Nurullah Bektaş
57468429900
Publications - 17
Data-Driven Pavement Performance: Machine Learning-Based Predictive Models
Publication Name: Applied Sciences Switzerland
Publication Date: 2025-04-01
Volume: 15
Issue: 7
Page Range: Unknown
Description:
Featured Application: This research provides effective methodology for pavement performance predictions using the data obtained from finite element analysis and merging it with machine learning algorithms. Traditional methods for predicting pavement performance rely on complex finite element modelling and empirical equations, which are computationally expensive and time-consuming. However, machine learning models offer a time-efficient solution for predicting pavement performance. This study utilizes a range of machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting, K-nearest neighbour, Support Vector Regression, LightGBM and CatBoost, to analyse their effectiveness in predicting pavement performance. The input variables include axle load, truck load, traffic speed, lateral wander modes, asphalt layer thickness, traffic lane width and tire types, while the output variables consist of number of passes to fatigue damage, number of passes to rutting damage, fatigue life reduction in number of years and rut depth at 1.3 million passes. A k-fold cross-validation technique was employed to optimize hyperparameters. Results indicate that LightGBM and CatBoost outperform other models, achieving the lowest mean squared error and highest R² values. In contrast, linear regression and KNN demonstrated the lowest performance, with MSE values up to 188% higher than CatBoost. This study concludes that integrating machine learning with finite element analysis provides further improvements in pavement performance predictions.
Open Access: Yes
DOI: 10.3390/app15073889
Sustainable waste management strategies for earthquake debris: Lessons from the 2008 China and 2023 Türkiye-Syria disasters
Publication Name: International Journal of Disaster Risk Reduction
Publication Date: 2025-01-01
Volume: 116
Issue: Unknown
Page Range: Unknown
Description:
Disasters like earthquakes produce immense debris, posing long-term environmental, economic and health risks if not managed properly. While earthquake-induced waste management has been studied in certain contexts, there is limited understanding of how distinct approaches, especially when considering the sustainability framework, impact recovery outcomes. This study addresses this gap by comparing the debris management strategies of the 2008 Sichuan and 2023 Türkiye-Syria earthquakes. Using life cycle analysis, it evaluates debris composition, carbon emission, eco-costs, and recycling and recovery practices. The results reveal the Sichuan earthquake produced waste with an eco-cost of €24.58 billion and 152.5 million tons of CO2 equivalents, while the Türkiye-Syria earthquake yielded €9.08 billion in eco-cost and 60.3 million tons of CO2 equivalents. The findings underscore the critical role of resilient construction practices, establishment of national waste management standards, and recycling-focused recovery efforts in mitigating the impact of earthquakes on communities and ecosystems. This study offers a pioneering framework for the comparative analysis of seismic waste management, providing actionable insights for stakeholders to develop disaster recovery strategies and improve waste management practices in earthquake-prone regions.
Open Access: Yes
Machine learning models for the elastic-critical buckling moment of sinusoidal corrugated web beam
Publication Name: Results in Engineering
Publication Date: 2024-09-01
Volume: 23
Issue: Unknown
Page Range: Unknown
Description:
The torsional stiffness of I-beams with sinusoidal corrugated web is higher than that of flat web beams and the accuracy of the available hand-calculation methods to determine the elastic critical lateral-torsional buckling moment depends on the geometrical parameters of the beam and the web corrugation. This study proposes different machine learning models to determine the elastic lateral-torsional buckling moments of corrugated web beams. Various machine-learning algorithms such as Decision Tree, Random Forests, Gradient Boosting, Support Vector Regression, Catboost, and Deep Neural Network were employed to develop and train for predicting the elastic-critical lateral-torsional buckling moments of I-beams with corrugated web. An extensive dataset with 2250 pieces was constructed using linear buckling analyses on full-shell finite element models to determine the elastic-critical buckling moment of simply supported beams with sinusoidal web corrugation. Based on the statistical parameters of the predicted and test data, the accuracy and safety assessment of the different machine learning models are examined. The accuracy of the available hand-calculation methods is also investigated. The results of the parametric study showed that the overall performance of the different machine learning models is promising, although, not all are directly suited for the described problem.
