1. Digital twin of a hydraulic loop: application to fault detection and parameter estimation
- Author
-
Jus, Yoann, Nassef, Amr, Lejeune, Hubert, Alzard, Cedric, Turpin, Raphaël, Lebret, Guy, Moussaoui, Saïd, Plestan, Franck, CEntre Technique des Industries Mécaniques (CETIM), CEntre Technique des Industries Mécaniques - Cetim (FRANCE), Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, and Nantes Université (Nantes Univ)
- Subjects
Machine Learning ,Détection de défauts ,Jumeau numérique ,Estimation de paramètres ,Jumeau numérique Machine Learning Détection de défauts Estimation de paramètres Boucle fluidique ,Boucle fluidique ,[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing ,[SPI.AUTO]Engineering Sciences [physics]/Automatic - Abstract
International audience; Hydraulic systems are used in several industrial applications, including manufacturing, automobiles and energy for example. Monitoring the condition of hydraulic equipment is essential to maintain high productivity and reduce the costs of system process. Best practices have been evolving from reactive maintenance to predictive maintenance, with intelligent fault diagnosis, using recent advances in industrial Internet of Things, artificial intelligence, edge computing, etc. Beyond design, the digital twins offer advantages in predictive maintenance and provides a new paradigm for fault diagnosis. The CETIM's "Fluid & Sealing Technologies" department proposes to present its R&D work to illustrate the concept of a digital twin of a fluidic loop. For this purpose, a closed hydraulic loop has been instrumented. It is equipped with a pump, a heat exchanger, a tank, a regulation valve and three piping sections. The objective of the study is to identify process faults (pipe clogging, exchanger performance degradation, etc.). These defects are manifested by a difference between the process variables (pressure, flow, and temperature) evaluated by the model and measured on the physical loop.
- Published
- 2022