Artificial intelligence assisted condition assessment

W. Nash, L. Holloway, T. Drummond, N. Birbilis

Research output: Contribution to conferencePaperOther

Abstract

The confluence of aging infrastructure and commodity prices has created a scenario where maintenance costs are often prohibitive and inspection has become the primary means of ensuring the integrity of critical infrastructure. This inspection comes at a considerable cost due to the need provide access to equipment that is often elevated and operating, for example, in the oil and gas environment. Deep learning and artificial intelligence (A.I.) computer vision systems are revolutionising many fields, and condition assessment can take advantage of this progress to provide expert opinion systems on site, and direct inspection resources to areas of high risk. In this work, the capability of semi-supervised deep learning networks to conduct rapid condition assessment of complex steel structures is presented. Currently this technology is applied in post-processing of site photos, although this provides for some time saving, a roadmap is provided to deploying this software for on-site assessment in real time, for example with cameras mounted on drones, or augmented reality headsets, and explore the challenges remaining for field deployment. Some pitfalls of artificial intelligence systems and how to avoid them are discussed, whilst a discussion of the extensibility of these systems is also be presented to illustrate how A.I. can be used to tackle problems in other areas.

Original languageEnglish
Publication statusPublished - 2017
EventAustralasian Corrosion Association (ACA) Conference 2017: Corrosion and Prevention - Sydney, Australia
Duration: 12 Nov 201715 Nov 2017

Conference

ConferenceAustralasian Corrosion Association (ACA) Conference 2017
CountryAustralia
CitySydney
Period12/11/1715/11/17

Keywords

  • Artificial intelligence
  • Corrosion
  • Deep learning
  • Inspection

Cite this

Nash, W., Holloway, L., Drummond, T., & Birbilis, N. (2017). Artificial intelligence assisted condition assessment. Paper presented at Australasian Corrosion Association (ACA) Conference 2017, Sydney, Australia.
Nash, W. ; Holloway, L. ; Drummond, T. ; Birbilis, N. / Artificial intelligence assisted condition assessment. Paper presented at Australasian Corrosion Association (ACA) Conference 2017, Sydney, Australia.
@conference{438e9207371d40eea3c7f7ee355b6d72,
title = "Artificial intelligence assisted condition assessment",
abstract = "The confluence of aging infrastructure and commodity prices has created a scenario where maintenance costs are often prohibitive and inspection has become the primary means of ensuring the integrity of critical infrastructure. This inspection comes at a considerable cost due to the need provide access to equipment that is often elevated and operating, for example, in the oil and gas environment. Deep learning and artificial intelligence (A.I.) computer vision systems are revolutionising many fields, and condition assessment can take advantage of this progress to provide expert opinion systems on site, and direct inspection resources to areas of high risk. In this work, the capability of semi-supervised deep learning networks to conduct rapid condition assessment of complex steel structures is presented. Currently this technology is applied in post-processing of site photos, although this provides for some time saving, a roadmap is provided to deploying this software for on-site assessment in real time, for example with cameras mounted on drones, or augmented reality headsets, and explore the challenges remaining for field deployment. Some pitfalls of artificial intelligence systems and how to avoid them are discussed, whilst a discussion of the extensibility of these systems is also be presented to illustrate how A.I. can be used to tackle problems in other areas.",
keywords = "Artificial intelligence, Corrosion, Deep learning, Inspection",
author = "W. Nash and L. Holloway and T. Drummond and N. Birbilis",
year = "2017",
language = "English",
note = "Australasian Corrosion Association (ACA) Conference 2017 : Corrosion and Prevention ; Conference date: 12-11-2017 Through 15-11-2017",

}

Nash, W, Holloway, L, Drummond, T & Birbilis, N 2017, 'Artificial intelligence assisted condition assessment' Paper presented at Australasian Corrosion Association (ACA) Conference 2017, Sydney, Australia, 12/11/17 - 15/11/17, .

Artificial intelligence assisted condition assessment. / Nash, W.; Holloway, L.; Drummond, T.; Birbilis, N.

2017. Paper presented at Australasian Corrosion Association (ACA) Conference 2017, Sydney, Australia.

Research output: Contribution to conferencePaperOther

TY - CONF

T1 - Artificial intelligence assisted condition assessment

AU - Nash, W.

AU - Holloway, L.

AU - Drummond, T.

AU - Birbilis, N.

PY - 2017

Y1 - 2017

N2 - The confluence of aging infrastructure and commodity prices has created a scenario where maintenance costs are often prohibitive and inspection has become the primary means of ensuring the integrity of critical infrastructure. This inspection comes at a considerable cost due to the need provide access to equipment that is often elevated and operating, for example, in the oil and gas environment. Deep learning and artificial intelligence (A.I.) computer vision systems are revolutionising many fields, and condition assessment can take advantage of this progress to provide expert opinion systems on site, and direct inspection resources to areas of high risk. In this work, the capability of semi-supervised deep learning networks to conduct rapid condition assessment of complex steel structures is presented. Currently this technology is applied in post-processing of site photos, although this provides for some time saving, a roadmap is provided to deploying this software for on-site assessment in real time, for example with cameras mounted on drones, or augmented reality headsets, and explore the challenges remaining for field deployment. Some pitfalls of artificial intelligence systems and how to avoid them are discussed, whilst a discussion of the extensibility of these systems is also be presented to illustrate how A.I. can be used to tackle problems in other areas.

AB - The confluence of aging infrastructure and commodity prices has created a scenario where maintenance costs are often prohibitive and inspection has become the primary means of ensuring the integrity of critical infrastructure. This inspection comes at a considerable cost due to the need provide access to equipment that is often elevated and operating, for example, in the oil and gas environment. Deep learning and artificial intelligence (A.I.) computer vision systems are revolutionising many fields, and condition assessment can take advantage of this progress to provide expert opinion systems on site, and direct inspection resources to areas of high risk. In this work, the capability of semi-supervised deep learning networks to conduct rapid condition assessment of complex steel structures is presented. Currently this technology is applied in post-processing of site photos, although this provides for some time saving, a roadmap is provided to deploying this software for on-site assessment in real time, for example with cameras mounted on drones, or augmented reality headsets, and explore the challenges remaining for field deployment. Some pitfalls of artificial intelligence systems and how to avoid them are discussed, whilst a discussion of the extensibility of these systems is also be presented to illustrate how A.I. can be used to tackle problems in other areas.

KW - Artificial intelligence

KW - Corrosion

KW - Deep learning

KW - Inspection

UR - http://www.scopus.com/inward/record.url?scp=85047315964&partnerID=8YFLogxK

M3 - Paper

ER -

Nash W, Holloway L, Drummond T, Birbilis N. Artificial intelligence assisted condition assessment. 2017. Paper presented at Australasian Corrosion Association (ACA) Conference 2017, Sydney, Australia.