Abstract
Structural health monitoring (SHM) is critical for ensuring the safety of infrastructure such as bridges. This article presents a digital twin solution for the SHM of railway bridges using low-cost wireless accelerometers and machine learning (ML). The system architecture combines on-premises edge computing and cloud analytics to enable efficient real-time monitoring and complete storage of relevant time-history datasets. After train crossings, the accelerometers stream raw vibration data, which are processed in the frequency domain and analyzed using machine learning to detect anomalies that indicate potential structural issues. The digital twin approach is demonstrated on an in-service railway bridge for which vibration data were collected over two years under normal operating conditions. By learning allowable ranges for vibration patterns, the digital twin model identifies abnormal spectral peaks that indicate potential changes in structural integrity. The long-term pilot proves that this affordable SHM system can provide automated and real-time warnings of bridge damage and also supports the use of in-house-designed sensors with lower cost and edge computing capabilities such as those used in the demonstration. The successful on-premises–cloud hybrid implementation provides a cost effective and scalable model for expanding monitoring to thousands of railway bridges, democratizing SHM to improve safety by avoiding catastrophic failures.
Original language | English |
---|---|
Article number | 2115 |
Journal | Sensors |
Volume | 24 |
Issue number | 7 |
DOIs | |
Publication status | Published - Apr 2024 |
Keywords
- building information modeling (BIM)
- digital twin (DT)
- hybrid computing
- low-cost MEMS accelerometers
- machine learning (ML)
- MLOps
- railway bridges
- structural health monitoring (SHM)
- vibration-based monitoring
- wireless sensor networks (WSNs)