Closed-Loop Active Model Diagnosis Using Bhattacharyya Coefficient: Application to Automated Visual Inspection

J. Noom*, Hieu Thao Nguyen, O.A. Soloviev, M.H.G. Verhaegen

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

39 Downloads (Pure)

Abstract

This manuscript presents an improvement of state-of-the-art Closed-Loop Active Model Diagnosis (CLAMD). The proposed method utilizes weighted Bhattacharyya coefficients evaluated at the vertices of the polytopic constraint set to provide a good trade-off between computational efficiency and satisfactory input choice for separation of candidate models of a system. A simulation of a dynamical system shows the closed-loop performance not being susceptible to the combination of candidate models. Additionally, the broad applicability of CLAMD is shown by means of a demonstrative application in automated visual inspection. This application involves sequential determination of the optimal object inspection region for the next measurement. As compared to the conventional approach using one full image to recognize handwritten digits from the MNIST dataset, the novel CLAMD-approach needs significantly (up to 78%) less data to achieve similar accuracy.
Original languageEnglish
Title of host publicationInternational Conference on Intelligent Systems Design and Applications
Subtitle of host publication20th International Conference on Intelligent Systems Design and Applications (ISDA 2020) held December 12-15, 2020
EditorsAjith Abraham, Vincenzo Piuri, Niketa Gandhi, Patrick Siarry, Arturas Kaklauskas, Ana Madureira
PublisherSpringer
Pages657-667
ISBN (Electronic)978-3-030-71187-0
ISBN (Print)978-3-030-71186-3
DOIs
Publication statusPublished - 2021
EventISDA 2020: 20th International Conference on Intelligent Systems Design and Applications (Online) -
Duration: 12 Dec 202015 Dec 2020

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1351
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceISDA 2020: 20th International Conference on Intelligent Systems Design and Applications (Online)
Period12/12/2015/12/20

Bibliographical note

Accepted Author Manuscript

Keywords

  • Active fault diagnosis
  • Model discrimination
  • Auxiliary signal design
  • Bhattacharyya coefficient
  • Machine vision

Fingerprint

Dive into the research topics of 'Closed-Loop Active Model Diagnosis Using Bhattacharyya Coefficient: Application to Automated Visual Inspection'. Together they form a unique fingerprint.

Cite this