Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (765kB) | Preview |
Ogbechie Condes, Alberto and Díaz Rozo, Javier and Larrañaga Múgica, Pedro María and Bielza Lozoya, María Concepción (2016). Dynamic Bayesian network-based anomaly detection for in-process visual inspection of laser surface heat treatment. In: "international Conference ML4CPS – Machine Learning for Cyber Physical Systems", 29 Sep 2016, Karlsruhe, Alemania. ISBN 978-3-662-53806-7. pp. 1-10. https://doi.org/10.1007/978-3-662-53806-7_3.
Title: | Dynamic Bayesian network-based anomaly detection for in-process visual inspection of laser surface heat treatment |
---|---|
Author/s: |
|
Item Type: | Presentation at Congress or Conference (Article) |
Event Title: | international Conference ML4CPS – Machine Learning for Cyber Physical Systems |
Event Dates: | 29 Sep 2016 |
Event Location: | Karlsruhe, Alemania |
Title of Book: | Machine Learning for Cyber Physical Systems |
Date: | 2016 |
ISBN: | 978-3-662-53806-7 |
Volume: | 1 |
Subjects: | |
Freetext Keywords: | Dynamic Bayesian network; Anomaly detection; Laser heat treatment; Visual inspection; Cyber-physical system |
Faculty: | E.T.S. de Ingenieros Informáticos (UPM) |
Department: | Inteligencia Artificial |
Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (765kB) | Preview |
We present the application of a cyber-physical system for inprocess quality control based on the visual inspection of a laser surface heat treatment process. To do this, we propose a classification framework that detects anomalies in recorded video sequences that have been preprocessed using a clustering-based method for feature subset selection. One peculiarity of the classification task is that there are no examples with errors, since major irregularities seldom occur in efficient industrial processes. Additionally, the parts to be processed are expensive so the sample size is small. The proposed framework uses anomaly detection, cross-validation and sampling techniques to deal with these issues. Regarding anomaly detection, dynamic Bayesian networks (DBNs) are used to represent the temporal characteristics of the normal process. Experiments are conducted with two diferent types of DBN structure learning algorithms, and classification performance is assessed on both anomalyfree examples and sequences with anomalies simulated by experts.
Type | Code | Acronym | Leader | Title |
---|---|---|---|---|
Government of Spain | TIC-20150093-P | Unspecified | Universidad Politécnica de Madrid | Unspecified |
Madrid Regional Government | S2013/ICE-2845 | CASI - CAM | Universidad Politécnica de Madrid | Conceptos y Aplicaciones de los Sistemas Inteligentes |
Item ID: | 46652 |
---|---|
DC Identifier: | http://oa.upm.es/46652/ |
OAI Identifier: | oai:oa.upm.es:46652 |
DOI: | 10.1007/978-3-662-53806-7_3 |
Official URL: | http://www.springer.com/de/book/9783662538050 |
Deposited by: | Memoria Investigacion |
Deposited on: | 07 Nov 2017 13:42 |
Last Modified: | 07 Nov 2017 13:42 |