A Reliability Evaluation Method for Power Communication Network Equipment Based on Capsule Network

A technology of network equipment and power communication, applied in biological neural network models, data processing applications, instruments, etc., can solve the problems of inconvenient and accurate evaluation of the reliability of power communication network equipment, prediction methods relying on manual preprocessing, feature extraction, etc. , to achieve the effect of improving versatility and deployment convenience, convenient and fast training and deployment, and achieving accurate evaluation

What is AI technical title?
AI technical title is built by PatSnap AI team. It summarizes the technical point description of the patent document.
A technology of network equipment and power communication, applied in biological neural network models, data processing applications, instruments, etc., can solve the problems of inconvenient and accurate evaluation of the reliability of power communication network equipment, prediction methods relying on manual preprocessing, feature extraction, etc. , to achieve the effect of improving versatility and deployment convenience, convenient and fast training and deployment, and achieving accurate evaluation

CN111080168BActive Publication Date: 2021-08-03INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER +1

0 Cites 0 Cited by

Image

Smart Image Click on the blue labels to locate them in the text.

Viewing Examples

Smart Image

Examples

Experimental program

Comparison scheme

Effect test

Embodiment 1

[0038] A method for evaluating the reliability of power communication network equipment based on a capsule network, comprising steps:

[0039] The reliability evaluation of the equipment is carried out through the trained power communication network equipment reliability evaluation model;

[0040] The power communication network equipment reliability assessment model is constructed based on the capsule network and obtained through training of original data and generated disturbance data.

[0041] Further, the input of the power communication network equipment reliability evaluation model is: text information of operation and maintenance data; the output is: the number of possible failures of equipment in a certain period in the future.

[0042] The model building process is:

[0043] The text information of the operation and maintenance data is processed by the word embedding method to obtain the input word vector, and the input word vector is extracted with convolution filte...

Embodiment 2

[0065] A method for evaluating the reliability of power communication network equipment based on a capsule network, comprising steps:

[0066] Step 1. Construct a reliability evaluation model for power communication network equipment with the capsule network as the core;

[0067] The overall framework of the capsule network model adopted in the present invention is as follows: figure 1 shown. The framework is built on top of general natural language processing frameworks and adapted to the problem of device reliability assessment. The model uses text information with a unified structure as the network input, so the long-term operation and maintenance data of the power network with different structures can be directly used as the original text to input the unified neural network structure. The input signal (that is, the input of the neural network structure) can be processed by the common word embedding method to obtain the input word vector of the same dimension. Feature ex...

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 a method for evaluating the reliability of power communication network equipment based on a capsule network, comprising the steps of: evaluating the reliability of the equipment through a trained power communication network equipment reliability evaluation model; After the text information is processed by the word embedding method, the input word vector is obtained, and the feature extraction is performed on the input word vector with convolution filters of different sizes. The extracted features are combined in series, and further Use the convolution filter to perform convolution filtering to form a capsule feature vector; bind an activation value to each capsule feature vector; after compressing the number of capsules, obtain a new capsule feature vector through the capsule routing method based on kernel density estimation And the new activation value; the new activation value is used for regression prediction; the new capsule feature vector is input into the decoder to reconstruct the input feature. The invention can conveniently and accurately evaluate the reliability of the power communication network equipment.

Description

technical field [0001] The invention relates to the fields of equipment reliability evaluation and machine learning, in particular to a capsule network-based power communication network equipment reliability evaluation method. Background technique [0002] Modern power communication networks are rapidly increasing in size and complexity. As an important infrastructure of the modern smart grid, the power communication network not only provides various guarantee services required by the grid, but also monitors the equipment and sensors on the network in real time and maintains key operating data. Therefore, it is more and more important to evaluate and analyze the reliability of the equipment of the communication network itself. Traditional power communication network operation and maintenance usually means periodic maintenance or short-term fault alarm recovery, and automatic reliability assessment and prediction methods can further reduce the risk of serious network failure...

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

03 Aug 2021

Publication

CN111080168B

IPC: G06Q10/06; G06Q10/00; G06Q50/06; G06K9/62; G06N3/04

CPC: G06Q10/0639; G06Q10/20; G06Q50/06; G06N3/045; G06F18/23213

Inventors: 缪巍巍; 吴海洋