Article
Construction & Building Technology
Jian Liu, Fangyu Liu, Chuanfeng Zheng, Daodao Zhou, Linbing Wang
Summary: This study used machine learning models based on 27 features to predict rut depth, with the Gradient boosting model showing the best predictive performance. A new asphalt mix design procedure based on this model was proposed.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Hoang Long Nguyen, Van Quan Tran
Summary: The aim of this study is to investigate and predict the rutting depth of asphalt concrete containing Reclaimed Asphalt Pavement (RAP) content using a data-driven approach with six tree algorithms. A database containing 396 data samples is created, and XGB model is found to have the highest performance. Temperature has the most significant impact on the rutting depth of asphalt pavement, while factors such as the number of load cycles and mix design considerations have a negligible effect.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Adnan Qadir, Uneb Gazder, Karam-un-Nisa Choudhary
Summary: The study found that the use of flexible geogrids can provide higher resistance to rutting in asphalt pavement. Additionally, the use of center gradation of aggregates significantly reduces rutting depth, while the control samples with fine gradation showed the highest rut depths.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Ba-Nhan Phung, Thanh-Hai Le, Thuy-Anh Nguyen, Huong-Giang Thi Hoang, Hai-Bang Ly
Summary: This study used the Extreme Gradient Boost (XGB) algorithm with Sailfish Optimizer (SFO) and Aquila Optimizer (AO) to construct novel prediction models for the Marshall Stability (MS) and Marshall Flow (MF) of basalt fiber asphalt concrete (BFAC). Two databases consisting of 128 and 89 experimental samples were used to train the models for MS and MF, respectively. The XGB model showed excellent and consistent predictive capacity for MS and MF, and the SFO optimization algorithm was applied for a constrained design optimization problem related to the composition mixture for BFAC.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Yasir Ali, Fizza Hussain, Muhammad Irfan, Abdul Salam Buller
Summary: This study proposes an eXtreme Gradient Boosting (XGBoost) approach for modeling the dynamic modulus of asphalt concrete mixtures, which outperforms competing models in terms of accuracy and transferability according to analysis and comparisons conducted with experimental data.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Imad L. Al-Qadi, Izak M. Said, Uthman Mohamed Ali, Jameel R. Kaddo
Summary: Strength and fracture-based tests were conducted to assess the cracking potential of asphalt concrete. The study found correlations between AC strengths and energy-based indices, with brittle AC exhibiting limited plasticity and ductile AC showing high plasticity in strength tests but limited plasticity in fracture tests. Digital image correlation was used to monitor crack development and path. Lower index values were reported for brittle AC mixtures, while no trend was observed for ductile AC mixtures. The Flexibility Index variability in fracture tests is a result of crack propagation speed and AC inhomogeneity.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Matteo Poggi, Fabio Tosi, Konstantinos Batsos, Philippos Mordohai, Stefano Mattoccia
Summary: This paper reviews recent research in the field of learning-based depth estimation from single and binocular images, highlighting the synergies, successes achieved so far, and the open challenges to be faced in the future.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Chemistry, Physical
Haoyang Wang, Yu Zhu, Weiguang Zhang, Shihui Shen, Shenghua Wu, Louay N. N. Mohammad, Xuhui She
Summary: This study evaluates the aging of asphalt in field conditions and investigates its impact on rutting performance. The results show that the stiffening of asphalt mixture is mainly caused by aging, but the effect may not be proportional. The most sensitive parameters to aging are MSCR R3.2 and dynamic modulus. Climate conditions, material properties, and air voids are found to be factors influencing rut depth.
