A gis state recognition method based on vibration signal principal component analysis

A principal component analysis, vibration signal technology, applied in character and pattern recognition, testing of mechanical parts, testing of machine/structural parts, etc., can solve the problem that the mechanical state and feature quantity are not in a one-to-one correspondence, and increase the workload of the computer , reduce the calculation speed and accuracy, etc., to achieve the effect of high accuracy, improved accuracy and speed, and fast convergence speed

CN110082082BActive Publication Date: 2020-11-17NANCHONG POWER SUPPLY COMPANY STATE GRID SICHUANELECTRIC POWER
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2020-11-17

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a GIS state recognition method based on principal component analysis of vibration signals, extracting 14 feature quantities of GIS vibration signals under normal and different fault states to form a 14-dimensional composite feature vector; The vector is compressed and dimensionally reduced into the principal component feature vector; then the corresponding decision function between the vibration signal principal component feature vector and the GIS state is obtained through the two-stage training of the deep belief network, and the principal component feature vector of the GIS vibration signal to be recognized is used. Carry out classification, and determine the GIS status according to the classification. Using principal component analysis to optimize the composite eigenvector not only retains the original information of the composite eigenvector, but also reduces the dimension of the eigenvector, improves the efficiency of the classifier, and effectively improves the accuracy and speed of GIS state recognition.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of gas-insulated metal-enclosed switchgear (GIS) state recognition technology, in particular to a GIS state recognition method based on a vibration signal principal component analysis method. Background technique

[0002] Gas Insulated Switchgear (GIS) came out in the 1960s and developed rapidly because of its small footprint, high reliability, strong safety, short installation period, and small maintenance workload. , has been widely used in substations of all levels around the world. However, due to its complex and fully enclosed structure, once GIS fails, it will have a wide range of effects and it is difficult to accurately locate and quickly repair it.

[0003] Therefore, in order to ensure the safe and stable operation of the power grid, the reliability of GIS is particularly important, so it has become a top priority to effectively identify the fault state of GIS. At present, the methods for monitor...

Examples

Embodiment

[0044] Such as figure 1 Shown, a kind of GIS state recognition method based on vibration signal principal component analysis method, described method comprises:

[0045] Step 1: Install a vibration acceleration sensor on the GIS to collect multiple groups of vibration signals under normal and fault conditions of the GIS;

[0046] Step 2: Process the GIS vibration signal collected in step 1, extract the time domain, frequency domain and energy features of the GIS vibration signal respectively, and construct the composite feature vector of the GIS vibration signal;

[0047] Step 2.1: Extract the time-domain features of the GIS vibration signal, including the peak-to-peak value, average value, skewness and kurtosis of the GIS vibration signal;

[0048] (1) peak-to-peak value

[0049] The peak-to-peak value can represent the GIS vibration intensity, and the calculation formula is:

[0050] x pp =x max -x min (1)

[0051] Where: x max Indicates the maximum value of the GIS...