An audio data-driven roadway digital twin and its underlying framework for a digitized transportation construction environment

The increasing need to build and maintain transportation systems has led project managers to manage multiple projects simultaneously. Roadway projects often entail several miles of job site, making it difficult to keep track of progress and maintenance activities. To improve the situation, this study proposes an audio data-driven roadway digital twin framework for real-time and remote monitoring of construction projects. The latent characteristics of a digital twin required for establishing a digitized work environment were investigated. As a primary method of seamlessly linking virtual and physical environments, audio data classified and analyzed by deep neural network (DNN) has been employed in the proposed system for identifying ongoing work activities in real-time, and their corresponding progress was measured using a global positioning system (GPS). Compared to visual monitoring systems, which are often limited by lighting conditions, blind spots, and heavy computational requirements, audio-based sensing enables omnidirectional data collection, reduces processing load, and improves adaptability to unstructured and dynamic construction environments. A wearable sensor has been developed for on-site data collection to overcome the difficulties of using static sensors. This study establishes a fundamental framework for developing digital twin prototypes with a focus on identifying the project’s progress in real-time and thereby estimating the future work schedule. The field experiment showed the system’s capability to provide critical information and real-time simulation data for analyzing and predicting future work logistics and possible bottlenecks. The overall accuracy of the system was over 90 %. The proposed framework is a stepping stone towards the development of full-fledged construction digital twin systems involving a variety of audio and sensor-based inputs and advanced artificial intelligence (AI) capabilities to manage various construction activities. Such a system is expected to be a useful tool towards obtaining critical information and data-sharing among stakeholders for well-informed and timely decision-making.