CN110221139A - A kind of failure prediction method of dry-type transformer, apparatus and system - Google Patents
A kind of failure prediction method of dry-type transformer, apparatus and system Download PDFInfo
- Publication number
- CN110221139A CN110221139A CN201910366173.8A CN201910366173A CN110221139A CN 110221139 A CN110221139 A CN 110221139A CN 201910366173 A CN201910366173 A CN 201910366173A CN 110221139 A CN110221139 A CN 110221139A
- Authority
- CN
- China
- Prior art keywords
- dry
- type transformer
- operation data
- data
- module
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of failure prediction methods of dry-type transformer, apparatus and system, which comprises obtains the operation data of the dry-type transformer；The operation data is filtered；By filtered operation data input fault prediction model trained in advance, to predict the health status of the dry-type transformer；When predicting that the dry-type transformer there are when potential faults, exports fault pre-alarming information.The operation data of more dry-type transformers is obtained in real time, and operation data is detected by fault prediction model trained in advance, to the dry transformer fault hidden danger of early warning, realize the running state real-time monitoring to dry-type transformer, potential faults present in dry-type transformer operation can be found in time, hidden danger was eliminated at failure initial stage, damage of the failure to dry-type transformer is reduced, to reduce transformer fault bring economic loss and security risk.
Description
Technical field
The present invention relates to energy technology field more particularly to a kind of failure prediction method of dry-type transformer, device and it is
System.
Background technique
Dry-type transformer has many advantages, such as that maintenance workload is small, operational efficiency is high, small in size, low noise, therefore, for matching
It is widely applied in electric system.But in operation, due to misuse, vibration, excessively high operation temperature, shove, overload, right
Control the maintenance of equipment not enough, the cleaning reasons such as bad especially when transformer station high-voltage side bus is when than relatively rugged environment will cause change
Depressor generates failure, seriously affects production or causes electrical hazard.
Currently, for running dry-type transformer, it can only be carried out by simple Daily Round Check and regularly stopping transport
Inspection and maintenance, observing each fastener has non-loosening, fever, and there is no cracking on winding insulation surface, climbs electricity and carbonized path, sound
It is whether normal etc..
Most of inside transformer insulation defect is occurred inside equipment, from being not easy to observe in appearance, Zhi Neng
Power equipment halt production period carries out preventive trial.It is right but for faint insulation defect, especially early stage property insulation fault
Power equipment operating status has little effect, in addition insulation preventive trial also test less than.This causes even if regularly pre-
Anti- property test, it is also difficult to timely and accurately discovery insulation hidden danger.Therefore, only by Daily Round Check and regularly out-of-service inspection be difficult to and
Potential faults existing for Shi Faxian transformer, and then may cause safety accident.
Summary of the invention
The present invention provides a kind of failure prediction method of dry-type transformer, apparatus and system, it can be achieved that more transformers
Health status be monitored, in advance find transformer station high-voltage side bus present in potential faults, reduce transformer fault bring warp
Ji loss and security risk.
In a first aspect, the present invention provides a kind of failure prediction methods of dry-type transformer, which comprises obtain institute
State the operation data of dry-type transformer；The operation data is filtered；The filtered operation data is inputted
Trained fault prediction model in advance, to predict the health status of the dry-type transformer；When the prediction dry-type transformer is deposited
In potential faults, warning information is exported.
Preferably,
The method also includes: history data, breakdown judge data, equipment factory based on the dry-type transformer
Parameter etc., is trained neural network, to obtain the fault prediction model, wherein breakdown judge data include dry type transformation
The operation data of device and the corresponding relationship of fault type.
Preferably,
The fault prediction model is three-layer neural network model, including input layer, hidden layer and output layer, wherein institute
The number of nodes of input layer is stated as the sum of the characteristic quantity of the history data, the number of nodes of the hidden layer is preset failure
The sum of type, the number of nodes of the output layer are the sum of preset failure type.
