Transformer fault diagnosis method based on radial basis function neural network
A technology based on neural networks and transformer faults, applied in the field of transformer fault diagnosis based on radial basis neural networks, can solve problems such as easy diagnosis errors, inaccurate transformer faults, and inability to make fault judgments, so as to ensure safe and reliable operation, The effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] Such as figure 1 As shown, the transformer fault diagnosis method based on radial basis neural network of the present invention comprises the following steps:
[0031] A: Collect the training sample data as the input vector; the training sample data are H2, CH4, C2H4, C2H2, C2H6 and CO2 gas content, and the training sample data is first normalized and then input into the network. The normalization formula is x i =(x i -x min ) / (x max -x min ), where Xi represents the value of the characteristic gas, and X min Indicates the smallest numerical value among all gases, X max Indicates the numerical value with the largest value among all gases;
[0032] B: Coding the known training samples and corresponding fault types respectively, and compiling the corresponding table of training samples and fault types; the corresponding table of training samples and fault types is: if the code is 100000, the fault type is low temperature and overheating; if If the code is 010000, ...
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