Multi-element image processing and pattern recognition method for defects of power equipment
A multi-image and power equipment technology, applied in character and pattern recognition, neural learning methods, biological neural network models, etc., to improve the accuracy of pattern recognition, eliminate hidden dangers, and improve recognition performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0069] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0070] A method for multiple image processing and pattern recognition of electrical equipment defects, comprising the following steps:
[0071] Step 1. Collect the PRPD spectrum of the partial discharge signal. The power frequency phase of the partial discharge signal is measured by the UHF sensor and the optical sensor respectively , the amount of discharge q and the number of discharges n, with The three physical quantities , q and n are the coordinate axes to establish a three-dimensional partial discharge PRPD map.
[0072] Step 2. According to the PRPD spectrum collected in step 1, construct Optical partial discharge maps and UHF partial discharge maps.
[0073] In order to effectively extract the relevant feature information of partial discharge during pattern recognition, according to the PRPD spectrum collected in step 1, such as figure 1 and ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


