CN104700213A - Distribution network device state assessment method based on neural network - Google Patents
Distribution network device state assessment method based on neural network Download PDFInfo
- Publication number
- CN104700213A CN104700213A CN201510108868.8A CN201510108868A CN104700213A CN 104700213 A CN104700213 A CN 104700213A CN 201510108868 A CN201510108868 A CN 201510108868A CN 104700213 A CN104700213 A CN 104700213A
- Authority
- CN
- China
- Prior art keywords
- distribution net
- net equipment
- distribution network
- neural network
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a distribution network device state assessment method based on a neural network. The technical feature is that the distribution network device state assessment method based on the neural network includes following steps: building a distribution network device neuron model according to relevant information of distribution network devices; obtaining a distribution network device neural network by clustering and analyzing state information of the distribution network devices; storing the state information of all the distribution network devices which need state assessment and information of the distribution network device neural network in a database; when updating the state information of one specific distribution network device, using state information of another distribution network device correlative with the specific distribution network device through nerves, at the same dimensionality as the specific distribution network device, for updating; using a neural network algorithm to output a state assessment result of the distribution network devices. The distribution network device state assessment method based on the neural network is reasonable in design, not only fully uses abundant distribution network fault and defect information and the state quantity information of the distribution network devices, but also reflects integrality of the distribution network devices, and can perform accurate health condition assessment on the distribution network devices.
Description
Technical field
The invention belongs to distribution net equipment technical field, especially a kind of distribution net equipment state evaluating method based on neural network.
Background technology
Along with carrying out in a deep going way of distribution net equipment service work, to the evaluation of distribution net equipment state and assessment more and more important.At present to the state evaluation of distribution net equipment mostly based on the quantity of state information of equipment itself, as infrared measurement of temperature, customary walkaround inspection etc.Traditional distribution net equipment state evaluation faces two difficulties: one be because distribution net equipment kind is many, quantity is large, have a very wide distribution, when obtaining distribution net equipment quantity of state information used, workload is very large, and under limited operation maintenance personnel condition, this work almost cannot complete; Two is that the distribution net equipment routine test cycle is longer, within the quite a while, cannot get effective status information of equipment amount.In sum, existing distribution net equipment state evaluating method ubiquity the numerous and problem that status information amount is less of equipment.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, provide a kind of reasonable in design, accuracy is high and be convenient to realize the distribution net equipment state evaluating method based on neural network
The present invention solves existing technical matters and takes following technical scheme to realize:
Based on a distribution net equipment state evaluating method for neural network, comprise the following steps:
Step 1, set up distribution net equipment neuron models according to distribution net equipment relevant information, this model contains the distribution net equipment status information that can characterize distribution net equipment health status;
Step 2, by carrying out cluster analysis to distribution net equipment status information, obtain distribution net equipment neural network;
Step 3, adopt the method establishment distribution net equipment relevant database of data mining according to distribution net equipment neural network, the distribution net equipment status information needing state estimation by all and distribution net equipment neural network information are stored in database;
Step 4, gather distribution net equipment status information by status information amount input system new for distribution net equipment, utilize neural equipment associated therewith to upgrade in the status information of same dimension;
Step 5, neural network algorithm is adopted to export distribution net equipment condition evaluation results according to distribution net equipment relevant database and the distribution net equipment status information amount after upgrading.
And described distribution net equipment status information comprises the information of breaking down, defect information and state detecting information.
Advantage of the present invention and good effect are:
1, the present invention not only takes full advantage of abundant Distribution Network Failure and defect information, and individual device is analyzed on the basis of large data, and equipment state amount information is fully used; And, reflect the globality of distribution net equipment, be different from high-tension power transmission and transformation equipment, distribution net equipment has more " internetworking " and " globality ", and the appraisal procedure based on neural network has taken into full account the relevance of a certain distribution net equipment and neighbouring device or equipment of the same type.
2, the present invention takes full advantage of the quantity of state information of distribution net equipment itself and associated equipment, can carry out health Evaluation more accurately to distribution net equipment.
Accompanying drawing explanation
Fig. 1 is the processing flow chart of invention.
Embodiment
Below in conjunction with accompanying drawing, the embodiment of the present invention is further described.
A kind of distribution net equipment state evaluating method based on neural network, that the health status of the distribution net equipment with a certain common trait is considered as a system, and the running status of equipment in whole system is assessed by the equipment failure that constantly occurs in this system and defect information, emphasize globality and the causality of distribution net equipment.Above-mentioned common trait refers to: distribution net equipment is in same running environment or by factors such as same producer manufactures.
As shown in Figure 1, the distribution net equipment state evaluating method based on neural network comprises the following steps:
Step 1, set up distribution net equipment neuron models according to distribution net equipment relevant information, this model contains the distribution net equipment status information that can characterize distribution net equipment health status, these distribution net equipment status informations can be regarded as " synapses " of each " neuron ", i.e. the status flag amount of this distribution net equipment.
Step 2, by carrying out cluster analysis to distribution net equipment status information, obtain the different dimensions reflecting distribution net equipment health status, these dimensions are exactly interactional passage between distribution net equipment, that is: distribution net equipment neural network.
