Abstract

Advanced Feature Selection for Simplified Pattern Recognition within the Damage Identification Framework

Highlights

  • There has been considerable success in recent years in considering the problem of damage identification as one of pattern recognition

  • The first author was involved in a body of research, funded by DERA/QinetiQ [1,2,3,4], on Structural Health Monitoring (SHM) which proposed a health monitoring system based upon novelty detection techniques

  • The first two parts [1,2] of the earlier work were concerned with experimental validation of novelty detection techniques to carry out the first level of health monitoring on a simulated stiffened skin panel and on the wing of a Gnat aircraft

Read more

Summary

Introduction

There has been considerable success in recent years in considering the problem of damage identification as one of pattern recognition. The first two parts [1,2] of the earlier work were concerned with experimental validation of novelty detection techniques to carry out the first level of health monitoring on a simulated stiffened skin panel and on the wing of a Gnat aircraft. Both these investigations met with a large degree of success. The two parts [3,4] extended these techniques to levels 2 and 3 in the damage hierarchy, respectively These were conducted on the wing of the Gnat aircraft. Reference [4] extended this work to damage assessment by using a neural network classifier, in conjunction with

Objectives
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call