Electric power communication equipment state prediction method and system
A technology for power communication and equipment status, applied in prediction, complex mathematical operations, biological neural network models, etc., can solve problems such as sparse features, poor effects, and complex sources of equipment status data, and achieve good results in status prediction
Active Publication Date: 2020-07-31
INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER
View PDF6 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the actual scene of power communication equipment, the source of equipment status data is complex, and there are often problems such as high data dimensionality and sparse features. The traditional means of status prediction based on limited field data are not effective.
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 Construction
[0035] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.
[0036] Such as figure 1 As shown, a method for predicting the state of power communication equipment includes the following steps:
[0037] Step 1, collect the characteristic data of the power communication equipment to be predicted, and preprocess it.
[0038] The collected feature data is generally a set of feature vectors, and the required feature data can be obtained through extraction, straightening, vacancy filling, normalization, and centering.
[0039] Step 2, use the preset mixed attention model to process feature data.
[0040] The preset mixed attention model is a pre-trained mixed attention model, and the VAE (variable autoencoder) method is generally used to train the mixed atten...
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 discloses an electric power communication equipment state prediction method. The method comprises the steps of collecting feature data of to-be-predicted electric power communication equipment; processing the feature data by adopting a preset mixed attention model; and inputting the processed feature data into a preset LSTM, and predicting the state of the to-be-predicted electric power communication equipment. The invention further discloses a corresponding system. According to the method, an end-to-end equipment state prediction framework is constructed based on an attention mechanism and an LSTM model, dimension reduction and information mining are carried out on the collected feature data, finally, the equipment operation state on the network node is predicted, and the state prediction effect is good when the data dimension is high and the features are sparse in a scene.
Description
technical field [0001] The invention relates to a method and system for predicting the state of power communication equipment, belonging to the field of signal and information processing. Background technique [0002] With the rapid growth of the power communication network, the modern power communication network not only undertakes the management function of the power grid, but also needs to record and maintain the operation status of key equipment. important meaning. In the actual scene of power communication equipment, the source of equipment status data is complex, and there are often problems such as high data dimensionality and sparse features. Some traditional means of status prediction based on limited field data are not effective. Contents of the invention [0003] The present invention provides a method and system for predicting the state of power communication equipment, which solves the problems disclosed in the background technology. [0004] In order to sol...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06N3/04G06F17/16G06Q50/06
CPCG06Q10/04G06F17/16G06Q50/06G06N3/044G06N3/045Y04S10/50
Inventor 吴海洋陈鹏郭波丁士长洪涛蒋春霞李霁轩
Owner INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER