Pavement asset management system (PAMS) assists agencies and decision makers to maintain deteriorating pavement assets with optimized budget allocation. The recent developments in pavement condition ...data collection and processing have significant effect on estimating remaining service life and selecting optimum maintenance strategies. Further, image processing (IP) and artificial intelligence (AI) tools have improved the overall performance of PAMS by helping analyze big data emanating from distress surveys. The objective of this review paper was to collect and report several current state-of-the-art developments in PAMS and the associated embedded processes, majorly focused on data collection procedures, analytical techniques, decision making tools, and processing methods. The shift from manual condition surveys to automated pavement condition surveys has profusely improved data collection rate. The wide-range of data collection methods, manual, automated vehicles, and cost-effective methods followed across the globe were reviewed. Further, the chronological development in data analysis, specifically, distress evaluation, homogeneous sectioning for selection of maintenance strategies, and prioritization and optimization of maintenance strategies were discussed while emphasizing the application of IP and AI in enhancing the efficacy of PAMS. In addition, this paper provided a narrative account of the interdisciplinary research and multi-scale developments that recognize the value-addition of cutting-edge technologies in AI and computer vision.
Display omitted
•Documented chronological developments in Pavement Asset Management Systems•Reviewed pavement condition state-of-the-art data collection technologies•Collected image processing and machine learning applications in PAMS data analysis•Discussed utilization of various heuristic techniques in effective decision making•Collation of literature indicative of vast scope to use AI in automating PAMS
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Pavement condition classification based on different condition parameters is one of the primary challenges in any effective Pavement Management System (PMS) and its use as a decision aid tool is ...inevitable. Agencies adopt different condition classification and assessment model based on the availability of resources for data collection and their ability to address pavement issues prevalent in the area. However, a system for pavement condition classification is not yet well established in India. Therefore, the present study develops a 0–100 scale Pavement Condition Rating Index (PCRI) for condition classification of asphalt pavements in India. The development of proposed condition rating index is based on expert opinions and existing guidelines. Six sub-indices were developed for cracking, ravelling, patching, potholes, rutting and roughness using curve fitting based on threshold values. Further the subindices were combined to PCRI using weight factors obtained by Analytical Hierarchy Procedure (AHP). The application of developed Pavement Condition Rating Index (PCRI) model is presented in terms of condition classification and priority rating. The PCRI was found to give similar results in terms of priority ranking when compared with widely recognised HDM4 tool. Further, a sensitivity analysis using Pawn index method was performed and it was found that developed PCRI model is highly sensitive towards the number of potholes.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Pavements are major assets of highway infrastructure. Maintenance and rehabilitation of these pavements to the desired level of serviceability is one of the challenging problems faced by pavement ...engineers and administration in the highway sector. The evaluation of pavement performance using pavement condition indicators is a basic component of any Pavement Management System. Various indicators like Pavement Condition Index (PCI), Present Serviceability Rating (PSR), Roughness Index (RI), etc. have been commonly used to assign a maintenance strategy for the existing pavements. The present paper is an effort in the similar direction, to develop a combined Overall Pavement Condition Index (OPCI) for the selected network of Noida urban roads.
The study area consists of 10 urban road sections constituting 29.92km of Noida city. The methodology includes identification of urban road sections, pavement distress data collection, development of individual distress index and finally developing a combined OPCI for the network. The four performance indices viz. Pavement Condition Distress Index (PCIDistress), Pavement Condition Roughness Index (PCIRoughness), Pavement Condition Structural Capacity Index (PCIStructure) and Pavement Condition Skid Resistance Index (PCISkid) are developed individually. Then all these indices are combined together to form an OPCI giving importance of each indicator. The proposed index is expected to be a good indicative of pavement condition and performance. The developed OPCI was used to select the maintenance strategy for the pavement section.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
International Roughness Index (IRI) and Pavement Condition Index (PCI) are among other pavement condition indices used to assess pavement surface condition. The literature suggests that most of the ...pavement indices are related as a result of which several models have been developed to predict one index from the other. This study uses the Long-Term Pavement Performance (LTPP) database to develop a simplified regression model that links PCI with IRI. Measured pavement distresses from 1448 LTPP sections from the Specific Pavement Studies (SPS) and General Pavement Studies (GPS) representing 12744 data points were utilised for the PCI estimation. A total of 1208 sections with 10868 data points were used for model development while 240 sections with 1876 data points were used for the model validation. A sigmoid function is found to best express the relationship between PCI and IRI with a coefficient of determination (R
2
) of 0.995. The bias in the predicted IRI values is significantly very low. The model validation using a different dataset also yielded highly accurate predictions (R
2
= 0.992). Finally, a pavement condition rating based on IRI is proposed. This system yields rating equivalent to the widely used PCI rating method which is based on the pavement condition.
Full text
Available for:
BFBNIB, DOBA, GIS, IJS, IZUM, KILJ, KISLJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Pavement management systems play a major role in preservation of a road network. The core of such systems is pavement condition evaluation. In order to evaluate pavement condition, a pavement ...condition index is required. To date, several pavement condition indices have been developed; however, they have not been comprehensive, cost-effective, and practical for automated data collection. The objective of this study is to develop a novel pavement condition index expressing comprehensive representation of pavement condition considering structural adequacy, pavement roughness, road safety, and surface distress using a machine learning model. The outcome shows approximately 84% reduction in pavement distress analysis efforts. Moreover, the model with more than 80% accuracy and precision is highly correlated with the Pavement Condition Index (PCI). Thus, the proposed index not only provides similar results to the PCI, but it is also much more cost-effective, practical, and time-saver than the PCI.
