Real-time Big-Data Visualization

In order to make informed decision about structural integrity or building operations, it is important to search, organize, and visualize vast amounts of vibration data effectively. We are using the highly-instrumented Goodwin Hall Smart Building as a platform for real-time data visualization to address some of the fundamental and practical challenges in this field.

Collaborators: Zhiwu Xie (Virginia Tech)

Online Stuctural Health Monitoring

We are designing a framework for structural health monitoring that functions fully online, without any prior information about the structure. As part of this effort, we are exploring several key principles that could help to accomplish this goal:

  1. Machine learning strategies that can handle high dimensional data, in order to avoid information loss due to dimensionality reduction.
  2. The use of Generative Adversarial Networks to overcome data scarcity and data imbalance.
  3. Alarm threshold tuning based on reliability analysis to reduce sensitivity to user-defined parameters.

Related Publications

Sorry, no publications matched your criteria.

Experimental Validation of Seismic Design Formulas for Metal Buildings

Metal building are highly-optimized structures with natural periods (resonances) that are not well represented by standard design formulas. We are developing cheap, deployable methods for obtaining empirical field measurements of a wide variety of metal buildings in order to validate a new seismic design formula.


Vibration Based Occupant Inference

Structural vibrations can be used to track occupant movement and activity.

Gait Diagnosis via Floor Vibrations

Gait can tell us much about a person’s state of health and floor vibrations are a non-intrusive way to monitor it.

Structural Monitoring and Traffic System Integration

The Varina Enon Bridge (Richmond, VA) serves as a platform to study how Structural Health Monitoring and Intelligent Traffic Systems data can be integrated to provide more holistic monitoring information.

Long-Term Operational Modal Analysis

The Goodwin Hall Smart Building uses 200+ accelerometers and Operational Modal Analysis to track modal parameters over the life of the building. The objectives of this research are:

  1. Refine methods for automated moda analysis
  2. Understand the impact of environmental parameters (wind, temperature, occupancy) on the response of the structure.

For more information on Goodwin Hall visit the Virginia Tech Smart Infrastructure Lab website.


We have developed a public, open-source MATLAB library for Operational Modal Analysis. Access it here.

Related Publications

Sorry, no publications matched your criteria.

Reality Capture to Structural Models

Points clouds from reality capture methods, such as LIDAR, photogrammetry, and depth cameras, produce detailed geometric data of as-built structures. In raw form, however, these data are heavy and have limited use for engineers. We have developed methods for reducing point clouds in to structural “skeletons” on which Building Information Models (BIM) or Finite Element Models (FEM) can be building. Over the life of a structure, the approach can yield an evolving, as-built structural representation which could serve as a foundation for full-fledged Civil Infrastructure Digital Twins.

Related Publictions

Sorry, no publications matched your criteria.