SENSIBILIDADE DE PARÂMETROS DA ESTRUTURA NA ANÁLISE DE DESEMPENHO DE PAVIMENTOS FLEXÍVEIS

The design of asphalt pavement structures is a process that involves the knowledge of variables that are difficult to predict and model.Sensitivity analysis applied to pavement performance prediction is essential to determine the most influential variables, and enable the optimization of design process. This study aimed to analyze the sensitivity of flexible pavements performance to variations in design parameters related to the thicknesses of asphalt layer, base and sub-base and resilient modulus of asphalt layer, base, sub-base and subgrade. For this purpose, a fractional factorial experiment was conducted, which had as output variables the accumulated damage in pavement structure, related to fatigue cracking and rutting in wheel wander. To obtain the accumulated damage, mechanistic-empirical design method was used, through PerRoad software. It was concluded that asphalt layer thickness isthe most sensitive parameter considering the distresses studied, having a higher sensitivity for fatigue cracking and a slightly lower sensitivity for rutting.

Effect of variations in layer thickness and resilience modulus on flexible pavement performance

A pavement mechanistic-empirical analysis is based on a pre-designed structure checked for required performance criteria. In case the latter are not met, this structure is modified and reprocessed. In this context, analyzing the effect of variations in project parameters on pavement performance prediction subsidizes a better understanding of results provided by computer programs. The objective of this study is to assess the effect of layer thickness and resilience modulus variations on flexible pavement performance. To do so, performance was estimated for the 20th project year through Elastic Layered System Model 5 (ELSYM5) software and American Association of State Highway and Transportation Officials (AASHTO) Mechanistic-Empirical method (ME). Using multiple regression models for result adjustment and through statistical assessments on regression coefficients calculated, it can be concluded that pavement lifespan consumption, predicted by simulations on ELSYM5, is sensitive to variations in coating and subbase thickness and in subgrade resilience modulus. For AASHTO ME method, predicted values for distresses were significantly sensitive to variations in coating, base and subbase thickness, and in base and subgrade resilience modulus. Comparing both approaches, it is concluded that ELSYM5 can be a viable alternative to the application of a ME pavement design method.

Review on Machine Learning Techniques for Developing Pavement Performance Prediction Models

Road transportation has always been inherent in developing societies, impacting between 10–20% of Gross Domestic Product (GDP). It is responsible for personal mobility (access to services, goods, and leisure), and that is why world economies rely upon the efficient and safe functioning of transportation facilities. Road maintenance is vital since the need for maintenance increases as road infrastructure ages and is based on sustainability, meaning that spending money now saves much more in the future. Furthermore, road maintenance plays a significant role in road safety. However, pavement management is a challenging task because available budgets are limited. Road agencies need to set programming plans for the short term and the long term to select and schedule maintenance and rehabilitation operations. Pavement performance prediction models (PPPMs) are a crucial element in pavement management systems (PMSs), providing the prediction of distresses and, therefore, allowing active and efficient management. This work aims to review the modeling techniques that are commonly used in the development of these models. The pavement deterioration process is stochastic by nature. It requires complex deterministic or probabilistic modeling techniques, which will be presented here, as well as the advantages and disadvantages of each of them. Finally, conclusions will be drawn, and some guidelines to support the development of PPPMs will be proposed.

Prediction of Highway Tunnel Pavement Performance Based on Digital Twin and Multiple Time Series Stacking

The existing pavement performance prediction methods are limited to single-factor predictions, which often face the challenges of high cost, low efficiency, and poor accuracy. It is difficult to simultaneously solve the temporal, spatial, and exogenous dependencies between pavement performance data and maintenance, the service life of highways, the environment, and other factors. Digital twin technology based on the building information modeling (BIM) model, combined with machine learning, puts forward a new perspective and method for the accurate and timely prediction of pavement performance. In this paper, we propose a highway tunnel pavement performance prediction approach based on a digital twin and multiple time series stacking (MTSS). This paper (1) establishes an MTSS prediction model with heterogeneous stacking of eXtreme gradient boosting (XGBoost), the artificial neural network (ANN), random forest (RF), ridge regression, and support vector regression (SVR) component learners after exploratory data analysis (EDA); (2) proposes a method based on multiple time series feature extraction to accurately predict the pavement performance change trend, using the highway segment as the minimum computing unit and considering multiple factors; (3) uses grid search with the k-fold cross validation method to optimize hyperparameters to ensure the robustness, stability, and generalization ability of the prediction model; and (4) constructs a digital twin for pavement performance prediction to realize the real-time dynamic evolution of prediction. The method proposed in this study is applied in the life cycle management of the Dalian highway-crossing tunnel in Shanghai, China. A dataset covering 2010–2019 is collected for real-time prediction of the pavement performance. The prediction accuracy evaluation shows that the mean absolute error (MAE) is 0.1314, the root mean squared error (RMSE) is 0.0386, the mean absolute percentage error (MAPE) is 5.10%, and the accuracy is 94.90%. Its overall performance is better than a single model. The results verify that the prediction method based on digital twin and MTSS is feasible and effective in the highway tunnel pavement performance prediction.