•Development of a new pavement condition index particularly for automated data collection.•Development of an Artificial Neural Network model for the index development.•Validation of results of the developed index with the Pavement Condition Index (PCI).•Reduction in pavement condition evaluation efforts using the developed index compared to the PCI.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
•The first pavement image dataset that contains wide variety of pavement distresses.•The model not only detects various distresses but also quantify their severity.•Predictive models developed to ...rank pavement conditions based on detected cracks.•The models eliminated human error from the pavement condition evaluation process.•Two GPS coordinates are needed to evaluate the pavement condition of pavement.
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.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Applications of non-destructive testing devices such as Falling Weight Deflectometer (FWD) provide crucial estimates of pavement health that assist in the optimisation of pavement management systems. ...However, regularly conducting these tests at a network level and post-processing of the collected data is cumbersome, which requires technical expertise, significant time, funds, and other resources. Due to this structural aspect of pavements during the selection of maintenance or repair, decisions are often ignored. This study attempts to develop reliable correlations for estimates of two different deflection basin parameters using a number of structural, functional, environmental, and subgrade soil attributes as input. The data has been obtained through field tests over a 124 km long pavement network. Different artificial neural network-based models are trained by varying the number of hidden layers and neurons in these layers, for the above-mentioned purpose. The coefficient of determination and mean square error is decisive for the selection of best network architecture. These outcomes are also compared to the results of the classical multiple linear regression method, and the superiority of neural networks over non-intelligent approaches for non-linear problems of pavement engineering is appreciated. In addition to this, the results justify the fact that the properties of the asphalt layer predominantly impact the entire pavement condition. The proposed approach is an alternative way to facilitate quick pavement condition assessment by reducing the frequency of deflection testing without compromising with the accuracy of its estimates. It would encourage the increased application of structural condition data in pavement maintenance and rehabilitation necessities with ease. However, the study does not intend to completely avoid conducting deflection testing and serve as a base for future studies.
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK
Airports strive to prevent safety issues, such as foreign object debris (FOD), by pavement management using the pavement condition index (PCI). The index is used in decision-making processes for ...overall pavement maintenance and repair, such as the prevention of additional damage due to cracks and the like. However, considering the current situation in Korea where mostly mid-sized and large commercial airports exist, problems regarding direct applications of the existing PCI deduct value have been consistently pointed out. In addition, as the relationship between the PCI and whether maintenance and repair are required is unrealistic, there have been difficulties in communication between maintenance and repair staff and decision makers. Therefore, to resolve these problems, this study first analyzed the calculation procedure of the existing PCI and then redefined the main distress type of Korean airport pavements. In addition, a deduct value curve (DVC) in terms of the severity level for six main distress factors of asphalt pavements and eight main distress factors of concrete pavements and a corrected deduct value curve (CDVC) for multiple distresses in terms of the pavement form were developed using panel rating, which is an engineering approach, by forming an airport pavement expert panel. Finally, a Korea airport pavement condition index (KPCI) was proposed using the curves, and the field application results were compared against the existing PCI to examine the adequacy of the KPCI. As a result, the developed criteria showed an overall trend lower than existing PCI. Moreover, it was verified that this trend increases with worsening pavement condition. It appears that a more discriminating evaluation may be possible when determining pavement conditions by PCI results of the developed criteria.
Pavement management systems play a significant role in country's economy since road authorities are concerned about preserving their priceless road assets for a longer time to save maintenance costs. ...An essential part of such systems is how to collect and analyze pavement condition data. This paper reviews the state-of-the-art techniques in pavement condition data evaluation using machine learning techniques, more specifically, the application of machine learning methods: image classification, object detection, and segmentation in pavement distress assessment is investigated. Furthermore, the pavement automated data collection tools and pavement condition indices have been reviewed from the lens of machine learning applications. The review concludes that the overall trends in pavement condition evaluation is to apply machine learning techniques although there are some limitations not only in detection of few pavement distresses with complicated patterns but also in indication of the severity and density of distresses leading to avenues for future research.
Display omitted
•Reviewed various data acquisition tools for pavement condition evaluation•Documented pavement distress detection using machine learning•Investigated on machine learning applications in assessment of pavement condition indices•Studied public and private datasets for training of machine learning models
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abstract
Pavements are the main assets of highway infrastructure. Pavement Condition Index (PCI) is a numerical index used to describe the general condition of a pavement. This paper is another trial ...in monitoring and find pavement condition index (PCI) by applying PAVER software version 5.2. This work aims to evaluate (PCI) of a flexible pavement of some miner collector highways in the north sector in Najaf city divaricate from both sides of Najaf- Karbala suburban main collector highway in its part away from Al- Askariin intersection towards Karbala. These highway sections are Al-Rahma, Al Hizam Al Akhdar, and Al Muearid, Al Shamalii garage highways which cover a total length approximately 11.54 km in both direction of traffic movement (diverging from Najaf- Karbala highway and return to it). Field survey data such as highway section geometric design and distresses type, dimension, and severity, were collected depending on sample size and number of samples extracted, and then entered into the PAVER program to calculate PCI. The result of PAVER shows Results approved that Al-Rahma and Al Shamalii garage highways sections are in satisfactory level, while Al Muearid highway section in (fair) and Al Hizam Al Akhdar in worst case (poor). In addition to that, reasons of these defects had been figuring out according to results obtained.