Sum of Gaussian Feature-Based Symbolic Representations of Eddy Current Defect Signatures
Source abstract
Abstract
This study investigates a novel symbolic representation method based on Symbolic Aggregate Approximation (SAX) of time series that focuses on differential coil (D-coil) eddy current (EC) defect responses. The method uses the Sum of Gaussian (SoG) approximation of the defect response, Fuzzy C-means (FCM) clustering, and the extrema values in the approximation to provide a reduced representation that can effectively analyze possible fault conditions in the defect response. Comparisons to existing SAX methods are performed with the new method indicating significant classification accuracy improvement.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Time Series Analysis and Forecasting · Neural Networks and Applications · Complex Systems and Time Series Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
76 Software Engineering Group/USAF, Tinker AFB, Midwest City, Oklahoma, USA
Funding
no financial
References (40)
Show source-provided references
1. 10.1007/BF0333944710.1007/BF03339447 ↗
2. L. Brasche, The Use of Nondestructive Inspection in Jet Engine Applications, Mater. Eval. 60 (7), 853–856 (2002).
3. C. Pairazaman, S. Keller, and C. Buynak, A Third Generation Robotic Eddy Current System for the Inspection of Gas Turbine Engine Components, World Conf. NDT 15 (2000).
4. Iowa State University Center for Nondestructive Evaluation “NDE-Ed.Org: about NDT and NDE” https://www.nde-ed.org/NDETechniques/EddyCurrent/ProbesCoilDesign/ProbesModeOp.xhtml (accessed 7 Apr. 2023).
5. R. E. Bellman, Dynamic Programming (Princeton University Press, New Jersey, USA 1957).
6. 10.1109/TIM.2020.304796510.1109/TIM.2020.3047965 ↗
7. 10.1007/PL0001166910.1007/PL00011669 ↗
8. 10.1007/s10618-007-0064-z10.1007/s10618-007-0064-z ↗
9. S. Malinowski et al., October. 1d-sax: A novel symbolic representation for time series, Int. Sym. Intel. Data Anlys. 12, 273–284 (2013).
10. 10.1016/j.eswa.2020.11416210.1016/j.eswa.2020.114162 ↗
11. 10.3390/app1019698010.3390/app10196980 ↗
12. 10.1016/j.neucom.2014.01.04510.1016/j.neucom.2014.01.045 ↗
13. 10.1080/003467602100001333110.1080/0034676021000013331 ↗
14. 10.1201/b1587010.1201/b15870 ↗
15. 10.1063/1.509973210.1063/1.5099732 ↗
16. 10.1007/978-3-540-70812-4_2510.1007/978-3-540-70812-4_25 ↗
17. 10.1109/ICDM.2013.5210.1109/ICDM.2013.52 ↗
18. 10.1109/CCDC.2018.840749810.1109/CCDC.2018.8407498 ↗
19. 10.1109/TIM.2022.318565810.1109/TIM.2022.3185658 ↗
20. P. M. Barnaghi, A. Abu Bakar, and Z. A. Othman. Enhanced symbolic aggregate approximation method for financial time series data representation. 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM2012), 23-25, Oct, Taipei, Taiwan (Serv. Sci. and Data Mining, 2012), p. 790–795.
21. 10.1007/978-3-642-38562-9_410.1007/978-3-642-38562-9_4 ↗
22. 10.1109/APWeb.2010.2310.1109/APWeb.2010.23 ↗
23. D. A. Stubbs R. W. Martin and N. D. Schehl AFRL-ML-WP-TR-2000-4035 2000. https://apps.dtic.mil/sti/citations/ADA388413 (accessed 10 Apr. 2023).
24. 10.1063/1.191675210.1063/1.1916752 ↗
25. 10.1109/ICDEW.2006.9910.1109/ICDEW.2006.99 ↗
26. 10.1016/0098-3004(84)90020-710.1016/0098-3004(84)90020-7 ↗
27. J. MacQueen, Some methods for classification and analysis of multivariate observations, Proc. Berkeley Symp. On Math. Stat. & Prob. 1 (14), 281–297 (1967).
28. 10.1109/WIECON-ECE.2015.744388910.1109/WIECON-ECE.2015.7443889 ↗
29. 10.1109/CICN.2010.8010.1109/CICN.2010.80 ↗
30. 10.1109/INFCOM.2005.149832010.1109/INFCOM.2005.1498320 ↗
31. 10.1016/j.ndteint.2003.10.00510.1016/j.ndteint.2003.10.005 ↗
32. 10.1109/ACCESS.2021.311551210.1109/ACCESS.2021.3115512 ↗
33. 10.2514/1.I01058710.2514/1.I010587 ↗
34. 10.1109/TIT.1967.105396410.1109/TIT.1967.1053964 ↗
35. 10.1007/s10618-016-0483-910.1007/s10618-016-0483-9 ↗
36. 10.1007/s10618-012-0250-510.1007/s10618-012-0250-5 ↗
37. 10.1007/978-1-4757-2440-010.1007/978-1-4757-2440-0 ↗
38. 10.1016/j.measurement.2012.09.01410.1016/j.measurement.2012.09.014 ↗
39. J. Xingliang et al., Energies, 4, 9, (2011).
40. 10.23919/MIPRO.2018.840004010.23919/MIPRO.2018.8400040 ↗