Unsupervised Fouling Reconstruction in the Pipe Bend

Denys Iablonskyi, Carlos-Omar Rasgado-Moreno, Madis Ratassepp, Arto Klami, Edward Haeggström, Ari Salmi

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Guided wave tomography allows the investigation of extended areas with a limited number of measurements, typically using transducer arrays. Most imaging methods rely heavily on the material properties such as dispersion curves, that in the case of fouling deposition are not always known. In the case of complex shaped structures, geometrical anisotropy can bring additional complexity. Here we present an unsupervised machine learning approach based on the Gaussian process to detect and characterize the fouling in a pipe bend that relies only on the difference between clean/healthy and fouled/damaged measured signals.
Original languageEnglish
Title of host publication2023 International Ultrasonics Symposium
Number of pages3
PublisherIEEE
Publication date7 Nov 2023
ISBN (Print)979-8-3503-4646-6
ISBN (Electronic)979-8-3503-4645-9
DOIs
Publication statusPublished - 7 Nov 2023
MoE publication typeA4 Article in conference proceedings
Event2023 IEEE International Ultrasonics Symposium (IUS) - Palais des congrès de Montréal, Montréal, Canada
Duration: 3 Sept 20238 Sept 2023

Publication series

Name
ISSN (Print)1948-5719
ISSN (Electronic)1948-5727

Fields of Science

  • 114 Physical sciences
  • guided waves
  • structural health monitoring
  • nondestructive testing
  • fouling detection
  • Gaussian processes

Cite this