Industrial Data-Driven Monitoring Based on Incremental Learning Applied to the Detection of Novel Faults. Saucedo-Dorantes, J. J., Delgado-Prieto, M., Osornio-Rios, R. A., & Romero-Troncoso, R. d. J. IEEE Transactions on Industrial Informatics, 16(9):5985–5995, September, 2020. Conference Name: IEEE Transactions on Industrial Informaticsdoi abstract bibtex The detection of uncharacterized events during electromechanical systems operation represents one of the most critical data challenges dealing with condition-based monitoring under the Industry 4.0 framework. Thus, the detection of novelty conditions and the learning of new patterns are considered as mandatory competencies in modern industrial applications. In this regard, this article proposes a novel multifault detection and identification scheme, based on machine learning, information data-fusion, novelty-detection, and incremental learning. First, statistical time-domain features estimated from multiple physical magnitudes acquired from the electrical motor under inspection are fused under a feature-fusion level scheme. Second, a self-organizing map structure is proposed to construct a data-based model of the available conditions of operation. Third, the incremental learning of the condition-based monitoring scheme is performed adding self-organizing structures and optimizing their projections through a linear discriminant analysis. The performance of the proposed scheme is validated under a complete set of experimental scenarios from two different cases of study, and the results compared with a classical approach.
@article{saucedo-dorantes_industrial_2020,
title = {Industrial {Data}-{Driven} {Monitoring} {Based} on {Incremental} {Learning} {Applied} to the {Detection} of {Novel} {Faults}},
volume = {16},
issn = {1941-0050},
doi = {10.1109/TII.2020.2973731},
abstract = {The detection of uncharacterized events during electromechanical systems operation represents one of the most critical data challenges dealing with condition-based monitoring under the Industry 4.0 framework. Thus, the detection of novelty conditions and the learning of new patterns are considered as mandatory competencies in modern industrial applications. In this regard, this article proposes a novel multifault detection and identification scheme, based on machine learning, information data-fusion, novelty-detection, and incremental learning. First, statistical time-domain features estimated from multiple physical magnitudes acquired from the electrical motor under inspection are fused under a feature-fusion level scheme. Second, a self-organizing map structure is proposed to construct a data-based model of the available conditions of operation. Third, the incremental learning of the condition-based monitoring scheme is performed adding self-organizing structures and optimizing their projections through a linear discriminant analysis. The performance of the proposed scheme is validated under a complete set of experimental scenarios from two different cases of study, and the results compared with a classical approach.},
number = {9},
journal = {IEEE Transactions on Industrial Informatics},
author = {Saucedo-Dorantes, Juan Jose and Delgado-Prieto, Miguel and Osornio-Rios, Roque Alfredo and Romero-Troncoso, Rene de Jesus},
month = sep,
year = {2020},
note = {Conference Name: IEEE Transactions on Industrial Informatics},
keywords = {Condition monitoring, Data models, Electromechanical systems, Fault detection, Industries, Monitoring, Self-organizing feature maps, Training, fault detection, feature extraction, incremental learning, machine learning, novelty detection},
pages = {5985--5995},
}
Downloads: 0
{"_id":"WAaN5mDFLfx6uzHpe","bibbaseid":"saucedodorantes-delgadoprieto-osorniorios-romerotroncoso-industrialdatadrivenmonitoringbasedonincrementallearningappliedtothedetectionofnovelfaults-2020","author_short":["Saucedo-Dorantes, J. J.","Delgado-Prieto, M.","Osornio-Rios, R. A.","Romero-Troncoso, R. d. J."],"bibdata":{"bibtype":"article","type":"article","title":"Industrial Data-Driven Monitoring Based on Incremental Learning Applied to the Detection of Novel Faults","volume":"16","issn":"1941-0050","doi":"10.1109/TII.2020.2973731","abstract":"The detection of uncharacterized events during electromechanical systems operation represents one of the most critical data challenges dealing with condition-based monitoring under the Industry 4.0 framework. Thus, the detection of novelty conditions and the learning of new patterns are considered as mandatory competencies in modern industrial applications. In this regard, this article proposes a novel multifault detection and identification scheme, based on machine learning, information data-fusion, novelty-detection, and incremental learning. First, statistical time-domain features estimated from multiple physical magnitudes acquired from the