A framework based on deep learning and the intelligent sensors for pavement assessment condition

Long-term pavement performance is a key topic in highway engineering. By diving deep into research on pavement systems, we can bring together past, fragmented knowledge and experiences into a solid, comprehensive engineering theory. This essentially helps guide practical work like pavement design, construction, maintenance, and management. In this research, we look at using a mentoring system for automatic monitoring of pavement performance. By placing various sensors in different positions like the road surface, base, and slopes, a sensor network powered by Internet of Things technology is created. This setup allows for accurate and ongoing observation of factors like weather, physical condition, mechanical responses, and structural changes. Given the large volume of data and the need for real-time analysis, a data from sensors measuring temperature, humidity, pressure, asphalt strain, and displacement are used to train a deep learning model based on a Convolutional Neural Network (CNN) algorithm. This model helps predict multi-point displacement in the pavement, which allows us to detect issues like pavement damage. Impressively, the CNN model achieved accuracy, regression rates, and F-score of 93.51%, 91.63%, and 90.64% respectively. To improve the experimental section of a deep learning study, we compared the performance of the proposed model against several established or simpler algorithms (baselines) in the literature such as K-Nearest Neighbors (K-NN), eXtreme Gradient Boosting (XGBoost), and support vector machine (SVM). This contextualizes the model's efficacy and demonstrates its advantage over existing methods. This study showcases how different sensors can support deep learning algorithms in the assessment of pavement performance over the long term.