Robust Optimization for Managing Pavement Maintenance and Rehabilitation

Angular fuzzy logic application for pavement maintenance and rehabilitation strategy in Ohio

Knowledge acquisition and representation model for developing an expert system for pavement maintenance and REhabilitation strategy in the State of Ohio (ESPRESSO)

Local government officials find themselves squeezed between the need to produce pavement rehabilitation and maintenance budgets by using rational, systematic approaches and the lack of pavement engineering expertise and scarce funds. To meet that challenge, an appropriate pavement management system (PMS) is required. Such a system must be sufficiently sophisticated, yet straightforward and transparent in use. This paper outlines the development of a PMS designed specifically to meet the unique needs of local governments having the task of managing pavement assets. It sketches the environment in which such systems must work to set the terms of reference, discusses data collection requirements, covers pavement deterioration, comments on maintenance and rehabilitation treatment selection, and details the desirable budgeting capabilities.

The goal of this paper is to summarize some practical issues of date research concerning the development and implementation of the risk management application Risk3M for Pavement Maintenance and Management System (PMMS). The paper also illustrates the need for potential development of such a risk system for analysis and risk factors and mitigation in pavement maintenance and rehabilitation strategies. We use a particular implementation of the k-nearest neighbors (k-NN) algorithm as a non parametric alternative method for reference class forecasting, based on mathematical kernel density estimate.

Purpose: Systematic pavement management plays a vital role in the better Road Asset Management system. The lifespan of pavement can be preserved and prolonged by adequate maintenance measures in proper time. By early detection and repair of defects at initial stages with predictive maintenance reduces the rapid deterioration of the pavement. Moreover, inaccuracy in pavement deterioration prediction leads to an improper maintenance with wastage of time, cost and labor strength. To overcome all of these obstacles, this paper attempts an approach on optimal pavement maintenance strategy by means of fuzzy rule-based system. Materials and Methods: In this research, four pavement indicators of PCI, IRI, PSR and PSI have been taken into account as antecedents and five different types of pavement maintenance as consequents. In this research, ASTM D-6433, Road Lab Pro software, AASHTO guidelines and Fuzzy Logic (Mamdani) model have been used to evaluate the current pavement condition and optimal pavement maintenance strategies. Findings: According to research area, 130 total pavement sample units were undertaken to study for the mean pavement condition of PCI value 54.93 (poor), IRI 7.01 (fair), PSR 3.33 (fair) and PSI 3.35 (fair). Due to 13 years-old life span of traffic volume, temperature and other external factors, this expressway is suffering from potholes, bleeding, longitudinal and transverse cracking, weathering, joint reflection cracking for Asphalt Concrete (AC) overlay and linear cracking, joint seal failure, scaling, faulting, depression, lane/shoulder drop off for existing concrete pavement. According to the fuzzy logic model results, 42 numbers of fuzzy If-Then maintenance rules were verified as the most relevant pavement maintenance and rehabilitation strategies for Yangon-Mandalay Expressway. Implications to Theory, Practice and Policy: This research provide implications to the study and contributions to theory, practice and policy. This research paper insights into effective infrastructure maintenance and investment, emphasizing the role of advanced computational techniques in transportation economics. The key advantage of this research paper is to be effective, supportive, easy and accessible decision-making tool for transportation and pavement engineers, expressway planners and highways department authorities especially from developing countries.

The problem of determining optimal pavement maintenance and rehabilitation strategies is a special case of a more general problem termed the asset depreciation problem. Perhaps the most general formulation and solution of the asset depreciation problem is the semi-Markov formulation. This paper illustrates how the semi-Markov formulation and solution of the general asset depreciation problem can be applied to pavements. The semi-Markov formulation, like the Markov formulation, characterizes pavement deterioration probabilistically and represents human intervention (maintenance and rehabilitation) as slowing or modifying the basic probabilities of deterioration. The Markov formulation, first implemented for the state of Arizona, is shown to be a special case of the more general, less computationally intensive semi-Markov formulation. The application of the semi-Markov formulation is illustrated at the project level for a heavy-duty pavement in Manitoba. Key words: asset depreciation, infrastructure management, pavement management, probabilistic modelling, Markov, semi-Markov, maintenance optimization, project level.

