Automatic Feature learning and Pattern recognition of Partial discharge applying deep-learning technologies

• Unité de recherche: INNOSUISSE
• Numéro de projet: 27662.1 PFES-ES
• Titre du projet anglais: Automatic Feature learning and Pattern recognition of Partial discharge applying deep-learning technologies

Description succincte (Allemand)

Automatic Feature learning and Pattern recognition of Partial discharge applying deep-learning technologies

Description succincte (Anglais)

Automatic Feature learning and Pattern recognition of Partial discharge applying deep-learning technologies

Résumé des résultats (Abstract) (Allemand)

Partial discharge (PD) is the most reliable monitoring for generator stator insulation health status, and has been applied in industry since the 1990's. This project aims to merge experience and knowledge from GE with state of the art methods in machine learning to improve the data analysis of PD.