Athanasios Karabinis

One of the most critical components of reinforced concrete structures are the beam-column joint systems, which greatly affect the overall behavior of the structure during a major seismic event. According to modern design codes, if the system fails, it should fail due to flexural yielding of the beam and not due to shear failure of the joint, which occurs suddenly and can lead to collapse, endangering human lives. Thus, a reliable tool is required for the prediction of the failure mode of the joints in a preexisting population of structures. In the present paper, a novel methodology for the derivation of analytical equations for this task is presented. The formulation is based on SHapley Additive exPlanations values, which is commonly employed as an explainability tool in Machine Learning. Instead, in the present paper, they are also utilized as a transformed target variable on which the analytical curves are fitted, which approximate the predictions of an underlying Machine Learning model. A dataset comprised of 478 experimental results is utilized and the eXtreme Gradient Boosting algorithm is initially fitted. This achieved an overall accuracy of ≈84%. The derived analytical equations achieved an accuracy of ≈78%. The corresponding metrics of Precision, Recall, and F1-Score ranged from ≈76% to ≈80% and were close across the two modes, indicating an unbiased model.

In the present study, a novel parametric family of fuzzy implications is introduced and its properties are examined. The parametric family of implications is produced only via a fuzzy negation. This in turn enables the effortless production of a wide range of implications from which to select the one that best fits a given problem, for example in fuzzy inference systems or fuzzy neural networks. The fuzzy negations that have been selected as a basis for the proposed methodology are strong, i.e., involutions, thus leading, in general, to the generated fuzzy implications possessing many desirable additional properties. We have examined which of these properties hold for the implications produced by our algorithm and under which conditions. Finally, it is demonstrated that the family of implications generated via the proposed methodology generalizes other well-established implications, including the Łukasiewicz implication.

One of the most critical aspects in the seismic behavior or reinforced concrete (RC) structures pertains to beam–column joints. Modern seismic design codes dictate that, if failure is to occur, then this should be the ductile yielding of the beam and not brittle shear failure of the joint, which can lead to sudden collapse and loss of human lives. To this end, it is imperative to be able to predict the failure mode of RC joints for a large number of structures in a building stock. In this research effort, various ensemble machine learning algorithms were employed to develop novel, robust classification models. A dataset comprising 486 measurements from real experiments was utilized. The performance of the employed classifiers was assessed using Precision, Recall, F1-Score, and overall Accuracy indices. N-fold cross-validation was employed to enhance generalization. Moreover, the obtained models were compared to the available engineering ones currently adopted by many international organizations and researchers. The novel ensemble models introduced in this research were proven to perform much better by improving the obtained accuracy by 12–18%. The obtained metrics also presented small variability among the examined failure modes, indicating unbiased models. Overall, the results indicate that the proposed methodologies can be confidently employed for the prediction of the failure mode of RC joints.

Seismic vulnerability assessment is one of the most impactful engineering challenges faced by modern societies. Thus, authorities require a reliable tool that has the potential to rank given structures according to their seismic vulnerability. Various countries and organizations over the past decades have developed Rapid Visual Screening (RVS) tools aiming to efficiently estimate vulnerability indices. In general, RVS tools employ a set of structural features and their associated weights to obtain a vulnerability index, which can be used for ranking. In this paper, Machine Learning (ML) models are implemented within this framework. The proposed formulation is used to train binary classifiers in conjunction with ad hoc rules, employing the features of various Codes (e.g., the Federal Emergency Management Agency, New Zealand, and Canada). The efficiency of this modeling effort is evaluated for each Code separately and it is clearly demonstrated that ML-based models are capable of outperforming currently established engineering practices. Furthermore, in the spirit of the aforementioned Codes, a linearization of the fully trained ML model is proposed. ML feature attribution techniques, namely SHapley Additive exPlanations (SHAP) are employed to introduce weights similar to engineering practices. The promising results motivate the potential applicability of this methodology towards the recalibration of the RVS procedures for various types of cases.

Structures inevitably suffer damage after an earthquake, with severity ranging from minimal damage of nonstructural elements to partial or even total collapse, possibly with loss of human lives. Thus, it is essential for engineers to understand the crucial factors that drive a structure towards suffering higher degrees of damage in order for preventative measures to be taken. In the present study, we focus on three well-known damage thresholds: the Collapse Limit State, Ultimate Limit State, and Serviceability Limit State. We analyze the features obtained via Rapid Visual Screening to determine whether or not a given structure crosses these thresholds. To this end, we use machine learning to perform binary classification for each damage threshold, and use explainability to quantify the effect of each parameter via SHAP values (SHapley Additive exPlanations). The quantitative results that we obtain demonstrate the potential applicability of ML methods for recalibrating the computation of structural vulnerability indices using data from recent earthquakes.

Structures inevitably suffer damages after an earthquake, with their severity ranging from minimal damages to non-structural elements to partial or even total collapse, possibly with loss of human lives. Thus, it is essential for engineers to understand the crucial factors that drive a structure towards suffering higher degrees of damage, so that preventative measures can be taken. In the present study, we focus on three well-known damage thresholds, namely Collapse Limit State, Ultimate Limit State and Serviceability Limit State and analyze which of the features obtained via Rapid Visual Screening, determine whether or not a given structure will cross that threshold. To this end, we use Machine Learning to perform binary classification for each damage threshold, as well as Explainability via SHAP values (acronym for SHapley Additive exPlanations) to quantify the effect of each parameter. The quantitative results obtained demonstrate the potential applicability of ML methods to re-calibrate the computation of structural vulnerability indices using data from recent earthquakes.