Fuzzy Syntactic Pattern Recognition Approach for Extracting and Classifying Flaw Patterns from and Eddy-Current Signal Waveform

  • Kang, Soon-Ju (School of Electronic and Electrical Engineering, Kyungpook National University)
  • Published : 1997.08.01

Abstract

In this paper, a general fuzzy syntactic method for recognition of flaw patterns and for the measurement of flaw characteristic parameters for a non-destructive inspections signal, called eddy-current, is presented. Solutions are given to the subtasks of primitive pattern selection, signal to symbol transformation, pattern grammar formulation, and event-synchronous flaw pattern extraction based on the grammars. Fuzzy attribute grammars are used as the model for the pattern grammar because of their descriptive power in the face of uncertain constraints caused by nose or distortion in the signal waveform, due to their ability to handle syntactic as well as semantic information. This approach has been implemented and the performance of eh resultant system has been evaluated using a library of law patterns obtained from steam generator tubes in nuclear power plants by an eddy current-based non-destructive inspection method.

Keywords

References

  1. Non-Destructive Testing Tutorial on Signal Processing and Pattern Recognition in Non-destructive Evaluation of Materials C.H.Chen;J.Boogaard(ed.);G.M.Van Dijk(ed.)
  2. Advanced Eddy Current Data Analyis Techniques for Steam Generator Tubing Training Book for LEVEL Ⅱ EPRI NDE Center
  3. Materials Evaluation v.49 no.9 Artificial intelligence in the eddy current inspection of aircraft engine components C.E.Chapman;A.Fahr;A.Pelletier;D.R.Hay
  4. Pacific Northwest Laboratory PNL-SA-7984 Pattern Recognition Methods for Classifying and Sizing Flaws Using Eddy-Current Data P.G.Doctor;T.P.Harrington;T.J.Davis
  5. Proc. of 10th Intl. Conf. on NDE A Syntax and Semantic-Directed Pattern Recognition Method for Extracting and Classifying Flaws from Eddy Current Signal S.J.Kang;N.S.Park;Y.H.Hur
  6. Ph.D. Thesis, Colorado State University Parametric Signal Processing for Eddy Current NDT S.R.Satish
  7. Materials Evaluation v.42 A Fourier Descriptor Classification Scheme for Differential Probe Signal S.S.Udpa;W.Lord
  8. Proc. of Intl. Conf. on Fuzzy Logic and Neural Networks, Iizuka, Japan, July 20-24 A Pattern Recognition System Detecting Corrosion Pits on Gas Pipelines H.Kotsubo;H.Furusawa;H.Tanaka;Y.Hosohara
  9. Handbook of Pattern Recognition and Image Processing K.S.Fu
  10. CACM v.19 Structural Pattern Recognition fo Carotid Pulse Waves Using a General Wave-form Parsing System S.George;K.Laveen;M.C.Kyle
  11. IEEE Trans. on PAMI v.12 no.7 Syntactic Pattern Recognition of the ECG T.Panagiotis;S.Emmanuel
  12. Signal Processing v.29 Symbolic representation of process monitoring signals W.A.Kittel;H.M.Hayes
  13. Pattern Recognition v.21 no.4 Automatic Recognition of Primitive Changes in Manufacturing Process Signals P.L.Love;M.Simaan
  14. IEEE Trans. on SMC v.SMC-16 no.5 Fuzzy Grammars in Syntactic Recongnition of Skeletal Maturity from X-Rays A.Pathak;K.P.Sankar
  15. IEEE Trans. on Pattern Anal. Machine Intelligence v.PAMI-2 no.2 Use of Fuzzy Algorithms for Phonetic and Phonemic Labeling of Continuous Speech R.D.Mori;P.Laface
  16. IEEE Trans. on Pattern Anal Machine Intelligence v.PAMI-4 no.4 Fuzzy Tree Automata and Syntactic Pattern Recognition E.T.Lee
  17. Information and Control v.8 Fuzzy Set L.A.Zadeh