Publication detail

Non-destructive Testing of CIPP Defects Using Machine Learning Approach

DVOŘÁK, R. PAZDERA, L. TOPOLÁŘ, L. JAKUBKA, L. PUCHÝŘ, J.

Original Title

Non-destructive Testing of CIPP Defects Using Machine Learning Approach

Type

journal article in Web of Science

Language

English

Original Abstract

In civil engineering, retrofitting actions involving repairs to pipes inside buildings and in extravehicular locations present complex and challenging tasks. Traditional repair procedures typically involve disassembling the surrounding structure, leading to technological pauses and potential work environment disruptions. An alternative approach to these procedures is using "cured-in-place pipes" (CIPP) technology for repairs. Unlike standard repairs, CIPP repairs do not require the disassembly of the surrounding structures; only the access points at the beginning and end of the pipe need to be accessible. However, this method introduces the possibility of different types of defects.1 This research aims to observe defects between the host and newly cured pipes. However, the presence of holes, cracks, or obstacles prevents attaining this desired close-fit state, ultimately reducing the life expectancy of the retrofitting action. This paper focuses on the non-destructive observation of these defects using the NDT Impact-Echo (IE) method. The study explicitly applies this method to CIPP composite pipe segments inside concrete host pipes, forming a testing polygon. Previous results have indicated that the mechanical behaviour of cured CIPP composite pipes can vary in stiffness depending on factors such as the curing procedure and environmental conditions.2 The change of acoustic parameters such as resonance frequency, attenuation and other features of typical IE signals can describe the stiffness evolution. This paper compares different sensors used for IE proposed testing, namely piezoceramic and microphone sensors. It evaluates their ability to distinguish between defects present in the body of the CIPP via a machine-learning approach using random tree classifiers.

Keywords

Retrofitting; Cured-in-Place Pipes; Non-Destructive Testing; Impact-Echo Method; Pipe Defects; Acoustic Parameters; Machine Learning; Classification.

Authors

DVOŘÁK, R.; PAZDERA, L.; TOPOLÁŘ, L.; JAKUBKA, L.; PUCHÝŘ, J.

Released

15. 9. 2024

Publisher

Materials and technology

ISBN

1580-2949

Periodical

Materiali in tehnologije

Year of study

58

Number

5

State

Republic of Slovenia

Pages from

13

Pages to

17

Pages count

6

URL

https://mater-tehnol.si/index.php/MatTech/article/view/1000

BibTex

@article{BUT189650,
  author="Richard {Dvořák} and Luboš {Pazdera} and Libor {Topolář} and Luboš {Jakubka} and Jan {Puchýř}",
  title="Non-destructive Testing of CIPP Defects Using Machine Learning Approach",
  journal="Materiali in tehnologije",
  year="2024",
  volume="58",
  number="5",
  pages="13--17",
  doi="10.17222/mit.2023.1000",
  issn="1580-2949",
  url="https://mater-tehnol.si/index.php/MatTech/article/view/1000"
}