Abstract Manager

Pavement infrastructure worldwide is pivotal to successful economic growth. However, like all infrastructure, it requires proper Maintenance and Rehabilitation (M&R) strategies and evidence-based Pavement Management Systems (PMS) to ensure that the pavement condition can meet the desired level of service under the impact of traffic loads and given climatic loading parameters. With the improvement of new paving materials, climate change and extreme weather events impacts solely relying on traditional M&R techniques, where monitoring periods are scheduled sporadically, may not be enough to understand pavement's performance and their mechanistic response to varying loading and climatic conditions. However, pavement design and management can benefit from the concept of Smart Pavements, considering the recent advances in Artificial Intelligence (AI) and instrumentation monitoring systems. This study presents a summary of the current progress for the “smart pavements” concept currently being implemented within a section of a major two-lane arterial roadway in Kitchener, Ontario. The goal is to enable pseudo-real-time monitoring of the section and understand the actual in-situ responses through advanced instrumentation and by running Machine Learning models to improve our understanding and prediction of long-term pavement performance. Thus far, the installation and construction of the instrumented section have been completed, and preliminary results have been obtained. This paper presents the preliminary pavement environmental and structural behaviours immediately after the construction of the section, as well as five months after construction. The instrumentation installed in each layer consists of horizontal and vertical asphalt concrete strain gauges, moisture probes, pressure cells, and temperature strings. The impact of asphalt temperature right after construction until service condition and loading frequencies on the structural behaviors of the pilot section were monitored through several rounds of known weight axial truck. The results are used to establish a baseline for better interpretation of the pavement structure during its in-service monitoring period.