Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Power grid monitoring alarm event identification method based on convolution and long-term and short-term memory network

A technology of long-term and short-term memory and alarm events, which is applied in neural learning methods, biological neural network models, and electrical digital data processing. The effect of low efficiency, improving work efficiency, and reducing the pressure on the monitor screen

Active Publication Date: 2020-06-12
HOHAI UNIV
View PDF6 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: Aiming at the problem that the manual judgment in the existing power grid monitoring and alarming is easy to miss and misjudgment, and the recognition efficiency is not high, the present invention provides a power grid monitoring and alarming event recognition method based on convolution and long-term short-term memory network

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
  • Power grid monitoring alarm event identification method based on convolution and long-term and short-term memory network
  • Power grid monitoring alarm event identification method based on convolution and long-term and short-term memory network
  • Power grid monitoring alarm event identification method based on convolution and long-term and short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] refer to figure 1 , figure 2 and image 3 , the method of the present invention is carried out according to the following steps:

[0064] The first step is to collect historical monitoring alarm information and the time stamp of each alarm information in the power grid monitoring system, and all substations and line names contained in the alarm information to form the training data set required for the grid monitoring alarm event recognition model;

[0065] The second step is to perform data preprocessing on the historical monitoring alarm information, conduct unsupervised training on the monitoring alarm information through the word2vec model, and generate an information vector containing signal features. The specific process is as follows:

[0066] (1) Word segmentation and removal of stop words

[0067] Update the power thesaurus, and collect the power thesaurus through data review, and import the substation name and line name derived from the historical monitori...

Embodiment 2

[0109] Taking more than 14 million pieces of historical monitoring alarm information of a city power grid company in 2016 and 2017 as the original corpus, 9 types of alarm event samples were extracted from it to train and test the recognition model. Take 90% of each type of alarm event samples as the training set and 10% as the test set. The types of alarm events and the number of samples of each type are shown in Table 1.

[0110] Table 1 Number of samples of alarm events

[0111]

[0112] In the event classification task, the classification result of the recognition model is generally represented by a confusion matrix, and the meaning of the binary classification confusion matrix is ​​shown in Table 2.

[0113] Table 2 Confusion matrix in event recognition

[0114]

[0115] The confusion matrix divides all events into four categories according to their actual attribution and identification attribution, and defines four indicators of accuracy (Accuracy), precision (Pre...

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 discloses a power grid monitoring alarm event identification method based on convolution and a long-term and short-term memory network, and the method comprises the steps: generating aninformation vector through historical monitoring alarm information and time marks in a power grid monitoring system, extracting event samples from the collected historical monitoring alarm information, and constructing an alarm event sample library; secondly, establishing a deep learning recognition model based on the combination of a long-term and short-term memory network and a convolutional neural network, and training the model by utilizing an alarm event sample; and finally, identifying the monitoring alarm information by using the trained deep learning model, and outputting the event category with the maximum probability as an identification result. According to the method, the excellent performance of the long-term and short-term memory network in time sequence problem processing and the excellent performance of the convolutional neural network in short text local feature mining are combined, the combined model is established, rapid identification of the power grid alarm event can be realized, the screen monitoring pressure of monitoring service personnel is effectively reduced, and the working efficiency of daily monitoring and accident exception handling is improved.

Description

technical field [0001] The invention belongs to the intelligent alarm control technology of electric power system, and in particular relates to a method for identifying alarm events of power grid monitoring based on convolution and long-term and short-term memory networks. Background technique [0002] As the scale of the power grid continues to expand, higher requirements are put forward for the regulators to quickly respond to grid equipment failures and restore the grid operation mode in a timely manner. Therefore, the intelligent level of grid equipment operation monitoring is improved, and the independent identification of grid alarm events is realized. The work efficiency of daily monitoring and accident handling is of great significance. [0003] Grid monitoring alarm information, as a kind of Chinese text data, is an important data basis for regulators to monitor the operation status of the power grid. With the expansion of power grid equipment and the improvement o...

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 Applications(China)
IPC IPC(8): G06F16/35G06F40/284G06N3/04G06N3/08
CPCG06F16/35G06N3/088G06N3/044G06N3/045
Inventor 臧海祥白子瑜程礼临孙国强卫志农
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com