Unlock instant, AI-driven research and patent intelligence for your innovation.

Secondary equipment anomaly diagnosis method based on deep learning network

A technology of deep learning network and secondary equipment, which is applied in the field of abnormal diagnosis of secondary equipment based on deep learning network, can solve problems such as inaccurate early warning, and achieve the effect of accurate early warning diagnosis

Pending Publication Date: 2021-02-12
ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY +2
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above methods all have inaccurate warnings.

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
  • Secondary equipment anomaly diagnosis method based on deep learning network
  • Secondary equipment anomaly diagnosis method based on deep learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Attached below figure 1 , attached figure 2 The present invention will be further described.

[0025] A method for diagnosing abnormalities of secondary equipment based on a deep learning network, comprising the steps of:

[0026] a) via the formula Establish the nonlinear mapping relationship between fault characteristics and fault types in power system operation and maintenance data, where P i is the fault feature set, m is the feature dimension, Q i is the fault type coding, n is the number of coding digits, and the fault feature set P i Perform normalization.

[0027] b) Use the SMOTE algorithm to resample the original data obtained by the secondary equipment monitoring and early warning system in the power system. The resampled original data randomly selects a point between two similar points adjacent to the Euclidean distance in the feature space, Generate new failure samples from all selected points. The generated new samples and the original samples hav...

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 secondary equipment anomaly diagnosis method based on a deep learning network, and the method comprises the steps of building a secondary equipment monitoring and early warning diagnosis model through employing an artificial intelligence algorithm with a deep self-learning function; performing big data training on the early warning diagnosis model by using association characteristics and rules between real-time operation and maintenance information and secondary equipment faults and based on a deep self-encoding network, adopting a mode of deep learning assisted by artificial experience participation, and taking secondary equipment defect historical data as a sample; and building an association mapping relationship between the multi-type operation and maintenancedata and the secondary equipment comprehensively, and realizing accurate early warning diagnosis of the secondary equipment.

Description

technical field [0001] The invention relates to the technical field of power system protection, in particular to a secondary equipment abnormality diagnosis method based on a deep learning network. Background technique [0002] The safe, reliable and continuous power supply of the power system is the basic condition for the normal operation of modern society. Accurate early warning and diagnosis of secondary equipment can inform in advance and take effective measures to protect the safe, stable and continuous operation of the power system to the greatest extent. Even the possible impact on public safety, so as to provide accurate and scientific power emergency response and protection. Therefore, research on how to establish the association and mapping relationship between operation and maintenance data and power grid faults to realize timely and accurate prediction of whether various data may cause faults is of great significance for troubleshooting system faults, restoring ...

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): G06Q10/00G06Q50/06G06N3/04G06N3/08
CPCG06Q10/20G06Q50/06G06N3/084G06N3/088G06N3/045
Inventor 梁正堂李玉敦李娜杨超唐毅马强赵斌超耿玉杰白英伟刘勇张国辉史方芳佟新元王昕李宽王永波王宏孙孔明
Owner ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY