NEURAL NETWORK APPROACH TO DETECTION OF CHANGES IN STRUCTURAL PARAMETERS

The authors present a neural network approach for the detection of changes in the characteristics of structure-unknown systems. Vibration measurements from a "healthy" system are used to train a neural network for identification purposes. The trained network is fed comparable vibration data from the same structure under different episodes of response in order to monitor the health of the structure. Simulation studies with linear and nonlinear models typically encountered in the applied mechanics field reveal that the proposed damage detection methodology is capable of detecting small changes in the structural parameters, even noise-polluted vibration measurements.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00721969
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jun 10 1996 12:00AM