Application of time-frequency analysis for automatic hidden corrosion detection in a multilayer aluminum structure using pulsed eddy current

被引:43
|
作者
Hosseini, Saleh [1 ]
Lakis, Aouni A. [1 ]
机构
[1] Ecole Polytech, Sect Appl Mech, Dept Mech Engn, Montreal, PQ H3T1J4, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Multi-layer aluminum structures; Pulsed eddy current; Time-frequency analysis; Feature extraction; K-means clustering; Expectation-maximization algorithm; CURRENT NDT; DEFECT CLASSIFICATION; FEATURE-EXTRACTION; CURRENT SIGNALS; INSPECTION; AIRCRAFT; SENSORS; PROBES;
D O I
10.1016/j.ndteint.2011.12.001
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
Pulsed eddy current (PEC) is a non-destructive testing method used to detect corrosion and cracks in multilayer aluminum structures which are typically found in aircraft applications. Corrosion and metal loss in thin multi-layer structures are complex and variable phenomena that diminish the reliability of pulsed eddy current measurements. In this article, pulsed eddy current signals are processed to improve the accuracy and reliably of these measurements. PEC's results (time domain data) are converted by time-frequency analysis (Rihaczek distribution) to represent data in three dimensions. The time-frequency approach generates a large amount of data. Principal component analysis is applied as feature extraction to reduce redundant data to provide new features for classifiers. K-means clustering and expectation-maximization are applied to classify data and automatically determine corrosion distribution in each layer. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码:70 / 79
页数:10
相关论文
共 50 条
  • [41] Automatic detection of epileptic seizure events using the time-frequency features and machine learning
    Zeng, Jiale
    Tan, Xiao-dan
    Zhan, Chang'an A.
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2021, 69
  • [42] Time-Frequency Analysis of Speech Signal Using Wavelet Synchrosqueezing Transform for Automatic Detection of Parkinson's Disease
    Warule, Pankaj
    Mishra, Siba Prasad
    Deb, Suman
    IEEE SENSORS LETTERS, 2023, 7 (10)
  • [43] Automatic segmentation of time-of-flight diffraction images using time-frequency techniques - application to rail-track defect detection
    Zahran, O
    Al-Nuaimy, W
    INSIGHT, 2004, 46 (06) : 338 - 343
  • [44] Detection and characterization of late potentials using time-frequency analysis techniques
    Lichorwic, DJ
    Jagadeesh, JM
    Nelson, SD
    PROCEEDINGS OF THE 1996 FIFTEENTH SOUTHERN BIOMEDICAL ENGINEERING CONFERENCE, 1996, : 129 - 132
  • [45] Specific Movement Detection In EEG Signal Using Time-Frequency Analysis
    Piroska, Haller
    Janos, Szalai
    COMPLEXITY IN ARTIFICIAL AND NATURAL SYSTEMS, PROCEEDINGS, 2008, : 230 - 236
  • [46] Detection of seizures in newborns using time-frequency analysis of EEG signals
    Boashash, B
    Carson, H
    Mesbah, M
    PROCEEDINGS OF THE TENTH IEEE WORKSHOP ON STATISTICAL SIGNAL AND ARRAY PROCESSING, 2000, : 564 - 568
  • [47] Detection of seizures in newborns using time-frequency analysis of EEG signals
    Boashash, Boualem
    Carson, Helen
    Mesbah, Mostefa
    IEEE Signal Processing Workshop on Statistical Signal and Array Processing, SSAP, 2000, : 564 - 568
  • [48] Specific movement detection in EEG signal using time-frequency analysis
    Piroska, Haller
    Janos, Szalai
    2008 COMPLEXITY & INTELLIGENCE OF THE ARTIFICIAL & NATURAL COMPLEX SYSTEMS, MEDICAL APPLICATIONS OF THE COMPLEX SYSTEMS, BIOMEDICAL COMPUTING, 2008, : 209 - 215
  • [49] Detection of nonlinear structural behavior using time-frequency and multivariate analysis
    Prawin, J.
    Rao, A. Rama Mohan
    SMART STRUCTURES AND SYSTEMS, 2018, 22 (06) : 711 - 725
  • [50] GNSS Interference Detection Using Statistical Analysis in the Time-Frequency Domain
    Wang, Pai
    Cetin, Ediz
    Dempster, Andrew G.
    Wang, Yongqing
    Wu, Siliang
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2018, 54 (01) : 416 - 428