Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

AI-based Online Warning and Lifetime Prediction System for Transformers, Motors, and Generators

Reference number
Coordinator WindingsAI AB
Funding from Vinnova SEK 880 000
Project duration September 2023 - May 2024
Status Completed
Venture Emerging technology solutions
Call Emerging technology solutions stage 1 2023

Important results from the project

** Denna text är maskinöversatt ** In the work, we have successfully produced a PoC that can predict PD and thus future health for electrical systems and components. In the work, we successfully developed the associated hardware component, software and investigated the best application with the associated customer benefit. We consider ourselves to have received encouraging results that seem promising for continued development of the innovation. With the project completed, we are now ready for further development and testing on a larger scale.

Expected long term effects

** Denna text är maskinöversatt ** After completing project we have now created greater awareness of our product and its potential. In our work, we have demonstrated and highlighted the value our technology can create for individual actors but also for society at large.

Approach and implementation

** Denna text är maskinöversatt ** The work has been led by WindingsAI where we have carried out the following activities Data collection and hardware assembly, ML-based PD signal filtering, ML-based feature extraction from PD, ML-based system for early warning and prediction of equipment life and efficiency, Testing and improvement and early commercialization and business development. We realized in our work how important it is to carefully carry out the fundamental steps of measurement, filtering and feature extraction in order to achieve good results for the prediction.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 28 June 2024

Reference number 2023-01365