Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis

Mojtaba Ghodsi, Hamidreza Ziaiefar, Milad Amiryan, Farhang Honarvar, Yousef Hojjat, Mehdi Mahmoudi, Amur Al-Yahmadi, Issam Bahadur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this research, a new method is presented for eliciting the proper features for recognizing and classifying the kinds of the defects by guided ultrasonic waves. After applying suitable preprocessing, the suggested method extracts the base frequency band from the received signals by discrete wavelet transform and discrete Fourier transform. This frequency band can be used as a distinctive feature of ultrasonic signals in different defects. Principal Component Analysis with improving this feature and decreasing extra data managed to improve classification. In this study, ultrasonic test with A0 mode lamb wave is used and is appropriated to reduce the difficulties around the problem. The defects under analysis included corrosion, crack and local thickness reduction. The last defect is caused by electro discharge machining (EDM). The results of the classification by optimized Neural Network depicts that the presented method can differentiate different defects with 95% precision and thus, it is a strong and efficient method. Moreover, comparing the elicited features for corrosion and local thickness reduction and also the results of the two's classification clarifies that modeling the corrosion procedure by local thickness reduction which was previously common, is not an appropriate method and the signals received from the two defects are different from each other.

Original languageEnglish
Title of host publicationNondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016
PublisherSPIE
Volume9804
ISBN (Electronic)9781510600454
DOIs
Publication statusPublished - 2016
EventNondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016 - Las Vegas, United States
Duration: Mar 21 2016Mar 24 2016

Other

OtherNondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016
CountryUnited States
CityLas Vegas
Period3/21/163/24/16

Fingerprint

Lamb Waves
Wavelet Transformation
Lamb waves
principal components analysis
pattern recognition
Surface waves
Principal component analysis
Principal Component Analysis
Feature Extraction
Feature extraction
Defects
defects
Corrosion
corrosion
Frequency bands
ultrasonic tests
Ultrasonics
Ultrasonic Wave
Guided Waves
Electric discharge machining

Keywords

  • ANN
  • Corrosion
  • Feature extraction
  • FFT
  • Lamb wave
  • PCA

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Ghodsi, M., Ziaiefar, H., Amiryan, M., Honarvar, F., Hojjat, Y., Mahmoudi, M., ... Bahadur, I. (2016). Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis. In Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016 (Vol. 9804). [98041F] SPIE. https://doi.org/10.1117/12.2218842

Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis. / Ghodsi, Mojtaba; Ziaiefar, Hamidreza; Amiryan, Milad; Honarvar, Farhang; Hojjat, Yousef; Mahmoudi, Mehdi; Al-Yahmadi, Amur; Bahadur, Issam.

Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016. Vol. 9804 SPIE, 2016. 98041F.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ghodsi, M, Ziaiefar, H, Amiryan, M, Honarvar, F, Hojjat, Y, Mahmoudi, M, Al-Yahmadi, A & Bahadur, I 2016, Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis. in Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016. vol. 9804, 98041F, SPIE, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016, Las Vegas, United States, 3/21/16. https://doi.org/10.1117/12.2218842
Ghodsi M, Ziaiefar H, Amiryan M, Honarvar F, Hojjat Y, Mahmoudi M et al. Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis. In Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016. Vol. 9804. SPIE. 2016. 98041F https://doi.org/10.1117/12.2218842
Ghodsi, Mojtaba ; Ziaiefar, Hamidreza ; Amiryan, Milad ; Honarvar, Farhang ; Hojjat, Yousef ; Mahmoudi, Mehdi ; Al-Yahmadi, Amur ; Bahadur, Issam. / Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis. Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016. Vol. 9804 SPIE, 2016.
@inproceedings{28d317d60fe841a68f61019ae4f18f60,
title = "Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis",
abstract = "In this research, a new method is presented for eliciting the proper features for recognizing and classifying the kinds of the defects by guided ultrasonic waves. After applying suitable preprocessing, the suggested method extracts the base frequency band from the received signals by discrete wavelet transform and discrete Fourier transform. This frequency band can be used as a distinctive feature of ultrasonic signals in different defects. Principal Component Analysis with improving this feature and decreasing extra data managed to improve classification. In this study, ultrasonic test with A0 mode lamb wave is used and is appropriated to reduce the difficulties around the problem. The defects under analysis included corrosion, crack and local thickness reduction. The last defect is caused by electro discharge machining (EDM). The results of the classification by optimized Neural Network depicts that the presented method can differentiate different defects with 95{\%} precision and thus, it is a strong and efficient method. Moreover, comparing the elicited features for corrosion and local thickness reduction and also the results of the two's classification clarifies that modeling the corrosion procedure by local thickness reduction which was previously common, is not an appropriate method and the signals received from the two defects are different from each other.",
keywords = "ANN, Corrosion, Feature extraction, FFT, Lamb wave, PCA",
author = "Mojtaba Ghodsi and Hamidreza Ziaiefar and Milad Amiryan and Farhang Honarvar and Yousef Hojjat and Mehdi Mahmoudi and Amur Al-Yahmadi and Issam Bahadur",
year = "2016",
doi = "10.1117/12.2218842",
language = "English",
volume = "9804",
booktitle = "Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016",
publisher = "SPIE",

