Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for detecting abnormity of dissolved gas in transformer oil

A technology of transformer oil and dissolved gas, applied in instruments, material inspection products, character and pattern recognition, etc., can solve the problems of long recognition time, long detection time, affecting abnormal detection results, etc., to avoid dimensional disaster and fast calculation speed , easy to capture effect

Active Publication Date: 2021-11-30
国家电网有限公司大数据中心
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the fixed threshold relies on expert experience, and does not consider the gas history trend analysis and potential faults that do not exceed the threshold, which directly affects the abnormal detection results
The artificial intelligence method also has shortcomings. Firstly, it is affected by the sample set and time characteristics. When the sample is improperly selected or there is continuous missing or fluctuating data, the recognition effect is not good; secondly, the gas rate change characteristics are not considered, only the gas content is analyzed, and the characteristics are single; finally The detection time is longer, when the detection sample size is large, the recognition time is longer

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for detecting abnormity of dissolved gas in transformer oil
  • Method and system for detecting abnormity of dissolved gas in transformer oil
  • Method and system for detecting abnormity of dissolved gas in transformer oil

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] A schematic flow chart of a method for abnormal detection of dissolved gas in transformer oil provided by the present invention is as follows figure 1 shown, including:

[0060] Step 1: Obtain the gas content in the monitoring data set of each gas dissolved in the transformer oil, and perform rate feature extraction according to the content of each gas to obtain the gas production rate of each gas;

[0061] Step 2: Use the isolated forest algorithm to conduct an abnormal preliminary inspection on the gas production rate and gas content of each gas, and obtain the abnormal score of each gas;

[0062] Step 3: Cluster the abnormal scores of each gas, and perform the final abnormal inspection of the gas according to the clustering results, the abnormal scores of each gas, the gas production rate of each gas and the content of each gas, and obtain the Abnormal final inspection results for each gas.

[0063] Among them, before step 1, it is also necessary to obtain the onli...

Embodiment 2

[0125] The technical solution will be clearly and completely described below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

[0126] The abnormal identification of dissolved gas in oil in the present invention is elaborated around three parts: data preprocessing, preliminary identification of dissolved gas anomaly in oil, and final screening of anomalies.

[0127] Data cleaning is a more important part of the present invention, and the degree of cleaning affects the accuracy of the detection model. The present invention eliminates the abnormality that may occur in the monitoring device and the transmission process, detects the abno...

Embodiment 3

[0210] Based on the same inventive concept, the present invention also provides a system for abnormal detection of dissolved gas in transformer oil, such as Figure 7 shown.

[0211] The system includes: rate feature extraction module, abnormal initial inspection module, abnormal final inspection module;

[0212] Wherein, the rate feature extraction module is used to obtain the gas content in the monitoring data set of each gas dissolved in the transformer oil, and perform rate feature extraction according to the content of each gas to obtain the gas production rate of each gas;

[0213] The abnormal initial inspection module is used to perform an abnormal initial inspection on the gas production rate and each gas content of each gas through the isolated forest algorithm, and obtain the abnormal score of each gas;

[0214] The abnormal final inspection module is used to cluster the abnormal scores of each gas, and carry out the abnormal final inspection of the gas according t...

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

No PUM Login to View More

Abstract

The invention provides a method and a system for detecting abnormity of dissolved gas in transformer oil, and the method comprises the steps: obtaining the gas content in a monitoring data set of each gas dissolved in the transformer oil, carrying out the rate feature extraction according to each gas content, and obtaining the gas production rate of each gas; performing abnormal initial detection on the gas production rate and the content of each gas through an isolated forest algorithm to obtain an abnormal score of each gas; and clustering the abnormal score of each gas, and carrying out gas abnormal final detection according to a clustering result, the abnormal score of each gas, the gas production rate of each gas and the content of each gas to obtain an abnormal final detection result of each gas dissolved in the transformer oil. According to the method, the dimension disaster of data features can be effectively avoided, and the calculation speed is high; meanwhile, gas content and gas rate change conditions are considered, and an anomaly score threshold value is set so that potential anomalies are more easily captured; by endowing different window time, whether the dissolved gas in the transformer oil is abnormal or not is effectively judged.

Description

technical field [0001] The invention belongs to the field of abnormal detection of oil-immersed transformers, and in particular relates to a method and system for detecting abnormalities of dissolved gas in transformer oil. Background technique [0002] Large-scale power transformers are important substation equipment in power systems, and their operating status is crucial to the safety and stability of the power grid. Online monitoring and real-time diagnosis of transformer status are of great significance. For a long time, the power equipment maintenance strategy mainly adopts regular maintenance based on time. Although regular maintenance can generally find defects in equipment during maintenance, it plays an important role in ensuring the safety and economical operation of equipment. However, there are also situations where regular maintenance is not timely, resulting in a decline in equipment reliability. Dissolved gas analysis technology in transformer oil is an impo...

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
no application Login to View More
IPC IPC(8): G01N33/28G06F17/18G06K9/62
CPCG01N33/28G06F17/18G06F18/23213G06F18/24323G06F18/214
Inventor 王宏刚纪鑫褚娟葛鑫亮武同心赵晓龙董林啸李建芳何禹德
Owner 国家电网有限公司大数据中心