Automated analysis of AGR fuel channel inspection videos

Michael Devereux, Paul Murray, Graeme West, Stephen Buckley-Mellor, Graeme Cocks, Chris Lynch, Adam Fletcher

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

Abstract

Remote Visual Inspection of the fuel channels which form the reactor cores of the UK’s fleet of Advanced Gas-Cooled Reactors (AGRs) occurs during planned periodic outages and provides station operators with a detailed understanding of core condition. A typical single fuel channel inspection generates a large amount of footage which must be analysed before the station is returned to power (provided it is safe to do so). While manual approaches are currently used, inspection videos can be analysed efficiently using techniques from image processing and computer vision. For example, the ASIST (Automated Software Image Stitching Tool) software processes inspection videos to construct a single image known as a chanorama (channel panorama) which allows the full inside surface of a single fuel channel to be viewed in a snapshot. To accurately characterise defects such as cracks in chanoramas, their dimensions need to be measured. This requires channel features of known size to serve as references to calculate scaling factors. These features vary from station to station and include overall brick dimensions, trepanned holes and keyways. In this paper, we propose a series of algorithms to automatically detect and measure the dimensions of each of these known features. In turn, this information can be used to generate a scaling factor which can be applied when sizing any cracks detected in a given chanorama.
LanguageEnglish
Title of host publication6th EDF-Energy Nuclear Graphite Conference (2018)
Number of pages10
Publication statusAccepted/In press - 1 Nov 2018
Event6th EDF Energy Nuclear Graphite Conference - kendal, United Kingdom
Duration: 15 Oct 201818 Oct 2018

Conference

Conference6th EDF Energy Nuclear Graphite Conference
CountryUnited Kingdom
Citykendal
Period15/10/1818/10/18

Fingerprint

Gas cooled reactors
Inspection
Keyways
Cracks
Reactor cores
Brick
Outages
Computer vision
Image processing
Defects

Keywords

  • imaging processing
  • Hough transform
  • hit of miss transform

Cite this

Devereux, M., Murray, P., West, G., Buckley-Mellor, S., Cocks, G., Lynch, C., & Fletcher, A. (Accepted/In press). Automated analysis of AGR fuel channel inspection videos. In 6th EDF-Energy Nuclear Graphite Conference (2018)
Devereux, Michael ; Murray, Paul ; West, Graeme ; Buckley-Mellor, Stephen ; Cocks, Graeme ; Lynch, Chris ; Fletcher, Adam. / Automated analysis of AGR fuel channel inspection videos. 6th EDF-Energy Nuclear Graphite Conference (2018). 2018.
@inproceedings{36c84db166184c37988d60627eb0569e,
title = "Automated analysis of AGR fuel channel inspection videos",
abstract = "Remote Visual Inspection of the fuel channels which form the reactor cores of the UK’s fleet of Advanced Gas-Cooled Reactors (AGRs) occurs during planned periodic outages and provides station operators with a detailed understanding of core condition. A typical single fuel channel inspection generates a large amount of footage which must be analysed before the station is returned to power (provided it is safe to do so). While manual approaches are currently used, inspection videos can be analysed efficiently using techniques from image processing and computer vision. For example, the ASIST (Automated Software Image Stitching Tool) software processes inspection videos to construct a single image known as a chanorama (channel panorama) which allows the full inside surface of a single fuel channel to be viewed in a snapshot. To accurately characterise defects such as cracks in chanoramas, their dimensions need to be measured. This requires channel features of known size to serve as references to calculate scaling factors. These features vary from station to station and include overall brick dimensions, trepanned holes and keyways. In this paper, we propose a series of algorithms to automatically detect and measure the dimensions of each of these known features. In turn, this information can be used to generate a scaling factor which can be applied when sizing any cracks detected in a given chanorama.",
keywords = "imaging processing, Hough transform, hit of miss transform",
author = "Michael Devereux and Paul Murray and Graeme West and Stephen Buckley-Mellor and Graeme Cocks and Chris Lynch and Adam Fletcher",
year = "2018",
month = "11",
day = "1",
language = "English",
booktitle = "6th EDF-Energy Nuclear Graphite Conference (2018)",