}

TY - GEN

T1 - Lamb wave feature extraction using discrete wavelet transformation and Principal Component Analysis

AU - Ghodsi, Mojtaba

AU - Ziaiefar, Hamidreza

AU - Amiryan, Milad

AU - Honarvar, Farhang

AU - Hojjat, Yousef

AU - Mahmoudi, Mehdi

AU - Al-Yahmadi, Amur

AU - Bahadur, Issam

PY - 2016

Y1 - 2016

N2 - In this research, a new method is presented for eliciting the proper features for recognizing and classifying the kinds of the defects by guided ultrasonic waves. After applying suitable preprocessing, the suggested method extracts the base frequency band from the received signals by discrete wavelet transform and discrete Fourier transform. This frequency band can be used as a distinctive feature of ultrasonic signals in different defects. Principal Component Analysis with improving this feature and decreasing extra data managed to improve classification. In this study, ultrasonic test with A0 mode lamb wave is used and is appropriated to reduce the difficulties around the problem. The defects under analysis included corrosion, crack and local thickness reduction. The last defect is caused by electro discharge machining (EDM). The results of the classification by optimized Neural Network depicts that the presented method can differentiate different defects with 95% precision and thus, it is a strong and efficient method. Moreover, comparing the elicited features for corrosion and local thickness reduction and also the results of the two's classification clarifies that modeling the corrosion procedure by local thickness reduction which was previously common, is not an appropriate method and the signals received from the two defects are different from each other.

AB - In this research, a new method is presented for eliciting the proper features for recognizing and classifying the kinds of the defects by guided ultrasonic waves. After applying suitable preprocessing, the suggested method extracts the base frequency band from the received signals by discrete wavelet transform and discrete Fourier transform. This frequency band can be used as a distinctive feature of ultrasonic signals in different defects. Principal Component Analysis with improving this feature and decreasing extra data managed to improve classification. In this study, ultrasonic test with A0 mode lamb wave is used and is appropriated to reduce the difficulties around the problem. The defects under analysis included corrosion, crack and local thickness reduction. The last defect is caused by electro discharge machining (EDM). The results of the classification by optimized Neural Network depicts that the presented method can differentiate different defects with 95% precision and thus, it is a strong and efficient method. Moreover, comparing the elicited features for corrosion and local thickness reduction and also the results of the two's classification clarifies that modeling the corrosion procedure by local thickness reduction which was previously common, is not an appropriate method and the signals received from the two defects are different from each other.

KW - ANN

KW - Corrosion

KW - Feature extraction

KW - FFT

KW - Lamb wave

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=84981320380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981320380&partnerID=8YFLogxK

U2 - 10.1117/12.2218842

DO - 10.1117/12.2218842

M3 - Conference contribution

AN - SCOPUS:84981320380

VL - 9804

BT - Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016

PB - SPIE

ER -