Step 3, adopt the method establishment distribution net equipment relevant database of data mining according to distribution net equipment neural network, the distribution net equipment status information needing state estimation by all and distribution net equipment neural network information are stored in database.
Step 4, break down according to distribution net equipment the status information amounts such as information, defect information and state detecting information, by status information amount input system new for distribution net equipment, utilizes neural equipment associated therewith to upgrade in the status information of same dimension.
Step 5, neural network algorithm is adopted to export distribution net equipment condition evaluation results according to distribution net equipment relevant database and the distribution net equipment status information amount after upgrading.
It is emphasized that; embodiment of the present invention is illustrative; instead of it is determinate; therefore the present invention includes the embodiment be not limited to described in embodiment; every other embodiments drawn by those skilled in the art's technical scheme according to the present invention, belong to the scope of protection of the invention equally.
Claims (2)
1., based on a distribution net equipment state evaluating method for neural network, it is characterized in that comprising the following steps:
Step 1, set up distribution net equipment neuron models according to distribution net equipment relevant information, this model contains the distribution net equipment status information that can characterize distribution net equipment health status;
Step 2, by carrying out cluster analysis to distribution net equipment status information, obtain distribution net equipment neural network;
Step 3, adopt the method establishment distribution net equipment relevant database of data mining according to distribution net equipment neural network, the distribution net equipment status information needing state estimation by all and distribution net equipment neural network information are stored in database;
Step 4, gather distribution net equipment status information by status information amount input system new for distribution net equipment, utilize neural equipment associated therewith to upgrade in the status information of same dimension;
Step 5, neural network algorithm is adopted to export distribution net equipment condition evaluation results according to distribution net equipment relevant database and the distribution net equipment status information amount after upgrading.
2. a kind of distribution net equipment state evaluating method based on neural network according to claim 1, is characterized in that: described distribution net equipment status information comprises the information of breaking down, defect information and state detecting information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510108868.8A CN104700213A (en) | 2015-03-13 | 2015-03-13 | Distribution network device state assessment method based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510108868.8A CN104700213A (en) | 2015-03-13 | 2015-03-13 | Distribution network device state assessment method based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104700213A true CN104700213A (en) | 2015-06-10 |
Family
ID=53347306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510108868.8A Pending CN104700213A (en) | 2015-03-13 | 2015-03-13 | Distribution network device state assessment method based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104700213A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007295650A (en) * | 2006-04-21 | 2007-11-08 | Ipb:Kk | Power management system for each dwelling of collective housing employing virtual power storage secondary battery, and power fee charging method |
CN102509108B (en) * | 2011-10-14 | 2014-12-17 | 桂林电子科技大学 | Welding spot defect identifying method |
-
2015
- 2015-03-13 CN CN201510108868.8A patent/CN104700213A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007295650A (en) * | 2006-04-21 | 2007-11-08 | Ipb:Kk | Power management system for each dwelling of collective housing employing virtual power storage secondary battery, and power fee charging method |
CN102509108B (en) * | 2011-10-14 | 2014-12-17 | 桂林电子科技大学 | Welding spot defect identifying method |
Non-Patent Citations (1)
Title |
---|
吴莉琳: "变压器状态评估与信息管理系统的研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技II辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108564254B (en) | Power distribution equipment state visualization platform based on big data | |
CN109489977B (en) | KNN-AdaBoost-based bearing fault diagnosis method | |
JP2013538543A (en) | Machine learning for power grids | |
CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
CN102654937B (en) | IEC61850 detection platform of power quality monitoring terminal and detection method thereof | |
CN104573906B (en) | System and method for analyzing oscillation stability in power transmission system | |
CN104390657A (en) | Generator set operating parameter measuring sensor fault diagnosis method and system | |
CN115423009A (en) | Cloud edge coordination-oriented power equipment fault identification method and system | |
CN105719094A (en) | State evaluation method of power transmission equipment | |
CN104933477A (en) | Method for optimizing maintenance strategy by using risk assessment of power transmission and transformation equipment | |
CN107124325A (en) | A kind of power communication network operation safety evaluation method and system | |
CN104317778A (en) | Massive monitoring data based substation equipment fault diagnosis method | |
CN113420162A (en) | Equipment operation chain state monitoring method based on knowledge graph | |
CN103529337B (en) | The recognition methods of nonlinear correlation relation between equipment failure and electric quantity information | |
Honarmand et al. | Reliability modeling of process-oriented smart monitoring in the distribution systems | |
CN111768022A (en) | Equipment detection method and device for coal machine production equipment | |
CN103606114A (en) | Estimation method for reliability of relaying protection equipment | |
CN108596450B (en) | Power grid risk early warning method and system | |
CN104484828A (en) | High-voltage electrical appliance operation quality evaluation method and system based on logistic regression | |
CN116756505B (en) | Photovoltaic equipment intelligent management system and method based on big data | |
CN105260814A (en) | Power transmission and transformation equipment evaluation model and processing method based on big data | |
CN105741184A (en) | Transformer state evaluation method and apparatus | |
CN104573864A (en) | Data analysis alarm method based on autoregressive prediction | |
CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
CN202091172U (en) | Device for monitoring state and analyzing reliability of gas compressor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150610 |