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

voltage sag disturbance classification method based on LSTM

A technology of voltage sag and classification method, applied in instruments, biological neural network models, character and pattern recognition, etc., can solve the problem of missing signal features, low accuracy of signal classification and recognition, and complicated and cumbersome manual feature extraction steps for sag signals. and other problems, to achieve high complexity, good anti-noise performance and generalization ability, and improve the classification accuracy.

Inactive Publication Date: 2019-05-17
NORTH CHINA ELECTRIC POWER UNIV (BAODING) +1
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a new LSTM-based voltage sag disturbance classification method for problems such as complex and cumbersome manual feature extraction steps for sag signals, easy loss of part of signal features, and low accuracy of signal classification and recognition.

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 disturbance classification method based on LSTM
  • voltage sag disturbance classification method based on LSTM
  • voltage sag disturbance classification method based on LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] like figure 1 As shown, the LSTM-based voltage sag disturbance classification method of this embodiment builds a four-layer deep learning network model containing a data processing layer, a 2-layer LSTM layer, a fully connected layer, and a classification layer, wherein the data processing layer is also the entire model The input layer, the classification layer is also the result output layer.

[0034] like figure 2 As shown, the training process of the model in this embodiment includes two steps of unsupervised pre-training and model fine-tuning, wherein the unsupervised pre-training process is used to determine the hyperparameters such as the number of neurons and the learning rate of each layer of the entire model, and the model fine-tuning is On the basis of pre-training, fine-tuning of parameters such as the weight of the model is performed, and the LSTM-based voltage sag disturbance classification model of the present invention is finally obtained through these ...

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 electric energy quality classification and identification, and discloses a voltage sag disturbance classification method based on a Long Shore-Term Memory algorithm. According to the method, firstly, voltage sag disturbance data are processed through a data processing layer, then feature values are extracted through two layers of LSTM networks, feature dimension reduction processing is conducted through a full connection layer, and finally classification recognition is conducted through a sigmoid network layer. The electric energy quality sag disturbance correlation characteristics are extracted through the deep learning algorithm, and the limitation of a classification recognition modeling method based on time domain, frequency domain, transformation domain and other physical characteristics in the complex power grid environment in the aspects of adaptability, algorithm efficiency and accuracy is overcome. By using the model, the defectsof tedious and complex extraction steps, possible loss of original characteristics of part of signals and the like in the traditional method can be well overcome; The defect that gradient explosion is likely to happen to a traditional recurrent neural network (RNN) is overcome, and high voltage sag disturbance recognition accuracy is achieved.

Description

technical field [0001] The invention relates to an LSTM-based voltage sag disturbance classification method, which belongs to the technical field of power quality classification and identification. Background technique [0002] The scale of the power grid continues to expand, and the grid structure and load types are becoming more and more complex; distributed new energy sources with significant randomness, intermittentity and volatility are connected to the distribution network directly or in the form of micro-grids; introduced to actively accommodate distributed power sources The application of a large number of nonlinear power electronic devices and the interaction of multiple factors between power sources and devices, devices and devices, such as switching of power sources and compensation capacitors, make the concept of modern power quality a complex field covering many topics. [0003] In a complex power grid environment, the factors causing voltage sag disturbances in...

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): G06K9/00G06N3/04
Inventor 齐林海陈倩潘爱强王红周健
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
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