This paper presents a new pavement management system (PMS) to achieve the optimal pavement maintenance and rehabilitation (M&R) strategy for a highway network using genetic algorithms (GAs). Optimal M&R strategy is a set of pavement activities that both minimise the maintenance cost of a highway network and maximise the pavement condition of the road sections on the network during a certain planning period. NSGA-II, a multi-objective GA, is employed to perform pavement maintenance optimisation because of its robust search capabilities and constraint handling method that deal with the multi-objective and multi-constrained optimisation problems. In the proposed approach, both deterministic and probabilistic pavement age gain models are utilised for evaluating the evolution of pavement condition over time because of their simplicity of application. The proposed PMS is applied to a case study network that consists of different kinds of road sections. The results obtained indicate that the model is a valuable toolbox for pavement engineers.

Rough Set Theory (RST) is an induction based decision-making technique, which can extract useful information from attribute-value (decision) table. This study introduces RST into pavement management system (PMS) for maintenance and rehabilitation (M&R) strategy induction. An empirical study is conducted by using the pavement distress data collected from 7 county roads by experienced pavement engineers of Taiwan Highway Bureau (THB). For each road section, the severity and coverage of existing distresses and required M&R treatment were separately recorded. The analytical database consisting of 2,348 records (2,000 records for rule induction, and 348 records for rule testing) are established to induce M&R strategies. On the basis of the testing results, total accuracy and total coverage for the induced strategies are as high as 88.7% and 84.2% respectively, which illustrates that RST certainly can reduce distress types and remove redundant records to induce the proper M&R strategies.

Pavement data collection is the most expensive and time consuming component of Pavement Management System (PMS). Thus, possible methods of minimizing the need of such data might be critical in reducing pavement condition monitoring costs. Also the ability to relate pavement performance prediction models (frequently roughness based) to hot mix asphalt field performance models (distress based) provides valuable conclusions and input in pavement design, performance assessment, maintenance and rehabilitation strategies. Objective of this study was to examine whether specific distresses can influence roadway profile so as to be able to relate the two. The influence of pavement distresses on road profile has been investigated over the years. However, past studies provided conflicting conclusions. Thus, in this study an alternative approach was considered due to the availability of high quality and detailed distress data collected with the Laser Crack Measurement System (LCMS) of the Automatic Road Analyzer, ARAN. As it was expected, specific distresses have higher impact in longitudinal roughness since they are present on the roadway surface at regular intervals (i.e., specific frequencies). For this reason, instead of using summary indexes (i.e., International Roughness Index (IRI), Pavement Condition Index (PCI)), the Power Spectral Density (PSD) of the roadway profile at specific frequency bandwidths was considered along with distresses. The analysis indicated that a specific subset of distresses is affecting roughness at definite wavelength frequencies. Alligator cracking and rutting standard deviation provided the best correlation. IRI was correlated better with distress (e.g. rutting standard deviation) at lower profile frequencies. At high frequency domain (i.e., below 0.8 m wavelengths) better correlation between IRI and high severity cracking was observed through the PSD. Considering multiple frequencies in the regression models between roughness and distresses, the goodness of fit has not necessarily improved. However, the role of different bandwidths was evident. In addition to the specific results, the methodology presented in this study can be used elsewhere to assess potential relations between pavement roughness and distress components.

The automatic pavement management system has the advantage of providing reliable pavement maintenance and rehabilitation strategies aiming at prolonging existing pavement service life. Therefore, the quality of noise reduction results, which is an unavoidable process of automatic pavement assessment evaluation, has a significant influence on the reliability of pavement maintenance operations suggested. The primary purpose of this paper is to propose an innovative three-dimensional (3D) pavement image-based data filtering protocol, thereby maintaining a highly functional pavement surface. First, a 3D pavement depth data collection system was developed using laser light and a charge-coupled device camera. After that, based on the analysis of Positive Noise and Negative Noise, which are optical instrument-related noises, and tilted pavement model noise, the Primary Surface Profile (PSP)-based raw data filtering approach was proposed which aims at improving the noise reduction quality. Validation experiments were conducted using both the proposed approach and the traditional data filtering method, and the results show that for the not tilted pavement surface model, the PSP-based filter method can achieve the highest noise reduction value (NRV), whereas for the tilted pavement surface model, with a slightly lower NRV than that of biphasic standard deviation average filtering, which demonstrates that the proposed data filtering method has self-adaptive and robust data filter advantages which can be incorporated into a high-performance pavement performance evaluation and management system.

