Summary
The increasing penetration of distributed energy resources, such as photovoltaic systems, electric vehicles, and heat pumps, places a greater emphasis on the importance of rotating machines like synchronous condensers and turbogenerators for maintaining grid stability. As a result, it is essential to monitor these assets effectively and generate actionable insights from their operational data. Advanced data analytics and machine learning play a vital role in supporting online monitoring, diagnosis, and anomaly detection for these critical machines.
Read more Read lessIn this context, the paper investigates the relationship between step iron temperature rise in turbine generators and their operating points by collecting operational data from multiple sites worldwide. For each generator, temperature rise is determined and modeled using statistical techniques, with Random Sample Consensus (RANSAC) regressors. Finally, this methodology provides the best fit for this analysis compared to other techniques.
These trained models enable the detection of abnormal behavior, such as unexpectedly high step iron temperature rise at specific operating points. Ultimately, developing subsystem models and implementing a digital twin application underscores the necessity for automated operational data processing to support maintenance planning and operations, thereby enhancing reliability.
Additional informations
| Publication type | Session Materials |
|---|---|
| Reference | A1_12400_2026 |
| Publication year | |
| Publisher | CIGRE |
| Country | Germany |
| Study committees | |
| File size | 5 MB |
| Price for non member | 30 € |
| Price for member | 30 € |
Authors
MUSIELAK Sven - Siemens Energy Global GmbH & Co. KG; STEINS Hendrik - Siemens Energy Global GmbH & Co. KG; DAHRA Nipun - Siemens Energy Global GmbH & Co. KG; HOFFMANN Jan - Siemens Energy Global GmbH & Co. KG; ROHR Claus - Siemens Energy Global GmbH & Co. KG
