and avoid RC columns with poor fire performance and, when possible, 2) upgrade the features/characteristics of columns of poor fire response to achieve an improved behavior. Overall, our analysis indicates that fire-exposed RC columns naturally fit into four clusters - each with unique properties and response - that are governed by the material, geometric and loading features.
  • No Thumbnail Available
    Item
    Weight optimization of steel frames with cellular beams through improved hunting search algorithm
    Dogan, E; Ciftcioglu, AO
    Hunting search method-based optimum design algorithm is presented to investigate the weight optimization of steel frames with cellular beams. Unlike practical applications where rolled sections are assigned to both the beams and columns, built-up sections are used for beams. Design specifications including the design of steel frames and that of cellular beams are taken from Load and Resistance Factor Design-American Institute of Steel Construction. The algorithm presented selects optimal W-sections to be used for the members of the unbraced plane frame from the ready section pool of the same code. In addition, number of holes and hole diameter of the beams are selected for optimal frame by the algorithm for satisfying the design constraints and making the weight of the frame to be minimum. Besides, Levy Flight procedure is also adopted to the simple hunting search method for better designs. Optimized steel frames with cellular beams are then analyzed by ABAQUS three-dimensional finite element software. The results attained from nonlinear finite element analysis of the steel frames are then taken into account for comparison with optimization outcomes. Results reveal that designing the beam members as cellular beams reduces the weight of the frame.
  • No Thumbnail Available
    Item
    Machine learning approach to predict the mechanical properties of cementitious materials containing carbon nanotubes
    Okasha, NM; Mirrashid, M; Naderpour, H; Ciftcioglu, AO; Meddage, DPP; Ezami, N
    This research explores the use of machine learning to predict the mechanical properties of cementitious materials enhanced with carbon nanotubes (CNTs). Specifically, the study focuses on estimating the elastic modulus and flexural strength of these novel composite materials, with the potential to significantly impact the construction industry. Seven key variables were analyzed including water-to-cement ratio, sand-to-cement ratio, curing age, CNT aspect ratio, CNT content, surfactant-to-CNT ratio, and sonication time. Artificial neural network, support vector regression, and histogram gradient boosting, were used to predict these mechanical properties. Furthermore, a user-friendly formula was extracted from the neural network model. Each model performance was evaluated, revealing the neural network to be the most effective for predicting the elastic modulus. However, the histogram gradient boosting model outperformed all others in predicting flexural strength. These findings highlight the effectiveness of the employed techniques, in accurately predicting the properties of CNT-enhanced cementitious materials. Additionally, extracting formulas from the neural network provides valuable insights into the interplay between input parameters and mechanical properties.