electrical motor under inspection are fused under a feature-fusion level scheme. Second, a self-organizing map structure is proposed to construct a data-based model of the available conditions of operation. Third, the incremental learning of the condition-based monitoring scheme is performed adding self-organizing structures and optimizing their projections through a linear discriminant analysis. The performance of the proposed scheme is validated under a complete set of experimental scenarios from two different cases of study, and the results compared with a classical approach.","number":"9","journal":"IEEE Transactions on Industrial Informatics","author":[{"propositions":[],"lastnames":["Saucedo-Dorantes"],"firstnames":["Juan","Jose"],"suffixes":[]},{"propositions":[],"lastnames":["Delgado-Prieto"],"firstnames":["Miguel"],"suffixes":[]},{"propositions":[],"lastnames":["Osornio-Rios"],"firstnames":["Roque","Alfredo"],"suffixes":[]},{"propositions":[],"lastnames":["Romero-Troncoso"],"firstnames":["Rene","de","Jesus"],"suffixes":[]}],"month":"September","year":"2020","note":"Conference Name: IEEE Transactions on Industrial Informatics","keywords":"Condition monitoring, Data models, Electromechanical systems, Fault detection, Industries, Monitoring, Self-organizing feature maps, Training, fault detection, feature extraction, incremental learning, machine learning, novelty detection","pages":"5985–5995","bibtex":"@article{saucedo-dorantes_industrial_2020,\n\ttitle = {Industrial {Data}-{Driven} {Monitoring} {Based} on {Incremental} {Learning} {Applied} to the {Detection} of {Novel} {Faults}},\n\tvolume = {16},\n\tissn = {1941-0050},\n\tdoi = {10.1109/TII.2020.2973731},\n\tabstract = {The detection of uncharacterized events during electromechanical systems operation represents one of the most critical data challenges dealing with condition-based monitoring under the Industry 4.0 framework. Thus, the detection of novelty conditions and the learning of new patterns are considered as mandatory competencies in modern industrial applications. In this regard, this article proposes a novel multifault detection and identification scheme, based on machine learning, information data-fusion, novelty-detection, and incremental learning. First, statistical time-domain features estimated from multiple physical magnitudes acquired from the electrical motor under inspection are fused under a feature-fusion level scheme. Second, a self-organizing map structure is proposed to construct a data-based model of the available conditions of operation. Third, the incremental learning of the condition-based monitoring scheme is performed adding self-organizing structures and optimizing their projections through a linear discriminant analysis. The performance of the proposed scheme is validated under a complete set of experimental scenarios from two different cases of study, and the results compared with a classical approach.},\n\tnumber = {9},\n\tjournal = {IEEE Transactions on Industrial Informatics},\n\tauthor = {Saucedo-Dorantes, Juan Jose and Delgado-Prieto, Miguel and Osornio-Rios, Roque Alfredo and Romero-Troncoso, Rene de Jesus},\n\tmonth = sep,\n\tyear = {2020},\n\tnote = {Conference Name: IEEE Transactions on Industrial Informatics},\n\tkeywords = {Condition monitoring, Data models, Electromechanical systems, Fault detection, Industries, Monitoring, Self-organizing feature maps, Training, fault detection, feature extraction, incremental learning, machine learning, novelty detection},\n\tpages = {5985--5995},\n}\n\n\n\n","author_short":["Saucedo-Dorantes, J. J.","Delgado-Prieto, M.","Osornio-Rios, R. A.","Romero-Troncoso, R. d. J."],"key":"saucedo-dorantes_industrial_2020","id":"saucedo-dorantes_industrial_2020","bibbaseid":"saucedodorantes-delgadoprieto-osorniorios-romerotroncoso-industrialdatadrivenmonitoringbasedonincrementallearningappliedtothedetectionofnovelfaults-2020","role":"author","urls":{},"keyword":["Condition monitoring","Data models","Electromechanical systems","Fault detection","Industries","Monitoring","Self-organizing feature maps","Training","fault detection","feature extraction","incremental learning","machine learning","novelty detection"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["yanwtMpCcFaHzRwWb","iwKepCrWBps7ojhDx"],"keywords":["condition monitoring","data models","electromechanical systems","fault detection","industries","monitoring","self-organizing feature maps","training","fault detection","feature extraction","incremental learning","machine learning","novelty detection"],"search_terms":["industrial","data","driven","monitoring","based","incremental","learning","applied","detection","novel","faults","saucedo-dorantes","delgado-prieto","osornio-rios","romero-troncoso"],"title":"Industrial Data-Driven Monitoring Based on Incremental Learning Applied to the Detection of Novel Faults","year":2020}