Academic Journal
Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis
| Title: | Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis |
|---|---|
| Authors: | Cariño Corrales, Jesús Adolfo, Delgado Prieto, Miquel, Zurita Millán, Daniel, Millan, Marta, Ortega Redondo, Juan Antonio, Romero Troncoso, Rene De Jesus |
| Contributors: | Universitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica, Universitat Politècnica de Catalunya. MCIA - Motion Control and Industrial Applications Research Group |
| Source: | Recercat. Dipósit de la Recerca de Catalunya instname UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) IEEE Access, Vol 4, Pp 7594-7604 (2016) |
| Publisher Information: | Institute of Electrical and Electronics Engineers (IEEE), 2016. |
| Publication Year: | 2016 |
| Subject Terms: | Màquines, Teoria de, Teoria de, Novelty Detection, Màquines, Enginyeria electrònica [Àrees temàtiques de la UPC], 02 engineering and technology, Fault Detection, fault detection, Condition monitoring, TK1-9971, Machine Learning, Maquinària, machine learning, Àrees temàtiques de la UPC::Enginyeria mecànica::Processos de fabricació mecànica, Machine learning, Aprenentatge automàtic, Enginyeria mecànica::Processos de fabricació mecànica [Àrees temàtiques de la UPC], 0202 electrical engineering, electronic engineering, information engineering, Electrical engineering. Electronics. Nuclear engineering, Àrees temàtiques de la UPC::Enginyeria electrònica, Condition Monitoring, novelty detection |
| Description: | This paper presents a condition-based monitoring methodology based on novelty detection applied to industrial machinery. The proposed approach includes both, the classical classification of multiple a priori known scenarios, and the innovative detection capability of new operating modes not previously available. The development of condition-based monitoring methodologies considering the isolation capabilities of unexpected scenarios represents, nowadays, a trending topic able to answer the demanding requirements of the future industrial processes monitoring systems. First, the method is based on the temporal segmentation of the available physical magnitudes, and the estimation of a set of time-based statistical features. Then, a double feature reduction stage based on Principal Component Analysis and Linear Discriminant Analysis is applied in order to optimize the classification and novelty detection performances. The posterior combination of a Feed-forward Neural Network and One-Class Support Vector Machine allows the proper interpretation of known and unknown operating conditions. The effectiveness of this novel condition monitoring scheme has been verified by experimental results obtained from an automotive industry machine. |
| Document Type: | Article |
| File Description: | application/pdf |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2016.2619382 |
| Access URL: | http://hdl.handle.net/2117/101874 https://doaj.org/article/b3df522828884477a1514f6ca6613a16 https://upcommons.upc.edu/handle/2117/101874 https://dblp.uni-trier.de/db/journals/access/access4.html#CarinoPZMRR16 https://upcommons.upc.edu/bitstream/2117/101874/3/General%2bv%2bFinal%2b4.pdf https://ieeexplore.ieee.org/document/7600383/ http://ieeexplore.ieee.org/document/7600383/ https://hdl.handle.net/2117/101874 https://doi.org/10.1109/access.2016.2619382 |
| Rights: | IEEE Open Access CC BY NC ND |
| Accession Number: | edsair.doi.dedup.....68d89a93b16fb0cd7919a947ac49ee76 |
| Database: | OpenAIRE |
| ISSN: | 21693536 |
|---|---|
| DOI: | 10.1109/access.2016.2619382 |