Summary
This paper presents an advanced analytics approach for condition monitoring in low-voltage distribution networks, aimed at detecting degrading and overloaded cables. Attenuation data is collected using a distributed vector network analyzer based on power line communication, enabling continuous, non-intrusive measurements along cable sections. Time-series evaluations are performed using waterfall plots to identify trends and gradual drifts indicative of cable degradation. An HDBSCAN clustering model is then trained to learn the normal operational distribution of each cable section and to detect anomalies. Finally, the paper outlines how these analytical techniques can be integrated in a monitoring system for improved asset management and preventive maintenance.
Additional informations
| Publication type | Session Materials |
|---|---|
| Reference | D2_12402_2026 |
| Publication year | |
| Publisher | CIGRE |
| Country | Germany |
| Study committees | |
| File size | 2 MB |
| Price for non member | 30 € |
| Price for member | 30 € |
Authors
SPIESS Sven - University of Duisburg- Essen, Germany; NUGROHO Andrew Bernhardt - University of Duisburg- Essen, Germany; NIESS Nora - University of Duisburg- Essen, Germany; FONTEYN Chris - University of Duisburg- Essen, Germany; KLAUKE QUEDER Thorsten - University of Duisburg- Essen, Germany; STAUBACH Axel - University of Duisburg- Essen, Germany; HIRSCH Holger - University of Duisburg- Essen, Germany
Keywords
Condition Monitoring, Power Line Communication, Smart Grid, Power Cable
