Voltage sag reason identification method based on deep learning model fusion

A technology of voltage sag and model fusion, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem of over-complicated information loss classification models

Active Publication Date: 2019-04-16
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the information loss in the feature extraction process and the over-complexity of the classification model also make the defects of the existing methods increasingly prominent.

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
  • Voltage sag reason identification method based on deep learning model fusion
  • Voltage sag reason identification method based on deep learning model fusion
  • Voltage sag reason identification method based on deep learning model fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] The reason for the sample sag data in this embodiment is to select 2100 voltage sag records from 2012 to 2016 in the power quality monitoring system of a certain province, and the records contain single-phase ground fault C 1 , Large induction motor start C 2 , Transformer switching C 3 , Multi-level voltage sag C caused by short circuit fault 4 , Single-phase grounding and large-scale induction motor starting compound C 5 、Composite C of single-phase grounding and transformer switching 6 And large-scale induction motor starting and transformer switching compound C 7 300 sets of sample data for each of the seven signals for the cause of voltage sag. By building a deep neural network and iterative training, it is possible to learn the abstract characteristic parameters of the recorded data corresponding to different causes of voltage sags and generate a fused model. Assuming several sets of voltage sag recording data, input the fusion model to get the corresponding voltage ...

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 voltage sag reason identification method based on deep learning model fusion, and belongs to the technical field of power quality analysis methods. The method comprises the following steps: carrying out data preprocessing on voltage sag recording and a sag reason tag thereof; establishing a convolutional neural network; carrying out supervised pre-training on the convolutional neural network; replacing a full connection layer of the convolutional neural network with a deep belief network; performing unsupervised pre-training on the deep belief network; adding a softmax layer; supervised training is carried out on the whole network; verifying the accuracy of the generated model; and judging the probability of each category output by the fusion model, and automatically identifying the sag reason type corresponding to the input. According to the method, historical voltage sag recording and a sag reason tag thereof are used for carrying out iterative training on anetwork, and a fused model is generated. Voltage sag wave records which may appear at the monitoring points are input into the model to obtain a corresponding sag reason type. The method is a great supplement for the existing power quality monitoring system, and has very important practical significance.

Description

Technical field [0001] The invention relates to a method for identifying the cause of voltage sag based on deep learning model fusion, and belongs to the technical field of power quality analysis methods. Background technique [0002] Power quality issues include two aspects: steady-state power quality and transient power quality. With the rapid development of industry and information society, on the one hand, the nonlinear load in the distribution network poses a serious threat to the power quality of the grid; on the other hand, the diversified application of power electronic equipment in the distribution network and industrial production The widespread use of sensitive electrical equipment puts forward requirements for high reliability, high controllability, and high transient constancy of power quality. Voltage sag is one of the power quality disturbance events that are unavoidable in the power system and most likely to cause economic losses for sensitive industrial users. A...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/088G06N3/047G06N3/045
Inventor 王红郑智聪齐林海
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap