A laboratory soil investigation for failed and serious pavementcondition rating show that the liquid limit varies from 33.02% -44.48% and Plasticity index from 11.3% - 25.56%, according to ERA manual, soils with LL< 50% and PI > 25% are suitable subgrade materials so all station are good. The soils were classified by ASSHTO under the A-6 and A-7-6 category which showed that the soils were fair to poor as a sub-grade material. The soaked CBR values of subgrade soil materials are between 7.9% - 10.4%. According to ERA manual CBR values greater than 5% are good subgrade materials. Therefore, from the laboratory test results the subgrade soil was not the cause of pavement failure for failed and serious pavementcondition rating.
3.4. Sweater Condition Environnementales conditions affect pavementcondition. Moisture in particular adversely affects pavement performance and causes the pavement to deteriorate faster. Moisture not only affects pavement ingredients but can also Effect by causing physical damage. In colder climates freezing may possibly lead to deterioration through cracks. Freeze-thaw cycle damages pavement integrity. An increase in the moisture content in pavement materials may lead to faster pavement deterioration. The prediction model, therefore, has to consider and account for adverse weather conditions. Since climatic diversity within Tehran is non-existent therefore this factor was considered a constant and not modeled.
Pavementcondition index is analyzing and evaluating of the pavementcondition for each segment in length. PCI can be determined by manual visualization and that has to be conducted periodically and the numerical rating starting from 1 to 100 is awarded to each road section. The typical rating is: 90 to 100 for excellent; 80 to 89 for very good; 70 to 79 for good; 60 to 69 for fair; and lower than 60 for poor. There are so many standards developed by different organizations such as the method of U.S Army corps of engineering, the Highway preservation system useful in Canada, the Indian Road Congress (IRC) method. Each method is based on different criteria. The main use of PCI is to determine the fund required to maintenance and rehabilitation and to determine the priority of the segment to be repaired first .
The pavementcondition forecasting models predict the deterioration of the pavement over time, which is manifested in various kinds of distresses. Pavementcondition deterioration estimation is an integral part of the pavement managementsystem. In a developing country like India, the funds being limited for the maintenance of the existing pavement, it is important to utilize the money in the most appropriate manner .To utilized the scarce resources and limited budget on right time as well as at right place there is a need offirst development of the pavementcondition forecasting models.
Pavements are complicated structures including several variables, as construction, performance, loads, materials, economics, maintenance and environment. Therefore, different procedure and economic elements must be taken into consideration when design, build and maintain better pavements. Furthermore, the road maintenance problems are still more compound because of road networks' dynamic nature where the network elements are changing continuously, may be removed or added. SO, these components must be maintained in good condition needs substantial expenditure, because these elements deteriorate with time (Mubarki, 2010). Roads which new paved, depreciate very slowly, and unnoticeably in the first (10-15) years of their life, after that depreciate more fast except timely repair is assumed. Accordingly, there is a require to use a controlled methodology to manage maintenance roads networks maintenance efficiently. A suitable system is able to allocate with total these variables, and recognize priorities for management so as to ensure the accomplishment of wanted goals of maintenance to perfect. Modifying PMS will assist highway agencies to accomplish and repair the networks in an active way (The word bank 1988). Determination of pavementcondition in Al-Muthanna City is the key component in deciding the extent and nature of the road repair should receive. This is being done by relying on field inspections and using computer software, in order to determining the maintenance needs at its numerous levels during the right time.
Fuel efficiency depends on a wide range of factors, including vehicle characteristics, road geometry, driving pattern and pavementcondition. The latter has been addressed, in the past, by many studies showing that a smoother pavement improves vehicle fuel efficiency. A recent study estimated that road roughness affects around 5% of fuel consumption (Zaabar & Chatti, 2010). However, previous studies were based on experi- ments using few instrumented vehicles, tested under controlled conditions (e.g. steady speed, no gradient etc.) on selected test sections. For this reason, the impact of pavementcondition on vehicle fleet fuel economy, un- der real driving conditions, at network level still remains to be verified.
To describe the pavementcondition, an index know as PCI (PavementCondition Index) is used of which value varied between 0 (for an unusable pavement) and 100 (for a proper pavement). PCI is both calculated from a field visual study and also accurately by considering the type and the severity of the deteriorations by measuring their amount. A schematic image of this technology is apparent in fig. (2), to determine PCI, a segment of pavement from all the pavement classification is selected. Due to deterioration state related to its general condition, the PCI number will be obtained that is saved in Micro Paver software database.
