Abstract


 
 
 We present a novel approach for measuring and representing acoustic emissions of transformers. The representation of location-based acoustic emissions enables improved monitoring of transformers, e.g., to detect and predict anomalies and failure events. Here, we introduce 3D acoustic heatmaps to visualize the sound emission patterns of a transformer. We use a combined sensing approach consisting of a 3D point cloud, a microphone array, and beamforming algorithms to generate the distributed representation of acoustic emissions over the entire surface of the transformer. In a further step, we intend to apply machine learning methods to the generated data to enable early fault prevention and predictive maintenance.
 
 

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call