Yazar "Kim, Sunghwan" seçeneğine göre listele

Listeleniyor 1 - 8 / 8
  • [ X ]
    Öğe
    ANNFAA: artificial neural network-based tool for the analysis of Federal Aviation Administration's rigid pavement systems
    (Taylor & Francis Ltd, 2022) Tarahomi, Adel; Kaya, Orhan; Ceylan, Halil; Gopalakrishnan, Kasthurirangan; Kim, Sunghwan; Brill, David R.
    Three-dimensional Finite Element (3D-FE) stress computations involved in the current rigid airport pavement design methodology, are time consuming when considering top-down cracking failure mode. In this study, Artificial Neural Network (ANN) models are integrated into a tool called ANNFAA to replace such 3D-FE computations. ANNFAA makes use of the best ANN models developed in MATLAB for 156 different airplanes without requiring any additional software installation or cumbersome learning of a new program. Within ANNFAA development, about 4,000 of 3D-FE simulations and many ANN models have been developed for each of these airplanes. Three useful tools were also developed using C# and MATLAB for implementing the 3D-FE analysis, post-processing the results, training the ANN models, and determining accuracy and performance of the ANN models. ANNFAA provides an accurate and rapid procedure for practitioners, engineers, and researchers for computing the critical stress responses associated with top-down cracking in multiple-slab rigid airfield pavements. This should make pavement design and analysis more practical, especially when a significantly large number of different cases that include top-down cracking failure mode are investigated. Also, this will help when currently used bottom-up cracking mode in the FAA standard rigid pavement design procedures is being considered in a design.
  • [ X ]
    Öğe
    Development of Pavement Performance and Remaining Service Life Prediction Tools for Iowa Jointed Plain Concrete Pavement Systems
    (Asce-Amer Soc Civil Engineers, 2023) Kaya, Orhan; Citir, Nazik; Ceylan, Halil; Kim, Sunghwan; Waid, Danny R.
    Moving Ahead for Progress in the Twenty-First Century (MAP-21) requires US state highway agencies (SHA) to utilize performance-based approaches in their pavement management decision-making processes, and use of a remaining service life (RSL) model would be one of such performance-based approaches for facilitating the pavement management decision-making process for SHAs. In this study, statistical and artificial neural network (ANN)-based pavement performance and RSL models were developed for Iowa jointed plain concrete pavement systems (JPCP) using actual pavement structural, traffic, construction history, and pavement performance records obtained from the Iowa Department of Transportation pavement-management information system database. While both models were found to be potentially useful for project and network level performance and RSL predictions, statistical and ANN-based models were respectively found to be more suitable for project and network level analysis. Using these models, efficient Microsoft Excel-based automation tools were created to predict future performance of a JPCP section and estimate RSL values based on predicted future performance and threshold limits for the performance indicators. Consequence analysis was also conducted to investigate the impact of traffic and preservation treatment (diamond grinding) on the RSL of a JPCP. The tool, also capable of estimating realistic pavement pretreatment and posttreatment performance and RSL, could be successfully used as part of performance-based pavement management strategies and helping decision-makers make better-informed pavement management decisions to properly allocate agency resource expenditures. Moreover, this study provides a better understanding of RSL and the factors that influence both the project and network level RSL.
  • [ X ]
    Öğe
    Estimating local pavement performance and remaining service interval using neural networks-based models and automation tool
    (Taylor & Francis Ltd, 2024) Citir, Nazik; Kaya, Orhan; Ceylan, Halil; Kim, Sunghwan; Waid, Danny
    This study introduces an integrated approach to enhance county pavement management, emphasising operational efficiency in determining the Remaining Service Interval (RSI) for rigid and flexible pavements. It establishes a robust methodology for systematically processing raw county road data through dynamic segmentation and summarisation to create a structured pavement database. It also incorporates innovative approaches and input configurations in employing Artificial Neural Networks (ANNs) to predict current and future county pavement performance indicators, including International Roughness Index (IRI), rutting, transverse, and longitudinal cracks, even with limited data. Evaluation of the ANN models on independent county road databases exhibited high prediction accuracies (0.86 < R-2 < 0.99), varying with specific performance indicators. The study results in an automation tool for expediting road performance estimation over multiple years. This tool seamlessly integrates the ANN models, empowering county engineers to make data-driven decisions and optimise resource allocation for effective pavement management, achieving significant cost savings.
  • [ X ]
    Öğe
    Evaluation of the Federal Aviation Administration's Rigid Airfield Pavement Cracking Failure Models
    (Asce-Amer Soc Civil Engineers, 2022) Kaya, Orhan; Ceylan, Halil; Kim, Sunghwan; Rezaei-Tarahomi, Adel
    The Federal Aviation Administration's (FAA's) pavement thickness design software, FAA Rigid and Flexible Iterative Elastic Layer Design (FAARFIELD) uses bottom-up fatigue cracking as the only failure criterion in its rigid pavement design procedure. However, top-down cracking has also been observed in two full-scale experimental studies under some circumstances; therefore, it should be included as one of the failure criteria in the analysis and design of rigid airfield pavement systems. In this study, FAA's current rigid airfield pavement design methodology was reviewed and evaluated in great detail to better identify needs for improvements with respect to cracking failure models and to produce recommendations on how current design methodology could be improved. Critical mechanical loading and pavement response locations for top-down and bottom-up cracking failure modes were also investigated to seek identification of input scenarios where critical pavement responses at slab top are higher than those at slab bottom. The effect of temperature loading in determining which failure mode (top-down or bottom-up cracking) would be dominant in rigid airfield pavement failure was also studied. Slab thickness calculations were carried out using the same slab thickness determination steps as FAARFIELD design software (version 1.42) when top-down cracking and bottom-up cracking are specified as failure modes. Recommendations are made with respect to including the top-down cracking failure mode in rigid airfield pavement design.