The existing road upgrading models mainly deal with pavement resurfacing. In 1980, the Transportation Research Board (TRB) introduces a ‘Decision Methodology for Maintenance and Upgrading’ of low-volume roads, estimat- ing maintenance cost and proposes a Generalised Road Roughness Index for Worldwide Use . In the same direction, the Minnesota Department of Transport (Mn/ DOT) uses three indices to report and quantify pavementcondition . The main outputs of the Highway Develop- ment and Management Manual  include prediction of pavement performance and maintenance, road improvement effects, user costs and benefits, estimates of environmental effects, standard economic indicators etc. In 2003, TRB publishes the results of a research entitled ‘Geometric De- sign Consistency on High-Speed Rural Two-Lane Road- ways’ . The quintessence of this particular research is focused in the definition of term ‘design consistency’ as follows: ‘ Design consistency is the conformance of a high- way’s geometric and operational features with driver expec- tancy’. The research team developed the basis for an expert system on design consistency to supplement work done by others in the development of FHWA ’s Interactive Highway Safety Design Model (IHSDM). In order to place the pro- posed design consistency system into perspective, a brief review of previous research on design consistency is here- after presented.
The objective of this study is to develop the most appropriate and simple technique of defining the pavementcondition state in the absence of detailed data of distress indices. For which historic development of pavementcondition indices are studied and limitations of the same are reviewed. Typical construction procedure used by Public Works Department of Maharashtra state is also studied. Average pavement life of bituminous rural road is observed as 14 years and hence the entire life span of a typical bituminous road is divided into 7 equal periods of 2 years each. Maintenance cost for such several pavement stretches in single lane rural road network is calculated for each of 2 year span of observation. Average repair cost required for improving quality of road stretch in various condition states is then identified from this data. Based on this observations condition states are defined in to 7 categories – from 7 (new condition state) to 1 (poor condition needing immediate total rehabilitation). For rate analysis, District Schedule Rates of Public Work Department, Pune 2012-13 is referred. The relationship between condition states of pavement v/s corresponding maintenance cost is plotted that helps to predict the nature of deterioration. This technique helps to find the right maintenance policy at particular time period and corresponding cost. This model provides guideline for identifying pavement distress types and defining the levels of severity and extent (area, length, count) associated with each distress.
• Other optimization methods include Neural Networks and Fuzzy Logic. Neural networks generalize and generate decisions by learning from examples. They are able to imitate the decision- making capability of humans without the use of any predefined mathematical equations. Fwa and Chan (1993) successfully demonstrate the use of neural networks for determining the priority rating of highway pavements. On the other hand, fuzzy logic systems can manage numerical data and linguistic knowledge. They can integrate vague qualitative data into the decision-making process. Moazami et al. (2011) applied fuzzy logic to prioritize 131 pavement sections in Tehran using such factors as pavementcondition index, traffic volume, road width, as well as rehabilitation and maintenance cost.
surface inspection to detect cracks and anomalies. Hyperspectral imaging, HSI, has been used previously to classify road conditions from satellite images     . The research was intended to classify road conditions in general and the spatial resolution can not detect road cracks or defects. Only few papers considered the detection of pavement cracks based on hyperspectral data    . In such case HSC were fitted on drones of low altitude flights to have higher spatial resolutions to enable observing cracks. The previous studies considered using descriptors of the spectrum such as the VIS2 (intensity difference between 830nm and 490nm-showing metal oxide content) and Short Wave Infra Red, SWIR (Intensity difference between 2120nm and 2340 showing hydrocarbon content). The metrics measure the rise and decay of spectral response curve at the wavelength regions for metal oxides and hydrocarbon which usually characterizes road conditions. These metrics have also been linked  to the PavementCondition Index, PCI,(A standard metric by ASTM D6433 and D5340, used to indicate the condition of road pavement and ranges 0-100) and is usually computed using visual surveys .
The primary aim of this process is to detect any distress (such as road surface cracks) at early stages in order to apply maintenance on time. Early detection of road surface cracks can assist maintenance before the repair costs become too high. In addition, measuring the condition and performance of roads are continuously developed overtime with the new methods and improvements. Recently, many researchers have proposed efficient collection of pavementcondition data. Significant progress in this field has been made, and new approaches have been proposed such as . The acquisition technique using images is more cost effective, easier, more dense (each millimeter), and more precise in measuring the defect. There are many image acquisition techniques are available -.
Abstract: Prediction models in mobility and transportation maintenance systems have been dramatically improved through using machine learning methods. This paper proposes novel machine learning models for an intelligent road inspection. The traditional road inspection systems based on the pavementcondition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi- layer perceptron (MLP) and radial basis function (RBF) neural networks as well their hybrids, i.e., Levenberg-Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE), and standard error (SD). The CMIS model outperforms other models with the promising results of APRE=2.3303, AAPRE=11.6768, RMSE=12.0056, and SD=0.0210.
