Towards a Hybrid Twin for Infrastructure Asset Management: Investigation on Power Transformer Asset Maintenance Management

In a resources scarcity context, grid asset management consists in operating power systems with a certain risk level while optimizing the assets service life. Transmission System Operators and owners inform their decision based on nominal physics-based models or monitor valuable assets and derive fully data-based digital twin. In this work, the hybrid twin capabilities are evaluated to support decision based on individual Power Transformers thermal behavior. It is shown that the generic IEC 60076-7 can be completed by machine learning features to obtain individual conditions at reasonable cost, to seek future application on maintenance optimization or dynamic transformer rating.