Automated Interpretation of Sensor Data for Evaluating In-Situ Conditions

  • Kenneth R. Maser


The research described herein proposes and develops a concept for Automated Interpretation of large quantities of Slensory Data (AISD). This concept automatically applies encoded knowledge to the interpretation of the signals generated by sensory devices used to detect the in-situ condition of materials and structures. The knowledge is structured according to the interpretive disciplines required, and the signals are digitally processed into signatures that can be recognized by the knowledge base. The objective of this work has been to demonstrate the feasibility of the AISD concept. Potential applications for the AISD concept were reviewed and the automated analysis of bridge deck deterioration using ground penetrating radar was selected as a model for further study. A knowledge base comprising bridge deck deterioration, bridge engineering, radar/concrete physics, and radar signal analysis was developed, structured, and encoded. Prototype computational tools to automate the application of this knowledge were developed and applied to simulated data. A prototype Intelligent Bridge Deck Analyzer (IBDA), was developed. IBDA accepts raw radar data and user knowledge as input, and produces interpretations of bridge deck conditions at each measurement location. Computational experiments were conducted to demonstrate the influence of the radar data and the user input on the condition interpretation. The results show how the interpretive process can be automated, and how knowledge from various sources can be automatically combined to produce stronger conclusions than any source individually. These findings significantly expand the future potential to develop automated in-situ measurement equipment.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alongi, A.V., T.R. Cantor, C.P. Kneeter, and A. Alongi Jr., “Concrete Evaluation by Radar Theoretical Analysis,” Transportation Research Record No. 853, 1982.Google Scholar
  2. Chung, T., C.R. Carter, D.G. Manning, and F.B. Holt, “Signature Analysis of Radar Waveforms Taken on Asphalt Covered Bridge Decks,” Canada Ministry of Transport and Communications, Report ME-84–01, June 1984.Google Scholar
  3. Clemena, G., “Non-Destructive Inspection of Overlaid Bridge Decks with Ground Penetrating Radar,” Transportation Research Record No. 899, 1984.Google Scholar
  4. Erman, L.D., F. Hayes Roth, V.R. Lesser, and R. Reddy, “The Hearsay-II Speech Understanding System: Integration of Knowledge to Resolve Uncertainty.” ACM Computing Surveys, Vol. 12, No. 1, pp. 213–253, June 1980.CrossRefGoogle Scholar
  5. Lindsay, R., et al, Applications of AI for Organic Chemistry: the DENDRAL Project. McGraw-Hill, New York, New York, 1981.Google Scholar
  6. Manning, D., and F.B. Holt, “Detecting Deterioration in Asphalt Covered Bridge Decks,” Transportation Research Record No. 899, 1984. Google Scholar
  7. National Cooperative Highway Research Program (NCHRP), “Durability of Concrete Bridge Decks,” NCHRP Synthesis of Highway Practice No. 57, May 1979.Google Scholar
  8. Nii, H.P., and E.A. Feigenbaum, “Rule-Based Understanding of Signals,” from D.A. Waterman and F. Hayes Roth (eds.). Pattern Directed Inference Systems (New York): Academic Press, 1978).Google Scholar
  9. Nii, H.P., E.A. Feigenbaum, J. Anton, and A.J. Rockmore, “Signal-to-Symbol Transformation: HASP/SIAP Case Study,” The AI Magazine, Spring, 1982.Google Scholar
  10. Shortliffe, W.H., Computer-Based Medical Consultations: MYCIN, Chapter 3, New York: Elsevier/North-Holland 1976.Google Scholar
  11. Smith, Reid, G., “On the Development of Commercial Expert Systems,” The AI Magazine, Fall, 1984.Google Scholar
  12. Ulriksen, C.P.F., Application of Impulse Radar to Civil Engineering, Doctoral Thesis, Lund University, Department of Engineering Geology, 1982.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1986

Authors and Affiliations

  • Kenneth R. Maser
    • 1
  1. 1.Massachusetts Institute of TechnologyUSA

Personalised recommendations