Open Access: Yes
2022 Düzce, Türkiye earthquake: advances in the past 2 decades, lessons learned, and future projections
Publication Name: Bulletin of Earthquake Engineering
Publication Date: 2024-09-01
Volume: 22
Issue: 11
Page Range: 5835-5862
Description:
In the year 1999, two devastating earthquakes (Mw 7.4 Kocaeli earthquake in August and Mw 7.2 Düzce earthquake in November) occurred in Northwest Türkiye. These two earthquakes led to a very large number of casualties and building collapses. When the 1999 earthquakes occurred, most of the structures in the earthquake-impacted region were not designed according to modern seismic design codes. During the 25 years following those earthquakes, there have been significant advances in building construction in the light of earthquake engineering, including adequate seismic codes, new regulations, and effective code enforcement in the earthquake impacted region. These advances have been reflected in the construction of new structures in the region and the retrofitting of existing ones. As a result, 70–80% of the current building stock in Düzce was designed, constructed, or retrofitted after the 1999 earthquakes. Almost 23 years later, in 2022, an Mw 6.1 earthquake occurred in Düzce, with ground shaking close to the seismic design code life safety performance level. The 2022 earthquake provided a great opportunity to evaluate the effectiveness and consequences of the advances in earthquake engineering and the relevant policy-making and regulations. This paper provides a comparative overview of the 1999 and 2022 earthquakes that struck the city of Düzce in terms of hazard, vulnerability, and consequences. Furthermore, other key lessons learned from the 2022 Düzce earthquake are documented based on field reconnaissance and numerical simulations. The lessons learned are expected to provide useful guidance for the reconstruction efforts after the 2023 Kahramanmaraş Türkiye earthquake sequence or in similar efforts in other parts of the world.
Open Access: Yes
Enhancing seismic assessment and risk management of buildings: A neural network-based rapid visual screening method development
Publication Name: Engineering Structures
Publication Date: 2024-04-01
Volume: 304
Issue: Unknown
Page Range: Unknown
Description:
Some of the existing buildings are designed based on lower design standards or even without considering seismic design standards. Recent earthquakes have further highlighted the vulnerability of these buildings when subjected to severe seismic activity. Consequently, it has become imperative to conduct seismic vulnerability assessments of the existing building stock. Therefore, the assessment of the existing building stock is required through the utilization of Rapid Visual Screening (RVS) methods. However, the existing conventional RVS methods used in seismic building assessments have shown limited accuracy. Furthermore, because these methods were developed based on expert opinions and/or due to access limitations to detailed assessment-based generated data used for their development, further enhancing them is challenging. To address these limitations, a new RVS method, which leverages Neural Networks (NN) and building-specific parameters, for reinforced concrete, adobe mud, bamboo, brick, stone, and timber buildings has been proposed in this study. Unlike conventional methods that rely on site seismicity class, the developed data-driven approach incorporates building-specific parameters such as the fundamental structural period and building spectral acceleration. The developed RVS method is specifically tailored to analyze diverse types of buildings in regions with varying seismicity risks, all in preparation for an impending earthquake. In this study, the developed RVS method demonstrated a promising 68% test accuracy, effectively representing the building performance against earthquakes. These findings illustrate the potential of the developed NN based RVS method in assessing existing buildings, thereby mitigating potential loss of life and property during imminent earthquake and alleviating the associated economic burden. Furthermore, this study introduces a new RVS method that can pave the way for future advancements in the field of seismic vulnerability assessment of existing buildings.