Preferably,
Being filtered to the operation data includes: to carry out frequency and amplitude analysis to the operation data, with right
The operation data is classified；Based on operation data after the classification, removed in the operation data by Predetermined filter
Interference data；Data reconstruction is carried out to the operation data for having removed interference data, the filtered operation can be obtained
Data.
Preferably,
The fault prediction model that the filtered operation data input is trained in advance, to predict that the dry type becomes
The operating status of depressor includes: to carry out feature extraction to the filtered operation data, to obtain the spy of the operation data
Sign amount；By characteristic quantity input fault prediction model trained in advance, to predict the operating status of the dry-type transformer.
Preferably,
The method also includes:
Show the operation data of the dry-type transformer and the operating status of prediction.
Dry-type transformer fault prediction device of the present invention, comprising: data acquisition module, for obtaining the dry type
The operation data of transformer；Filter module, for being filtered to the operation data；Prediction module, being used for will be described
Filtered operation data input fault prediction model trained in advance, to predict the health status of the dry-type transformer；It is defeated
Module out, for when predicting that the dry-type transformer there are when potential faults, exports fault pre-alarming information.
Preferably,
The fault prediction device further include: model training module, for the history run based on the dry-type transformer
Data, breakdown judge data and equipment factory parameter, are trained neural network, to obtain the fault prediction model,
In, breakdown judge data include the operation data of dry-type transformer and the corresponding relationship of fault type.
Preferably,
Described device further include: display module, for showing the operation data and predictive information of the dry-type transformer.
Another aspect of the present invention also provides a kind of failure prediction system of dry-type transformer, and the system includes:
Data monitoring terminal, data acquisition module, intelligent gateway and dry-type transformer above-mentioned fault prediction device；
Wherein, the data monitoring terminal includes local discharge sensor, voltage sensor, current sensor, winding temperature
Spend at least one of sensor, environment humidity sensor and vibrating sensor；
Data acquisition module includes A/D conversion module, communication module, power module and memory module；
The intelligent gateway includes RS485 communication module, ethernet module, protocol conversion module, controller module, power supply
Module；
Preferably,
One data acquisition module of every transformer configuration；
The intelligent gateway include RS485 communication module, Ethernet wireless module, protocol conversion module, controller module,
Power module.
A kind of failure prediction method of dry-type transformer, apparatus and system workflow are as follows: the data monitoring
Terminal is responsible for carrying out duration perception to the operating parameter of transformer, and the data acquisition module is by the fixed cycle to data monitoring
The data that terminal uploads are sampled, and analog quantity is converted into digital quantity, after the data summarization acquired every time, by 485 buses
It is transferred to intelligent gateway；Intelligent gateway can at least be communicated with the same data acquisition module, obtain acquisition module transmission
After the data arrived, protocol conversion is carried out according to ICP/IP protocol, monitoring cloud platform is transmitted to by wireless ethernet.Monitor cloud
Platform analyzes the data of acquisition, and is compared with fault characteristic value, finally judges transformer state, if hair
Existing failure then carries out fault alarm prompting on platform, and sends operation maintenance personnel for warning information.
A kind of failure prediction method of dry-type transformer provided by the invention, device and system can obtain more in real time and do
The operation data of formula transformer, and equipment health status is judged by fault prediction model trained in advance, thus and
Potential faults existing for early discovery transformer, realize the maintenance in advance to dry-type transformer, and hidden danger is eliminated in failure initial stage, drop
Low failure is to the more macrolesion of transformer, to reduce transformer fault bring economic loss and security risk.
