A method for intelligent identification of power cable fault discharge sound
A cable fault and power cable technology, which is applied in the direction of measuring electricity, measuring electrical variables, and testing dielectric strength, etc., can solve the problems of manual identification of fault discharge sound experience and skills out of the field environment, environmental noise interference, difficulty in teaching and inheritance, etc. , to reduce training costs and labor costs, reduce environmental noise and interference, and improve work efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Examples
example 1
[0097] The above steps will be described in detail below through an example of a cable fault discharge sound and an example of a non-cable fault discharge sound. Example 1: When the sound information is the sound of cable fault discharge:
[0098] Step 1, collect the sound signal at one end with a duration T of 100ms, and use an A / D converter with a unipolar resolution N of 12 bits to obtain a group of original data x of cable fault discharge sound with a sampling point n of 800 0 (i), whose waveform is as figure 2 shown.
[0099] Step 2, the original data of cable fault discharge sound x 0 (i) Carry out DC processing to obtain data x after DC processing 1 (i), if image 3 shown. Then for data x 1 (i) Perform normalization processing to obtain data x 2 (i), if Figure 4 shown.
[0100] Using normalized data x 2 (i), calculate the short-term energy distribution x of the sound signal data with a step size D of 50 3 (i) (if Figure 5 shown), calculate the short-term ...
example 2
[0105] Example 2: When the sound information is non-cable fault discharge sound:
[0106] Step 1, collect the sound signal at one end with a duration T of 100ms, and use an A / D converter with a unipolar resolution N of 12 bits to obtain a set of original data x' of cable fault discharge sound with a sampling point n of 800 0 (i), whose waveform is as Figure 8 shown.
[0107] Step 2, the original data x' of cable fault discharge sound 0 (i) Carry out DC processing to obtain the data x' after DC processing 1 (i), if Figure 9 shown. Then for data x' 1 (i) Perform normalization processing to obtain data x' 2 (i), if Figure 10 shown.
[0108] Using normalized data x' 2 (i), calculate the short-term energy distribution x' of the sound signal data with a step size D of 50 3 (i) (if Figure 11 shown), calculate the short-term zero-crossing rate x' with a threshold th of 0.5 4 (i), (if Figure 12 shown).
[0109] Using the short-term energy distribution data x' 3 (i),...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More