Open Access: Yes
Earthquake-Induced Waste Repurposing: A Sustainable Solution for Post-Earthquake Debris Management in Urban Construction
Publication Name: Buildings
Publication Date: 2024-04-01
Volume: 14
Issue: 4
Page Range: Unknown
Description:
Product sustainability has moved beyond being an elective preference to becoming a certain necessity. However, earthquakes in different regions, particularly Türkiye–Syria, Afghanistan, and Morocco, have produced a substantial amount of construction waste and debris. In the context of green urban initiatives and environmental preservation, theeffective management and reduction of environmental impact (EI) are imperative. This urgency underscores the significance of the study’s focus on a ten-story reinforced concrete (RC) dormitory building in Győr, Hungary, chosen as a case study. The research delves into the incorporation of three distinct concrete compositions through seismic design, aligning with the innovative approach of emphasizing recycled aggregate-based concrete to mitigate the EI. Utilizing AxisVM X7 and Revit software, the study meticulously created and analyzed a detailed building model, revealing a significant percentage (35%) and amount (1519.89 tons) of concrete waste that could be incorporated into construction. The results also showed a reduction in both total carbon emissions and the price of materials by falling 27.5% and 9.13%, respectively. We propose an eco-friendly way to effectively reuse debris from earthquakes, focusing on the case study of the 2023 Türkiye–Syria earthquake and encouraging resource efficiency while also addressing the construction waste problems that arise after an earthquake.
Open Access: Yes
Seismic Performance and Sustainability of Reinforced Concrete Buildings: a Comprehensive Assessment
Publication Name: Chemical Engineering Transactions
Publication Date: 2024-01-01
Volume: 114
Issue: Unknown
Page Range: 781-786
Description:
Recent earthquakes such as the 2023 Türkiye-Syria, Morocco, and Afghanistan, 2015 Gorkha Nepal, and 2009 Indonesia earthquakes have demonstrated the vulnerability of existing building stock. Throughout Europe, many existing buildings were constructed considering low or moderate standards or without considering them. This study investigates the seismic performance of reinforced concrete (RC) buildings, exemplified as a six-story RC dormitory building, focusing on various support and foundation conditions, soil characteristics, and site seismicity scenarios representing the seismicity of Europe. The research aims to assess the potential effects of exceeding anticipated site seismic intensities, potentially leading to safer communities and infrastructure in the face of impending earthquakes. Robot Structural Analysis Professional software is used for structural analysis and design throughout soil-structure interactions and site seismicity considerations. Moreover, this study investigates the environmental implications of RC buildings, which represent the future building inventory in Europe. It examines the varying material usage required to design structures compliant with Eurocode standards through a life cycle analysis. The methodology employed in this investigation aligns with the core principles of practical design encompassing economic and environmental sustainability. The study's key findings indicate that increasing member size can enhance performance at lower intensities, but this may not be a sufficient strategy at higher intensities, where shear walls may be necessary in high seismic zones. Sustainable design necessitates a balance between material use, performance, and environmental impact.
Open Access: Yes
DOI: 10.3303/CET24114131
Developing a machine learning-based rapid visual screening method for seismic assessment of existing buildings on a case study data from the 2015 Gorkha, Nepal earthquake
Publication Name: Bulletin of Earthquake Engineering
Publication Date: 2025-09-01
Volume: 23
Issue: 12
Page Range: 4981-5019
Description:
Each existing building is required to be assessed before an impending severe earthquake utilizing Rapid Visual Screening (RVS) methods for its seismic safety since many buildings were constructed before seismic standards, without taking into account current regulations, and because they have a limited lifetime and safety based on how they were designed and maintained. Building damage brought on by earthquakes puts lives in danger and causes significant financial losses. Therefore, the fragility of each building needs to be determined and appropriate precautions need to be taken. RVS methods are used when assessing a large building stock since further in-depth vulnerability assessment methods are computationally expensive and costly to examine even one structure in a large building stock. RVS methods could be implemented in existing buildings in order to determine the damage potential that may occur during an impending earthquake and take necessary measures for decreasing the potential hazard. However, the reliability of conventional RVS methods is limited for accurately assessing large building stock. In this study, building inspection data acquired after the 2015 Gorkha, Nepal earthquake is used to train nine different machine learning algorithms (Decision Tree Classifier, Logistic Regression, Light Gradient Boosting Machine Classifier, eXtreme Gradient Boosting Classifier, Gradient Boosting Classifier, Random Forest Classifier, Support Vector Machines, K-Neighbors Classifier, and Cat Boost Classifier), which ultimately led to the development of a reliable RVS method. The post-earthquake building screening data was used to train, validate, and ultimately test the developed model. By incorporating advanced feature engineering techniques, highly sophisticated parameters were introduced into the developed RVS method. These parameters, including the distance to the earthquake source, fundamental structural period, and spectral acceleration, were integrated to enhance the assessment capabilities. This integration enabled the assessment of existing buildings in diverse seismically vulnerable areas. This study demonstrated a strong correlation between determining building damage states using the established RVS method and those observed after the earthquake. When comparing the developed method with the limited accuracy of conventional RVS methods reported in the literature, a test accuracy of 73% was achieved, surpassing conventional RVS methods by over 40% in accurately classifying building damage states. This emphasizes the importance of detailed data collection after an earthquake for the effective development of RVS methods.
