No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Real-time measurement on dynamic temperature variation of asphalt pavement using machine learning
Abstract
Temperature segregation of asphalt mixture is one of the major reasons for pavement damage. The premise of ensuring desired properties of the asphalt mixture is to propose a reliable measuring method to monitor temperature variations before paving. Few existing studies focus on this issue due to the absence of suitable and efficient measuring instruments. This study proposes an innovative method to evaluate the temperature variation of asphalt mixture throughout the transportation process by combining the infrared camera and machine learning algorithms. Static and dynamic field tests are performed to measure the contact and non-contact temperatures of the asphalt mixture. A set of temperature measuring probes is specially designed. Influences of the measuring depth, measuring location, and environmental conditions are considered. Correlations between the infrared temperature and the contact temperature are identified using regression model, Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost). The accuracy of the proposed model is verified against the experimental result.
ResearchGate has not been able to resolve any citations for this publication.
Temperature segregation during the paving of asphalt pavements is one of the causes of asphalt pavement distress. Therefore, controlling the paving temperature is crucial in the construction of asphalt pavements. To quickly evaluate the road performance of asphalt mixtures during paving, in this work, we used unmanned aerial vehicle infrared thermal imaging technology to monitor the construction work. By analyzing the temperature distribution at the paving site, and conducting laboratory tests, the relationship between the melt temperature, high-temperature stability, and water stability of the asphalt mix was assessed. The results showed that the optimal temperature measurement height for an unmanned aerial vehicle (UAV) with an infrared thermal imager was 7–8 m. By coring the representative temperature points on the construction site and then conducting a Hamburg wheel tracking (HWT) test, the test results were verified through the laboratory test results in order to establish a prediction model for the melt temperature and high-temperature stability of y = 10.73e0.03x + 1415.78, where the predictive model for the melt temperature and water was y = −19.18e−0.02x + 98.03. The results showed that using laboratory tests combined with UAV infrared thermography could quickly and accurately predict the road performance of asphalt mixtures during paving. We hope that more extensive evaluations of the roadworthiness of asphalt mixtures using paving temperatures will provide reference recommendations in the future.
Solid wastes are increasingly used to stabilize marine soft clay. Disposals of alkali slag and steel slag cause serious problems in Lianyungang City. These two waste materials are used to produce the compound cementitious material by mixing with GGBS, replacing the cement to treat the soft clay in Xuwei Port. The raw materials are collected from fields. The orthogonal test is performed to investigate the unconfined compressive strength (UCS) of the treated soil. The influence of alkali slag-soft soil (SR-S) ratio, the steel slag-GGBS (SS-GGBS) ratio, the curing agent, and the curing time are considered, followed by the investigation of reaction mechanisms. The optimal mixing ratio is recommended when the SR-S ratio is 1:1 and the curing agent content equals 10%. A well-documented dataset is developed by summarizing 1069 data of UCS from the literature. A PSO-BP-NN model is developed using the collected data and the experimental data so that generalization is guaranteed. The model is feasible to predict the UCS of treated soil by considering characters of the material properties and experimental techniques. This study aims to provide a reference for initially determining the mixing ratio of cementitious materials at field treatments.
The major criteria that control pile foundation design is pile bearing capacity (Pu). The load bearing capacity of piles is affected by the various characteristics of soils and the involvement of multiple parameters related to both soil and foundation. In this study, a new model for predicting bearing capacity is developed using an extreme gradient boosting (XGBoost) algorithm. A total of 200 driven piles static load test-based case histories were used to construct and verify the model. The developed XGBoost model results were compared to a number of commonly used algorithms— Adaptive Boosting (AdaBoost), Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM) using various performance measure metrics such as coefficient of determination, mean absolute error, root mean square error, mean absolute relative error, Nash–Sutcliffe model efficiency coefficient and relative strength ratio. Furthermore, sensitivity analysis was performed to determine the effect of input parameters on Pu. The results show that all of the developed models were capable of making accurate predictions however the XGBoost algorithm surpasses others, followed by AdaBoost, RF, DT, and SVM. The sensitivity analysis result shows that the SPT blow count along the pile shaft has the greatest effect on the Pu.
Machine learning (ML) models are excellent alternative solutions to model complex engineering issues with high reliability and accuracy. This paper presents two extensively explored ensemble models for predicting asphalt pavement temperature, the Markov chain Monte Carlo (MCMC) and random forest (RF). The RF and multiple MCMC (RF-MCMC) were used to hybridise the proposed algorithms for the optimal prediction of asphalt pavement temperature. This study used thermal instruments to measure the asphalt pavement temperature in Gaza Strip, Palestine. The temperature measurements were made at a two-hour interval from March 2012 to February 2013. The temperature data was used to model the pavement temperature. More than 7200 measured pavement temperatures were used to train and validate the proposed models. The validation showed that the ML models are satisfactory. The modelling results ensured the value of the proposed hybridisation models in predicting the asphalt pavement temperature levels. The developed hybrid algorithms regression model achieved acceptable and better prediction results with a coefficient of determination (R2) of 0.96. Generally, the results confirmed the significance of the proposed hybrid model as a reliable alternative computer-aided model for predicting asphalt pavement temperature.
The volatile organic compounds (VOC) present in the exhaled breath can be used as the biomarkers of certain diseases especially pulmonary diseases. A system and device are required for the diagnosis of these diseases that can be applied easily, non-invasive, produce high accuracy results, and minimal side effects as possible. This work seeks to generate biomarkers from non-invasive and accessible breath samples that facilitate diagnostic strategies. The objective of this study is to establish breath fingerprints in human exhaled breath for the timely diagnosis of lung cancer, chronic obstructive pulmonary disease (COPD), and asthma through the use of metabolomics tools. An electronic nose (e-nose) system is developed for the analysis of exhaled breath, which was applied to detect and classify a set of exhaled breath samples from healthy people and patients with lung cancer, COPD, and asthma. Breath samples of 218 people, including 48 lung cancer patients, 52 COPD patients, 55 asthma Patients, and 68 healthy controls were evaluated. To evaluate the performance in discriminating patients from healthy controls, eight different machine learning models were designed. The KPCA-XGBoost model attained good results with accuracy, sensitivity, and specificity of 91.74%, 90.57%, and 92.65% respectively for lung cancer prediction; 89.84%, 88.14%, and 91.30% respectively for COPD prediction, and 70.66%, 68.75%, and 72.41% respectively for asthma prediction.
