This page has only limited features, please log in for full access.
Railway bridges are an integral part of any railway communication network. As more and more railway bridges are showing signs of deterioration due to various natural and artificial causes, it is becoming increasingly imperative to develop effective health monitoring strategies specifically tailored to railway bridges. This paper presents a new damage detection framework for element level damage identification, for railway truss bridges, that combines the analysis of acceleration and strain responses. For this research, operational acceleration and strain time-history responses are obtained in response to the passage of trains. The acceleration response is analyzed through a sensor-clustering-based time-series analysis method and damage features are investigated in terms of structural nodes from the truss bridge. The strain data is analyzed through principal component analysis and provides information on damage from instrumented truss elements. A new damage index is developed by formulating a strategy to combine the damage features obtained individually from both acceleration and strain analysis. The proposed method is validated through a numerical study by utilizing a finite element model of a railway truss bridge. It is shown that while both methods individually can provide information on damage location, and severity, the new framework helps to provide substantially improved damage localization and can overcome the limitations of individual analysis.
Riasat Azim; Mustafa Gül. Development of a Novel Damage Detection Framework for Truss Railway Bridges Using Operational Acceleration and Strain Response. Vibration 2021, 4, 422 -443.
AMA StyleRiasat Azim, Mustafa Gül. Development of a Novel Damage Detection Framework for Truss Railway Bridges Using Operational Acceleration and Strain Response. Vibration. 2021; 4 (2):422-443.
Chicago/Turabian StyleRiasat Azim; Mustafa Gül. 2021. "Development of a Novel Damage Detection Framework for Truss Railway Bridges Using Operational Acceleration and Strain Response." Vibration 4, no. 2: 422-443.
Advances in smart infrastructure produces a natural demand of system identification techniques for structural health and performance monitoring that can be scaled to regions and large asset inventories. Conventional approaches require sensors to be installed, often in long‐term deployments, on the monitored infrastructure systems, which is a costly undertaking when thousands of systems (e.g., bridges) need to be monitored. This paper presents a novel mode shape identification method for bridges that uses data collected from moving vehicles as input—a paradigm that can overcome limitations associated with conventional approaches. The method consists of two steps. First, the data collected from moving measurement points are mapped to virtual fixed points to generate a sparse matrix. Then, a “soft‐imputing” technique is employed to fill the sparse matrix. Finally, a singular value decomposition is applied to extract the mode shapes of the bridge. Experiments with synthetic, yet realistic, data are conducted to verify the method. The sensitivity of the proposed approach to different factors, including the number of vehicles, car speed, road roughness, and measurement errors, are also investigated. The results show that the proposed method is capable of identifying the mode shapes of the bridge accurately.
Qipei Mei; Nima Shirzad‐Ghaleroudkhani; Mustafa Gül; S. Farid Ghahari; Ertugrul Taciroglu. Bridge mode shape identification using moving vehicles at traffic speeds through non‐parametric sparse matrix completion. Structural Control and Health Monitoring 2021, 28, e2747 .
AMA StyleQipei Mei, Nima Shirzad‐Ghaleroudkhani, Mustafa Gül, S. Farid Ghahari, Ertugrul Taciroglu. Bridge mode shape identification using moving vehicles at traffic speeds through non‐parametric sparse matrix completion. Structural Control and Health Monitoring. 2021; 28 (7):e2747.
Chicago/Turabian StyleQipei Mei; Nima Shirzad‐Ghaleroudkhani; Mustafa Gül; S. Farid Ghahari; Ertugrul Taciroglu. 2021. "Bridge mode shape identification using moving vehicles at traffic speeds through non‐parametric sparse matrix completion." Structural Control and Health Monitoring 28, no. 7: e2747.
This paper develops an enhanced inverse filtering-based methodology for drive-by frequency identification of bridges using smartphones for real-life applications. As the vibration recorded on a vehicle is dominated by vehicle features including suspension system and speed as well as road roughness, inverse filtering aims at suppressing these effects through filtering out vehicle- and road-related features, thus mitigating a few of the significant challenges for the indirect identification of the bridge frequency. In the context of inverse filtering, a novel approach of constructing a database of vehicle vibrations for different speeds is presented to account for the vehicle speed effect on the performance of the method. In addition, an energy-based surface roughness criterion is proposed to consider surface roughness influence on the identification process. The successful performance of the methodology is investigated for different vehicle speeds and surface roughness levels. While most indirect bridge monitoring studies are investigated in numerical and laboratory conditions, this study proves the capability of the proposed methodology for two bridges in a real-life scale. Promising results collected using only a smartphone as the data acquisition device corroborate the fact that the proposed inverse filtering methodology could be employed in a crowdsourced framework for monitoring bridges at a global level in smart cities through a more cost-effective and efficient process.