The quality of data in a pavement management system (PMS) has a direct impact on pavement maintenance and rehabilitation (M&R) decisions and management. However, pavement performance data and M&R action data often suffer from problems such as omissions and anomalies. To solve these problems, this study proposes a data cleaning framework based on artificial neural networks (ANNs) that can clean pavement performance data and M&R action data simultaneously. First, data are classified and labeled by the framework using the percentile method and considering the nature of the PMS data itself. Then two ANNs are established, one to clean data from anomalous or omitted pavement performance, and another to fill in data from omitted M&R actions. Applying the framework to the PMS in Shanxi Province, China, the following conclusions can be drawn. In terms of filling in the omitted M&R action, ANN calculated less average loss and improved the average prediction accuracy by 7.88% compared to the logistic regression model, proving the superiority of ANN in filling in the omitted M&R action data. Compared to the framework of filling in the omitted M&R action data by ANN without cleaning the pavement performance data, the proposed framework resulted in less average loss values and 5.71% improvement in average accuracy, demonstrating the need for cleaning both types of data simultaneously. The framework can provide a higher-quality data set for pavement M&R decisions and management.

Multi-objective decision support system for large-scale network pavement maintenance and rehabilitation management to enhance sustainability

This paper presents a research effort undertaken to explore the applicability of data mining and knowledge discovery (DMKD) in combination with Geographic Information System (GIS) technology to pavement management to better decide maintenance strategies, set rehabilitation priorities, and make investment decisions. The main objective of the research is to utilize data mining techniques to find pertinent information hidden within the pavement database. Mining algorithm C5.0, including decision trees and association rules, has been used in this analysis. The selected rules have been used to predict the maintenance and rehabilitation strategy of road segments. A pavement database covering four counties within the state of North Carolina, which was provided by North Carolina DOT (NCDOT), has been used to test this method. A comparison was conducted in this paper for the decisions related to a rehabilitation strategy proposed by the NCDOT to the proposed methodology presented in this paper. From the experimental results, it was found that the rehabilitation strategy derived by this paper is different from that proposed by the NCDOT. After combining with the AIRA Data Mining method, seven final rules are defined. Using these final rules, the maps of several pavement rehabilitation strategies are created. When their numbers and locations are compared with ones made by engineers at the Institute for Transportation Research and Education (ITRE) at North Carolina State University, it has been found that error for the number and the location are various for the different rehabilitation strategies. With the pilot experiment in the project, it can be concluded: (1) use of the DMKD method for the decision of road maintenance and rehabilitation can greatly increase the speed of decision making, thus largely saving time and money, and shortening the project period; (2) the DMKD technology can make consistent decisions about road maintenance and rehabilitation if the road conditions are similar, i.e., interference from human factors is less significant; (3) integration of the DMKD and GIS technologies provides a pavement management system with the capabilities to graphically display treatment decisions against distresses; and (4) the decisions related to pavement rehabilitation made by the DMKD technology is not completely consistent with that made by ITRE, thereby, the postprocessing for verification and refinement is necessary.

Optimizing pavement maintenance and rehabilitation (M&R) strategies is essential, especially in developing countries with limited budgets. This study presents an integrated framework combining a deterioration prediction model and a genetic algorithm (GA)-based optimization model to plan cost-effective M&R strategies for flexible pavements, including asphalt concrete (AC) and double bituminous surface treatment (DBST). The GA schedules multi-year interventions by accounting for varied deterioration rates and budget constraints to maximize pavement performance. The optimization process involves generating a population of candidate solutions representing a set of selected road sections for maintenance, followed by fitness evaluation and solution evolution. A mixed Markov hazard (MMH) model is used to model uncertainty in pavement deterioration, simulating condition transitions influenced by pavement bearing capacity, traffic load, and environmental factors. The MMH model employs an exponential hazard function and Bayesian inference via Markov Chain Monte Carlo (MCMC) to estimate deterioration rates and life expectancies. A case study on Cambodia’s road network evaluates six budget scenarios (USD 12–27 million) over a 10-year period, identifying the USD 18 million budget as the most effective. The framework enables road agencies to access maintenance strategies under various financial and performance conditions, supporting data-driven, sustainable infrastructure management and optimal fund allocation.

This article presents a framework and an illustrative example for identifying the optimal pavement maintenance and rehabilitation (M&R) strategy using a mixed-integer nonlinear programming model. The objective function is to maximize the cost-effectiveness expressed as the ratio of the effectiveness to the cost. The constraints for the optimization problem are related to performance, budget, and choice. Two different formulations of effectiveness are derived using treatment-specific performance models for each constituent treatment of the strategy; and cost is expressed in terms of the agency and user costs over the life cycle. The proposed methodology is demonstrated using a case study. Probability distributions are established for the optimization input variables and Monte Carlo simulations are carried out to yield optimal solutions. Using the results of these simulations, M&R strategy contours are developed as a novel tool that can help pavement managers quickly identify the optimal M&R strategy for a given pavement section.