Open Access: Yes
Enhancing Seismic Performance: A Comprehensive Study on Masonry and Reinforced Concrete Structures Considering Soil Properties and Environmental Impact Assessment
Publication Name: Advances in Civil Engineering
Publication Date: 2024-01-01
Volume: 2024
Issue: Unknown
Page Range: Unknown
Description:
Approximately 20,000 people are killed annually on average by building and infrastructure collapses and failures caused by seismic activities. In earlier times, seismic design codes and specifications set minimal requirements for life safety performance levels. Earthquakes can be thought of as recurring events in seismically active areas, with severity states ranging from serviceability to ultimate levels. Buildings designed in accordance with site-specific response spectra, which take into account soil properties based on ground motion amplification data, are better at withstanding such forces and serving their design purposes. This study aims to investigate the site response of reinforced and masonry buildings, considering the effect of soil properties based on the amplification of ground motion data, and to compare the life cycle assessment of the buildings under consideration based on the design and the site-specific response spectrum. In terms of soil properties and site-specific response spectra, STRATA is used to determine the site-specific response for the considered locations for a return period of 475 years for 100 realizations based on the randomization of site properties. For structural analysis, AxisVM software, which is a compatible finite element analysis, is used for building design and analysis, generating comparative results based on the design- and site-specific spectra. To determine and identify potential failures in the model, response spectra were applied to understand the difference in horizontal deflection in two different instances (for elastic design- and site-specific spectra). After building design and analysis is performed, a life cycle analysis in terms of environmental impact assesments using OpenLCA and IdematLightLCA is done. This is done to ascertain the additional expenses in terms of ecocosts and carbon footprints on some failed elements in the structure which are required to make the buildings more resilient when the site-specific response spectrum is applied and to compare the potential economic losses that may occur based on ecological costs. The study presents a comprehensive investigation into the seismic response of masonry and reinforced concrete buildings in Győr, Hungary, incorporating advanced geophysical techniques like multichannel surface wave (MASW) and structural analysis software, AxisVM. Additionally, tailored retrofitting strategies are explored to enhance structural resilience in seismic-prone regions. Significant ground amplifications in soil properties across different profiles are revealed, emphasizing the effectiveness of these strategies in reducing structural deflection and improving resilience. Highlights of the results are observed where the site-specific response spectra are higher than the EC8 design response spectrum. Furthermore, the research underscores the substantial environmental impact, considering both ecocosts and CO2 emissions associated with retrofitting measures, highlighting the importance of sustainable structural interventions in mitigating seismic risks.
Open Access: Yes
DOI: 10.1155/2024/4505901
Assessing the Performance of Machine Learning Algorithms in Predicting Buckling Moments of Corrugated Web Beams
Publication Name: Advances in Transdisciplinary Engineering
Publication Date: 2024-01-01
Volume: 59
Issue: Unknown
Page Range: 121-127
Description:
I-beams with corrugated webs have higher torsional stiffness than that of flat web beams. Furthermore, the geometrical dimensions of the beam and the web corrugation heavily influence the precision of the currently used traditional pen-andpaper methods for determining the elastic lateral-torsional buckling moment. This study aims to suggest several machine learning models with the intention of predicting the elastic lateral-torsional buckling moment of corrugated web beams. Multiple machine learning models, including Random Forests, Gradient Boosting, Categorical Boosting, and Deep Neural Networks, were deployed to develop and train models to predict the elastic critical lateral-torsional buckling moments of Ibeams with corrugated web. The database used for training the different models was compiled through linear bifurcation analyses conducted on shell finite element models. The study evaluates the precision of the various machine learning models by examining their performance against statistical parameters derived from both predicted and test data. The findings from the parametric evaluation highlight the surprisingly high performance and accuracy of the machine learning models.
