Sum of Gaussian Feature-Based Symbolic Representations of Eddy Current Defect Signatures

被引：3
作者：
Earnest, James [1 ,2 ]
机构：
[1] Tinker AFB, 76 Software Engn Grp USAF, Midwest City, OK USA
[2] Tinker AFB, 76 Software Engn Grp, Midwest City, OK 73145 USA
来源：
RESEARCH IN NONDESTRUCTIVE EVALUATION | 2023年 / 34卷 / 3-4期
关键词：
Eddy current; differential coil; pattern recognition; time series symbolic representation; machine learning; FAULT-DETECTION;
D O I：
10.1080/09349847.2023.2217094
中图分类号：
TB3 [工程材料学];
学科分类号：
0805 ; 080502 ;
摘要：
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.
引用
收藏
页码：136 / 153
页数：18
相关论文
共 40 条
  • [1] Intelligence Augmentation in Nondestructive Evaluation
    Aldrin, John C.
    Lindgren, Eric A.
    Forsyth, David S.
    [J]. 45TH ANNUAL REVIEW OF PROGRESS IN QUANTITATIVE NONDESTRUCTIVE EVALUATION, VOL 38, 2019, 2102
  • [2] ENGINE COMPONENT RETIREMENT-FOR-CAUSE - A NON-DESTRUCTIVE EVALUATION (NDE) AND FRACTURE MECHANICS-BASED MAINTENANCE CONCEPT
    ANNIS, CG
    CARGILL, JS
    HARRIS, JA
    VANWANDERHAM, MC
    [J]. JOURNAL OF METALS, 1981, 33 (07): : 24 - 28
  • [3] [Anonymous], 1967, P 5 BERKELEY S MATH, DOI DOI 10.1007/S11665-016-2173-6
  • [4] The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances
    Bagnall, Anthony
    Lines, Jason
    Bostrom, Aaron
    Large, James
    Keogh, Eamonn
    [J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2017, 31 (03) : 606 - 660
  • [5] Time series classification based on multi-feature dictionary representation and ensemble learning
    Bai, Bing
    Li, Guiling
    Wang, Senzhang
    Wu, Zongda
    Yan, Wenhe
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2021, 169 (169)
  • [6] Bai X., 2013, P INT C WEB AG INF M, P37, DOI [10.1007/978-3-642-38562-94, DOI 10.1007/978-3-642-38562-94]
  • [7] Banerjee S., 2015, IEEE INT WIE C EL CO, DOI [10.1109/WIECON-ECE.2015.7443889, DOI 10.1109/WIECON-ECE.2015.7443889]
  • [8] Barnaghi PM, 2012, 2012 6TH INTERNATIONAL CONFERENCE ON NEW TRENDS IN INFORMATION SCIENCE, SERVICE SCIENCE AND DATA MINING (ISSDM2012), P790
  • [9] DYNAMIC PROGRAMMING
    BELLMAN, R
    [J]. SCIENCE, 1966, 153 (3731) : 34 - &
  • [10] FCM - THE FUZZY C-MEANS CLUSTERING-ALGORITHM
    BEZDEK, JC
    EHRLICH, R
    FULL, W
    [J]. COMPUTERS & GEOSCIENCES, 1984, 10 (2-3) : 191 - 203
1234