Article
Construction & Building Technology
Elyas Asadi Shamsabadi, Chang Xu, Aravinda S. Rao, Tuan Nguyen, Tuan Ngo, Daniel Dias-da-Costa
Summary: This research proposes a ViT-based framework for crack detection on asphalt and concrete surfaces, achieving enhanced real-world crack segmentation performance through transfer learning and IoU loss function. Compared to CNN-based models, TransUNet with a CNN-ViT backbone shows better average IoU on small and multiscale crack semantics and ViT helps the encoder-decoder network exhibit robust performance against various noisy signals.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Construction & Building Technology
Zehui Huo, Ling Wang, Yimiao Huang
Summary: This study aims to develop a robust and accurate machine learning-based model to improve the prediction accuracy of carbonation depth in complex concrete structures. Two hybrid ensemble methods, the inverse variance method and the artificial neural network-based ensemble method, were proposed to integrate multiple algorithms. The models were trained on a dataset of 532 data points with 6 input variables. The results showed that the hybrid ensemble models outperformed the single models, with the inverse variance-based model achieving the highest performance (R = 0.975, RMSE = 2.978 mm). Additionally, the contribution analysis indicated that carbonation time, CO2 concentration, and the amount of binder were the most influential factors. This study provides an efficient prediction model for carbonation depth and valuable insights for carbonation-resistant design in concrete structures.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Construction & Building Technology
Alexis Jair Enriquez-Leon, Thiago Delgado de Souza, Francisco Thiago Sacramento Aragao, Delson Braz, Andre Maues Brabo Pereira, Liebert Parreiras Nogueira
Summary: X-ray micro-computed tomography is an advanced technique for examining the volumetric characteristics of asphalt mixtures, with segmentation being a key step for air void quantification. Machine learning and deep learning have recently emerged as promising alternatives to conventional manual threshold selection, offering accurate results albeit at the cost of longer processing times.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2022)
Article
Construction & Building Technology
Ba Nhan Phung, Thanh-Hai Le, Hai-Van Thi Mai, Thuy-Anh Nguyen, Hai -Bang Ly
Summary: This study investigates the application of Machine Learning (ML) models, specifically the classical Gradient Boosting (CGB) algorithm, in conjunction with metaheuristic algorithms, to predict and optimize the design of Basalt Fiber Asphalt Concrete (BFAC) mixtures. The findings highlight the importance of combining ML and materials engineering expertise in optimizing the mixtures and improving the design and performance of BFAC.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2023)
Article
Construction & Building Technology
Manish Kumar, Manish Kumar, Shatakshi Singh, Sunggon Kim, Ashutosh Anand, Shatrudhan Pandey, S. M. Mozammil Hasnain, Adham E. Ragab, Ahmed Farouk Deifalla
Summary: This study presents a simulation environment based on Artificial Intelligence to predict the compressive strength and carbonation level of concrete. Using input parameters such as water/cement ratio, fly-ash percentage, and time duration, a 1D-CNN-LSTM model is proposed to estimate the carbonation depth and compressive strength. The model achieves an accuracy of 80% for estimating carbonation depth and 96% for predicting compressive strength.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2023)
Article
Engineering, Civil
Afshin Famili, Wayne A. Sarasua, Alireza Shams, William J. Davis, Jennifer H. Ogle
Summary: Periodic measurement and identification of pavement rutting locations using mobile terrestrial LiDAR scanning (MTLS) data is crucial for pavement management programs. Calibrated MTLS systems can provide accurate transverse profiles for identifying pavement rut areas. Analyzing the curvature of MTLS raster surfaces can reliably identify pavement rutting locations, leading to the development of a novel method for this purpose.
TRANSPORTATION RESEARCH RECORD
(2021)
Review
Construction & Building Technology
Mohammad Mohtasham Moein, Ashkan Saradar, Komeil Rahmati, Seyed Hosein Ghasemzadeh Mousavinejad, James Bristow, Vartenie Aramali, Moses Karakouzian
Summary: Concrete is widely used in civil engineering and its mechanical properties are important for design and evaluation. Machine learning and deep learning have been applied to predict these properties, offering advantages such as accuracy and responsiveness. This paper reviews successful applications of ML and DL models and provides suggestions for future research.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Construction & Building Technology
Jose Rivera-Perez, John Huang, Imad L. Al-Qadi
Summary: This study investigates the sources of pay disincentives in the two HMA pay specifications developed by the Illinois Department of Transportation, and finds that production and construction issues are the main causes of pay disincentives to contractors.