Nima Shirzad-Ghaleroudkhani; Mustafa Gül. An Enhanced Inverse Filtering Methodology for Drive-By Frequency Identification of Bridges Using Smartphones in Real-Life Conditions. Smart Cities 2021, 4, 499 -513.
AMA StyleNima Shirzad-Ghaleroudkhani, Mustafa Gül. An Enhanced Inverse Filtering Methodology for Drive-By Frequency Identification of Bridges Using Smartphones in Real-Life Conditions. Smart Cities. 2021; 4 (2):499-513.
Chicago/Turabian StyleNima Shirzad-Ghaleroudkhani; Mustafa Gül. 2021. "An Enhanced Inverse Filtering Methodology for Drive-By Frequency Identification of Bridges Using Smartphones in Real-Life Conditions." Smart Cities 4, no. 2: 499-513.
Sports poses a unique challenge for high-speed, unobtrusive, uninterrupted motion tracking due to speed of movement and player occlusion, especially in the fast and competitive sport of squash. The objective of this study is to use video tracking techniques to quantify kinematics in elite-level squash. With the increasing availability and quality of elite tournament matches filmed for entertainment purposes, a new methodology of multi-player tracking for squash that only requires broadcast video as an input is proposed. This paper introduces and evaluates a markerless motion capture technique using an autonomous deep learning based human pose estimation algorithm and computer vision to detect and identify players. Inverse perspective mapping is utilized to convert pixel coordinates to court coordinates and distance traveled, court position, ‘T’ dominance, and average speeds of elite players in squash is determined. The method was validated using results from a previous study using manual tracking where the proposed method (filtered coordinates) displayed an average absolute percent error to the manual approach of 3.73% in total distance traveled, 3.52% and 1.26% in average speeds <9 m/s with and without speeds <1 m/s, respectively. The method has proven to be the most effective in collecting kinematic data of elite players in squash in a timely manner with no special camera setup and limited manual intervention.
Maria Martine Baclig; Noah Ergezinger; Qipei Mei; Mustafa Gül; Samer Adeeb; Lindsey Westover. A Deep Learning and Computer Vision Based Multi-Player Tracker for Squash. Applied Sciences 2020, 10, 8793 .
AMA StyleMaria Martine Baclig, Noah Ergezinger, Qipei Mei, Mustafa Gül, Samer Adeeb, Lindsey Westover. A Deep Learning and Computer Vision Based Multi-Player Tracker for Squash. Applied Sciences. 2020; 10 (24):8793.
Chicago/Turabian StyleMaria Martine Baclig; Noah Ergezinger; Qipei Mei; Mustafa Gül; Samer Adeeb; Lindsey Westover. 2020. "A Deep Learning and Computer Vision Based Multi-Player Tracker for Squash." Applied Sciences 10, no. 24: 8793.
In recent years, energy efficiency and sustainability have garnered widespread attention as buildings account for 30–40% of total primary energy use in North America and 24% of global greenhouse gas emissions. Owing to the cold climate in Canada, energy-efficient building practices have drawn significant interest among authorities and researchers who aim to develop sustainable means of improving energy efficiency. Among these means is the use of environmentally friendly building materials that also contribute to improving thermal resistance. This research investigates and evaluates the long-term thermal performance of innovative multi-functional panels (MFPs) in various wall assembly configurations for residential buildings under varying climatic conditions. The two types of MFPs under investigation combine two layers of wood sheathing with either wood fiber or extruded polystyrene (XPS) as an additional external layer to conventional light wood-frame wall assemblies in order to improve the overall energy efficiency of the conventional wall assemblies. For this purpose, two full-scale identical demonstration buildings (test houses) are built for in-situ testing—one located in the cold continental climate of Edmonton, Canada, and the other in the humid coastal climate of Vancouver, Canada. The two types of MFPs (with wood fiber or XPS) are added to conventional wall assemblies and placed on both north and south façades of each of the test houses. Sensors are installed on each wall assembly under controlled indoor climatic conditions to monitor temperature, moisture content, and heat flux at the inner, middle, and outer layers and at three different vertical levels for each wall assembly. The indoor climatic conditions are maintained by installing a floor heating system, an air conditioner, and a rotating fan for even air circulation. Also, each test house is equipped with a weather station to monitor solar radiation, precipitation, atmospheric pressure, outdoor temperature, and relative humidity, among other metrics such as dew point, wind direction, and wind speed. Results from this study demonstrate the effect of various weather conditions on the thermal performance of MFPs in comparison with conventional wall assemblies and future research will determine the long-term hygrothermal performance of the MFPs under investigation. The ongoing long-term study will provide a practical guideline for the use of wood fiber—an environmentally friendly and recyclable material—as a sustainable insulation material in the North American housing market.