Open Access: Yes
DOI: 10.3233/ATDE240535
Seismic Vulnerability Assessment of an Unanchored Circular Storage Tank Against Elephant’s Foot Buckling
Publication Name: Journal of Vibration Engineering and Technologies
Publication Date: 2023-06-01
Volume: 11
Issue: 4
Page Range: 1661-1678
Description:
Purpose: Seismic vulnerability assessment of liquid containing storage tanks is the most vital relevance for industrial plants and society safety to endure damage during impending earthquakes. Because such systems also play an essential role in the public lifeline and also ensure continued use in emergencies. Furthermore, considering that the material contained in individual plants could be hazardous, requisite precautions have paramount importance against undesired leakage. The high internal pressure and axial forces exerted by the liquid in the steel tanks near the tank wall bottom produce elastic–plastic buckling, also known as Elephant’s Foot Buckling (EFB). As far as the authors are aware, no study has been carried out that involves a critical assessment and comparison of IDA and truncated IDA-based EFB failure criterion. This study provides insight into incremental dynamic analysis (IDA) and truncated IDA-based seismic evaluation of cylindrical unanchored steel storage tanks by employing a developed pressure-based surrogate modeling approach. For this purpose, probability-based seismic assessment of a representative sample is considered based on IDA and truncated IDA approaches to identify the potential of the EFB failure and to explore potential enhancements in the sophisticated structural analysis model to prevent the hazardous effects of impending earthquakes. Methods: Due to the significance of industrial plants for public safety and benefit, the structural response evaluation methods for different types of storage tanks have been widely reported. In the literature, the most comprehensive analytical assessment methodology is the IDA approach, in which nonlinear time-history analyses are considered in the finite element analysis model to assess the structural model’s seismic performance. Results: To generate fragility curves, both IDA approaches are employed, taking into consideration and ignoring uncertainty of material properties. The values of the two methods-based fragility curves approach each other as the magnitude of dispersion increases. Conclusion: The two fragility curves give the probability of failures close to each other as the dispersion amount increases while considering the uncertainty of the material properties. In addition, fragility curves generated based on the truncated IDA have been found to give a higher probability of failure, up to 32.5 percent. When compared to the IDA-based fragility curves, the truncated IDA-based fragility curves were found to be on the conservative side.
Open Access: Yes
Development in Machine Learning Based Rapid Visual Screening Method for Masonry Buildings
Publication Name: Lecture Notes in Civil Engineering
Publication Date: 2023-01-01
Volume: 433 LNCE
Issue: Unknown
Page Range: 411-421
Description:
The susceptibility of existing buildings to earthquakes is required to be assessed since building stock consists of structures that were constructed before the development of seismic standards, whether by disregarding them or by taking into account lower seismic regulations. Damage to buildings due to earthquakes not only endanger people’s lives but also causes economic losses. Because examining a large number of buildings by employing detailed building assessment methods is computationally expensive, Rapid Visual Screening (RVS) techniques are capable of assessing large building stock. Previous studies demonstrate that accuracy of the conventional RVS methods to precisely determine buildings’ damage states is limited. Therefore, it is required to develop a new RVS method. Since machine learning is extremely competent in establishing a relationship between input parameters and the target variable, this study introduces a new machine learning-based highly accurate RVS method, that can be applied in different countries, for masonry buildings using post-earthquake building screening data of 273 masonry buildings collected after the 2019 Mugello, Italy earthquake. The developed method differs from conventional RVS methods in terms of considered parameters such as spectral acceleration, the fundamental natural frequency of buildings, and the distance to the earthquake source. By comparing calculated building damage states with identified damage states through post-earthquake inspection, the developed method’s potential efficiency has been demonstrated as 88.9% accurate.
