A Method for Identifying Internal and External Faults of UHVDC Transmission Lines
A UHV DC, fault identification technology, applied in the fault location and other directions, can solve problems such as unreliable criteria, inability to achieve full-line protection, etc., to achieve good statistical learning effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0033] Embodiment 1: as Figure 1-2 As shown, a method for identifying faults inside and outside the UHV DC transmission line area, the specific steps of the method are:
[0034] Step1. After the UHV DC transmission system fails, the data acquisition device on the rectification side collects the fault voltage data in the time window 50ms after the arrival of the first wave of the fault voltage traveling wave;
[0035] Step2. Decompose the detected fault voltage signal by wavelet multi-scale to obtain the wavelet reconstruction high-frequency coefficients of each layer, calculate the singular spectral entropy of the wavelet reconstruction high-frequency coefficients of each layer, and combine all the wavelet reconstruction high-frequency coefficients of each layer Singular spectral entropy forms an m×n dimensional eigenvector matrix, and divides the data in the eigenvector matrix into training set and test set;
[0036] Step3. Set the training set label and the test set label ...
Embodiment 2
[0043] Embodiment 2: as Figure 1-2 As shown, a method for identifying faults inside and outside the UHV DC transmission line area, the specific steps of the method are:
[0044] Step1. After the UHV DC transmission system fails, the data acquisition device on the rectification side collects the fault voltage data in the time window 50ms after the arrival of the first wave of the fault voltage traveling wave;
[0045] Step2. Decompose the detected fault voltage signal by wavelet multi-scale to obtain the wavelet reconstruction high-frequency coefficients of each layer, calculate the singular spectral entropy of the wavelet reconstruction high-frequency coefficients of each layer, and combine all the wavelet reconstruction high-frequency coefficients of each layer Singular spectral entropy forms an m×n dimensional eigenvector matrix, and divides the data in the eigenvector matrix into training set and test set;
[0046] Step3. Set the training set label and the test set label ...
Embodiment 3
[0057] Embodiment 3: as Figure 1-2 As shown, a method for identifying faults inside and outside the UHV DC transmission line area, the specific steps of the method are:
[0058] Step1. After the UHV DC transmission system fails, the data acquisition device on the rectification side collects the fault voltage data in the time window 50ms after the arrival of the first wave of the fault voltage traveling wave;
[0059] Step2. Decompose the detected fault voltage signal by wavelet multi-scale to obtain the wavelet reconstruction high-frequency coefficients of each layer, calculate the singular spectral entropy of the wavelet reconstruction high-frequency coefficients of each layer, and combine all the wavelet reconstruction high-frequency coefficients of each layer Singular spectral entropy forms an m×n dimensional eigenvector matrix, and divides the data in the eigenvector matrix into training set and test set;
[0060] Step3. Set the training set label and the test set label ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com