This paper casts pipe inspection by ultrasonic guided waves in a feature extraction and automatic classification framework. The specific defect under investigation is a small notch cut in an ASTM-A53-F steel pipe at depths ranging from 1% to 17% of the pipe cross-sectional area. A semi-analytical finite element method is first used to model wave propagation in the pipe. In the experiment, reflection measurements are taken and six features are extracted from the discrete wavelet decomposition of the raw signals and from the Hilbert and Fourier transforms of the reconstructed signals. A six-dimensional damage index is then constructed, and it is fed to an artificial neural network that classifies the size and the location of the notch. Overall, the wavelet-based multifeature analysis demonstrates good classification performance and robustness against noise and changes in some of the operating parameters.
Skip Nav Destination
e-mail: prizzo@soe.ucsd.edu
e-mail: ibartoli@ucsd.edu
e-mail: alessandro.marzani@mail.ing.unibo.it
e-mail: flanza@ucsd.edu
Article navigation
August 2005
Research Papers
Defect Classification in Pipes by Neural Networks Using Multiple Guided Ultrasonic Wave Features Extracted After Wavelet Processing
Piervincenzo Rizzo,
Piervincenzo Rizzo
Assistant Project Scientist
NDE & Structural Health Monitoring Laboratory, Department of Structural Engineering,
e-mail: prizzo@soe.ucsd.edu
University of California
, San Diego, 9500 Gilman Drive, M.C. 0085, La Jolla, CA 92093-0085
Search for other works by this author on:
Ivan Bartoli,
Ivan Bartoli
Graduate Student Researcher
NDE & Structural Health Monitoring Laboratory, Department of Structural Engineering,
e-mail: ibartoli@ucsd.edu
University of California
, San Diego, 9500 Gilman Drive, M.C. 0085, La Jolla, CA 92093-0085
Search for other works by this author on:
Alessandro Marzani,
Alessandro Marzani
Assistant Professor
Dip. di Ingegneria delle Strutture, dei Transporti, delle Acque, del Rilevamento, del Territorio (DISTART),
e-mail: alessandro.marzani@mail.ing.unibo.it
Universitá degli Studi di Bologna
, Viale Risorgimento 2, Bologna 40136, Italy
Search for other works by this author on:
Francesco Lanza di Scalea
Francesco Lanza di Scalea
Associate Professor
NDE & Structural Health Monitoring Laboratory, Department of Structural Engineering,
e-mail: flanza@ucsd.edu
University of California
, San Diego, 9500 Gilman Drive, M.C. 0085, La Jolla, CA 92093-0085
Search for other works by this author on:
Piervincenzo Rizzo
Assistant Project Scientist
NDE & Structural Health Monitoring Laboratory, Department of Structural Engineering,
University of California
, San Diego, 9500 Gilman Drive, M.C. 0085, La Jolla, CA 92093-0085e-mail: prizzo@soe.ucsd.edu
Ivan Bartoli
Graduate Student Researcher
NDE & Structural Health Monitoring Laboratory, Department of Structural Engineering,
University of California
, San Diego, 9500 Gilman Drive, M.C. 0085, La Jolla, CA 92093-0085e-mail: ibartoli@ucsd.edu
Alessandro Marzani
Assistant Professor
Dip. di Ingegneria delle Strutture, dei Transporti, delle Acque, del Rilevamento, del Territorio (DISTART),
Universitá degli Studi di Bologna
, Viale Risorgimento 2, Bologna 40136, Italye-mail: alessandro.marzani@mail.ing.unibo.it
Francesco Lanza di Scalea
Associate Professor
NDE & Structural Health Monitoring Laboratory, Department of Structural Engineering,
University of California
, San Diego, 9500 Gilman Drive, M.C. 0085, La Jolla, CA 92093-0085e-mail: flanza@ucsd.edu
J. Pressure Vessel Technol. Aug 2005, 127(3): 294-303 (10 pages)
Published Online: January 27, 2005
Article history
Received:
January 25, 2005
Revised:
January 27, 2005
Citation
Rizzo, P., Bartoli, I., Marzani, A., and Lanza di Scalea, F. (January 27, 2005). "Defect Classification in Pipes by Neural Networks Using Multiple Guided Ultrasonic Wave Features Extracted After Wavelet Processing." ASME. J. Pressure Vessel Technol. August 2005; 127(3): 294–303. https://doi.org/10.1115/1.1990213
Download citation file:
Get Email Alerts
On the possibility of extending the crack length criterion in the master curve methodology
J. Pressure Vessel Technol
Investigation of Fracture Prediction Capability of XFEM and FEM using SENT Specimens
J. Pressure Vessel Technol
The Behavior of Elbow Elements at Pure Bending Applications Compared to Beam and Shell Element Models
J. Pressure Vessel Technol (February 2025)
Related Articles
On-Line Seam Detection in Rolling Processes Using Snake Projection and Discrete Wavelet Transform
J. Manuf. Sci. Eng (October,2007)
Gas Coupled Ultrasonic Measurement of Pipeline Wall Thickness
J. Pressure Vessel Technol (August,2005)
Feature Selection for Fault Detection in Rolling Element Bearings Using Mutual Information
J. Vib. Acoust (December,2011)
On-Line Quality Detection of Ultrasonic Wire Bonding via Refining Analysis of Electrical Signal From Ultrasonic Generator
J. Electron. Packag (December,2010)
Related Proceedings Papers
Related Chapters
Interval Type-2 Fuzzy Logic for Improving Feature Extraction and Response Integration in Modular Neural Networks for Image Recognition
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17
Feature Extraction of Vehicle Type Based on Wavelet and Hough Transform
International Symposium on Information Engineering and Electronic Commerce, 3rd (IEEC 2011)
Identifying Climate Teleconnection Signatures by Data Feature Extraction through Wavelet Spectral Decomposition
Intelligent Engineering Systems through Artificial Neural Networks Volume 18