摘要
The study of long-term pavement performance is a fundamental topic in the field of highway engineering.Through comprehensive and in-depth research on the pavement system,the previous scattered,one-sided,superficial,and perceptual knowledge and experience are summarized and sublimated into a systematic and complete engineering theory,thereby providing powerful guidance and assistance for the practice of pavement design,construction,maintenance,operation,and management.In this research,the mentoring system deployment technology for automatic monitoring is carried out for long-term pavement performance.By burying a variety of sensors in different parts of the road surface,base,roadbed,slope,etc.,a sensor monitoring network based on the Internet of Things technology is formed to achieve accurate,reliable,and continuous observation of environmental meteorology,physical state,mechanical response,structural deformation,and other indicators.The large amount of data and high real-time requirements mean that the perception data collected from sensors,including temperature,humidity,pressure,asphalt strain,and displacement,can be used to train a deep learning model based on a Convolutional Neural Network(CNN)algorithm.This model predicts multi-point pavement displacement to detect damage such as asphalt cracks and potholes.The response of the proposed CNN achieved a high accuracy rate,regression rate,and F-score equal to 87.24%,84.12%,and 85.96%,respectively.This work highlights the potential of using a variety of sensors to aid deep learning algorithms for monitoring long-term pavement performance.
