High-voltage cable aluminum sheath corrosion damage identification method, system and equipment based on semi-supervised learning, and medium
The invention discloses a high-voltage cable aluminum sheath corrosion damage identification method, system and device based on semi-supervised learning and a medium, and the method comprises the steps: collecting aluminum sheath guided wave monitoring signals without corrosion damage as a source do...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
03.02.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a high-voltage cable aluminum sheath corrosion damage identification method, system and device based on semi-supervised learning and a medium, and the method comprises the steps: collecting aluminum sheath guided wave monitoring signals without corrosion damage as a source domain data set, and collecting guided wave signals under different corrosion damage conditions as a target domain data set; preprocessing the source domain data set and the target domain data set through waveform alignment and band-pass filtering to obtain a training sample; feature extraction of training samples of source domain and target domain signals is realized through a multi-layer deep convolutional network; a deep feature distance is reduced by training a feature adaptation network, and inherent damage features under different corrosion conditions are obtained; and inputting the inherent characteristics into a structural state classifier, and identifying the corrosion damage in the aluminum sheath. The new |
---|---|
Bibliography: | Application Number: CN202211389861 |