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

Grouping Method of Coherent Crew Based on Multi-index Panel Data Based on Feature Extraction

A feature extraction, multi-index technology, applied in the value field, can solve problems such as single index, insufficient feature extraction, and incomplete extraction of transient changes in time.

Active Publication Date: 2021-04-16
NORTH CHINA ELECTRIC POWER UNIV (BAODING) +4
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it should be noted that the method of identifying the coherent unit based on the difference of the swing angle of the generator rotor has problems such as single index and insufficient feature extraction in the process of coherent identification, and the transient quantity after the disturbance of the generator is not fully extracted. Changes in feature quantities over 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Grouping Method of Coherent Crew Based on Multi-index Panel Data Based on Feature Extraction
  • Grouping Method of Coherent Crew Based on Multi-index Panel Data Based on Feature Extraction
  • Grouping Method of Coherent Crew Based on Multi-index Panel Data Based on Feature Extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0093] In order to verify the effectiveness of the proposed WCAOPD-based coherent unit group, the EPRI-36 node standard system is used for simulation. The calculation example is simulated on the PSASP platform, and the algorithm is realized by MATLAB programming. The EPRI-36 node system contains 36 nodes and 8 generators. At time 0, a three-phase short-circuit fault occurs at bus-9 of the system for 1s, and the fault is removed after 1s. The integral step is 0.01s. The monitoring time is from the time when the fault occurs to the end of 10s. curve, voltage curve, and angular velocity. The processed power angle curve, voltage curve and rotor angular velocity curve are as follows: image 3 , 4 , 5 shown.

[0094] Sampling the obtained generator power angle curve, machine terminal voltage and rotor angular velocity, the total time is 5s, the sampling interval is 0.01s, the total number of samples is 3×500, and the data is processed to obtain the power angle curve difference, ...

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 belongs to the technical field of power system dynamic equivalence, and in particular relates to a method for grouping coherent units based on multi-indicator panel data of feature extraction, including: obtaining three indicators of the unit from failure to failure removal by simulation under fault conditions: The power angle swing curve, machine terminal voltage curve, and rotor angular velocity form panel data; the panel data are forwarded and normalized; multiple feature quantities of N units under 3 indicators are extracted in time series: absolute Value features, fluctuation features, skewness features, kurtosis features, and trend features; based on the extracted feature quantities, an analytic hierarchy process model was established, and the entropy weight method was used to calculate the weights of the three indicators and the weights of the feature values ​​extracted under each indicator, and calculate The distance matrix of multiple feature quantities between N units under three indicators is finally obtained to calculate the weighted distance matrix of N units, and the clustering of coherent units is realized by using the Ward.D clustering method.

Description

technical field [0001] The invention belongs to the technical field of electric power system dynamic equivalence, and in particular relates to a method for grouping coherent units based on multi-index panel data of feature extraction. Background technique [0002] With the continuous expansion of the scale of the power grid and the development of the power system, the power grid is gradually developing towards the operation direction of the AC and DC large power grid, which makes the electromagnetic transient analysis of the power system more and more difficult. Reducing the scale of a large system can improve the efficiency of analysis and calculation, and the dynamic equivalent method becomes an effective way to solve this problem. In addition, when the power system is severely disturbed and causes out-of-synchronization oscillation among the fleets, emergency decoupling is required to prevent further expansion of the accident and lead to the collapse of the entire network...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/20
CPCG06F30/20
Inventor 陈艳波张智吕盼刘建琴王智冬胥威汀叶希
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)