The widespread availability of cost-effective sensing technologies is translating into an increasing number of highway bridges being instrumented with structural health monitoring (SHM) systems. Current bridge SHM systems are only capable of measuring bridge responses and lack the ability to directly measure the traffic loads inducing bridge responses. The output-only nature of the monitoring data available often leaves damage detection algorithms ill-posed and incapable of robust detection. Attempting to overcome this challenge, this study leverages state-of-the-art computer vision techniques to establish a means of reliably acquiring load data associated with the trucks inducing bridge responses. Using a cyberenabled highway corridor consisting of cameras, bridge monitoring systems, and weigh-in-motion (WIM) stations, computer vision methods are used to track trucks as they excite bridges and pass WIM stations where their weight parameters are acquired. Convolutional neural network (CNN) methods are used to develop automated vehicle detectors embedded in GPU-enabled cameras along highway corridors to identify and track trucks from real-time traffic video. Detected vehicles are used to trigger the bridge monitoring systems to ensure structural responses are captured when trucks pass. In the study, multiple one-stage object detection CNN architectures have been trained using a customized dataset to identify various types of vehicles captured at multiple locations along a highway corridor. YOLOv3 is selected for its competitive speed and precision in identifying trucks. A customized CNN-based embedding network is trained following a triplet architecture to convert each truck image into a feature vector and the Euclidean distance of two feature vectors is used as a measure of truck similarity for reidentification purposes. The performance of the CNN-based feature extract is proved to be more robust than a hand-crafted method. Reidentification of the same vehicle allows truck weights measured at the WIM station to be associated with measured bridge responses collected by bridge monitoring systems.
With advances in sensing and communication technologies, engineering systems are now commonly instrumented with sensors for system monitoring and management. Occasionally, when sensors become malfunction, it is advantageous to automatically determine faulty sensors in the system and, if possible, recover missing or faulty data. This paper investigates the use of machine learning techniques for sensor data reconstruction and anomaly detection. Specifically, bidirectional recurrent neural network (BRNN) is employed to build a data-driven model for sensor data reconstruction based on the spatiotemporal correlation among the sensor data. The reconstructed sensor data can be used not only for recovering the data of the faulty sensors, but also for detecting anomalies based on an analytical redundancy approach. The proposed method is tested with vibration data based on a numerical simulation of a sensor network for bridge monitoring application. In terms of prediction accuracy, the results show that the BRNN-based sensor data reconstruction method performs better than other existing sensor data reconstruction methods. Furthermore, the sensor data reconstructed can be used to detect and isolate the anomalies caused by faulty sensors.
Proc. SPIE. 10168, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2017
KEYWORDS: Information fusion, Safety, Roads, Data modeling, Sensors, Databases, Computing systems, Clouds, Sensor networks, Structural health monitoring, Finite element methods, Bridges, System integration, Web services
This paper describes a cloud-based cyberinfrastructure framework for the management of the diverse data involved in bridge monitoring. Bridge monitoring involves various hardware systems, software tools and laborious activities that include, for examples, a structural health monitoring (SHM), sensor network, engineering analysis programs and visual inspection. Very often, these monitoring systems, tools and activities are not coordinated, and the collected information are not shared. A well-designed integrated data management framework can support the effective use of the data and, thereby, enhance bridge management and maintenance operations. The cloud-based cyberinfrastructure framework presented herein is designed to manage not only sensor measurement data acquired from the SHM system, but also other relevant information, such as bridge engineering model and traffic videos, in an integrated manner. For the scalability and flexibility, cloud computing services and distributed database systems are employed. The information stored can be accessed through standard web interfaces. For demonstration, the cyberinfrastructure system is implemented for the monitoring of the bridges located along the I-275 Corridor in the state of Michigan.
This paper describes an information repository to support bridge monitoring applications on a cloud computing platform.
Bridge monitoring, with instrumentation of sensors in particular, collects significant amount of data. In addition to
sensor data, a wide variety of information such as bridge geometry, analysis model and sensor description need to be
stored. Data management plays an important role to facilitate data utilization and data sharing. While bridge information
modeling (BrIM) technologies and standards have been proposed and they provide a means to enable integration and
facilitate interoperability, current BrIM standards support mostly the information about bridge geometry. In this study,
we extend the BrIM schema to include analysis models and sensor information. Specifically, using the OpenBrIM
standards as the base, we draw on CSI Bridge, a commercial software widely used for bridge analysis and design, and
SensorML, a standard schema for sensor definition, to define the data entities necessary for bridge monitoring
applications. NoSQL database systems are employed for data repository. Cloud service infrastructure is deployed to
enhance scalability, flexibility and accessibility of the data management system. The data model and systems are tested
using the bridge model and the sensor data collected at the Telegraph Road Bridge, Monroe, Michigan.
This paper discusses a data management infrastructure framework for bridge monitoring applications. As sensor technologies mature and become economically affordable, their deployment for bridge monitoring will continue to grow. Data management becomes a critical issue not only for storing the sensor data but also for integrating with the bridge model to support other functions, such as management, maintenance and inspection. The focus of this study is on the effective data management of bridge information and sensor data, which is crucial to structural health monitoring and life cycle management of bridge structures. We review the state-of-the-art of bridge information modeling and sensor data management, and propose a data management framework for bridge monitoring based on NoSQL database technologies that have been shown useful in handling high volume, time-series data and to flexibly deal with unstructured data schema. Specifically, Apache Cassandra and Mongo DB are deployed for the prototype implementation of the framework. This paper describes the database design for an XML-based Bridge Information Modeling (BrIM) schema, and the representation of sensor data using Sensor Model Language (SensorML). The proposed prototype data management framework is validated using data collected from the Yeongjong Bridge in Incheon, Korea.