🚧 We're currently working on a new version of the loss estimation system that utilises fine-grained information of the thermal signature for a much higher accuracy.
Every thermal anomaly detected by SIDEREAL has an estimated loss associated to it. It's visible in the information overview of a specific anomaly, and in statistics mode.
Learn more about loss estimation in statistics mode
The loss estimation system was developed together with Imec* as part of the Analyst research project. A rule-based AI system was trained on monitoring system data from several sites to learn how the type of the anomaly and the temperature information influence the induced losses.
💡 Note that these losses are estimations based on the thermal signature of the anomaly. They're typically quite accurate relatively speaking, allowing you to prioritise anomalies with respect to each other. As the actual loss depends on a lot of factors (irradiance, air temperature, other panels in the string, etc.), they should not be used to predict accurate energy gains.
The table below shows some of the rules the system learned, sorted from highest loss to lowest loss.
Anomaly | Derivation |
String Open panel Missing panel | Complete loss of panel production. |
Hotspot | Loss is calculated based on delta temperature of the anomaly. |
Multiple hotspot | Loss is calculated based on delta temperature of the anomaly. |
Single bypassed substring | 1 of 3 substrings not producing. |
Double bypassed substring | 2 of 3 substrings not producing |
PID | Average rule due to high variability. |
Potential PID | Average rule due to high variability. |
Single diode | Average rule due to high variability. |
Multi diode | Average rule due to high variability. |
Thin film multi cross cell | Average rule due to high variability. |
Thin film single cross cell | Average rule due to high variability. |
Junction box | Average rule due to high variability. |
❗️Losses are only calculated on panel level and do not factor in the effect that the anomaly will have on the rest of the string.
* IMEC: Interuniversity Micro-Electronics Center is an independent research center in the field of microelectronics, nanotechnology, artificial intelligence, design methods and technologies for ICT systems.