For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
It is of vital importance to extract and analyze the characteristic information in PD signal for faults recognition and operational maintenance of power transformer. According to the feature of PD ultrahigh frequency signal, this paper proposes a blind source separation (BSS) method based on similar matrix for data pre-processing of original PD signals, to effectively extract the UHF PD feature. Then, four typical PD pattern UHF signals are captured with UHF PD sensor. After signal acquisition, pretreatment is performed as mentioned above. Finally, the processed data is used as training samples of convolutional neural network (CNN) recognition, and the recognition accuracy is up to 90%, thus improving the accuracy of PD pattern recognition.
Inspec keywords: pattern recognition; partial discharges; blind source separation; feature extraction; deep learning (artificial intelligence); convolutional neural nets
Subjects: Signal processing and detection; Digital signal processing; Dielectric breakdown and discharges; Neural nets