Use of random forests regression for predicting IRI of asphalt pavements

In recent years, there has been an increasing interest in the application of machine learning for the prediction of pavement performance. Prediction models are used to predict the future pavement c...

Machine learning approach for pavement performance prediction

Economy and nonproductive sectors of each country could not function without a transport system (TS) Having analysed research works on the interaction of separate TS elements, it was identified that there is no common model for all types of interaction TS consists of material (physical) objects: traffic participants and freight to be carried, a transportation process and operations’ control TS classification scheme devised according to systematically selected criteria, showing that several criteria are often applied at the same time in official documents, is presented Original TS physical elements’ interaction model with 6 interaction levels is presented as well The model is suitable for all modes of transport Six levels of interaction are distinguished: autointeraction of transport elements, the first level; TS elements’ interaction, the second level; TS elements’ interaction with external environment, the third level; interaction of transport modes, the fourth level; TS interaction with t

/pdf/modelling-the-interaction-of-transport-system-elements-rkqe6prbua.pdf

Modelling the interaction of transport system elements

Improving accuracy of rutting prediction for mechanistic-empirical pavement design guide with deep neural networks

Pavement structural evaluation based on roughness and surface distress survey using neural network model

At a certain point in the life of a flexible pavement, rehabilitation is required to improve pavement condition and to defer reconstruction. Pavement managers seek the best rehabilitation treatment on the basis of cost effectiveness. Using 1994–2002 data from a wet-freeze mid-Western state in the United States, this paper analyzes the cost effectiveness of four flexible pavement rehabilitation treatments: functional hot-mix asphalt (HMA) overlay, structural HMA overlay, resurfacing (partial 3R standards), and mill full-depth and asphaltic concrete overlay. The performance indicator used is the international roughness index and treatment effectiveness is measured in terms of performance jump (short-term), and service life and increase in pavement performance (long-term). The treatment cost is the equivalent uniform annual cost per lane-km incurred by the agency and user; and cost effectiveness is the ratio of effectiveness to cost. The study estimated treatment effectiveness under various combinations of traffic loading and climatic condition, and initial pavement condition. The results suggest that in the short-term, HMA structural overlay is the most effective treatment. For the long-term, the results are equivocal: HMA structural overlay is most effective from the perspective of average performance over the treatment life; resurfacing (partial 3R standards) is the most effective from the perspective of treatment service life. With regard to cost effectiveness, however, the results were consistent: for all three measures of treatment effectiveness, mill full-depth and asphaltic concrete overlay unequivocally appears to be the most cost effective treatment. Finally, the paper recommends that cost effectiveness analysis should be accompanied by a candid deliberation of project constraints, the local environment, and agency practices.

Evaluating the Cost Effectiveness of Flexible Rehabilitation Treatments Using Different Performance Criteria

The Indiana Department of Transportation (INDOT) is increasingly committed to the pavement management system. For this reason, updated simple pavement performance prediction models with the least number of explanatory variables are required to predict the performance of various pavement types for future planning of rehabilitation or replacement. In Indiana, the two main pavement types are jointed concrete pavement and bituminous pavement. 1999 and 2000 year data were used to develop regression models for different pavement types for the interstate and non-interstate roads system. The international roughness index, in inches over mile, was mainly used for dependent variables while the age of pavement and the current average annual daily traffic were used as independent variables in best model searching. The data from the road test sections, which were randomly selected for this study, did not yield statistically strong pavement performance prediction models more probably due to non-uniform construction and foundation of the test sections. The rutting is recommended to be used as safety factor along with the pavement prediction models.

/pdf/development-of-improved-pavement-performance-prediction-4u8uv32jrm.pdf

Development of Improved Pavement Performance Prediction Models for the Indiana Pavement Management System

Development of a structural index for pavement management: An exploratory analysis

Several states have experimented with performance warranties on hotmix asphalt (HMA) pavements. Generally, the quality of warranted HMA is perceived to be better. Also, it is believed that HMA extends pavement life. Various methods can be used to define the benefits of warranties. Benefits have to be related to the performance life of the pavement and the cost. This study documents the effectiveness of the Indiana 5-year performance warranties and demonstrates that projected lifetimes of the warranted HMA pavements are being extended an additional 9 years in evaluations of international roughness index (IRI) and rutting criteria over the typical design life of the pavements. The cost-effectiveness of the warranted pavements, even though the initial costs are 5% to 10% higher, is significant when one considers the extended life of the warranted pavements. Overall cost to maintain the network Interstate smoothness at a constant 2002 value is $ 1.08 billion with warranties and $ 1.47 billion for nonwarranty ...

Benefits of warranties to indiana

Transportation agencies spend billions of dollars annually on pavement maintenance and rehabilitation to meet public, legislative, and agency expectations. Knowledge of the structural condition of a highway pavement is crucial for pavement management at both the network level and the project level, particularly when the system monitoring, evaluation, and decision-making are to be made in a context of multiple criteria that include structural condition. A key aspect of the performance criteria for multiple criteria decision making is that the criteria must be amenable to scaling so that it can be duly incorporated in the overall utility function. The main objectives of this research study are: 1) To develop a pavement structural strength index (SSI), scaled logistically from zero to a 100, based on the falling weight deflectometer (FWD) deflection measurements; 2) To formulate SSI in such a manner to be used as an index or employ the value of “100 – SSI” as a deduct value from pavement distresses surface index; and 3) To develop models by which the SSI could be estimated given functional class, age, and drainage condition wherever deflection measurements are not available. Extensive literature review of existing information related to pavement structural capacity assessment was conducted. Necessary data was collected from the Indiana Department of Transportation (INDOT) pavement management databases and deflection measurements available at INDOT Research and Development for both project and network levels. Information from INDIPAVE (a database that includes data on weather conditions, highway classification, traffic, and other information at over 10,000 one-mile pavement sections in the State of Indiana) were also employed. Weather information was also collected from the Indiana State Climate Office. The data includes information on 12,250 road sections from 1999 to 2007. Data was classified by pavement surface type (whether it is asphalt or concrete) and system classification (whether it is an interstate, a non-interstate but part of the national highway system (NHS), or a non interstate and not a part of the national highway system (non-NHS).

/pdf/development-of-a-structural-index-as-an-integral-part-of-the-37pm75hl7t.pdf

William Flora

Papers

Evaluating the Cost Effectiveness of Flexible Rehabilitation Treatments Using Different Performance Criteria

Development of Improved Pavement Performance Prediction Models for the Indiana Pavement Management System

Development of a structural index for pavement management: An exploratory analysis

Benefits of warranties to indiana

Development of a Structural Index as an Integral Part of the Overall Pavement Quality in the INDOT PMS