DATA-DRIVEN MODELING OF IN-SERVICE PERFORMANCE OF FLEXIBLE PAVEMENTS, USING LIFE-CYCLE INFORMATION

Abstract

Current pavement performance prediction models are based on the parameters such as climate, traffic, environment, material properties, etc. while all these factors are playing important roles in the performance of pavements, the quality of construction and production are also as important as the other factors. The designed properties of Hot Mix Asphalt (HMA) pavements, known as flexible pavements, are subjected to change during production and construction stages. Therefore, most of the times the final product is not the exact reflection of the design. In almost any highway project, these changes are common and likely to occur from different sources, by various causes, and at any stage. These changes often have considerable impacts on the long-term performance of a project. The uncertainty of the traffic and environmental factors, as well as the variability of material properties and pavement structural systems, are obstacles for precise prediction of pavement performance. Therefore, it is essential to adopt a hybrid approach in pavement performance prediction and design; in which deterministic values work along with stochastic ones. Despite the advancement of technology, it is natural to observe variability during the production and construction stages of flexible pavements. Quality control programs are trying to minimize and control these variations and keep them at the desired levels. Utilizing the information gathered at the production and construction stages is beneficial for managers and researchers. This information enables performing analysis and investigations of pavements based on the as-produced and as-constructed values, rather than focusing on design values. This study describes a geo-relational framework to connect the pavement life-cycle information. This framework allows more intelligent and data-driven decisions for the pavements. The constructed geo-relational database can pave the way for artificial intelligence tools to help both researchers and practitioners having more accurate pavement design, quality control programs, and maintenance activities. This study utilizes data collected as part of quality control programs to develop more accurate deterioration and performance models. This data is not only providing the true perspective of actual measurements from different pavement properties but also answers how they are distributed over the length of the pavement. This study develops and utilizes different distribution functions of pavement properties and incorporate them into the general performance prediction models. These prediction models consist of different elements that are working together to produce an accurate and detailed prediction of performance. The model predicts occurrence and intensity of four common flexible pavement distresses; such as rutting, alligator, longitudinal and transverse cracking along with the total deterioration rate at different ages and locations of pavement based on material properties, traffic, and climate of a given highway. The uniqueness of the suggested models compared to the conventional pavement models in the literature is that; it carries out a multiscale and multiphysics approach which is believed to be essential for analyzing a complex system such as flexible pavements. This approach encompasses the discretization of the system into subsystems to employ the proper computational tools required to treat them. This approach is suitable for problems with a wide range of spatial and temporal scales as well as a wide variety of different coupled physical phenomena such as pavements. Moreover, the suggested framework in this study relies on using stochastic and machine learning techniques in the analysis along with the conventional deterministic methods. In addition, this study utilizes mechanical testing to provide better insights into the behavior of the pavement. A series of performance tests are conducted on field core samples with a variety of different material properties at different ages. These tests allow connecting the lab test results with the field performance survey and the material, environmental and loading properties. Moreover, the mix volumetrics extracted from the cores assisted verifying the distribution function models. Finally, the deterioration of flexible pavements as a result of four different distresses is individually investigated and based on the findings; different models are suggested. Dividing the roadway into small sections allowed predicting finer resolution of performance. These models are proposed to assist the highway agencies s in their pavement management process and quality control programs. The resulting models showed a strong ability to predict field performance at any age during the pavements service life. The results of this study highlighted the benefits of highway agencies in adopting a geo-relational framework for their pavement network. This study provides information and guidance to evolve towards data-driven pavement life cycle management consisted of quality pre-construction, quality during construction, and deterioration post-construction.