Hadia Awad; Lana Secchi; Mustafa Gül; Hua Ge; Robert Knudson; Mohamed Al-Hussein. Thermal resistance of multi-functional panels in cold-climate regions. Journal of Building Engineering 2020, 33, 101838 .
AMA StyleHadia Awad, Lana Secchi, Mustafa Gül, Hua Ge, Robert Knudson, Mohamed Al-Hussein. Thermal resistance of multi-functional panels in cold-climate regions. Journal of Building Engineering. 2020; 33 ():101838.
Chicago/Turabian StyleHadia Awad; Lana Secchi; Mustafa Gül; Hua Ge; Robert Knudson; Mohamed Al-Hussein. 2020. "Thermal resistance of multi-functional panels in cold-climate regions." Journal of Building Engineering 33, no. : 101838.
Railway bridges are a critical part of the railway infrastructure system and the majority of these bridges are approaching their expected design lifespan. These bridges need to be maintained effectively. This article proposes a damage detection framework for truss railway bridges based on operational strain responses. The method relies on principal component analysis (PCA) of strain responses of the truss bridge. Strain time-history responses under baseline and damaged bridge conditions are used to compute the principal components which are then ranked based on their corresponding eigenvectors. The results are demonstrated in terms of damage indicators which is obtained by comparing the geometric distance of coordinates of the principal component space between the baseline and damaged bridge condition. The method is numerically verified through a finite element model of a truss railroad bridge with added artificial noise. It is shown that the proposed method could identify, locate and relatively assess the severity of the damage induced by stiffness change (at least 20% to as low as 10%, depending on operational variability and measurement noise level) in instrumented truss elements. This method can be useful in assisting the existing bridge maintenance techniques and formulating an effective structural health monitoring framework.
Riasat Azim; Mustafa Gül. Data-driven damage identification technique for steel truss railroad bridges utilizing principal component analysis of strain response. Structure and Infrastructure Engineering 2020, 1 -17.
AMA StyleRiasat Azim, Mustafa Gül. Data-driven damage identification technique for steel truss railroad bridges utilizing principal component analysis of strain response. Structure and Infrastructure Engineering. 2020; ():1-17.
Chicago/Turabian StyleRiasat Azim; Mustafa Gül. 2020. "Data-driven damage identification technique for steel truss railroad bridges utilizing principal component analysis of strain response." Structure and Infrastructure Engineering , no. : 1-17.
This paper presents a crowdsensing framework employing smartphones in monitoring populations of bridges in future smart cities. In this regard, because there are a variety of vehicles with different features traveling over the bridge at different speeds, it is critical to investigate the robustness of indirect monitoring methods against vehicle features. Therefore, an experimental study was performed, including two lab-scale bridges with different boundary conditions and a robot car that was capable of maintaining a variety of speeds and suspension systems. The proposed framework focuses on the identification of frequencies of the bridge using acceleration signals recorded on the car. It was demonstrated that by using a large set of passing cars with different features, the fundamental frequency of the bridge was captured. Successful identification of the deviation of fundamental frequencies between two bridges with relatively close frequency values proved that the framework is capable of detecting damage induced frequency changes of the bridge. Since this framework relies on the use of smartphones, it provides the opportunity to efficiently monitor a plethora of bridges in a metropolitan area with minimum cost.
Nima Shirzad-Ghaleroudkhani; Qipei Mei; Mustafa Gül. Frequency Identification of Bridges Using Smartphones on Vehicles with Variable Features. Journal of Bridge Engineering 2020, 25, 04020041 .
