Decision tree algorithm-based 220kV main transformer state assessment prediction method
A technology of main transformer and decision-making algorithm, applied in the field of main transformer state evaluation and prediction and monitoring real-time data fusion, it can solve problems such as spending a lot of manpower, operation and maintenance personnel can not grasp, and can not achieve real-time monitoring, so as to improve safety and reliability. sexual effect
Inactive Publication Date: 2017-09-22
云南电网有限责任公司信息中心 +1
View PDF5 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] At present, in the online monitoring data collected by the 220KV main transformer equipment, there is a large amount of real-time information on equipment operation that has not been well utilized. For the real-time data of these equipment, the operation and maintenance personnel (or monitoring personnel) cannot grasp or grasp it accurately. The mastery of the operating status of these devices mainly depends on the manual experience of operation and maintenance personnel (or monitoring personnel). For the status of unattended equipment, real-time monitoring cannot be achieved, and a lot of manpower is required to go to the site for verification.
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
[0037] 1) Use the online monitoring device to obtain the hydrogen content (H2), oil temperature, and status (1 or 0) information of the 220kV main transformer at fixed intervals (such as 15 minutes), as the basic data for training samples.
[0038] 2) The average value filling method is used to deal with the abnormality of the training sample data. Obtain reliable data that can be input into the decision tree algorithm for calculation, including high (H) and low (L) data values of oil temperature, hydrogen content (H2) data values, and equipment status (normal 1, abnormal 0) values.
[0039] 3) Input the sample data into the decision tree for recursive calculation, and execute the left and right nodes separately until each node meets the requirements. The intuitive way is to stop when each child node has only one type of record.
[0040] 4) Take the unique type of node as the output to get the state of the 220kV main transformer, normal (1) or abnormal (0).
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 decision tree algorithm-based 220kV main transformer state assessment and prediction method. According to the method, online data monitoring, decision algorithm training and main transformer state assessment judgment are carried out; and various online monitoring data of 220KV main transformers are intensively fused and collected through data fusion by utilizing a decision algorithm technology, so as to form valuable data, so that powerful predicted data and measure support for 220KV main transformer state assessment, the safety and reliability of equipment are enhanced, and an improvement upon main transformer state assessment prediction is brought.
Description
technical field [0001] The invention relates to a technical method for evaluating and predicting the state of main transformers in a power grid and monitoring real-time data fusion, and is a method for evaluating and predicting the state of a 220kV main transformer in a power grid. Background technique [0002] At present, in the online monitoring data collected by the 220KV main transformer equipment, there is a large amount of real-time information on equipment operation that has not been well utilized. For the real-time data of these equipment, the operation and maintenance personnel (or monitoring personnel) cannot grasp or grasp it accurately. The mastery of the operating status of these devices mainly depends on the manual experience of the operation and maintenance personnel (or monitoring personnel). For the status of unattended equipment, real-time monitoring cannot be achieved, and a lot of human resources must be spent on site to check. Therefore, research and est...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06K9/62G06Q10/04G06Q50/06
CPCG06F16/22G06F16/285G06Q10/04G06Q50/06G06F18/214G06F18/24323
Inventor 张莉娜赵志宇马文徐敏杨东宁肖颖婷李华锋
Owner 云南电网有限责任公司信息中心