Electromagnetic Interference (EMI) diagnostics aid in identifying insulation and mechanical faults arising in High Voltage (HV) electrical power assets. EMI frequency scans are analysed to detect the frequencies associated with these faults. Timeresolved signals at these key frequencies provide important information for fault type identification and trending. An end-to-end fault classification approach based on real-world EMI time-resolved signals was developed which consists of two classification stages each based on 1D-Convolutional Neural Networks (1D-CNN) trained using transfer learning techniques. The first stage filters the in-distribution signals relevant to faults from out-of-distribution signals that may be collected during the EMI measurement. The fault signals are then passed to the second stage for fault type classification. The proposed analysis exploits the raw measured timeresolved signals directly into the 1D-CNN which eliminates the need for engineered feature extraction and reduces computation time. These results are compared to previously proposed CNN-based classification of EMI data. The results demonstrate high classification performance for a computationally efficient inference model. Furthermore, the inference model is implemented in an industrial instrument for HV condition monitoring and its performance is successfully demonstrated in tested in both a HV laboratory and an operational power generating site.

No abstract

The deployment of radio frequency interference (RFI) measurement has gained increasing acceptance as a front line, non-invasive technique to assess the condition of individual high-voltage (HV) electrical equipment items as part of a substation surveillance program. However, successful detection and discrimination of low-repetition rate discharges that typically accompany electrical deterioration is constrained by the capabilities and limitations of the field spectrum/RFI analysers used and the electro-magnetic interference (EMI) measurement techniques supported. This paper presents a novel approach to RFI measurement and assessment that is more sensitive to the RFI emissions that typically accompany electrical deterioration and provides more effective discrimination of the discharge phenomena from the ambient frequency spectrum and noise. Case studies from substation surveillance are presented to demonstrate the effectiveness of the approach. The technique is effective with a wide range of HV equipment and is less reliant on expert knowledge for a practicing engineer to confidently characterise and trace electrical deterioration with a high degree of confidence.

No abstract

No abstract