Related analysis and Mahalanobis distance based transformer online monitoring information aggregation analysis method
A technology of Mahalanobis distance and monitoring information, which is applied in the field of aggregation and analysis of transformer online monitoring information, can solve the problems of low data accuracy, difficulty in ensuring data continuity, unrealized interconnection of equipment information, etc., and achieve the effect of reducing errors
Active Publication Date: 2016-01-27
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, due to the low data accuracy of substation online monitoring equipment, it is difficult to guarantee the continuity of data, which has led to serious information islands of "signs" of substation equipment, and has not realized the interconnection and intercommunication of information such as equipment operation and monitoring, resulting in the lack of equipment-based operation and multi-dimensional monitoring of each monitoring unit. Reliable comprehensive diagnosis of panoramic information in the horizontal dimension of information and the longitudinal dimension of time
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
[0030] Embodiment 1: In this example, the online monitoring data of the No. 1 main transformer of the 220kV substation is selected as an example for demonstration. The sampling interval for monitoring dissolved gas in oil of No. 1 main transformer is 24 hours, that is, one sampling point per day. This example shows historical data within 73 days. The data includes 12 types of online monitoring data, namely: A, B, C three-phase dielectric loss, carbon monoxide, methane, ethane, leakage current, micro water, acetylene, hydrogen, ethylene, and total hydrocarbons.
[0031] (1) Normalize and standardize the 12 types of online monitoring data with different sampling frequencies and units. Since hydrogen is a variety of transformer fault characterization gases, hydrogen is selected as the object of analysis related to the rest of the monitoring quantities. Calculate the root mean square of the hydrogen gas x(n) and the rest of the monitored quantity data y(n). After normalizing th...
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 provides a related analysis and Mahalanobis distance based transformer online monitoring information aggregation analysis method, and belongs to the technical field of state monitoring of high-voltage devices of power systems. According to the technical scheme provided by the invention, the method comprises: by utilizing multi-dimensional information obtained by transformer online monitoring, performing data normalization and standardized data preprocessing first, and then performing local related coefficient computing on preprocessed data by forming a set of time window lengths by first M points of current sampling points; and then, computing a Mahalanobis distance between each sample and a distribution center by utilizing an obtained original multi-dimensional information feature matrix, extracting a data exception sample with the distance greater than a distance setting value zset, finding a corresponding original exceptional data sample based on the exceptional sample, and finally performing data exception verification. The simulation shows that the use of the Mahalanobis distance from the center can not only qualitatively detect an exception but also quantitatively represent an exceptional degree, so that operators can perceive operation states conveniently.
Description
technical field [0001] The invention provides a method for aggregation and analysis of transformer online monitoring information based on correlation analysis and Mahalanobis distance, and belongs to the technical field of state monitoring of high-voltage equipment in power systems. Background technique [0002] Since the online monitoring system of substation equipment can reflect the operating status of equipment in real time, it is widely used in the intelligentization of primary equipment in smart substations. Under the premise of safety and reliability, reasonable arrangements for testing and maintenance, and improving the utilization rate and service life of power equipment have always been the pursuit of power systems. The online monitoring system came into being under such demand. At present, due to the low data accuracy of online monitoring equipment in substations, it is difficult to guarantee the continuity of data, which has led to serious information islands of...
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): G06F17/50
Inventor 束洪春吕蕾董俊孟祥飞卢杨
Owner KUNMING UNIV OF SCI & TECH