From exchanging budgetary instruments to tracking individual spending plans to detail a business's profit, money-related organisations utilise computational innovation day by day. Here in this paper, we focus on the significance of innovation in accounts such as financial risk management and stock prediction. We discuss two significant algorithms that have a notable role in stock forecasting. Artificial Neural Networks (ANN), as absenteeism of some data points, does not hamper the network functioning. Secondly, Support Vector Machines (SVM) has several features, and due to simple decision boundaries, it avoids over-fitting. The paper first looks at the different technologies applied in stock market prediction. It examines how sentimental analysis, decision trees, moving average algorithm, and data mining is applied in various stock prediction scenarios. The paper covers the recent past studies to explore the concepts and methodologies through which ANN's and SVM's have been used. Additionally, the paper incorporates significant aspects of novel methods and technologies in which ANN as a hybrid model like ANN-MLP, GARCH-MLP, a combination of the Backpropagation algorithm and Multilayer Feed-forward network, yields better results. Simultaneously, SVM's have been successfully applied in stock prediction, giving an accuracy of about 60%–70% for simple SVM, which is further improved by combining methods like Random Forest, Genetic Algorithm more accurate outcomes. Further, we present our thoughts on where SVM's and ANN's stand as prediction algorithms and challenges like the time constraint, current scenarios, data limitation, and cold start problems were raised. Conclusively SVM and ANN played prominent roles in tackling these issue to an extent and can further be enhanced with their integration with other novel techniques resulting in hybrid methodologies. It will lead students, researchers and financial enthusiasts to more potent approaches for Stock forecasting.
These days, the classification between normal and cancerous tissues and between different
types of cancers represents a very important issue. Selecting the little informative number of genes is
considered the main challenge in the cancer diagnosis issue. Therefore, Gene selection is usually the
preliminary step for solving the cancer classification problems. Bio-inspired metaheuristic optimization
algorithms, when used to solve gene selection and classification problems, they demonstrate their effectiveness. Barnacles Mating Optimizer (BMO) algorithm, which imitates the behavior of mating barnacles in nature for solving optimization problems, is considered one of these algorithms. In this paper, Barnacles Mating Optimizer (BMO) algorithm augmented with Support Vector Machines (SVM) called BMO-SVM
is proposed for a microarray gene expression profiling in order to select the most predictive and informative genes for cancer classification. Conducting a comparative experimental study among a set of the most common bio-inspired optimization techniques to specify the most effective. A binary microarray dataset
(i.e., leukemia1) and a multi-class microarray dataset (i.e., SRBCT, lymphoma, and leukemia2) are used for testing the performance of the proposed model. The experimental results revealed the superiority of the proposed BMO-SVM approach against several well-known meta-heuristic optimization algorithms, such as the Tunicate Swarm Algorithm (TSA), Genetic Algorithm (GA), Particle Swarm Optimization (PSO),
and Artificial Bee Colony (ABC). It is worth mentioning that our proposed algorithm achieves a high informational superiority percentage compared to other algorithms
The performance of bituminous materials is mainly affected by the prevailing maximum and minimum temperatures, and their mechanical properties can vary significantly with the magnitude of the temperature changes. The given effect can be observed from changes occurring in the bitumen or asphalt mixture stiffness and the materials’ serviceable life. Furthermore, when asphalt pavement layer are used, the temperature changes can be credited to climatic factors such as air temperature, solar radiation and wind. Thus in relevance to the discussed issue, the contents of this paper displays a comprehensive review of the collected existing 38 prediction models and broadly classifies them into their corresponding numerical, analytical and statistical models. These models further present different formulas based on the climate, environment, and methods of data collection and analyses. Corresponding to which, most models provide reasonable predictions for both minimum and maximum pavement temperatures. Some models can even predict the temperature of asphalt pavement layers on an hourly or daily basis using the provided statistical method. The analytical models can provide straight-forward solutions, but assumptions on boundary conditions should be simplified. Critical climatic and pavement factors influencing the accuracy of predicting temperature were examined. This paper recommends future studies involving coupled heat transfer model for the pavement and the environment, particularly consider to be made on the impact of surface water and temperature of pavements in urban areas.
Air temperature is one of the critical factors influencing the bearing ability and performance of temperature-sensitive asphalt materials. This research investigates the relationship between air temperature at different depths and time to predict asphalt pavement temperature and evaluate asphalt performance. This paper discusses four deep learning-based regression models for calculating asphalt pavement temperature based on air temperature, depth from the asphalt surface, and time. Measurement of pavement temperature was made in the Gaza Strip. Monitoring stations were set up to measure asphalt pavement temperature and air temperature at different depths and times. The data were collected by hand measurement for the period from March 2012 to February 2013. The data is trained and validated using the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Gated Recurrent Unit (GRU). Bi-LSTM has an R2 of 0.9555 for the generated dataset and outperforms other algorithms because of its superiority in feature extraction and multidimensional data processing. Through deep learning techniques, Bi-LSTM has demonstrated outstanding robustness and promising potential in predicting asphalt pavement temperature.
In road construction, it can happen that, for different reasons, the time between hot-mix asphalt (HMA) production and paving is extended to some hours. This can be reflected in several problems such as mix cooling and temperature segregation, but also in an extremely severe bitumen ageing due to its prolonged exposure to high temperatures. This paper deals with the investigation of these phenomena both in the laboratory and on site. In particular, the first part of the research aimed at observing the influence of the conditioning time, when the loose HMA is kept in the oven at a high temperature, on the mix properties. The second part focused on the ageing/cooling that happens on site during HMA hauling, as a function of time and type of truck. Temperatures were monitored using a thermal camera and different probes, and gyratory compactor specimens were produced by sampling some HMA from the trucks every 1 h for 3 h. The results showed that HMA stiffness rises if the time when the loose mix stays in the laboratory oven before compaction increases. However, on site, the HMA volumetric and mechanical properties do not change with hauling time up to 3 h, probably because the external material in the truck bed protects the HMA core from the access of oxygen, hindering bitumen oxidation and loss of volatiles. The temperature monitoring highlighted that temperature segregation, after 3 h hauling, can be higher than 30 °C but it can be reduced using insulated truck beds.
