Data fusion in automated inspection systems

M. Friedrich, S.G. Pierce, W. Galbraith, G. Hayward

Research output: Contribution to conferencePaper

Abstract

Teams of small modular inspection vehicles for automated inspection tasks offer the possibility of employing a variety of different NDE inspection methods simultaneously. By synergistically utilising information derived from multiple sources, individual deficiencies and limitations can be partially compensated, leading to a more accurate and precise evaluation of the condition of the engineering structure under test. This paper presents approaches based on fusion of NDE data that have been obtained by a heterogeneous team of small inspection robots which are equipped with payloads for magnetic flux leakage, eddy current and ultrasonic inspection. Any potential uncertainties in individual measurements regarding the location of defects constitute the basis for fusion methods based on statistical and probabilistic algorithms. Images of a two-dimensional test structure have been constructed from data derived from different scans, indicating the positions of detected artificial defects. Applying the Dempster-Shqfer theory of evidence and Bayesian analysis, the confidence level in the accuracy of these images is increased and the uncertainty reduced.
LanguageEnglish
Publication statusPublished - 2007
EventBINDT Annual Conference NDT 2007 -
Duration: 18 Sep 200719 Sep 2007

Conference

ConferenceBINDT Annual Conference NDT 2007
Abbreviated titleNDT 2007
Period18/09/0719/09/07

Fingerprint

Data fusion
Inspection
Defects
Magnetic flux
Eddy currents
Ultrasonics
Robots
Uncertainty

Keywords

  • data fusion
  • robotics
  • inspection systems

Cite this

Friedrich, M., Pierce, S. G., Galbraith, W., & Hayward, G. (2007). Data fusion in automated inspection systems. Paper presented at BINDT Annual Conference NDT 2007, .
Friedrich, M. ; Pierce, S.G. ; Galbraith, W. ; Hayward, G. / Data fusion in automated inspection systems. Paper presented at BINDT Annual Conference NDT 2007, .
@conference{3eb83254eb1d468285a2306b7a253e60,
title = "Data fusion in automated inspection systems",
abstract = "Teams of small modular inspection vehicles for automated inspection tasks offer the possibility of employing a variety of different NDE inspection methods simultaneously. By synergistically utilising information derived from multiple sources, individual deficiencies and limitations can be partially compensated, leading to a more accurate and precise evaluation of the condition of the engineering structure under test. This paper presents approaches based on fusion of NDE data that have been obtained by a heterogeneous team of small inspection robots which are equipped with payloads for magnetic flux leakage, eddy current and ultrasonic inspection. Any potential uncertainties in individual measurements regarding the location of defects constitute the basis for fusion methods based on statistical and probabilistic algorithms. Images of a two-dimensional test structure have been constructed from data derived from different scans, indicating the positions of detected artificial defects. Applying the Dempster-Shqfer theory of evidence and Bayesian analysis, the confidence level in the accuracy of these images is increased and the uncertainty reduced.",
keywords = "data fusion, robotics, inspection systems",
author = "M. Friedrich and S.G. Pierce and W. Galbraith and G. Hayward",
year = "2007",
language = "English",
note = "BINDT Annual Conference NDT 2007, NDT 2007 ; Conference date: 18-09-2007 Through 19-09-2007",

}

Friedrich, M, Pierce, SG, Galbraith, W & Hayward, G 2007, 'Data fusion in automated inspection systems' Paper presented at BINDT Annual Conference NDT 2007, 18/09/07 - 19/09/07, .

Data fusion in automated inspection systems. / Friedrich, M.; Pierce, S.G.; Galbraith, W.; Hayward, G.

2007. Paper presented at BINDT Annual Conference NDT 2007, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Data fusion in automated inspection systems

AU - Friedrich, M.

AU - Pierce, S.G.

AU - Galbraith, W.

AU - Hayward, G.

PY - 2007

Y1 - 2007

N2 - Teams of small modular inspection vehicles for automated inspection tasks offer the possibility of employing a variety of different NDE inspection methods simultaneously. By synergistically utilising information derived from multiple sources, individual deficiencies and limitations can be partially compensated, leading to a more accurate and precise evaluation of the condition of the engineering structure under test. This paper presents approaches based on fusion of NDE data that have been obtained by a heterogeneous team of small inspection robots which are equipped with payloads for magnetic flux leakage, eddy current and ultrasonic inspection. Any potential uncertainties in individual measurements regarding the location of defects constitute the basis for fusion methods based on statistical and probabilistic algorithms. Images of a two-dimensional test structure have been constructed from data derived from different scans, indicating the positions of detected artificial defects. Applying the Dempster-Shqfer theory of evidence and Bayesian analysis, the confidence level in the accuracy of these images is increased and the uncertainty reduced.

AB - Teams of small modular inspection vehicles for automated inspection tasks offer the possibility of employing a variety of different NDE inspection methods simultaneously. By synergistically utilising information derived from multiple sources, individual deficiencies and limitations can be partially compensated, leading to a more accurate and precise evaluation of the condition of the engineering structure under test. This paper presents approaches based on fusion of NDE data that have been obtained by a heterogeneous team of small inspection robots which are equipped with payloads for magnetic flux leakage, eddy current and ultrasonic inspection. Any potential uncertainties in individual measurements regarding the location of defects constitute the basis for fusion methods based on statistical and probabilistic algorithms. Images of a two-dimensional test structure have been constructed from data derived from different scans, indicating the positions of detected artificial defects. Applying the Dempster-Shqfer theory of evidence and Bayesian analysis, the confidence level in the accuracy of these images is increased and the uncertainty reduced.

KW - data fusion

KW - robotics

KW - inspection systems

UR - http://dx.doi.org/10.1784/insi.2008.50.2.88

M3 - Paper

ER -

Friedrich M, Pierce SG, Galbraith W, Hayward G. Data fusion in automated inspection systems. 2007. Paper presented at BINDT Annual Conference NDT 2007, .