Open Access: Yes
A Holistic Framework to Prioritizing Building Interventions for Sustainable and Resilient Construction in Seismic-Prone Regions
Publication Name: Chemical Engineering Transactions
Publication Date: 2023-01-01
Volume: 107
Issue: Unknown
Page Range: 1-6
Description:
During earthquakes, damage and collapse of structures pose physical risks but also social, economic, and environmental challenges. Even buildings that appear not significantly damaged may require demolition and reconstruction to ensure their resilience. The demolition of existing buildings not only results in the loss of property and lives but also contributes to the unsustainability of the building stock. To mitigate these challenges, development of a comprehensive framework is imperative, one that can seamlessly integrate vulnerability and sustainability parameters. This holistic approach aims to achieve a sustainable building stock that not only mitigates physical vulnerabilities but also can be used to address the social and economic aspects. This study presents an interpretable, adaptable, and transparent Rapid Visual Screening (RVS) method combining machine learning, fuzzy logic, and neural networks to assess existing buildings and prioritize them based on intervention requirements and promote building stock sustainability. Buildings with higher scores indicate lower seismic sustainability ratings, emphasizing the need for intervention and improvement to enhance their resilience. The implementation of this framework facilitates the development of a safe, resilient, and environmentally sustainable building stock. In its initial stages, the proposed RVS method achieved an accuracy rate surpassing both conventional methods and the baseline. Ultimately, its application extends beyond existing buildings, as the method can also be used during the design of new buildings in seismic-prone regions.
Open Access: Yes
DOI: 10.3303/CET23107001
Development in Fuzzy Logic-Based Rapid Visual Screening Method for Seismic Vulnerability Assessment of Buildings
Publication Name: Geosciences Switzerland
Publication Date: 2023-01-01
Volume: 13
Issue: 1
Page Range: Unknown
Description:
In order to prevent possible loss of life and property, existing building stocks need to be assessed before an impending earthquake. Beyond the examination of large building stocks, rapid evaluation methods are required because the evaluation of even one building utilizing detailed vulnerability assessment methods is computationally expensive. Rapid visual screening (RVS) methods are used to screen and classify existing buildings in large building stocks in earthquake-prone zones prior to or after a catastrophic earthquake. Buildings are assessed using RVS procedures that take into consideration the distinctive features (such as irregularity, construction year, construction quality, and soil type) of each building, which each need to be considered separately. Substantially, studies have been presented to enhance conventional RVS methods in terms of truly identifying building safety levels by using computer algorithms (such as machine learning, fuzzy logic, and neural networks). This study outlines the background research that was conducted in order to establish the parameters for the development of a fuzzy logic-based soft rapid visual screening (S-RVS) method as an alternative to conventional RVS methods. In this investigation, rules, membership functions, transformation values, and defuzzification procedures were established by examining the data of 40 unreinforced masonries (URM) buildings acquired as a consequence of the 2019 Albania earthquake in order to construct a fuzzy logic-based S-RVS method.
Open Access: Yes
Development of a Fuzzy Inference System Based Rapid Visual Screening Method for Seismic Assessment of Buildings Presented on a Case Study of URM Buildings
Publication Name: Sustainability Switzerland
Publication Date: 2022-12-01
Volume: 14
Issue: 23
Page Range: Unknown
Description:
Many conventional rapid visual screening (RVS) methods for the seismic assessment of existing structures have been designed over the past three decades, tailored to site-specific building features. The objective of implementing RVS is to identify the buildings most susceptible to earthquake-induced damage. RVS methods are utilized to classify buildings according to their risk level to prioritize the buildings at high seismic risk. The conventional RVS methods are employed to determine the damage after an earthquake or to make safety assessments in order to predict the damage that may occur in a building before an impending earthquake. Due to the subjectivity of the screener based on visual examination, previous research has shown that these conventional methods can lead to vagueness and uncertainty. Additionally, because RVS methods were found to be conservative and to be partially accurate, as well as the fact that some expert opinion based developed RVS techniques do not have the capability of further enhancement, it was recommended that RVS methods be developed. Therefore, this paper discusses a fuzzy logic based RVS method development to produce an accurate building features responsive examination method for unreinforced masonry (URM) structures, as well as a way of revising existing RVS methods. In this context, RVS parameters are used in a fuzzy-inference system hierarchical computational pattern to develop the RVS method. The fuzzy inference system based RVS method was developed considering post-earthquake building screening data of 40 URM structures located in Albania following the earthquake in 2019 as a case study. In addition, FEMA P-154, a conventional RVS method, was employed to screen considered buildings to comparatively demonstrate the efficiency of the developed RVS method in this study. The findings of the study revealed that the proposed method with an accuracy of 67.5% strongly outperformed the conventional RVS method by 42.5%.