AMA StyleNima Shirzad-Ghaleroudkhani, Qipei Mei, Mustafa Gül. Frequency Identification of Bridges Using Smartphones on Vehicles with Variable Features. Journal of Bridge Engineering. 2020; 25 (7):04020041.
Chicago/Turabian StyleNima Shirzad-Ghaleroudkhani; Qipei Mei; Mustafa Gül. 2020. "Frequency Identification of Bridges Using Smartphones on Vehicles with Variable Features." Journal of Bridge Engineering 25, no. 7: 04020041.
Track foundation stiffness (also referred as the track modulus) is one of the main parameters that affect the track performance, and thus, quantifying its magnitudes and variations along the track is widely accepted as a method for evaluating the track condition. In recent decades, the train-mounted vertical track deflection measurement system developed at the University of Nebraska–Lincoln (known as the MRail system) appears as a promising tool to assess track structures over long distances. Numerical methods with different levels of complexity have been proposed to simulate the MRail deflection measurements. These simulations facilitated the investigation and quantification of the relationship between the vertical deflections and the track modulus. In our previous study, finite element models (FEMs) with a stochastically varying track modulus were used for the simulation of the deflection measurements, and the relationships between the statistical properties of the track modulus and deflections were quantified over different track section lengths using curve-fitting approaches. The shortcoming is that decreasing the track section length resulted in a lower accuracy of estimations. In this study, the datasets from the same FEMs are used for the investigations, and the relationship between the measured deflection and track modulus averages and standard deviations are quantified using artificial neural networks (ANNs). Different approaches available for training the ANNs using FEM datasets are discussed. It is shown that the estimation accuracy can be significantly increased by using ANNs, especially when the estimations of track modulus and its variations are required over short track section lengths, ANNs result in more accurate estimations compared to the use of equations from curve-fitting approaches. Results also show that ANNs are effective for the estimations of track modulus even when the noisy datasets are used for training the ANNs.
Ngoan T. Do; Mustafa Gül; Saeideh Fallah Nafari. Continuous Evaluation of Track Modulus from a Moving Railcar Using ANN-Based Techniques. Vibration 2020, 3, 149 -161.
AMA StyleNgoan T. Do, Mustafa Gül, Saeideh Fallah Nafari. Continuous Evaluation of Track Modulus from a Moving Railcar Using ANN-Based Techniques. Vibration. 2020; 3 (2):149-161.
Chicago/Turabian StyleNgoan T. Do; Mustafa Gül; Saeideh Fallah Nafari. 2020. "Continuous Evaluation of Track Modulus from a Moving Railcar Using ANN-Based Techniques." Vibration 3, no. 2: 149-161.
In this paper, a non‐parametric damage detection method for truss railroad bridges is presented which utilizes statistical analysis of bridge strain responses to operational train loading. Strain time‐history responses obtained under baseline and damaged bridge conditions are used to compute the coefficient of variation matrices. The results are presented in terms of the difference of the covariance matrix of the truss bridge between the baseline and damaged condition. The damage in the bridge is detected and located by observing the coefficients of the difference matrix as structural changes occur in the bridge. The magnitudes of the coefficients could be used to relatively estimate the severity of the damage. A finite element model of a truss railroad bridge is utilized for numerical validation of the proposed method. It is demonstrated that the proposed method yields encouraging results for identifying, locating, and relatively assessing the damage even under different operational conditions (e.g., different train speeds and loads). The proposed method could be very useful for early detection of damage and thus could assist in developing effective maintenance strategies for railway bridges.
Riasat Azim; Mustafa Gül. Damage detection framework for truss railway bridges utilizing statistical analysis of operational strain response. Structural Control and Health Monitoring 2020, 27, 1 .
AMA StyleRiasat Azim, Mustafa Gül. Damage detection framework for truss railway bridges utilizing statistical analysis of operational strain response. Structural Control and Health Monitoring. 2020; 27 (8):1.
Chicago/Turabian StyleRiasat Azim; Mustafa Gül. 2020. "Damage detection framework for truss railway bridges utilizing statistical analysis of operational strain response." Structural Control and Health Monitoring 27, no. 8: 1.
