Zobrazeno 1 - 10
of 81
pro vyhledávání: '"N. Amyot"'
Publikováno v:
ICPHM
More and more scientific disciplines are using deep learning techniques for the automatic classification of massive high dimensionality unlabeled data. Among these disciplines, the classification of partial discharge (PD) patterns is one that represe
Publikováno v:
2021 IEEE Electrical Insulation Conference (EIC).
Publikováno v:
2020 Prognostics and Health Management Conference (PHM-Besançon)
2020 Prognostics and Health Management Conference (PHM-Besançon), May 2020, Besancon, France. pp.235-240, ⟨10.1109/PHM-Besancon49106.2020.00046⟩
2020 Prognostics and Health Management Conference (PHM-Besançon), May 2020, Besancon, France. pp.235-240, ⟨10.1109/PHM-Besancon49106.2020.00046⟩
International audience; Deep learning (DL) has been recently used in several applications of machine health monitoring systems. Unfortunately , most of these DL models are considered as black-boxes with low interpretability. In this research, we prop
Autor:
Olivier Blancke, Mélanie Lévesque, N. Amyot, Antoine Tahan, Claude Hudon, Jean-François Boudreau, Dragan Komljenovic
Publikováno v:
Engineering Assets and Public Infrastructures in the Age of Digitalization ISBN: 9783030480202
Asset management is an enabling discipline that is defined by the International Standard ISO 55000 as the coordinated activities of an organization to realize value from assets. Prognostic and health management (PHM), component and system reliability
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef9ee71663b648bfe235d6fd220c8a1b
https://doi.org/10.1007/978-3-030-48021-9_29
https://doi.org/10.1007/978-3-030-48021-9_29
Publikováno v:
Reliability Engineering & System Safety. 180:136-151
The aim of this paper is to propose a holistic multi-failure mode prognosis approach that takes into account the complexity of failure mechanisms as a system. Model assumptions are first proposed by experts and then formalized using graph theory and
Predictive Maintenance Approach for Complex Equipment Based on a Failure Mechanism Propagation Model
Autor:
Mélanie Lévesque, Claude Hudon, Antoine Tahan, Noureddine Zerhouni, Olivier Blancke, Dragan Komljenovic, Amélie Combette, N. Amyot
Publikováno v:
International Journal of Prognostics and Health Management. 10
The aim of this paper is to propose a comprehensive approach for the predictive maintenance of complex equipment. The approach relies on a physics of failure ( PoF ) model based on expert knowledge and data. The model can be represented as a multi-st
Publikováno v:
2018 IEEE Electrical Insulation Conference (EIC).
Hydro-Quebec has started carrying out Polarization and Depolarization Current measurements (PDC) more than 20 years ago. A Direct Current Ramp Test (DCRT) apparatus has also been built in house in the early 2000's and since 2012 systematic measuremen
Publikováno v:
2016 XXII International Conference on Electrical Machines (ICEM).
Hydroelectric generator shaft current faults, which are mainly due to human error and electromagnetic anomalies in the generator, can cause mechanical bearing failures in several different modes. Because of the silo structure of maintenance departmen
Publikováno v:
2015 IEEE Electrical Insulation Conference (EIC).
To get the best generator diagnosis possible, multiple tests must be done but this is time consuming and not always possible. For a company such as Hydro-Quebec (HQ), operating more than 350 generators, a diagnostic strategy had to be defined to be a
Publikováno v:
IEEE Transactions on Dielectrics and Electrical Insulation. 9:458-466
Residual mechanical stresses from manufacturing always exist in freshly extruded HV cables. These stresses are not uniformly distributed in the cable insulation bulk material. Five different HV cables were analyzed with respect to residual mechanical