Laser-based powder-bed fusion (L-PBF) is a widely used additive manufacturing technology that contains several variables (processing parameters), which makes it challenging to correlate them with the desired properties (responses) when optimizing the responses. In this study, the influence of the five most influential L-PBF processing parameters of Ti-6Al-4V alloy-laser power, scanning speed, hatch spacing, layer thickness, and stripe width-on the relative density, microhardness, and various line and surface roughness parameters for the top, upskin, and downskin surfaces are thoroughly investigated. Two design of experiment (DoE) methods, including Taguchi L25 orthogonal arrays and fractional factorial DoE for the response surface method (RSM), are employed to account for the five L-PBF processing parameters at five levels each. The significance and contribution of the individual processing parameters on each response are analyzed using the Taguchi method. Then, the simultaneous contribution of two processing parameters on various responses is presented using RSM quadratic modeling. A multi-objective RSM model is developed to optimize the L-PBF processing parameters considering all the responses with equal weights. Furthermore, an artificial neural network (ANN) model is designed and trained based on the samples used for the Taguchi method and validated based on the samples used for the RSM. The Taguchi, RSM, and ANN models are used to predict the responses of unseen data. The results show that with the same amount of available experimental data, the proposed ANN model can most accurately predict the response of various properties of L-PBF components.
With the increasing complexity of spacecraft structure and thermal design, it is more difficult to implement surface temperature measurement technology, and the temperature measurement area tends to diverse. Therefore, there is an increasing demand for the application of non-contact temperature measurement technology in spacecraft thermal test. This paper takes the application of infrared temperature measuring equipment in vacuum and high temperature environment as the research object, designs the thermal protection scheme and device of the equipment, and simulates and analyses the thermal protection of infrared temperature measuring equipment based on node network method. Through physical test, the device can effectively realize the thermal protection of equipment in vacuum and high temperature environment, and ensure that the equipment is in the normal working temperature range and its temperature measurement algorithm model is not affected, the accuracy of temperature measurement is better than ±2°C, which meets the use requirements in spacecraft thermal test.
Accurate assessment of undrained shear strength (USS) for soft sensitive clays is a great concern in geotechnical engineering practice. This study applies novel data-driven extreme gradient boosting (XGBoost) and random forest (RF) ensemble learning methods for capturing the relationships between the USS and various basic soil parameters. Based on the soil data sets from TC304 database, a general approach is developed to predict the USS of soft clays using the two machine learning methods above, where five feature variables including the preconsolidation stress (PS), vertical effective stress (VES), liquid limit (LL), plastic limit (PL) and natural water content (W) are adopted. To reduce the dependence on the rule of thumb and inefficient brute-force search, the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF. The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation (CV). It is shown that XGBoost-based and RF-based methods outperform these approaches. Besides, the XGBoost-based model provides feature importance ranks, which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.
Soil temperature has a vital importance in biological, physical and chemical processes of terrestrial ecosystem and its modeling at different depths is very important for land-atmosphere interactions. The study compares four machine learning techniques, extreme learning machine (ELM), artificial neural networks (ANN), classification and regression trees (CART) and group method of data handling (GMDH) in estimating monthly soil temperatures at four different depths. Various combinations of climatic variables are utilized as input to the developed models. The models’ outcomes are also compared with multi-linear regression based on Nash-Sutcliffe efficiency, root mean square error, and coefficient of determination statistics. ELM is found to be generally performs better than the other four alternatives in estimating soil temperatures. A decrease in performance of the models is observed by an increase in soil depth. It is found that soil temperatures at three depths (5, 10 and 50 cm) could be mapped utilizing only air temperature data as input while solar radiation and wind speed information are also required for estimating soil temperature at the depth of 100 cm
Asphalt is a temperature sensitive material, distribution characteristics and vary rules of asphalt pavement temperature have an important impact on the bearing capacity and performance of pavement, which is a concern of domestic and foreign researchers. The objective of this study was to explore the correlation between pavement temperature of asphalt pavements and meteorological factors and implement an accurate trend prediction of the asphalt pavement temperature. First, errors and missing data in the meteorological dataset were cleaned. Then, the three kinds of temperature prediction models of asphalt pavements in winter were established by Gradient Boosting Decision Tree (GBDT), Random Forest (RF) and Linear Regression (LR). The results indicate that GBDT would perform an excellent ability on prediction. The mean-square-error of the GBDT predicting results has a lower value of 1.5 when compared with the Random Forest and Linear Regression owing to the high robustness and the good generalization ability, which reflects the GBDT model has a good applicability in the field of prediction. The research would serve as a technical support for the machine learning algorithms applied in the field of the application of prediction problems.
Pavement condition assessment provides information to make more cost-effective and consistent decisions regarding management of pavement network. Generally, pavement distress inspections are performed using sophisticated data collection vehicles and/or foot-on-ground surveys. In either approach, the process of distress detection is human-dependent, expensive, inefficient, and/or unsafe. Automated pavement distress detection via road images is still a challenging issue among pavement researchers and computer-vision community. In recent years, advancement in deep learning has enabled researchers to develop robust tools for analyzing pavement images at unprecedented accuracies. Nevertheless, deep learning models necessitate a big ground truth dataset, which is often not readily accessible for pavement field. In this study, we reviewed our previous study, which a labeled pavement dataset was presented as the first step towards a more robust, easy-to-deploy pavement condition assessment system. In total, 7237 google street-view images were extracted, manually annotated for classification (nine categories of distress classes). Afterward, YOLO (you look only once) deep learning framework was implemented to train the model using the labeled dataset. In the current study, a U-net based model is developed to quantify the severity of the distresses, and finally, a hybrid model is developed by integrating the YOLO and U-net model to classify the distresses and quantify their severity simultaneously. Various pavement condition indices are developed by implementing various machine learning algorithms using the YOLO deep learning framework for distress classification and U-net for segmentation and distress densification. The output of the distress classification and segmentation models are used to develop a comprehensive pavement condition tool which rates each pavement image according to the type and severity of distress extracted. As a result, we are able to avoid over-dependence on human judgement throughout the pavement condition evaluation process. The outcome of this study could be conveniently employed to evaluate the pavement conditions during its service life and help to make valid decisions for rehabilitation or reconstruction of the roads at the right time.
