All programmes
Industrial Internet methods for electrical energy conversion systems monitoring and diagnostics
Project promoter: Vilnius Gediminas Technical University
Project title: Industrial Internet methods for electrical energy conversion systems monitoring and diagnostics
Project code: LT08-1-ŠMSM-K01-005 (Project contract No S-BMT-21-5 (LT08-2-LMT-K-01-040))
Project eligible expenditure: EUR 993750 (EUR 844687,5 grant from the EEA Financial Mechanism and EUR 149062,5 budget co-financing)
Project signature date: 18 December 2020
Project implementation period: 1 January 2021 - 31 December 2023
Project partners:
University of Adger (NO)
Riga Technical University (LV)
Tallinn University of Technology (EE)
Project website
Project partners:
University of Adger (NO)
Riga Technical University (LV)
Tallinn University of Technology (EE)
Project website
Project summary:
We present solutions for predictive maintenance by combining equipment virtual Sensors (mathematical models) with powerful AI tools. Developed new models of the underlying devices that can run in real time and The project is intended to create and investigate methods and tools that will significantly reduce the maintenance of electrical and electronic devices, and will allow devices to be used efficiently, using innovative mathematical methods, thus reducing the number of serious device failures and reducing the number of negative events for users and possible environmental pollution.
The main goal of the proposal is to develop a specialized unsupervised diagnosis and prognosis internet platform for electrical energy systems.
Benefit of this work is a created solution which should monitor thermal, mechanical, and electrical stresses. The data from the equipment will be used in failure models to predict the remaining lifetime of the devices allowing for fault-tolerant and overload usage of the said devices, as well as condition-based maintenance. This is possible if the models are used in combination with AI or machine learning engines running in the clouds. The data for training the AI-engines will be generated from physical models of the devices, such as the finite element models of electrical machines, or in some cases from reduced models of these devices, to speed up the learning process. We expect the methodology to detect localized failure potentials in critical components, such as bearings, gearboxes, motors and generators. The possibility to apply the methodology to power electronic devices will be investigated.
The main goal of the proposal is to develop a specialized unsupervised diagnosis and prognosis internet platform for electrical energy systems.
Benefit of this work is a created solution which should monitor thermal, mechanical, and electrical stresses. The data from the equipment will be used in failure models to predict the remaining lifetime of the devices allowing for fault-tolerant and overload usage of the said devices, as well as condition-based maintenance. This is possible if the models are used in combination with AI or machine learning engines running in the clouds. The data for training the AI-engines will be generated from physical models of the devices, such as the finite element models of electrical machines, or in some cases from reduced models of these devices, to speed up the learning process. We expect the methodology to detect localized failure potentials in critical components, such as bearings, gearboxes, motors and generators. The possibility to apply the methodology to power electronic devices will be investigated.