Owing to their harsh operating conditions, oil-ﬁlled transformers tend to degrade over time and leak oil, which results in failure, reduced life, or fire hazard. The main indicators of transformer health are oil level and top oil temperature. Further, being highly optimized for cost, these transformers have very minimal instrumentation.
Simit Pradhan and the Corporate Technology team at Siemens developed a health monitoring system that remotely senses the oil level using temperature sensors ﬁtted on the transformer housing. A physics-based model of the transformer enables the team to relate the temperature measurements to the amount of oil present in real time. This non-invasive solution can be retroﬁtted on any ONAN transformer and enable real-time condition monitoring of the asset.
The next step in implementation was ﬁeld deployment. The team used MATLAB Production Server™ to deploy their algorithms to the cloud. Prototype IoT devices deployed on individual transformers stream data to the cloud, where the algorithm generates signals for predictive maintenance of the respective assets.
- Oil-level monitoring with non-invasive temperature sensors
- Retrofittable solution, enabling commissioning on brownfield transformers as well
- User-friendly commissioning and online learning for the algorithm