Additive manufacturing (AM), also known as three-dimensional printing, is gaining increasing attention from academia and industry due to the unique advantages it has in comparison with traditional subtractive manufacturing. However, AM processing parameters are difficult to tune, since they can exert a huge impact on the printed microstructure and on the performance of the subsequent products. It is a difficult task to build a process–structure–property–performance (PSPP) relationship for AM using traditional numerical and analytical models. Today, the machine learning (ML) method has been demonstrated to be a valid way to perform complex pattern recognition and regression analysis without an explicit need to construct and solve the underlying physical models. Among ML algorithms, the neural network (NN) is the most widely used model due to the large dataset that is currently available, strong computational power, and sophisticated algorithm architecture. This paper overviews the progress of applying the NN algorithm to several aspects of the AM whole chain, including model design, in situ monitoring, and quality evaluation. Current challenges in applying NNs to AM and potential solutions for these problems are then outlined. Finally, future trends are proposed in order to provide an overall discussion of this interdisciplinary area. Keywords: Additive manufacturing, 3D printing, Neural network, Machine learning, Algorithm
This paper presents innovative machine learning methods called gene expression programming (GEP) and hybrid artificial neural network/simulated annealing (ANN/SA) to predict the fracture energy of asphalt mixture specimens. The GEP and ANN/SA models are developed using an experimental database including a number of disk-shaped compact tension (DC(T)) test results for fracture energy. The fracture energy is formulated in terms of various predictor variables such as asphalt binder performance grading (PG), asphalt content, aggregate size, aggregate gradation, reclaimed asphalt pavement (RAP) content, reclaimed asphalt shingles (RAS) content, crumb rubber content, and test temperature. A calculation procedure is presented to interpret the models and transform them into practical design equations. A sensitivity analysis is conducted to evaluate the effect of these predictor variables on the fracture energy. Based on the results, the proposed design equations accurately characterize the fracture energy of asphalt mixtures. The GEP model appears to be more practical than the ANN/SA model because of its better generalization and simpler functional structure. The models are recommended for pre-design purposes or as a means to determine asphalt mixture fracture energy when testing is not feasible.
This study constructs an automatic model for detecting and classifying asphalt pavement crack. Image processing techniques including steerable filters, projective integral of image, and an enhanced method for image thresholding are employed for feature extraction. Different scenarios of feature selection have been attempted to create data sets from digital images. These data sets are then employed to train and verify the performance of machine learning algorithms including the support vector machine (SVM), the artificial neural network (ANN), and the random forest (RF). The feature set that consists of the properties derived from the projective integral and the properties of crack objects can deliver the most desirable outcome. Experimental results supported by the Wilcoxon signed-rank test show that SVM has achieved the highest classification accuracy rate (87.50%), followed by ANN (84.25%), and RF (70%). Accordingly, the proposed automatic approach can be helpful to assist transportation agencies and inspectors in the task of pavement condition assessment.
This paper focuses on developing empirical statistical pavement temperature prediction models based on two years of field data collected from an instrumented test road located in Edmonton, Alberta, Canada, from September 2014 to September 2016. Step-wised regression analysis was utilized for developing the regression models based on the most important predictors. The developed models were divided into four categories, including average daily pavement temperature for cold and warm seasons and maximum and minimum daily pavement temperatures at any depth throughout the asphalt layer. One of the models in the literature was adopted and calibrated for the test road to predict instantly the pavement temperature at different depths, which is highly useful for precisely analyzing the results of Falling Weight Deflectometer (FWD) tests. All the models presented in this study showed a significantly high coefficient of correlation. The models were validated using the field data from September to October 2016 and showed satisfactory results.
Segregation determination in the asphalt pavement is an issue causing many disputes between agencies and contractors. The visual inspection method has commonly been used to determine pavement texture and in-place core density test used for verification. Furthermore, laser-based devices, such as the Florida Texture Meter (FTM) and the Circular Track Meter (CTM), have recently been developed to evaluate the asphalt mixture texture. In this study, an innovative digital image processing approach is used to determine pavement segregation. In this procedure, the standard deviation of the grayscale image frequency histogram is used to determine segregated regions. Linear Discriminate Analysis (LDA) is then implemented on the obtained standard deviations from image processing to classify pavements into the segregated and nonsegregated areas. The visual inspection method is utilized to verify this method. The results have demonstrated that this new method is a robust tool to determine segregated areas in newly paved FC9.5 pavement types.
Forecasting the output power of solar systems is required for the good operation of the power grid or for the optimal management of the energy fluxes occurring into the solar system. Before forecasting the solar systems output, it is essential to focus the prediction on the solar irradiance. The global solar radiation forecasting can be performed by several methods; the two big categories are the cloud imagery combined with physical models, and the machine learning models. In this context, the objective of this paper is to give an overview of forecasting methods of solar irradiation using machine learning approaches. Although, a lot of papers describes methodologies like neural networks or support vector regression, it will be shown that other methods (regression tree, random forest, gradient boosting and many others) begin to be used in this context of prediction. The performance ranking of such methods is complicated due to the diversity of the data set, time step, forecasting horizon, set up and performance indicators. Overall, the error of prediction is quite equivalent. To improve the prediction performance some authors proposed the use of hybrid models or to use an ensemble forecast approach.
The compaction quality of a highway subgrade is influenced by the compaction parameters and soil properties. Current practice lacks reliable models to assess this multivariate situation. This paper describes a monitoring and evaluation method based on intelligent compaction (IC) and artificial neural networks (ANNs) to assess the compaction quality of a highway subgrade. Field compaction tests were conducted at various roller speeds and vibratory modes. The compactness was predicted using a particle-swarm-optimization optimized backpropagation neural network (PSO-BP-NN) model. The model was integrated into the IC system to automatically evaluate compaction quality. It also demonstrated the advantage of high prediction accuracy with multiple input variables of operation parameters and soil gradation. By efficiently controlling subgrade compaction, the model can be employed for engineering practice and facilitate IC applications.
Highway construction strategies impact the early damage of asphalt pavement and its sustainability. The pavement quality is directly influenced by the temperature segregation of the mixture during transportation, which has rarely been investigated. Low-temperature transportation strategies for highway pavement are proposed by assessing the temperature variations in the mixture through field tests. The extreme condition of winter construction is considered, and the effects of insulation materials are considered in laboratory and field tests. A 3D Multiphysics Coupling Finite Element model is developed in COMSOL to analyse the heat transfer mechanism. The vehicle speed, thermal conductivity and ambient temperatures are considered in this parametric study. The economic efficiency of intelligent transportation is improved by optimising the effective area and the thickness of insulation materials. This study aims to propose economic strategies to avoid the temperature segregation of pavement materials and to explore more environmentally friendly insulation measures for low-temperature highway constructions.
