Pavement roughness is one of the essential parameters of pavement quality affecting ride quality, driving safety, and fuel consumption. The International Roughness Index has been widely deployed to evaluate pavement surface roughness. A vibration-based system is developed by using a low-cost three-axis Micro-Electro-Mechanical Systems accelerometer and a Global Positioning System sensor, which are connected to an Arduino board and embedded in a vehicle to monitor the road condition. The pavement profile is obtained by double integration of Z-axis acceleration data, and then the International Roughness Index is calculated via the Process Valves & Automation Systems Software using the obtained profile. The calculated International Roughness Index is correlated with ground truth data captured by a Road Surface Profiler with the coefficient of determination of 0.82 and an average error of 15%. The results demonstrate that the developed system can calculate the International Roughness Index with adequate accuracy at the network level. Besides, due to the low system cost and ease of use, it can be widely applied by road users to monitor pavement roughness as a crowdsourcing-based data collection system.

Measuring pavement roughness and detecting pavement surface defects are two of the most important tasks in pavement management. While existing pavement roughness measurement approaches are expensive, the primary aim of this paper is to use a cost-effective and sufficiently accurate RGB-D sensor to estimate the pavement roughness in the outdoor environment. An algorithm is proposed to process the RGB-D data and autonomously quantify the road roughness. To this end, the RGB-D sensor is calibrated and primary data for estimating the pavement roughness are collected. The collected depth frames and RGB images are registered to create the 3D road surfaces. We found that there is a significant correlation between the estimated International Roughness Index (IRI) using the RGB-D sensor and the manual measured IRI using rod and level. By considering the Power Spectral Density (PSD) analysis and the repeatability of measurement, the results show that the proposed solution can accurately estimate the different pavement roughness.

CO₂ emission reduction in large-scale pavement network maintenance planning has been an immense concern. The conventional single-objective optimisation modelsoverlook environmental issues such as CO₂ emission. However, the introduced multi-objective optimisation aims to enhance the network condition and minimise CO₂ emissions simultaneously. Two single-objective (coyote optimisation algorithm and genetic algorithm) and two multi-objective metaheuristic algorithms (multi-objective coyote optimisation algorithm and non-dominated sorting genetic algorithm) are employed to assess the effectiveness of the introduced environmental approach. Pavement maintenance planning optimisation requires the deterioration function formula and treatment improvement equation to be modelled. Hence, a new machine learning method called ‘differential evolutionary programming’ is introduced, which can provide the output-input formula. Differential evolutionary programming predicts the pavement deterioration value and overlay improvement with R² of 0.992 and 0.970, respectively. The results indicate that the coyote optimisation algorithm’s objective function is 66% lower than that of the genetic algorithm. Likewise, the multi-objective coyote optimisation algorithm reduces the first objective function by 72% on average compared to the non-dominated sorting genetic algorithm. The grey relational analysis is performed to compare single-objective and multi-objective optimal solutions. All optimal solutions presented by multi-objective modelling dominates the single-objective optimisation optimal solution based on the grey relational grade.

One of the key parts of a pavement management system is the maintenance and rehabilitation planning. The planning is usually developed under the assumption that all parameters are known with certainty. In practice, there are various parameters afflicted with large uncertainty. Ignoring the uncertainty may lead to a suboptimal plan adversely affecting the network conditions. The objective of this study is to develop an optimisation framework for network-level pavement maintenance and rehabilitation planning considering the uncertain nature of pavement deterioration and the budget with an applicable approach. A multistage stochastic mixed-integer programming model is proposed to find the optimal plan that is feasible for all possible scenarios of uncertainty and optimise the expectation of objective function. Two case studies of 4 and 21 pavement sections are presented to show the applicability of the proposed method. The value of stochastic solution and the expected value of perfect information which are the indices for evaluating the benefits of using the stochastic model are, respectively, 30% and 85% of the objective function of here and now model for the first case study and 26% and 42% of it regarding the second one. The indices are high indicating the effectiveness of the stochastic solution.

Appropriate pavement maintenance is of great importance due to the increasing deterioration of pavements and limited resources. Nowadays, highway agencies face large-scale networks. The management of large-scale networks is a challenge concerning the computational complexity, which typically increases exponentially with the dimension of the network. Water cycle and genetic algorithms are utilised in this paper to find the optimal maintenance schedule of large-scale pavement networks. A new practical constraint is introduced in the mathematical formulation that the total annual costs should not fluctuate more than a predefined limit over the planning horizon. Moreover, a novel index is developed to calculate the equity level in pavement maintenance scheduling, and the outcomes of the algorithms are compared based on this equation. A real road network with 103 pavement sections is the case study of this paper. The results show that ‘Equity index’ is reduced by 94% and 48% during the analysis period by WCA and GA, respectively. Drawing on WCA and GA optimal solutions, the average international roughness index of the network is decreased by 35% and 31% respectively in a 5-year horizon. Moreover, the variance of the maximum and minimum allocated budget in the analysis period is less than 15%.