Acoustic emission corrosion feature extraction and severity prediction using hybrid wavelet packet transform and linear support vector classifier

被引:9
|
作者
May, Zazilah [1 ,2 ]
Alam, M. K. [1 ]
Nayan, Nazrul Anuar [2 ]
Rahman, Noor A'in A. [1 ]
Mahmud, Muhammad Shazwan [3 ]
机构
[1] Univ Teknol PETRONAS, Elect & Elect Engn Dept, Seri Iskandar, Perak, Malaysia
[2] Univ Kebangsaan Malaysia, UKM, Fac Engn & Built Environm, Dept Elect Elect & Syst Engn, Bangi, Malaysia
[3] Univ Teknol PETRONAS, Mech Engn Dept, Seri Iskandar, Perak, Malaysia
来源
PLOS ONE | 2021年 / 16卷 / 12期
关键词
SIGNALS;
D O I
10.1371/journal.pone.0261040
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Corrosion in carbon-steel pipelines leads to failure, which is a major cause of breakdown maintenance in the oil and gas industries. The acoustic emission (AE) signal is a reliable method for corrosion detection and classification in the modern Structural Health Monitoring (SHM) system. The efficiency of this system in detection and classification mainly depends on the suitable AE features. Therefore, many feature extraction and classification methods have been developed for corrosion detection and severity assessment. However, the extraction of appropriate AE features and classification of various levels of corrosion utilizing these extracted features are still challenging issues. To overcome these issues, this article proposes a hybrid machine learning approach that combines Wavelet Packet Transform (WPT) integrated with Fast Fourier Transform (FFT) for multiresolution feature extraction and Linear Support Vector Classifier (L-SVC) for predicting corrosion severity levels. A Laboratory-based Linear Polarization Resistance (LPR) test was performed on carbon-steel samples for AE data acquisition over a different time span. AE signals were collected at a high sampling rate with a sound well AE sensor using AEWin software. Simulation results show a linear relationship between the proposed approach-based extracted AE features and the corrosion process. For multi-class problems, three corrosion severity stages have been made based on the corrosion rate over time and AE activity. The ANOVA test results indicate the significance within and between the feature-groups where F-values (F-value>1) rejects the null hypothesis and P-values (P-value<0.05) are less than the significance level. The utilized L-SVC classifier achieves higher prediction accuracy of 99.0% than the accuracy of other benchmarked classifiers. Findings of our proposed machine learning approach confirm that it can be effectively utilized for corrosion detection and severity assessment in SHM applications.
引用
收藏
页数:23
相关论文
共 50 条
  • [1] Feature Extraction from Acoustic Emission Waveforms using a Discrete Wavelet Transform
    Hensman, J.
    Worden, K.
    Mohd-Saleh, S.
    [J]. PROCEEDINGS OF THE FOURTH EUROPEAN WORKSHOP ON STRUCTURAL HEALTH MONITORING 2008, 2008, : 1152 - 1162
  • [2] ECG feature extraction and classification using wavelet transform and support vector machines
    Zhao, QB
    Zhang, LQ
    [J]. PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND BRAIN, VOLS 1-3, 2005, : 1089 - 1092
  • [3] Feature extraction and classification with wavelet transform and support vector machines
    Zhang, SY
    Xue, XR
    Zhang, X
    [J]. IGARSS 2005: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-8, PROCEEDINGS, 2005, : 3795 - 3798
  • [4] Feature Extraction of the Indonesian Phonemes Using Discrete Wavelet and Wavelet Packet Transform
    Hidayat, Risanuri
    Kristomo, Domy
    Togarma, Immer
    [J]. PROCEEDINGS OF 2016 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND ELECTRICAL ENGINEERING (ICITEE), 2016,
  • [5] The wavelet transform in the acoustic emission signal feature extraction of the rubbing fault
    Jin Zhihao
    Wang Dan
    Jin Wen
    Wen Bangchun
    [J]. FIRST INTERNATIONAL WORKSHOP ON DATABASE TECHNOLOGY AND APPLICATIONS, PROCEEDINGS, 2009, : 283 - +
  • [6] Bearing fault diagnosis using wavelet packet transform, hybrid PSO and support vector machine
    Rajeswari, C.
    Sathiyabhama, B.
    Devendiran, S.
    Manivannan, K.
    [J]. 12TH GLOBAL CONGRESS ON MANUFACTURING AND MANAGEMENT (GCMM - 2014), 2014, 97 : 1772 - 1783
  • [7] FEATURE EXTRACTION FROM UNDERWATER SIGNALS USING WAVELET PACKET TRANSFORM
    Li Xin-xin
    Yang Shi-e
    Yu Ming
    [J]. 2008 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND SIGNAL PROCESSING, VOLS 1 AND 2, 2007, : 400 - 405
  • [8] Feature extraction of acoustic emission signals for cable damage based on wavelet packet analysis
    Deng, Yang
    Ding, You-Liang
    Li, Ai-Qun
    [J]. Zhendong yu Chongji/Journal of Vibration and Shock, 2010, 29 (06): : 154 - 158
  • [9] Acoustic emission source identification based on harmonic wavelet packet and support vector machine
    Yu J.
    Ding M.
    Meng F.
    Qiao Y.
    Wang Q.
    [J]. Journal of Southeast University (English Edition), 2011, 27 (03) : 300 - 304
  • [10] An effective Power Quality classifier using Wavelet Transform and Support Vector Machines
    De Yong, D.
    Bhowmik, S.
    Magnago, F.
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (15-16) : 6075 - 6081