Construction method, system and early warning method of relay protection equipment fault early warning model
A relay protection and equipment failure technology, applied in the field of construction of relay protection equipment fault early warning model, can solve problems such as data processing dependence, equipment failure, downtime maintenance, etc., to improve stability and reliability, and reduce abnormal losses , the effect of improving the convergence speed
Active Publication Date: 2022-06-03
STATE GRID ANHUI ELECTRIC POWER CO LTD +1
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Although the traditional early warning technology of relay protection equipment can monitor and warn the operating status and failure of the equipment, there are several problems: first, when the system alarms, the equipment has already failed and can only be shut down for maintenance; second, A large number of physical parameters will be generated during the normal operation of the relay protection device, and the processing of these data depends on expert experience
In addition, due to the development of network technology and signal processing technology, relay protection equipment generates massive amounts of information all the time, which cannot be processed by only relying on limited experts
[0005] The invention patent application with the publication number CN107918690A discloses a state evaluation method for relay protection equipment based on BP neural network algorithm. The historical maintenance data is imported into the BP neural network for learning to form a state evaluation model, and the state evaluation model is used to evaluate the state of the relay protection device. Evaluate the environment without equipment operating environment, etc., obtain the evaluation results, and then arrange maintenance, but this method is mainly used to determine the scope of maintenance, and cannot realize early warning of relay protection equipment failures
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
[0075]
[0076]
[0077]
[0078] Wherein, g(a) is a correction function.
[0079] The traditional BP neural network model uses the sigmoid function whose value range is in the [0,1] interval as the activation function, so most algorithms
[0085]
[0086]
[0089] Transfer the hidden layer data to the output layer
[0090]z
[0091]
[0094]
[0095] If E
[0097]
[0099]
[0100]
[0102]
[0103] e
[0107]c
[0108]
[0109]
[0111] Step vi: let n=n+1, go back to step ii, until the model is output in step iii.
[0114]
[0115]
[0117] During training, the convergence time under different hidden layer numbers and tolerances is as follows:
[0118]
[0119] Therefore, in the case of a single hidden layer, the allowable error range is at least 5% to 10%.
[0120] The historical data is input into the prediction model obtained by training and verified, and the results are as follows:
[0121]
[0122] There is only one identification error in the above results, and the accuracy...
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 provides a method for constructing a fault early warning model of relay protection equipment, including step A: collecting historical fault information of relay protection equipment, and dividing all faults into at least two levels; step B: sorting out faults where protection functions fail The result vector is obtained from the data, and the matrix constructed by the corresponding historical fault information is used as the cause matrix; Step C: Normalize the result vector and the cause matrix respectively; Step D: Determine the structure and parameters of the BP neural network, and normalize The final cause matrix and result vector are respectively imported into the BP neural network as input and output values for training. The invention also provides a method for fault warning based on the model. The present invention takes the failure of the protection function as the cause and the result of the failure of the protection function as an early warning for the relay protection equipment, reduces the abnormal loss, and improves the stability and reliability of the power grid operation.
Description
Construction method, system and early warning method of fault early warning model of relay protection equipment technical field The present invention relates to technical field of relay protection, relate in particular to the construction side of relay protection equipment fault early warning model [0001] methods, systems and early warning methods. Background technique [0002] With the development of economy and various industries, people's demand for power supply continues to increase. power system as economic development The important guarantee of its operation, the stability, reliability and safety of its operation are becoming more and more important. But the power system goes from generating to A series of processes of electricity use are complex and coupled, which makes its reliable, safe and stable operation face many problems and test. Therefore, people introduce intelligent substations in modern transmission and distribution network systems. The emergence...
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 Patents(China)
IPC IPC(8): G06F30/27G06N3/04G06N3/08G06Q50/06
CPCG06F30/27G06N3/084G06Q50/06G06N3/044Y02E40/70
Inventor 叶远波李端超谢民汪胜和汪伟邵庆祝程晓平王薇项忠华陈晓东刘宏君赵子根丛雷韩啼啼
Owner STATE GRID ANHUI ELECTRIC POWER CO LTD