Digital Twin-Driven Framework for TBM Performance Prediction, Visualization, and Monitoring through Machine Learning

Abstract

The rapid development in underground infrastructure is encouraging faster and more modern ways, such as TBM tunneling, to meet the needs of the world. However, tunneling activities generate complex and heterogeneous data, which makes it difficult to visualize the performance of a project. Advancements in information technology, such as digital twins and machine learning, provide platforms for digital demonstration, visualization, and system performance monitoring of such data. Therefore, this study proposes a digital twin-driven framework for TBM performance prediction through machine learning, visualization, and monitoring. This novel approach integrates machine learning and real-time performance data to predict, visualize, and monitor the status of the tunnel construction progress. A digital twin virtual model of TBM was constructed based on TBM design parameters, the input parameter, boring energy, RPM, torque, thrust force, speed, gripper pressure, total revolution, and Q-value provided to SVR and ANN models to predict the TBM AR and PR, and TBM daily progress was visualized continuously. The predictive performance indices R2 (0.97) and RMSE (0.011) were estimated for AR prediction, showing the accuracy of the proposed model. To demonstrate the proposed framework, this study shows the its effectiveness. By implementing this framework, stakeholders can minimize the risk associated with the cost and schedule of a tunneling project by simultaneously visualizing and monitoring the performance of TBMs through digital twin and machine learning algorithms.

Integration of Cyber-Physical Systems, Digital Twins and 3D Printing in Advanced Manufacturing: A Synergistic Approach

“…By intеgrating sеnsor data, Intеrnеt of Things (IoT) dеvicеs and advancеd data analytics, DT еnablеs manufacturеrs to capturе rеal-timе insights into production mеtrics, еnvironmеntal conditions and еquipmеnt pеrformancе, thеrеby fostеring a proactivе approach to production managеmеnt and quality control (Constantinescu et al, 2020). This rеal-timе monitoring capability еmpowеrs manufacturеrs to dеtеct anomaliеs, dеviations, or potеntial inеfficiеnciеs as thеy occur, allowing for swift corrеctivе actions, proactivе maintеnancе intеrvеntions and thе optimization of production workflows to еnsurе optimal pеrformancе and product quality (Latif et al, 2023).…”

Real-Time Adjustment Method for Metro Systems with Train Delays Based on Improved Q-Learning

“…Therefore, the goal is to minimize the sum of discrepancies for all trains at each physical station between the scheduled timetable and the rescheduled timetable. The objective function is represented by Equation (1).…”

“…In today's urbanization process, tunnels have become an essential component of urban infrastructure due to the increasingly constrained urban space. Tunnels play a critical role in various domains, including transportation, water supply, and energy transmission, significantly improving the efficiency of urban operations [1]. Specifically, in the transportation field, the rapid development of metro systems, which are built upon tunnel engineering, has effectively mitigated the mounting traffic congestion in densely populated areas.…”

Building Cyber-Resilient Smart Grids with Digital Twins and Data Spaces

“…A digital twin (DT) is a virtual replica of a physical system, created using sensors, data analytics, and machine learning algorithms. It captures and analyzes real-time data from the physical system and has the potential to transform the monitoring, analysis, and optimization of physical objects and systems in Industry 4.0 [10][11][12]. Digital twins allow engineers to gain insights from real-time data generated by IoT devices, enabling simulation, analysis, and optimization for increased efficiency, productivity, and cost savings.…”