Nowadays, there is a considerable effort to develop technologies for smart cities. Smart buildings are a critical component of such smart cities, and their automated structural health monitoring is essential. This paper presents a new, efficient, and robust methodology for automated structural damage detection of shear‐type buildings. The proposed method uses output‐only acceleration response to separately detect changes in stiffness and mass using adaptive zero‐phase component analysis (AZCA) in conjunction with time series analysis, that is, autoregressive moving average models with exogenous inputs (ARMAX). In our efforts to tackle the effects of operational factors on structural damage detection processes, herein, mass changes are differentiated from structural damage. Assuming the mass at one DOF at any location is constant (a priori knowledge about the location is not needed), changes in the ARMAX model coefficients are then employed to build stiffness change features (SCFs) and mass change features (MCFs) from which changes in mass and stiffness can be detected separately. A four‐story shear structure was constructed in the laboratory to experimentally validate the proposed methodology. The experiment results demonstrate that the approach is successful in eliminating mass effect to determine the existence, location, and severity of the structural damage accurately.
Ngoan T. Do; Mustafa Gül. Structural damage detection under multiple stiffness and mass changes using time series models and adaptive zero‐phase component analysis. Structural Control and Health Monitoring 2020, 27, 1 .
AMA StyleNgoan T. Do, Mustafa Gül. Structural damage detection under multiple stiffness and mass changes using time series models and adaptive zero‐phase component analysis. Structural Control and Health Monitoring. 2020; 27 (8):1.
Chicago/Turabian StyleNgoan T. Do; Mustafa Gül. 2020. "Structural damage detection under multiple stiffness and mass changes using time series models and adaptive zero‐phase component analysis." Structural Control and Health Monitoring 27, no. 8: 1.
This paper presents a novel framework for transportation infrastructure monitoring using sensors in crowdsourced moving vehicles. Vehicles equipped with various kinds of sensors have the potential to be the perfect tools for assessing the overall health condition of transportation infrastructure at the city level. Three applications of crowdsensing-based techniques are introduced in this paper to evaluate the framework. First, a methodology using the vibration data collected from a large number of smartphones in moving vehicles for bridge damage detection is presented. Lab experiments are conducted to verify the method. Second, a lab experiment investigating the feasibility of gyroscope in smartphones for road deformation measurement is described. Third, a sport camera is used to assess road surface condition. These three applications demonstrate the potential of crowdsensing-based techniques to accomplish low cost and efficient transportation infrastructure monitoring.
Qipei Mei; Mustafa Gül; Nima Shirzad-Ghaleroudkhani. Towards smart cities: crowdsensing-based monitoring of transportation infrastructure using in-traffic vehicles. Journal of Civil Structural Health Monitoring 2020, 10, 653 -665.
AMA StyleQipei Mei, Mustafa Gül, Nima Shirzad-Ghaleroudkhani. Towards smart cities: crowdsensing-based monitoring of transportation infrastructure using in-traffic vehicles. Journal of Civil Structural Health Monitoring. 2020; 10 (4):653-665.
Chicago/Turabian StyleQipei Mei; Mustafa Gül; Nima Shirzad-Ghaleroudkhani. 2020. "Towards smart cities: crowdsensing-based monitoring of transportation infrastructure using in-traffic vehicles." Journal of Civil Structural Health Monitoring 10, no. 4: 653-665.
Automatic crack detection on pavement surfaces is an important research field in the scope of developing an intelligent transportation infrastructure system. In this paper, a cost effective solution for road crack inspection by mounting the commercial grade sport camera, GoPro, on the rear of the moving vehicle is introduced. Also, a novel method called ConnCrack combining conditional Wasserstein generative adversarial network and connectivity maps is proposed for road crack detection. In this method, a 121-layer densely connected neural network with deconvolution layers for multi-level feature fusion is used as generator, and a 5-layer fully convolutional network is used as discriminator. To overcome the scattered output issue related to deconvolution layers, connectivity maps are introduced to represent the crack information within the proposed ConnCrack. The proposed method is tested on a publicly available dataset as well our collected data. The results show that the proposed method achieves state-of-the-art performance compared with other existing methods in terms of precision, recall and F1 score.
Qipei Mei; Mustafa Gül. A cost effective solution for pavement crack inspection using cameras and deep neural networks. Construction and Building Materials 2020, 256, 119397 .
AMA StyleQipei Mei, Mustafa Gül. A cost effective solution for pavement crack inspection using cameras and deep neural networks. Construction and Building Materials. 2020; 256 ():119397.
Chicago/Turabian StyleQipei Mei; Mustafa Gül. 2020. "A cost effective solution for pavement crack inspection using cameras and deep neural networks." Construction and Building Materials 256, no. : 119397.
