Minimal Information Data-Modelling (MID) and an Easily Implementable Low-Cost SHM System for Use on a Short-Span Bridge

Abstract

Structural Health Monitoring (SHM) is a technique that involves gathering information to ensure that a structure is safe and behaving as expected. Within SHM, vibration-based monitoring is generally seen as one of the more cost-effective types of monitoring. However, vibration-based monitoring has mostly been undertaken on long-span bridges using data collected with a dense network of sensors. Historically, the logistical difficulty of collecting data on short- and medium-span bridges has meant that the usefulness of vibration-based methods on these bridges is largely unknown. Therefore, this study proposes Minimal Information Data-modelling (MID). MID is an approach that utilises low-cost, easily implementable sensors that are potentially feasible for operators to purchase and operate across a network. This approach will be investigated to determine whether MID is a feasible approach for monitoring short- and medium- span bridges. The results from MID were assessed to determine whether they could detect a suitably small shift in frequency, which is indicative of damage. It was determined that the data models could reliably detect frequency shifts as low as 0.01 Hz. This magnitude of frequency shift is similar to the level of frequency shift reported for a range of bridge damage cases found by others and validated with FE models. The accuracy achieved by the data models indicates that MID could potentially be used as a damage detection method. The cost of the equipment used to collect the data was approximately £370, demonstrating that it is feasible to use MID to monitor bridges across an entire network.

Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study

“…The article [21] proposes minimal information data modeling (MID) using low-cost (equipment costs around EUR 400) and easy-to-install sensors, which is also one of the key aspects of our proposal. In this sense, the novel technique presented in the aforementioned article offers high accuracy with low-range sensors and damage detection sensitivity down to 0.01 Hz frequency shifts, whereas in our approach, we rely on clustering that addresses the variability in identification due to multiple factors.…”

“…It makes several key contributions beyond these preceding studies. First, it demonstrates how minimal low-cost sensing can be integrated into a complete digital twin architecture: advancing from pure data science [21] to a production SHM system.…”

“…Specifically, our digital twin integrates inexpensive IoT acceleration sensors (equipment costs around EUR 300) with MQTT [28] connectivity, on-premises fog computing, cloud big data and machine learning services, and a visualization application. Compared to [21], the sensor data are augmented by their contextual placement within a digital twin model of the bridge for enhanced structural insights, with particular potential for monitoring local variables (such as strain) through the use of other types of sensors beyond accelerometers. This article applies the digital twin concept conforming to the definition given in [20] and comprises the next features: The article [29] presents a pre-trained network with synthetic data, i.e., supervised with finite element models, which, based on deep learning techniques, could provide a fast response for damage identification if integrated with real-time monitoring, and which would be computationally suitable to be included in the digital twin system we present, thus extending its simulation performance for model inclusion (adding the MOD and DIAG function in the simulation capabilities according to the structural digital twin conceptualization presented in [20]).…”

Refinement and Validation of the Minimal Information Data-Modelling (MID) Method for Bridge Management

“…To achieve these characteristics, the authors in [ 15 ] proposed to use a single MEMS accelerometer in conjunction with a sparse data modelling approach. The study demonstrated the concept on a single-span half-through girder bridge with data spanning approximately two years and identified that they could potentially identify a local stiffness loss of 23.6% and global damages of 1.7%.…”

“…The study demonstrated the concept on a single-span half-through girder bridge with data spanning approximately two years and identified that they could potentially identify a local stiffness loss of 23.6% and global damages of 1.7%. While the work of [ 15 ] was useful in demonstrating the concept, it is unknown if local and global stiffness loss detection capability were specific to the studied bridge or if the method would remain performant across a range of bridge types. Furthermore, Ref.…”