  • [ X ]
    Öğe
    Incorporating the effectiveness of preservation and rehabilitation techniques on flexible pavement service life predictions using machine learning approach
    (American Society of Civil Engineers (ASCE), 2021) Citir, Nazik; Ceylan, Halil; Kim, Sunghwan; Kaya, Orhan
    A flexible pavement network may be exposed to traffic changes over time because of detours that may cause unusually high traffic loading on some parts of the pavement sections. Such sections, therefore, need to be preserved earlier than their expected service life. This study focuses on incorporating the effectiveness of preservation and rehabilitation techniques, e.g., functional thin overlay and structural asphalt overlay on flexible pavement service life predictions using a machine learning approach. The developed models are capable of estimating the current and future international roughness index (IRI) and of detecting performance recovery after application of preservation treatment, thereby forecasting the remaining service life. The traffic, pavement structural, and performance data were obtained from the pavement management information system (PMIS) of the Iowa Department of Transportation (DOT). This study describes realistic what-if scenarios considering various treatment techniques to provide a better understanding of the effectiveness of treatments on extending flexible pavement service life. Such outcomes will help facilitate better pavement preservation management strategies. © ASCE.All right reserved.
  • [ X ]
    Öğe
    Incorporating the Effectiveness of Preservation and Rehabilitation Techniques on Flexible Pavement Service Life Predictions Using Machine Learning Approach
    (Amer Soc Civil Engineers, 2021) Citir, Nazik; Ceylan, Halil; Kim, Sunghwan; Kaya, Orhan
    A flexible pavement network may be exposed to traffic changes over time because of detours that may cause unusually high traffic loading on some parts of the pavement sections. Such sections, therefore, need to be preserved earlier than their expected service life. This study focuses on incorporating the effectiveness of preservation and rehabilitation techniques, e.g., functional thin overlay and structural asphalt overlay on flexible pavement service life predictions using a machine learning approach. The developed models are capable of estimating the current and future international roughness index (IRI) and of detecting performance recovery after application of preservation treatment, thereby forecasting the remaining service life. The traffic, pavement structural, and performance data were obtained from the pavement management information system (PMIS) of the Iowa Department of Transportation (DOT). This study describes realistic what-if scenarios considering various treatment techniques to provide a better understanding of the effectiveness of treatments on extending flexible pavement service life. Such outcomes will help facilitate better pavement preservation management strategies.
  • [ X ]
    Öğe
    Long-term performance evaluation of Iowa concrete overlays
    (Taylor & Francis Ltd, 2022) Chen, Yu-An; Ceylan, Halil; Nlenanya, Inya; Kaya, Orhan; Smadi, Omar G.; Taylor, Peter C.; Kim, Sunghwan
    The use of concrete overlays has long been recognised as a cost-effective pavement maintenance and rehabilitation strategy. However, the long-term performance of various types of concrete overlays has not been fully investigated since there has not been enough performance data available to conduct such an evaluation. Concrete overlays have been regularly constructed on Iowa roadways since the late 1970s and many older projects are still in use. Performance-related data for in-service concrete overlays have been acquired from the available resources to evaluate long-term performance of concrete overlays in Iowa. The information collected includes Pavement Condition Index (PCI), International Roughness Index (IRI), overlay type, construction year, overlay thickness, joint spacing, traffic, and other construction and design-related data. Based on an evaluation of PCI and IRI changes during service life, it is observed that concrete overlays can provide at least 20 years of service life. In terms of PCI ratings, 89% of concrete overlays investigated have PCI values greater than 60% as of the time of the analysis. Similarly, 93% of concrete overlays have IRI values lower than 2.7 m/km (170 in/mile). The effects of overlays type and design features on long-term performance of Iowa concrete overlays are also discussed.
  • [ X ]
    Öğe
    Sensitivity Index comparison of pavement mechanistic-empirical design input variables to reflective cracking model for different climatic zones
    (Taylor & Francis Ltd, 2021) Gopisetti, Leela Sai Praveen; Ceylan, Halil; Kim, Sunghwan; Cetin, Bora; Kaya, Orhan
    One of the main types of distress observed in Asphalt Concrete (AC) overlays is reflective cracking, and a reflective cracking model has been recently incorporated into the latest released version of AASHTOWare Pavement ME Design (PMED) software. This study documents the complete results of the sensitivity with respect to the design inputs and material properties of reflective cracking distress predicted by the PMED software. Six representative locations distributed across different climate zones of the United States were considered for studying the effects of climate extremities on changes in predicted reflective cracking distress. One-at-a-time (OAT) sensitivity analyses was performed to determine the Normalized Sensitivity Index (NSI), with two scenarios considered for OAT analyses: (i) sensitivity of short-term reflective cracking prediction (i.e., the year when predicted distress reached 4000 ft/mile) and (ii) sensitivity of long-term reflective cracking prediction (20-year design life). The summary of NSI ranking for varying traffic levels are presented.