Transformer bushing partial discharge mode identification method
A technology of transformer bushing and partial discharge, which is applied in the fields of instruments, measurement of electricity, measurement of electric variables, etc., can solve the problems of large demand for samples, long training period, false positives and false negatives, etc., and achieves high recognition accuracy and short learning time. Effect
Pending Publication Date: 2021-09-03
SHANDONG ELECTRICAL ENG & EQUIP GRP
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The BP neural network method is widely used in the field of partial discharge pattern recognition, but this method has disadvantages such as large sample demand, long training period, and easy to fall into local minimum.
Statistical recognition and fuzzy recognition have the problem of low recognition accuracy for small samples, and engineering applications often have false positives and false positives
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0032] This embodiment discloses a transformer bushing partial discharge pattern recognition method. This method designs the interference suppression and feature extraction method of the original partial discharge signal, and uses BGWO-SVM to establish the relationship between the seven characteristic parameters of partial discharge and the four discharge modes. Relationship, select the appropriate sampling function to select the sample with the optimal value of the SVM classifier for training, and achieve the purpose of matching the discharge type to confirm the equipment failure. like figure 1 As shown, the pattern recognition implementation steps are as follows:
[0033] S01), obtain the original partial discharge signal, perform signal interference suppression processing, use the translation invariant wavelet trace method to perform signal denoising processing, and obtain the scale coefficient through wavelet analysis on the original signal, and then perform threshold proc...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a transformer bushing partial discharge mode identification method. The method comprises the steps of optimizing a support vector machine based on an improved grey wolf algorithm, and then carrying out the discharge mode identification through an optimized support vector machine model BGWO-SVM. According to the method, the judgment accuracy of the four types of faults can be improved to 90% or above, in engineering application, the small sample recognition accuracy of the algorithm is higher than that of a traditional support vector machine method or a BP neural network method, the learning time is short, the identification accuracy is high, and the purpose of accurately identifying the small sample partial discharge mode is achieved.
Description
technical field [0001] The invention relates to the field of on-line monitoring of transformers, in particular to a method for identifying partial discharge patterns of transformer bushings. Background technique [0002] Partial discharge will have varying degrees of impact on the insulation of transformers, and in severe cases, it will lead to dielectric breakdown and equipment failure. The partial discharge of the transformer bushing mainly includes four common defects: suspension at the top of the bushing, poor contact of the lead wire at the end screen, suspension of the lower equalizing ring and discharge along the surface of the lower porcelain bushing. At present, the identification methods of partial discharge patterns generally include statistical pattern recognition, fuzzy pattern recognition and artificial neural network method. Various partial discharge detection methods mostly use partial discharge phase distribution (PRPD), pulse sequence phase distribution (PR...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G01R31/12G06F17/15G06F30/20
CPCG01R31/1227G06F17/15G06F30/20
Inventor 张文赋温胜姜良刚刘振雷李磊张栋平阳乐秦源
Owner SHANDONG ELECTRICAL ENG & EQUIP GRP