In this paper, a damage identification framework for steel-truss railroad bridges, based on acceleration responses to operational train loading, is presented. The method is based on vertical and longitudinal sensor clustering–based time-series analysis of the operational acceleration response of bridges to the passage of trains. The results are presented in terms of damage features extracted from each sensor, which were obtained by comparing actual acceleration responses from the sensors to the predicted responses from the time-series model. Bridge damage was detected by observing changes in the damage features of the bridges as structural changes occurred in the bridges. The relative severity of damage was quantitatively assessed by observing the magnitude of the changes in the damage features. A finite-element model of a steel-truss railroad bridge was utilized to verify the method. Continuous condition assessment of railway bridges in this manner is deemed very valuable for the early detection of damage and, therefore, for increasing the safety and operational reliability of railway networks.
Riasat Azim; Mustafa Gül. Damage Detection of Steel-Truss Railway Bridges Using Operational Vibration Data. Journal of Structural Engineering 2020, 146, 04020008 .
AMA StyleRiasat Azim, Mustafa Gül. Damage Detection of Steel-Truss Railway Bridges Using Operational Vibration Data. Journal of Structural Engineering. 2020; 146 (3):04020008.
Chicago/Turabian StyleRiasat Azim; Mustafa Gül. 2020. "Damage Detection of Steel-Truss Railway Bridges Using Operational Vibration Data." Journal of Structural Engineering 146, no. 3: 04020008.
This paper puts forward a novel methodology of employing inverse filtering technique to extract bridge features from acceleration signals recorded on passing vehicles using smartphones. Since the vibration of a vehicle moving on a bridge will be affected by various features related to the vehicle, such as suspension and speed, this study focuses on filtering out these effects to extract bridge frequencies. Hence, an inverse filter is designed by employing the spectrum of vibration data of the vehicle when moving off the bridge to form a filter that will remove the car-related frequency content. Later, when the same car is moving on the bridge, this filter is applied to the spectrum of recorded data to suppress the car-related frequencies and amplify the bridge-related frequencies. The effectiveness of the proposed methodology is evaluated with experiments using a custom-built robot car as the vehicle moving over a lab-scale simply supported bridge. Nine combinations of speed and suspension stiffness of the car have been considered to investigate the robustness of the proposed methodology against car features. The results demonstrate that the inverse filtering method offers significant promise for identifying the fundamental frequency of the bridge. Since this approach considers each data source separately and designs a unique filter for each data collection device within each car, it is robust against device and car features.
Nima Shirzad-Ghaleroudkhani; Mustafa Gül. Inverse Filtering for Frequency Identification of Bridges Using Smartphones in Passing Vehicles: Fundamental Developments and Laboratory Verifications. Sensors 2020, 20, 1190 .
AMA StyleNima Shirzad-Ghaleroudkhani, Mustafa Gül. Inverse Filtering for Frequency Identification of Bridges Using Smartphones in Passing Vehicles: Fundamental Developments and Laboratory Verifications. Sensors. 2020; 20 (4):1190.
Chicago/Turabian StyleNima Shirzad-Ghaleroudkhani; Mustafa Gül. 2020. "Inverse Filtering for Frequency Identification of Bridges Using Smartphones in Passing Vehicles: Fundamental Developments and Laboratory Verifications." Sensors 20, no. 4: 1190.
Cracks are important signs of degradation in existing infrastructure systems. Automatic crack detection and segmentation plays a key role in developing smart infrastructure systems. However, this field has been challenging over the last decades due to irregular shape of the cracks and complex illumination conditions. This article proposes a novel deep-learning architecture for crack segmentation at pixel-level. In this architecture, one convolutional layer is densely connected to multiple other layers in a feed-forward fashion. Max pooling layers are used to reduce the dimensions of the features, and transposed convolution layers are used for multi-level feature fusion. A depth-first search–based algorithm is applied as post-processing tool to remove isolated pixels and improve the accuracy. The method is tested on two previously published data sets. It can reach 92.02%, 91.13%, and 91.58% for the first data set, and 92.17%, 91.61%, and 91.89% for the second data set for precision, recall, and F1 score, respectively. The performance of the proposed method outperforms other state-of-the-art methods. At the end of the article, the influence of feature fusion methods and transfer learning are also discussed.