Pavement distress detection is the first and most important step in pavement maintenance procedures. The detection results directly determine the maintenance mileage and strategy. Traditional detection methods are either inaccurate or expensive. It is necessary to develop an accurate and inexpensive pavement distress detection method. This study presents an advanced pavement distress detection method based on deep learning and binocular stereo vision. The Genetic Algorithm (GA)-DenseNet is used to classify more than 6500 distress datasets to identify both two-dimensional (2D) and three-dimensional (3D) distresses. The input image size of the model is 224 * 224 pixels, and the recognition speed is 0.33 s per piece. Binocular stereo vision and point cloud processing are used for 3D reconstruction and extracting morphology features of potholes. The test results show that the average accuracy of depth and area is 98.9% and 98.0%, respectively. The RGB image is first used to calculate the pavement damage rate (DR) and pavement surface condition index (PCI) of road pothole defect in millimeter-level accuracy, and the overall detection accuracy is 88.2%. This study demonstrates a promising inexpensive way to automatically detect 3D pavement distresses, thereby providing direct guidance in pavement maintenance decision-making.
Aggregates segregation is a major form of defect that accelerates the pavement deterioration rate. Therefore, asphalt pavement segregation needs to be detected accurately and early during the quality survey process. This study proposes and verifies a computer vision based method for automatic identification of aggregate segregation. The new method includes Extreme Gradient Boosting Machine integrated with Attractive Repulsive Center-Symmetric Local Binary Pattern (ARCSLBP-XGBoost) and Deep Convolutional Neural Network (DCNN). Experimental results obtained from a repetitive random data sampling process with 20 runs show that the ARCSLBP-XGBoost is a capable approach for detecting asphalt pavement segregation with outstanding performance measurement metrics (classification accuracy rate = 0.95, precision = 0.93, recall = 0.98, and F1 score = 0.95).
Pavement needs to be maintained from the moment its service life begins. The maintenance strategy is mainly based on pavement quality indexes, such as the road damage rate (DR). Accurate pavement distress detection is generally costly and complicated. An inappropriate pavement distress detection strategy could yield a low efficiency of budget usage and untreated road diseases. This study describes an innovative vision-based pavement crack detection strategy that provides a direct pavement surface condition index (PCI) for a specific pavement location. This strategy was achieved with the application of the convolutional neural network (CNN) algorithm to mine a database that contains over five thousand pavement distress images to classify the pavement crack type. To improve the accuracy of the network, a genetic algorithm (GA) was employed to optimize the model. To simultaneously consider the efficiency and accuracy, an enhanced image processing method was used to measure the DR of the pavement. The model input image size is 100 × 100 pixels and the test results showed that the proposed method has satisfactory performance in robustness, accuracy, and processing speed. The accuracy of classifying different crack types reached 98%, and the processing time for an image is 0.047 s. This research, for the first time, proposed an ellipse fitting method to calculate the block of mesh cracks. The overall accuracy in detecting the pavement damage rate reached 90%. This study demonstrates the potential of an innovative deep learning method in automated pavement quality index calculations to provide direct guidance for long-term asphalt pavement optimal rehabilitation and maintenance (R&M) decisions.
Decision-making in highway preventive maintenance (PM) is generally costly and complicated. An inappropriate maintenance strategy could yield a low efficiency of budget usage and untreated road distress. This study describes an innovative predictive maintenance strategy that provides direct maintenance guidance to specific highway mileposts. This was achieved with the application of the artificial neural network (ANN) algorithm to mine a maintenance database. Ten-year distress measurement data at 100-m intervals, traffic load data, climatic history, and maintenance records of a chosen highway were regarded as the input data of the ANN model. A data quality control method was proposed to ensure asphalt pavement performance improvement continuity over time based on the idea of the maintenance year as the starting point for prediction. The backpropagation neural network (BPNN) model and a hybrid neural network (HNN) were applied to predict five indexes of the highway asphalt pavement performance, and the genetic algorithm (GA) was employed to optimize the hyperparameters of these models. The results indicate that the GA enhanced HNN model could increase the accuracy by 35% on average compared with traditional ANN in predicting the highway asphalt distress performance. Furthermore, a notable agreement is attained when comparing the predicted indexes to the whole-year measurement data invalidation with average coefficient of determination (R²) reaches 0.74. This study demonstrates the potential of an innovative ANN method in highway distress prediction to provide direct guidance for long-term highway asphalt pavement optimal rehabilitation and maintenance (R&M) decisions.
Mixture segregation is a common defect in the construction of epoxy asphalt mixture (EAM) deck pavement. The segregation can affect the compaction quality of EAM deck pavement, while the compaction action can also change the segregation degree in the EAM. Therefore, the appropriate compaction technique can decrease the mixture segregation. The objective of this study is to investigate the mutual effect of mixture segregation and EAM compaction. To achieve this goal, the Superpave gyratory compaction (SGC) test was conducted, and a field compaction DEM (Discrete element method) model for EAM on the steel bridge deck was developed using a partitioned deposition method, to study the segregation characteristics of EAM during the compaction. Results show that the partitioned distribution segregation of aggregate in the EAM decreases first and then increases with the increase of gyration compactions. As a thermosetting material, the segregation is more likely to occur in the lowly cured EAM during the compaction process. In the field compaction, the initial vertical distribution segregation of loose EAM has a significantly negative effect on the compaction quality of EAM deck pavement, while the compaction action could also influence the segregation degree of EAM. Under the over repeated compaction, the increasing 1segregation degree of fine EAM particles and too tight contact between EAM particles make the extrusion separation of asphalt mastic between the coarse particles, which could result in the surface bleeding problem. The findings from this study are helpful to decrease mixture segregation and improve compaction quality of EAM deck pavement..
The reliable correlation model for intelligent compaction (IC) is to be developed by integrating characteristics of the filling material and control parameters of the vibratory roller. Key characteristics of the backfill soil from the construction site of Rongwu Highway are tested through the modified Proctor test and the direct shear test. A well-documented dataset is built by summarizing 4000 shear strengths from open literature and 246 data from laboratory tests in this study. The PSO-BP-NN model is developed based on this dataset to predict the shear strength and compactness of the subgrade soil in the scope of mechanical properties and compaction powers. The importance analysis of the input variables is performed with the Random Forest algorithm. The influence mechanism is analyzed in sequence. The plain soil and the lime soil demonstrate typical compaction curves, and the lime soil is less sensitive to the influence factors. An optimal compaction power exists for determining the optimal moisture content utilizing the shear strength, tending to be less conservative. The moisture content is the most important factor for the compactness, followed by the compaction power; the particle size is suggested to be considered for real-time evaluations. The compaction mechanism is mainly attributed to the water film theory and the electrochemical property of the filling soil. This study aims to provide a reliable model to estimate the compactness in the aspect of material properties so as to enhance the accuracy of the IC model.