Abstract: Construction of different roads, such as freeways, highways, major roads or minor roads must be accompanied by constant monitoring and evaluation of service delivery. Pavements are generally assessed by engineers in terms of the smoothness, surface condition, structural condition and surface safety. Pavement assessment is often conducted using the qualitative indices such as international roughness index (IRI), pavementcondition index (PCI), structural condition index (SCI) and skid resistance value (SRV), which are used for smoothness assessment, surface condition assessment, structural condition assessment, and surface safety assessment, respectively. In this paper, Tehran-Qom Freeway in Iran has been selected as the case study and its smoothness and pavement surface conditions are assessed. At 2-km intervals, a 100-meter sample unit is selected in the slow-speed lane (totally, 118 sample units). In these sample units, the PCI is calculated after a visual inspection of the pavement and the recording of distresses. Then, in each sample unit, the average IRI is computed. The purpose of this study is to provide a method for estimating PCI based on IRI. The proposed theory was developed by Random Forest (RF), and Random Forest optimized by Genetic Algorithm (RF-GA) methods and these methods were validated using correlation coefficient (CC), scattered index (SI), and Willmott’s index of agreement (WI) criteria. The proposed method reduces costs, saves time and eliminates the safety risks.
causes and pavementcondition have positive coefficients implying that a unit increase in these characteristics results in an increase in the chance of grievous injury. A unit decrease in road curve radius, vehicle responsible and day/night leads to an increase in the chance of grievous injury. The odds ratios of causes and pavementcondition are greater than 1 implying that a grievous injury has a higher chance of occurrence as the values of these characteristics increase. The odds ratios for road curve radius, vehicle responsible and day/night are less than 1 indicating that the chance of occurrence of non-injury increases as the values of these characteristics increases.
highway agencies in United States and other Countries has been collected data on pavementcondition, climate, and traffic volumes and loads from more than an thousand pavement test sections . Although developed as a tool for the LTPP program, the manual has broader application. It provides a common language for describing cracks, potholes, rutting, spelling and other pavement distresses being monitored by the LTPP program. Although not specifically designed as a pavement management tool, the Distress Identification Manual can play an important role in a state’s pavement management program by ridding reports of inconsistencies and variations caused by a lack of standardized terminology. Most pavement management program do not need to collect data at the level of detail and precision required for the LTTP program, nor are the severity level used in the manual necessary appropriate for all pavement management situations.
There are many pavement management software packages developed by various pavement engineers and researchers that are capable of identifying pavement distress types, severities and density of distress, analyzing pavement data to detect pavement distress types, severities and densities. Analyzed data can be stored in readable format or in GIS map forms that show the ranking of collected data according to certain manuals and guidelines. One of these systems is Uni-analyze software that can analyze the collected pavement images. Uni-analyze software measures the pavement distress types, density and severity of cracking manually and automatically. Then, a color coded digital map presented by the system which analyzes pavementcondition data after processing its. The system is cost-effective and user friendly to set up for the maintenance and rehabilitation scheduling. Also, the system is capable of measuring the quality assurance for automated crack detection systems and validating the uni- analyze system and other systems as well. Three different crack classification manuals standards were used SHRP- LTPP , AASHTO  and Unified cracking index  and the software can implement another standard upon the need of transportation agencies .
regression techniques to model crash frequency on four-lane rural roads in Italy, using five years crash data collected from 1999-2003 on 46.6 km (29 miles) of highway segment both during dry and wet pavement conditions, with AADT values ranging from 17,600 to 47,400. The authors proposed separate models for curve and tangent sections of wet and dry pavement surface conditions of the highways. The terms included in the study were AADT, segment length, sight distance, curvature, side friction coefficient, longitudinal slope, and rainfall. The results identified the presence of junctions, segment length, and AADT were the main factors contributed to severe crashes. When pavement surface condition was included as a variable, their model showed that wet pavementcondition was found to be a statistically significant variable, and the number of crashes occurred during wet pavementcondition increased by a factor of 2.32 for tangent sections as compared with the crashes on dry pavement surfaces. This result was different from the findings of (Krull et al., 2000), which suggested more crashes were likely to occur on dry pavement surface conditions. The 2008 and 2009 traffic crash data on Texas highways, were used by (Li et al., 2013), to analyze the impacts of pavement conditions rating including pavement distress, ride quality (smoothness), skid resistance, and International Roughness Index (IRI), on highway crash severity. Based on Texas Department of Transportation, the IRI scores between 1-95, 96-170 and 171-950 in/mi are considered very good, fair and poor respectively. The data analysis approach mainly used in the crash analysis was Pearson Chi-square of the crash severity outcomes and the predictor variables associated with pavement surface conditions followed by