Qipei Mei; Mustafa Gül. Multi-level feature fusion in densely connected deep-learning architecture and depth-first search for crack segmentation on images collected with smartphones. Structural Health Monitoring 2020, 19, 1726 -1744.
AMA StyleQipei Mei, Mustafa Gül. Multi-level feature fusion in densely connected deep-learning architecture and depth-first search for crack segmentation on images collected with smartphones. Structural Health Monitoring. 2020; 19 (6):1726-1744.
Chicago/Turabian StyleQipei Mei; Mustafa Gül. 2020. "Multi-level feature fusion in densely connected deep-learning architecture and depth-first search for crack segmentation on images collected with smartphones." Structural Health Monitoring 19, no. 6: 1726-1744.
One of the main challenges in damage detection of in-service civil structures is the effect of operational and environmental changes. This paper presents a novel output-only vibration based method for detection of stiffness and mass changes in shear-type structures using a proposed time series analysis along with sensor clustering technique. AutoRegressive Moving Average models with eXogenous inputs (ARMAX) are incorporated with the equations of motion written for different sensor clusters. Together with two assumptions, changes in the ARMAX model coefficients are employed to build Stiffness Damage Features (SDF) and Mass Damage Features (MDF). Using SDFs and MDFs, existence, location, severity of changes, i.e., stiffness reduction due to damage, and changes in mass due to operational conditions, can be identified separately and accurately. To demonstrate the effectiveness of the proposed method in its current form, first, the shear-type IASC-ASCE numerical benchmark problem is employed. Subsequently, a laboratory-scale four-storey steel structure is developed and tested to study the proposed approach with experimental data. The results show that the approach can successfully identify the location and severity of damage and mass changes separately and very accurately using output-only vibration data.
Ngoan T. Do; Mustafa Gül. A time series based damage detection method for obtaining separate mass and stiffness damage features of shear-type structures. Engineering Structures 2019, 208, 109914 .
AMA StyleNgoan T. Do, Mustafa Gül. A time series based damage detection method for obtaining separate mass and stiffness damage features of shear-type structures. Engineering Structures. 2019; 208 ():109914.
Chicago/Turabian StyleNgoan T. Do; Mustafa Gül. 2019. "A time series based damage detection method for obtaining separate mass and stiffness damage features of shear-type structures." Engineering Structures 208, no. : 109914.
In order to develop smart cities, the demand for assessing the condition of existing infrastructure systems in an automated manner is burgeoning rapidly. Among all the early signs of potential damage in infrastructure systems, formation of cracks is a critical one because it is directly related to the structural capacity and could significantly affect the serviceability of the infrastructure. This paper proposes a novel deep learning-based method considering the connectivity of pixels for automatic pavement crack detection which has the potential to complement the current practice involving visual inspection which is costly, inefficient and time-consuming. In the proposed method, the convolutional layers are densely connected in a feed-forward fashion to reuse features from multiple layers, and transposed convolution layers are used for multiple level feature fusion. A novel loss function considering the connectivity of pixels is introduced to overcome the issues related to the output of transposed convolution layers. The proposed method is tested on two datasets, where the first one is collected from a handheld smartphone and the second one is collected from a high-speed camera mounted on the rear of a moving car. In both datasets, the proposed method shows superior performance than other available methods.
Qipei Mei; Mustafa Gül; Riasat Azim. Densely connected deep neural network considering connectivity of pixels for automatic crack detection. Automation in Construction 2019, 110, 103018 .
AMA StyleQipei Mei, Mustafa Gül, Riasat Azim. Densely connected deep neural network considering connectivity of pixels for automatic crack detection. Automation in Construction. 2019; 110 ():103018.
Chicago/Turabian StyleQipei Mei; Mustafa Gül; Riasat Azim. 2019. "Densely connected deep neural network considering connectivity of pixels for automatic crack detection." Automation in Construction 110, no. : 103018.
