Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis
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 previousl...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2016-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/7600383/ |
| _version_ | 1819120527056306176 |
|---|---|
| author | Jesus A. Carino Miguel Delgado-Prieto Daniel Zurita Marta Millan Juan Antonio Ortega Redondo Rene Romero-Troncoso |
| author_facet | Jesus A. Carino Miguel Delgado-Prieto Daniel Zurita Marta Millan Juan Antonio Ortega Redondo Rene Romero-Troncoso |
| author_sort | Jesus A. Carino |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-12-22T06:22:05Z |
| format | Article |
| id | doaj.art-b3df522828884477a1514f6ca6613a16 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T06:22:05Z |
| publishDate | 2016-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b3df522828884477a1514f6ca6613a162022-12-21T18:35:56ZengIEEEIEEE Access2169-35362016-01-0147594760410.1109/ACCESS.2016.26193827600383Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal AnalysisJesus A. Carino0https://orcid.org/0000-0003-4069-3561Miguel Delgado-Prieto1Daniel Zurita2https://orcid.org/0000-0001-6388-7559Marta Millan3Juan Antonio Ortega Redondo4https://orcid.org/0000-0002-1403-8152Rene Romero-Troncoso5https://orcid.org/0000-0003-3192-5332Electronic Department, Technical University of Catalonia, Terrassa, Barcelona, SpainElectronic Department, Technical University of Catalonia, Terrassa, Barcelona, SpainElectronic Department, Technical University of Catalonia, Terrassa, Barcelona, SpainMAPRO Sistemas de ensayo S.A. Company, Barcelona, SpainElectronic Department, Technical University of Catalonia, Terrassa, Barcelona, SpainHSP Digital Research Group, University of Guanajuato, Guanajuato, MexicoThis 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.https://ieeexplore.ieee.org/document/7600383/Condition monitoringfault detectionmachine learningnovelty detection |
| spellingShingle | Jesus A. Carino Miguel Delgado-Prieto Daniel Zurita Marta Millan Juan Antonio Ortega Redondo Rene Romero-Troncoso Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis IEEE Access Condition monitoring fault detection machine learning novelty detection |
| title | Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis |
| title_full | Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis |
| title_fullStr | Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis |
| title_full_unstemmed | Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis |
| title_short | Enhanced Industrial Machinery Condition Monitoring Methodology Based on Novelty Detection and Multi-Modal Analysis |
| title_sort | enhanced industrial machinery condition monitoring methodology based on novelty detection and multi modal analysis |
| topic | Condition monitoring fault detection machine learning novelty detection |
| url | https://ieeexplore.ieee.org/document/7600383/ |
| work_keys_str_mv | AT jesusacarino enhancedindustrialmachineryconditionmonitoringmethodologybasedonnoveltydetectionandmultimodalanalysis AT migueldelgadoprieto enhancedindustrialmachineryconditionmonitoringmethodologybasedonnoveltydetectionandmultimodalanalysis AT danielzurita enhancedindustrialmachineryconditionmonitoringmethodologybasedonnoveltydetectionandmultimodalanalysis AT martamillan enhancedindustrialmachineryconditionmonitoringmethodologybasedonnoveltydetectionandmultimodalanalysis AT juanantonioortegaredondo enhancedindustrialmachineryconditionmonitoringmethodologybasedonnoveltydetectionandmultimodalanalysis AT reneromerotroncoso enhancedindustrialmachineryconditionmonitoringmethodologybasedonnoveltydetectionandmultimodalanalysis |