Open Access: Yes
DOI: 10.3390/su142316318
Conventional RVS Methods for Seismic Risk Assessment for Estimating the Current Situation of Existing Buildings: A State-of-the-Art Review
Publication Name: Sustainability Switzerland
Publication Date: 2022-03-01
Volume: 14
Issue: 5
Page Range: Unknown
Description:
Developments in the field of earthquake engineering over the past few decades have contributed to the development of new methods for evaluating the risk levels in buildings. These research methods are rapid visual screening (RVS), seismic risk indexes, and vulnerability assessments, which have been developed to assess the levels of damage in a building or its structural components. RVS methods have been proposed for the rapid pre-and/or post-earthquake screening of existing large building stock in earthquake-prone areas on the basis of sidewalk surveys. The site seismicity, the soil type, the building type, and the corresponding building characteristic features are to be separately examined, and the vulnerability level of each building can be identified by employing the RVS methods. This study describes, evaluates, and compares the findings of previous investigations that utilized conventional RVS methods within a framework. It also suggests the methods to be used for specific goals and proposes prospective enhancement strategies. Furthermore, the article discusses the time-consuming RVS methods (such as FEMA 154, which requires from 15 to 30 min, while NRCC requires one hour), and provides an overview of the application areas of the methods (pre-earthquake: FEMA 154, NRCC, NZEE, etc.; postearthquake: GNDT, EMS, etc.). This review of the traditional RVS methods offers a comprehensive guide and reference for field practitioners (e.g., engineers, architects), and recommends enhancement techniques (e.g., machine learning, fuzzy logic) for researchers to be used in future improvements.
Open Access: Yes
DOI: 10.3390/su14052583
FUZZY LOGIC BASED RAPID VISUAL SCREENING METHODOLOGY FOR STRUCTURAL DAMAGE STATE DETERMINATION OF URM BUILDINGS
Publication Name: World Congress in Computational Mechanics and Eccomas Congress
Publication Date: 2022-01-01
Volume: Unknown
Issue: Unknown
Page Range: Unknown
Description:
Most of the Unreinforced Masonry (URM) buildings are quite old in Europe based on “Building stock inventory to assess seismic vulnerability across Europe” [1] report. Following the earthquakes (Albania, Italy, etc.) that occurred in Europe, it was revealed that masonry buildings are extremely vulnerable. While probabilistic and deterministic approaches are important for examining a small number of buildings, they do not offer the opportunity to examine a large building stock in a short period of time. Rapid Visual Screening (RVS) methods are used to identify building pre- and post-earthquake vulnerability. Several RVS techniques have been presented in literature over last 30 years. Recent earthquakes have highlighted critical necessity of a rapid vulnerability assessment method for pre-earthquake warning, mitigation, preparedness, and post-earthquake damage state assessment of existing buildings. These findings demonstrate the importance of using an accurate RVS technique to inspect buildings. Due to the subjectivity of the screener, these RVS methods contain uncertainty and vagueness. Fuzzy Inference System (FIS) overcomes nonrandom uncertainty and vagueness by considering building characteristics in terms of their degree of truth. This paper introduces a FIS-based S-RVS case implementation and compares FIS-based Soft-RVS (S-RVS) to traditional RVS methods for identifying building damage state taking into account rapid visual assessment reports about damage caused by the 2019 Albania earthquake. To determine the damage states of URM buildings, 40 buildings damaged in the 2019 Albania earthquake were analyzed and processed to use in the applied fuzzy logic mathematical model. Initial findings demonstrate that the site-specific FIS-based S-RVS method is capable of accurately determining the damage states of at least half of the buildings.
Open Access: Yes