The premise of improving the ride comfort of all-terrain crane by controlling the active suspensions is to realize the accurate identification of the road level. Existing researches on road level identification using vehicle responses are mostly based on small vehicles with two axles, while few researches on multi-axle large vehicles. This paper analyzes the response parameters of all-terrain crane when driving on typical roads, and proposes a method of road level identification based on the Support Vector Machine (SVM) by using the data of oil pressure and displacement of active suspensions. The training of SVM is completed by using the models of random road and all-terrain crane to generate the response information of vehicle traveling on each level of road. The accuracy of the models and the identification results are verified. The verified results on an independent test set show that the identification accuracy of road level can reach 98%.
Agencies responsible for construction and maintenance of roadways often use some measure of performance to qualify asphalt mixtures before being used in construction. As of this writing, the state of Texas uses the Hamburg wheel tracking test and indirect tensile strength test to qualify a hot mix asphalt produced for roadway construction and maintenance. Optimizing the mixture design to produce mixtures with the desired performance criteria has been a topic of interest for asphalt researchers and industry personnel. This study explores the use of machine learning methods to estimate the rut depth from the Hamburg wheel tracking test and the indirect tensile strength from the mixture design and volumetric information. Support vector regression analysis and decision tree based ensemble methods, including bagging, random forests, extra-trees, and gradient boosting algorithms were trained with data collected by the Texas Department of Transportation for quality control and quality assurance purposes. Metrics related to mixture design including aggregate gradation and absorption, asphalt binder content and performance grade, use of warm mix asphalt, recycled materials, and laboratory-molded density as well as test information, such as number of wheel-passes applied in the Hamburg wheel tracking test, were used as input variables. The analysis showed that all of the machine learning algorithms adopted in this study were able to estimate the mixture performance criteria from the mixture design and volumetric properties when the models were trained with curated and sufficient data. While extra-trees provided the best performance in terms of the coefficient of determination, gradient boosting and support vector regression models were found to learn from the imbalanced data better than the other methods. This study offers opportunities for the development of data-driven performance-oriented mixture design optimization technique that can potentially replace the trial and error, mostly experience based, and time consuming processes preceding the laboratory verification during the mix design process.
Pavement temperature prediction plays a key role in determining the structural capacity and deflection of asphalt pavement, owing to the viscoelastic behavior of asphalt. Thus, a high degree of accuracy is desirable for the prediction of asphalt temperature from available parameters such as air temperature and solar radiation. Asphalt temperature prediction models can be based on different approaches, including analytical, numerical, and statistical methods. Each of these models has its own strengths and weaknesses, and their accuracy varies based on site conditions. The goal of this research is to compare the accuracy of machine learning approach in general with existing models for prediction of temperature in asphalt pavements, based on 6 years of data collected from temperature sensors embedded in an instrumented test road in Alberta. A sensitivity analysis was performed to determine the most important parameters for prediction of temperature, and MATLAB regression learner was used for implementing machine learning-based algorithms based on parameters, which were determined to be air temperature, solar radiation, and day of the year. The machine learning methods were compared with existing literature models for prediction of average, minimum, and maximum daily pavement temperatures at different depths throughout the asphalt layer. The predicted results were validated by comparison with available field data. All machine learning algorithms used in this study resulted in the prediction of temperature values with higher accuracy compared to existing models, demonstrating the applicability of these machine learning models for improved pavement temperature prediction.
The segregation of asphalt pavement is the main reason for the decrease of safety, comfort and actual service life of the road, and the paving segregation is the main inducement for asphalt pavements segregation. Thus, a kind of effective paving segregation detection method can reduce the occurrence of asphalt pavement segregation. The traditional asphalt segregation detection methods are mainly divided into contact detection and non-contact detection. The contact detection method can only detect the segregation of pavement after paving or in use, and the non-contact detection method is also generally limited by the noise and expensive equipment. In recent years, the rapid development of image processing technology has provided a new research direction for asphalt paving segregation detection, but the accuracy and efficiency of the existing image-based asphalt paving segregation detection methods are insufficient. In order to solve these problems, this paper proposes an asphalt paving segregation detection method based on image texture features. Firstly, based on the traditional algorithms LBP (Local Binary Pattern) and GLCM (Gray-level Co-occurrence Matrix), a new texture feature extraction algorithm uniform pattern LBP-GLCM is proposed. Secondly, a detection method based on uniform pattern LBP-GLCM in combination with SVM (Support Vector Machine) is proposed. Then, the detection method proposed is validated using Kylbery texture dataset, the result show that this detection methods has great accuracy and efficiency in the classification of targets with similar texture features, it also means the texture feature extract method based on uniform pattern LBP-GLCM can combine the advantages of LBP and GLCM to achieve improvement of feature extraction's performance and efficiency. Finally, the detection method is applied to the diagnosis of asphalt paving segregation, and the accuracy of diagnosis achieves 94%. Compared with the existing algorithms, detection method based on uniform pattern LBP-GLCM has higher diagnostic accuracy and efficiency. Specifically, detection method with uniform pattern LBP-GLCM can improve accuracy in comparison with single asphalt pavement paving segregation detection method, and it can improve efficiency in comparison with existing hybrid asphalt pavement paving segregation detection method. The results of this study can potentially be used for real-time detection of asphalt paving segregation.
Segregation of asphalt mixture is one of the main concerns causing early-stage failure of asphalt pavement. However, currently, the generation and degree of segregation are mostly judged according to the visual observation which is highly subjective and only applicable to large particle size and coarse asphalt mixture. Otherwise, facing to tedious and huge detection results, inefficient traditional recording and Excel presentation methods reveals a poor productivity. Therefore, this study proposes a new framework for quantitative analysis and visual presentation of segregation in asphalt mixture by integrating both digital image processing (DIP) and Building Information Modeling (BIM) technologies. In this method, a new algorithmic language is established for DIP approach, which could extract more image information, such as segmentation number and edge length in each area. Furthermore, a quantitative index is proposed to evaluate extent of segregation in asphalt mixture, which classifies segregation of asphalt mixture into mild, moderate and severe segregation. Besides, the framework incorporates BIM as a supporting technology to visualize the detection results of pavement segregation on 3D images. Meanwhile, warning points are generated for future maintenance. Finally, a case study demonstrates the feasibility of the proposed framework. This paper contributes by offering a new approach for the detection of the segregation in asphalt mixture by an easy operation and low cost way. Additionally, this approach also represents the DIP result by an intuitive review based on BIM, which improve the efficiency and decrease time-consuming during the construction phase.