}

Devereux, M, Murray, P, West, G, Buckley-Mellor, S, Cocks, G, Lynch, C & Fletcher, A 2018, Automated analysis of AGR fuel channel inspection videos. in 6th EDF-Energy Nuclear Graphite Conference (2018). 6th EDF Energy Nuclear Graphite Conference, kendal, United Kingdom, 15/10/18.

Automated analysis of AGR fuel channel inspection videos. / Devereux, Michael; Murray, Paul; West, Graeme; Buckley-Mellor, Stephen; Cocks, Graeme; Lynch, Chris; Fletcher, Adam.

6th EDF-Energy Nuclear Graphite Conference (2018). 2018.

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

TY - GEN

T1 - Automated analysis of AGR fuel channel inspection videos

AU - Devereux, Michael

AU - Murray, Paul

AU - West, Graeme

AU - Buckley-Mellor, Stephen

AU - Cocks, Graeme

AU - Lynch, Chris

AU - Fletcher, Adam

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Remote Visual Inspection of the fuel channels which form the reactor cores of the UK’s fleet of Advanced Gas-Cooled Reactors (AGRs) occurs during planned periodic outages and provides station operators with a detailed understanding of core condition. A typical single fuel channel inspection generates a large amount of footage which must be analysed before the station is returned to power (provided it is safe to do so). While manual approaches are currently used, inspection videos can be analysed efficiently using techniques from image processing and computer vision. For example, the ASIST (Automated Software Image Stitching Tool) software processes inspection videos to construct a single image known as a chanorama (channel panorama) which allows the full inside surface of a single fuel channel to be viewed in a snapshot. To accurately characterise defects such as cracks in chanoramas, their dimensions need to be measured. This requires channel features of known size to serve as references to calculate scaling factors. These features vary from station to station and include overall brick dimensions, trepanned holes and keyways. In this paper, we propose a series of algorithms to automatically detect and measure the dimensions of each of these known features. In turn, this information can be used to generate a scaling factor which can be applied when sizing any cracks detected in a given chanorama.

AB - Remote Visual Inspection of the fuel channels which form the reactor cores of the UK’s fleet of Advanced Gas-Cooled Reactors (AGRs) occurs during planned periodic outages and provides station operators with a detailed understanding of core condition. A typical single fuel channel inspection generates a large amount of footage which must be analysed before the station is returned to power (provided it is safe to do so). While manual approaches are currently used, inspection videos can be analysed efficiently using techniques from image processing and computer vision. For example, the ASIST (Automated Software Image Stitching Tool) software processes inspection videos to construct a single image known as a chanorama (channel panorama) which allows the full inside surface of a single fuel channel to be viewed in a snapshot. To accurately characterise defects such as cracks in chanoramas, their dimensions need to be measured. This requires channel features of known size to serve as references to calculate scaling factors. These features vary from station to station and include overall brick dimensions, trepanned holes and keyways. In this paper, we propose a series of algorithms to automatically detect and measure the dimensions of each of these known features. In turn, this information can be used to generate a scaling factor which can be applied when sizing any cracks detected in a given chanorama.

KW - imaging processing

KW - Hough transform

KW - hit of miss transform

UR - https://britishcarbon.org/2018/01/31/6th-edf-energy-nuclear-graphite-conference-2018/

M3 - Conference contribution book

BT - 6th EDF-Energy Nuclear Graphite Conference (2018)

ER -

Devereux M, Murray P, West G, Buckley-Mellor S, Cocks G, Lynch C et al. Automated analysis of AGR fuel channel inspection videos. In 6th EDF-Energy Nuclear Graphite Conference (2018). 2018