Flat roof solar PV design is an important and challenging process as it requires various parameters to be considered (such as weather, location, shading, regulations, purpose of use, etc.), and standard guidelines for building a solar PV system are not currently available. An even more challenging task is to improve the design of a solar PV system in order to optimize energy generation in a cost-effective manner, particularly in high-latitudes. In the present research, in order to determine optimal system size, parameters optimization should be carried out. The primary focus of this study is to develop an optimized system which maximizes generating capacity while maintaining cost-effectiveness of the solar PV system prior to the system implementation. Hence, a multi-objective optimization model is developed. The solar PV system design process is improved by optimizing the tilt angle and the inter-row spacing of solar PV modules. An objective function is developed based on the total solar energy generation per PV system and energy generation per PV module in order to improve cost effectiveness. The goal is to maximize these two outputs of the objective function. The particle swarm optimization (PSO) method is used to accomplish the optimization. Given that the two objectives are different and both have equal and opposite effects on the other, modifications are made to the PSO. Finally, the outputs of the optimization model are compared and validated with a case study. The model presented in this paper will assist users in decision making based on the technical output and financial aspects of the PV system.
Hadia Awad; K.M. Emtiaz Salim; Mustafa Gül. Multi-objective design of grid-tied solar photovoltaics for commercial flat rooftops using particle swarm optimization algorithm. Journal of Building Engineering 2019, 28, 101080 .
AMA StyleHadia Awad, K.M. Emtiaz Salim, Mustafa Gül. Multi-objective design of grid-tied solar photovoltaics for commercial flat rooftops using particle swarm optimization algorithm. Journal of Building Engineering. 2019; 28 ():101080.
Chicago/Turabian StyleHadia Awad; K.M. Emtiaz Salim; Mustafa Gül. 2019. "Multi-objective design of grid-tied solar photovoltaics for commercial flat rooftops using particle swarm optimization algorithm." Journal of Building Engineering 28, no. : 101080.
In this paper, we develop a damage identification framework based on acceleration responses for railroad bridges. The methodology uses sensor‐clustering‐based time series analysis of bridge acceleration responses to the motion of the train. The results are expressed in terms of damage features, and damage to the bridge is investigated by observing the magnitude of these damage features. The investigation demonstrates the damage features by comparing the fit ratios of locations of interest so that damage can be identified and located and the relative severity of the damage assessed. The damage cases considered are stiffness loss, moment capacity reduction, and change in boundary conditions. In this study, a finite element analysis of a railway bridge model is used to verify our methodology. Our findings show that the proposed damage detection framework is very promising for continuously assessing the condition of railway bridges and thus will facilitate early detection of potential structural damage. This will be valuable for infrastructure owners seeking to develop more economical and effective maintenance strategies.
Riasat Azim; Mustafa Gül. Damage detection of steel girder railway bridges utilizing operational vibration response. Structural Control and Health Monitoring 2019, 26, 1 .
AMA StyleRiasat Azim, Mustafa Gül. Damage detection of steel girder railway bridges utilizing operational vibration response. Structural Control and Health Monitoring. 2019; 26 (11):1.
Chicago/Turabian StyleRiasat Azim; Mustafa Gül. 2019. "Damage detection of steel girder railway bridges utilizing operational vibration response." Structural Control and Health Monitoring 26, no. 11: 1.
Green building has been acknowledged as a leading practice for mitigating the environmental impact throughout the life cycle of buildings. Recent studies have explored a wide range of systems, modeling tools, standards, and rating tools to facilitate the implementation of green building design concepts. However, these studies continue to utilize generic design parameters (factors) without considering their impact on the overall building environmental performance. This can lead to delays during the design process as a result of practitioners relying on their intuition to select and prioritize relevant factors. The proposed research establishes an evidence-based ranking system for green building design factors (GBDFs) in order to improve the green building design process based on an extensive systematic literature review. The identification phase of GBDFs is conducted through an extensive review of the literature on green buildings in reference to representative modeling tools. The evaluation phase is then carried out based on the frequency of relevant publications in accordance with leading modeling tools to generate the proposed evidence-based GBDF ranking. This ranking pioneers an innovative endeavor to prioritize GBDFs that not only assists designers, but also establishes baselines for further development of existing modeling tools.
Aladdin Alwisy; Samer BuHamdan; Mustafa Gül. Evidence-based ranking of green building design factors according to leading energy modelling tools. Sustainable Cities and Society 2019, 47, 101491 .
AMA StyleAladdin Alwisy, Samer BuHamdan, Mustafa Gül. Evidence-based ranking of green building design factors according to leading energy modelling tools. Sustainable Cities and Society. 2019; 47 ():101491.
Chicago/Turabian StyleAladdin Alwisy; Samer BuHamdan; Mustafa Gül. 2019. "Evidence-based ranking of green building design factors according to leading energy modelling tools." Sustainable Cities and Society 47, no. : 101491.