The characteristic of temperature field plays a significant role in the compaction quality of asphalt pavement , and various factors could affect the thermal parameters of the pavement and thus affect the distribution of the temperature field during compaction. In this research, the temperature transfer theoretical model and finite element model of asphalt pavement were established and calibrated through field measured data, and the sensitivity analysis was conducted to evaluate the factors affecting the temperature field, also a quantitative model of effective compaction time was established. The results found that the initial rolling temperature and layer thickness affected the overall temperature field during com-paction, and the wind speed and air temperature mainly affected the temperature field of the upper layer of hot mix asphalt (HMA). The change of the underlying layer temperature mainly affected the temperature field of the bottom of the layer. The established quantitative model provided a mathematic tool for the guidance of the field compaction process.
In recent years, an enormous amount of research has been carried out on support vector machines (SVMs) and their application in several fields of science. SVMs are one of the most powerful and robust classification and regression algorithms in multiple fields of application. The SVM has been playing a significant role in pattern recognition which is an extensively popular and active research area among the researchers. Research in some fields where SVMs do not perform well has spurred development of other applications such as SVM for large data sets, SVM for multi classification and SVM for unbalanced data sets. Further, SVM has been integrated with other advanced methods such as evolve algorithms, to enhance the ability of classification and optimize parameters. SVM algorithms have gained recognition in research and applications in several scientific and engineering areas. This paper provides a brief introduction of SVMs, describes many applications and summarizes challenges and trends. Furthermore, limitations of SVMs will be identified. The future of SVMs will be discussed in conjunction with further applications. The applications of SVMs will be reviewed as well, especially in the some fields.
Hot mix asphalt (HMA) compacted at low temperatures develops many distresses due to high air voids. Asphalt compaction operations in the field are mostly based on the experience of field staff. Hence, independent of the actual temperature of the HMA. In this study, temperature variation in hot mix asphalt (HMA) was investigated during paving operations at eight test locations in field. Two most commonly used HMA layer thicknesses i.e. 5 cm and 8 cm were studied. Temperature of the fresh HMA layer was noted at the centre, surface and at the interface points by four node K-type thermocouple assembly. The average laying temperature of the HMA for eight tests was calculated as 136.92 °C. Whereas, the average compaction start temperature for eight tests was noted as 127.81 °C which shows the critical temperature loss of 9.11 °C before the compaction starts. The average compaction end temperature calculated was 62.89 °C which is below the common cut off temperature of 80 °C. Temperature difference between day and night tests was 10 °C which can be attributed as the effect of sunlight. The results of this study can be helpful to the field staff in decision making during paving operations.
As thermal energy storage (TES) technologies gain more significance in the global energy market, there is an increasing demand to improve their energy efficiency and, more importantly, reduce their costs. In this article, two different methods for insulating TES systems that are either incorporated inside residential buildings or buried underground in direct vicinity of the building are reviewed and discussed. Boundary conditions are storage volumes in the range 10 – 1000 m3 and storage temperatures up to 90 °C. The first method involves the application of thermal insulation materials on the outside of the storage. Thermophysical properties and costs of conventional materials (such as mineral wools and organic foams) are compared against those of state-of-the-art products such as vacuum insulation panels and aerogels. A parametric comparative analysis is conducted to evaluate the combined costs of thermal insulation and living space occupied by the thermal insulation for TES systems integrated inside buildings. It is shown, for example, that the use of vacuum insulation panels becomes advantageous when the economic value of saving living space outweighs the extra cost of the insulation itself. The second method discussed is the so-called evacuated powders, in which the insulation is realized by creating an evacuated double-wall powder-containing envelope around the storage. The theoretical foundations of this method are discussed and the properties of commonly used powders – such as expanded perlite and fumed silica – are provided. Reference costs of double-wall vacuum-insulated TES tanks are provided and the use of evacuated powders is compared against the application of conventional insulation materials.
Floods, as a catastrophic phenomenon, have a profound impact on ecosystems and human life. Modeling flood susceptibility in watersheds and reducing the damages caused by flooding is an important component of environmental and water management. The current study employs two new algorithms for the first time in flood susceptibility analysis, namely multivariate discriminant analysis (MD), and classification and regression trees (CART), incorporated with a widely used algorithm, the support vector machine (SVM), to create a flood susceptibility map using an ensemble modeling approach. A flood susceptibility map was developed using these models along with a flood inventory map and flood conditioning factors (including altitude, slope, aspect, curvature, distance from river, topographic wetness index, drainage density, soil depth, soil hydrological groups, land use, and lithology). The case study area was the Khiyav-Chai watershed in Iran. To ensure a more accurate ensemble model, this study proposed a framework for flood susceptibility assessment where only those models with an accuracy of >80% were permissible for use in ensemble modeling. The relative importance of factors was determined using the Jackknife test. Results indicated that the MDA model had the highest predictive accuracy (89%), followed by the SVM (88%) and CART (0.83%) models. Sensitivity analysis showed that slope percent, drainage density, and distance from river were the most important factors in flood susceptibility mapping. The Ensemble modeling approach indicated that residential areas at the outlet of the watershed were very susceptible to flooding, and that these areas should, therefore, be prioritized for the prevention and remediation of floods.
The knowledge of global solar radiation (H) is a prerequisite for the use of renewable solar energy, but H measurements are always not available due to high costs and technical complexities. The present study proposes two machine learning algorithms, i.e. Support Vector Machine (SVM) and a novel simple tree-based ensemble method named Extreme Gradient Boosting (XGBoost), for accurate prediction of daily H using limited meteorological data. Daily H, maximum and minimum air temperatures (Tmax and Tmin), transformed precipitation (Pt, 1 for rainfall > 0 and 0 for rainfall = 0) and extra-terrestrial solar radiation (H0) during 1966–2000 and 2001–2015 from three radiation stations in humid subtropical China were used to train and test the models, respectively. Two combinations of input parameters, i.e. (i) only Tmax, Tmin and Ra, and (ii) complete data were considered for simulations. The proposed machine learning models were also compared with four well-known empirical models to evaluate their performances. The results suggest that the SVM and XGBoost models outperformed the selected empirical models. The performance of the machine learning models was improved by 5.9–12.2% for training phase and by 8.0–11.5% for testing phase in terms of RMSE when information of precipitation was further included. Compared with the SVM model, the XGBoost model generally showed better performance for training phase, and slightly weaker but comparable performance for testing phase in terms of accuracy. However, the XGBoost model was more stable with average increase of 6.3% in RMSE, compared to 10.5% for the SVM algorithm. Also, the XGBoost model (3.02 s and 0.05 s for training and testing phase, respectively) showed much higher computation speed than the SVM model (27.48 s and 4.13 s for training and testing phase, respectively). By jointly considering the prediction accuracy, model stability and computational efficiency, the XGBoost model is highly recommended to estimate daily H using commonly available temperature and precipitation data with excellent performance in humid subtropical climates.