ROAD MATERIALS AND PAVEMENT DESIGN
(2023)
Article
Construction & Building Technology
Lama Abufares, Qingqing Cao, Imad L. Al-Qadi
Summary: Ground-penetrating radar (GPR) is used to assess civil structures like pavements by predicting asphalt concrete (AC) layer thicknesses and dry densities. Moisture content quantification in AC improves density prediction, while in cold recycled pavements, it helps monitor the curing process. The Al-Qadi-Cao-Abufares (ACA) model predicts AC density and moisture content accurately.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2023)
Article
Construction & Building Technology
Zehui Zhu, Imad L. Al-Qadi
Summary: This article proposes a deep neural network, CrackPropNet, for measuring crack propagation on asphalt concrete (AC) specimens. It offers an accurate, flexible, efficient, and low-cost solution using images collected during cracking tests. CrackPropNet differs from traditional deep learning networks by learning to locate displacement field discontinuities through feature matching in reference and deformed images. It achieved high F-1 scores on the testing dataset and showed promising generalization on different images. The CrackPropNet can accurately and efficiently detect complex crack patterns in AC cracking tests, making it useful for characterizing cracking phenomena and validating theoretical models.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2023)
Article
Engineering, Civil
Jose Rivera-Perez, Imad L. Al-Qadi
Summary: Asphalt concrete (AC) balanced mix design (BMD) is used to control pavement cracking and rutting potential by selecting aggregate gradation, component volumetrics, and binder content. This study proposes an autoencoder deep neural network (ADNN) to develop optimized AC mix design alternatives that can meet a prescribed flexibility index (FI) and rut depth (RD). The autoencoder learns the patterns in the input data and creates a compressed representation of the AC mix design. Models were trained using a database of 5,357 data sets to predict binder content and aggregate gradation based on target mix type, FI, and RD.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Ester Tseng, Imad L. Al-Qadi, Erol Tutumluer, Issam I. A. Qamhia, Hasan Ozer
Summary: This paper presents case studies to demonstrate that appropriately designed and constructed flexible pavements can withstand climatic changes. Techniques such as mechanically or chemically stabilized subgrade, proper drainage, and minimizing plastic fines in unbound layers can effectively control moisture damage.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Imad L. Al-Qadi, Angeli Jayme, Egemen Okte
Summary: The Georgia Department of Transportation (GDOT) has successfully used a combination of open-graded friction course (OGFC) and stone-matrix asphalt (SMA) layers on its Interstate highways for over two decades. Through life-cycle assessment and cost analysis, GDOT compared the environmental and economic impacts of different resurfacing cycles on a section of Interstate 95. The evaluation showed that the SMA and micro-milling combination had positive outcomes in terms of field performance, environmental impacts, and long-term economic benefits.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Izak M. Said, Imad Al-Qadi
Summary: A framework for incorporating dynamic loading in pavement design is introduced, consisting of five main steps. Input parameters are determined, and a database of critical pavement responses is built using finite element models. AASHTOWare's transfer function is used to predict pavement damage and calculate the international roughness index. The load spectrum is adjusted to include roughness-induced dynamic loading. A simple analytical dynamic-loading model is developed, and multiple case studies were performed, validating the outcome.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Xiuyu Liu, Imad L. Al-Qadi
Summary: This paper presents an integrated vehicle-pavement approach and investigates the excess fuel consumption of a seven-DOF full-car model on rough pavements. The study concluded that overlooking local roughness variance may underestimate excess fuel consumption by 30%. Compared with a 2D half-car model, a 3D full-car model reduces computation error of excess fuel consumption by approximately 11%.
JOURNAL OF TRANSPORTATION ENGINEERING PART B-PAVEMENTS
(2023)
Article
Engineering, Civil
Watheq Sayeh, Imad L. Al-Qadi
Summary: Pay for Performance (PFP) is a statistical-based quality assurance specification used to evaluate asphalt concrete construction. The study analyzed data from highway construction seasons in Illinois to determine variability trends. The results showed that reducing density standard deviation led to an increase in pay factor. If density standard deviation had been reduced, the average increase in pay per project would be $38,000.
JOURNAL OF TRANSPORTATION ENGINEERING PART B-PAVEMENTS
(2023)
Article
Engineering, Civil
Zehui Zhu, Imad L. Al-Qadi
Summary: This study proposes a framework for detecting surface cracks in asphalt concrete specimens using two-dimensional digital image correlation (DIC). The framework addresses the decorrelation issue caused by deformation and discontinuities, and detects cracks based on displacement fields. The framework can accurately measure strains and determine crack development. It can be used to study cracking phenomena, evaluate fracture properties, assess testing protocols, and develop theoretical models.
JOURNAL OF TRANSPORTATION ENGINEERING PART B-PAVEMENTS
(2023)
Article
Engineering, Civil
Aravind Ramakrishnan, Imad L. Al-Qadi
Summary: The axle load limits for single and tandem axles were assessed using an advanced finite element model. It was found that the distresses caused by tandem axles were greater than those caused by single axles. The load equivalency was found to be dependent on various parameters such as tire type, pavement material, and structure.
JOURNAL OF TRANSPORTATION ENGINEERING PART B-PAVEMENTS
(2023)
Article
Construction & Building Technology
Babak Asadi, Ramez Hajj, Imad L. Al-Qadi
Summary: This paper presents a probabilistic model for predicting the dynamic modulus of asphalt concrete using a Bayesian Neural Network. The model successfully predicted unseen testing datasets and enhanced interpretability through SHAP analysis.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2023)