Underground cable early fault detection and identification method based on DAE-CNN
A technology for underground cables and early faults, which is applied in the fault location, fault detection according to conductor type, and electrical measurement. High speed, wide use of space, high efficiency effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0077] This embodiment discloses a DAE-CNN-based underground cable early fault detection and identification method, such as figure 1 As shown, the steps are as follows:
[0078] S1. Simulate the early faults of underground cables to obtain current simulation data:
[0079] 1) According to the characteristics of several typical overcurrent disturbances of underground cables (cable half-cycle early faults, cable multi-cycle early faults, metallic short-circuit faults, transformer excitation inrush current, capacitor bank input, motor startup), in PSCAD / EMTDC and Laboratory Establish circuit models separately, and simulate current waveforms of different disturbance types to form a simulation data set;
[0080] 2) Normalize the simulation data:
[0081]
[0082] Among them, X i is the i-th data value in the simulation data set, X max is the maximum value of the data in the simulation data set, X min is the minimum value of the data in the simulation data set, X * is the n...
Embodiment 2
[0127] This embodiment discloses a DAE-CNN-based early fault detection and identification device for underground cables, which can realize the early fault detection and identification method for underground cables in Embodiment 1. The device includes a simulation module, a feature extraction module, a discriminator building module and a recognition module connected in sequence, and the feature extraction module is also connected to the recognition module;
[0128] Among them, the simulation module is used to simulate the early failure of the underground cable to obtain the simulation data of the current;
[0129] The feature extraction module is used to extract the features of the simulation data or the current data of the underground cable to be tested by using the noise reduction autoencoder to obtain the current data after dimension reduction;
[0130] The discriminator building block is used to train a convolutional neural network with dimensionality-reduced current data t...
Embodiment 3
[0134] This embodiment discloses a computer-readable storage medium, which stores a program. When the program is executed by a processor, the DAE-CNN-based underground cable early fault detection and identification method described in Embodiment 1 is implemented, specifically as follows:
[0135] Simulate the early faults of underground cables to obtain current simulation data;
[0136] Use the noise reduction autoencoder to extract the features of the simulation data, and obtain the current data after dimension reduction;
[0137] The convolutional neural network is trained using the dimensionally reduced current data to generate a discriminator that can be used to detect and identify early faults in underground cables;
[0138] A noise-reduction autoencoder is used to extract the features of the current data of the underground cable to be tested, and the dimension-reduced current data is obtained, which is used as the input of the discriminator, and the early fault identific...
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