In this paper, the behaviour of geosynthetic cementitious composite mat (GCCM) made of geotextiles and cement powder was investigated. The aims of the development of the GCCM are focused on geotechnical engineering applications. Experimental study includes physical and mechanical properties investigation of GCCM under installation and loading conditions. Testing of tension and flexure by monotonic loading showed that the GCCM can be used in soil reinforced structure. Additionally, puncture and frictional resistances of the GCCM are also important properties for slope protection. In conclusion, enhancing geosynthetic with cement paste can provide both strength and durability to be used for slope stabilisation. The key properties of GCCM reported in this paper can be used as design parameters of GCCM for geotechnical engineering applications.
In this study, properties of warm mix asphalt (WMA) compacted with various levels of gradation segregation were evaluated in the laboratory. Six segregated gradations were designed to compare with the control gradation and test sections were paved with the control gradation. Then pavement quality indicator (PQI) and field coring were used to evaluate the uniformity of the WMA test sections with the statistical method. In addition, sieve analysis of the cores was conducted to evaluate the level of segregation. The test results show that gradation segregation has a remarkable effect on water stability, high-temperature stability, low-temperature cracking, and tensile strength of WMA mixtures. Statistical analysis results show that the levels of segregation in localized areas are quite typical because the air void contents follow a normal distribution and the mixtures along the central line are denser than other areas. Sieve analyses of the cores show that most places of the typical segregated localized areas in the test sections have no segregation or low-level segregation, so the construction quality is good. It also shows that the air void content increases as the gradation gets coarser, which is consistent with laboratory test results.
Temperature segregation is non-uniform temperature distribution across the uncompacted asphalt mat during paving operations and may have detrimental effects on the quality and performance of asphalt pavements. However, many research studies conducted across the US have reported mixed observations regarding its effects on the initial quality and long-term performance of asphalt pavements. The objective of this study was to determine the effects of the temperature segregation on the density and mechanical properties of Louisiana asphalt mixtures. Seven asphalt rehabilitation projects across Louisiana were selected. A multisensor infrared bar (Pave-IR) system and a hand-held portable thermal camera were used to measure the temperature of asphalt mats. Field core samples were collected from various areas with varying severity levels of temperature segregation and tested for the density, fracture resistance (Jc) by semi-circular bending (SCB), rut depth by wheel tracking, and dynamic modulus (|E*|) by indirect tension (IDT) devices. Two distinctive patterns of non-uniform temperature distribution were observed: a cyclic and irregular temperature segregations. Laboratory test results showed that highly temperature segregated asphalt pavements (i.e., temperature differentials ≥41.7°C) can have significantly lower densities and the mechanical properties than the non-segregated area, especially when the temperature differentials are measured at compaction.
Segregation of asphalt mixtures indicates an artificially altered aggregate gradation, which consists of excessive coarse aggregates and insufficient fine aggregates that may result in premature failures and eventually reduce the pavement service life. Since segregation may cause a significant change in aggregate structure of asphalt mixtures, segregated mixtures may exhibit an increased potential for rutting among all other distresses. However, the effect of segregation on rutting potential has not been clearly identified. In this study, the effect of segregation on change in aggregate gradation (particularly for coarse aggregate structure) that may negatively affect the rutting potential of asphalt mixtures was evaluated. The Dominant Aggregate Size Range (DASR) gradation model and the DASR porosity parameter found to be well correlated with rutting performance of asphalt mixtures were employed for evaluation. A total of four field sections exhibiting different severities of segregation were selected and evaluated. Results of laboratory testing and DASR analysis indicated that segregated mixtures caused a significant shift in aggregate gradation, especially for coarse aggregate portion of the mixture gradation, which may result in significantly increased the potential for rutting. The results obtained from laboratory tests and the DASR approach were then compared and verified with those of actual filed rutting performance.
Temperature segregation, which occurs as a result of differential cooling of asphalt mixtures, is a serious challenge during asphalt paving operations. The objective of this study is to investigate temperature segregation caused by paver stoppage through field measurements, laboratory tests, and finite-element (FE) analyses. Five Louisiana asphalt rehabilitation projects were selected for the study. A multisensor infrared temperature scanning bar (IR-bar) system was used for field measurements of the real-time thermal profiles of uncompacted asphalt mats behind the paver. Laboratory performance of thermally segregated asphalt pavements from three selected projects were evaluated by measuring the fracture resistance of field asphalt samples at 25°C using the semicircular bend (SCB) test. From field measurements, it was clear that temperature segregation occurs whenever the paver stops, and the level of segregation (temperature drop) is dependent on the duration of paver stoppage, e.g., temperature segregation of more than 55°C can occur within less than 1 h of the stoppage. Laboratory performance test results showed that the asphalt samples from unsegregated areas generally had better fracture resistance than the samples from the segregated areas did. FE analysis results showed nonlinear decreases of temperature in the uncompacted asphalt mats. Furthermore, the cooling rate of hot-mix asphalt (HMA) was almost twice as fast as the warm-mix. To avoid high-severity temperature segregation (more than 21°C), it is recommended that paver stoppage time should be kept minimum with a maximum duration of 4 min for hot-mix and 6 min for warm-mix asphalts, respectively.
Temperature segregation refers to as different mixture cooling areas during construction in asphalt pavements. The objective of this study is to evaluate the effect of temperature segregation on warm mix asphalt (WMA) with laboratory and field tests. The performance of WMA compacted at four various temperatures was evaluated in the laboratory. The temperatures were measured during construction in the field sections with infrared thermography and plug-in thermometers. The pavement quality indicator (PQI) was applied to measure the density and the air void content at 216 testing locations the day after construction. In addition, field cores were collected to verify some of the PQI results. The test results showed that temperature segregation of WMA had a remarkable effect on the aggregate structure, density, water stability, high temperature stability, low temperature cracking and tensile strength. The reason for temperature segregation and related preventive measures are recommended at the same time. Based on the study, the preliminary temperature segregation criteria are recommended with the consideration of the field measurement. In application, the temperature segregation of a typical gradation with a nominal maximum aggregate size of 19 mm, referred to as AC-20 WMA, was suggested to be divided into four levels in view of the air void content: no segregation, low-level segregation, medium-level segregation and high-level segregation. The corresponding temperature differences were <3 °C, 3–8 °C, 8–18 °C and >18 °C, respectively.