Non-Contact Intelligent Inspection of Infrastructure

Details

• Alternative Title:
  Non-contact intelligent inspection of infrastructure Research Area: #1 Transportation
• Creators:
  Tang, Jiong ; Zhang, Yang ; Wang, Ting
• Corporate Creators:
  University of Connecticut ; University of Maine. Transportation Infrastructure Durability Center (TIDC)
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  Analysis Artificial Intelligence Decision Making False Alarms Impedance Measurement Implementation Infrastructure Inspection Inverse Analysis Machine Learning Magneto-mechanical Coupling Measurement Non-contact Transducer Sensors Structural Damage Identification Structural Deterioration And Defects Structural Health Monitoring Transducers Transportation

  More +
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  University of Maine. Transportation Infrastructure Durability Center (TIDC)
• Abstract:
  In this project, we develop non-contact sensing mechanism for health monitoring as well as the associated machine-learning based technique for decision making. Currently available sensory systems for structural health monitoring are almost all based on transducers that are directly attached to or embedded in structures monitored. As a result, they face with critical barriers, such as extremely high implementation cost in very large-scale structures due to the large number of sensors needed and relatively high false alarm rate due to malfunction of sensors themselves. The non-contact nature of the proposed sensing modality will cause paradigm shift: it leads to mobile sensory system that can monitor very large-scale structures employing only a small number of sensors, and it allows us to increase considerably the confidence level of structural health monitoring. In this research, concurrent breakthroughs in sensor synthesis and data analysis are pursued. We (a) develop a new non-contact impedance-based sensing mechanism via two-way magneto-mechanical dynamic interaction that is enhanced by adaptive electrical circuitry integration, which facilitates the tunable high-frequency interrogation to disclose structural anomaly; and (b) formulate accurate and robust decision-making strategies that that take full advantage of the new machine learning techniques.
• Format:
  PDF
• Funding:
  69A3551847101
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:76b26e780160d021ecec1054adf80b81734ae8098e00aa818b5653e0a5e7215082c9601a12cc21abb1851bcc3fc23e1b81284346fef9a1c960b7ab31b1250707
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/88728/dot_88728_DS1.pdf
• File Type:
  [PDF - 662.11 KB ]