Detailed description of the invention
It, below will be to embodiment or existing skill in order to illustrate more clearly of this specification embodiment or existing technical solution
Attached drawing needed in art description is briefly described, it should be apparent that, the accompanying drawings in the following description is only this explanation
The some embodiments recorded in book, for those of ordinary skill in the art, without any creative labor,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of the failure prediction method for dry-type transformer that one embodiment of the invention provides；
Fig. 2 is a kind of structural schematic diagram of the fault prediction device for dry-type transformer that one embodiment of the invention provides；
Fig. 3 is a kind of failure prediction system structural schematic diagram for dry-type transformer that one embodiment of the invention provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of this specification clearer, below in conjunction with specific embodiment and accordingly
Attached drawing the technical solution of this specification is clearly and completely described.Obviously, described embodiment is only this specification
A part of the embodiment, instead of all the embodiments.The embodiment of base in this manual, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, the range of this specification protection is belonged to.
With the development of the technologies such as sensing measurement, communication, computer and artificial intelligence, dry-type transformer is supervised in real time
Survey, and by analysis to fault characteristic value, compare, lay a good foundation for the failure predication of dry-type transformer.At this stage, dry type
Transformer in the process of running, is difficult to overhaul it, is difficult to find so as to cause potential faults therein, and waits until failure
Stoppage in transit maintenance is carried out after generation again, it will seriously affect production, cause biggish economic loss.Based on this, the present invention is quasi- to be provided
The online failure prediction method and system of a kind of dry-type transformer are, it can be achieved that the operating status to more dry-type transformers is supervised in real time
It surveying, finds potential faults existing for dry-type transformer in time, by eliminating hidden danger at failure initial stage, reducing failure to transformer
Damage, to reduce transformer fault bring economic loss and security risk.
It is carried out below in conjunction with failure prediction method and system of the attached drawing to a kind of dry-type transformer provided by the invention detailed
Thin description so that those skilled in the art can clearly, accurately understand technical solution of the present invention.
Fig. 1 is a kind of flow diagram of the failure prediction method for dry-type transformer that one embodiment of the invention provides.
As shown in Figure 1, the embodiment of the invention provides a kind of failure prediction method of dry-type transformer, this method be can wrap
Include following steps:
Step 110, the operation data of dry-type transformer is obtained.
It in embodiments of the present invention, can be for example, by voltage sensor, current sensor, winding temperature sensor, ring
The operation data of the acquisition dry-type transformer such as border Temperature Humidity Sensor and vibrating sensor.It is come from by data transmission interface acquisition
The operation data of the sensor acquisition.
In an exemplary embodiment of the invention, operation data includes but is not limited to the electricity in dry-type transformer operational process
Press data, current data, Partial Discharge Data, winding temperature data, ambient temperature data etc..In the present invention not to this into
Row limitation, can add corresponding sensor according to actual prediction demand to obtain desired operation data.
Step 120, operation data is filtered.
In this step, it may be implemented are as follows: frequency and amplitude analysis are carried out to the operation data, to the operation number
According to classifying；Based on operation data after the classification, the interference data in the operation data are removed by Predetermined filter；
Data reconstruction is carried out to the operation data for having removed interference data, has obtained the filtered operation data.It is exemplary
Ground can classify different types of operation data after step 110 gets the operation data of dry-type transformer, point
Not Jing Guo the removal of preset traffic filter wherein interfere data, obtain desired operation data.
Illustratively, low-frequency sampling data (such as voltage data, current data, temperature data etc.) can be using smooth filter
Wave and bandwidth filtering are filtered；High frequency sampled data (for example, Partial Discharge Data) can be carried out using wavelet filtering mode
Filtering processing.Further for example, it can analyze the operation data of dry-type transformer, such as analyze its frequency range and its amplitude model
It encloses；The local discharge signal of acquisition is decomposed according to frequency range, frequency range where then removing interference signal and the letter in amplitude thresholds
Number；Through wavelet reconstruction recovering signal, to obtain true local discharge signal.
Step 130, the fault prediction model that the input of filtered operation data is trained in advance, to predict dry-type transformer
Health status.
An exemplary embodiment according to the present invention, trained fault prediction model is defeated with filtered operation data in advance
Enter, using the prediction result of the health status of dry-type transformer as output.The step may be implemented are as follows: to the filtered fortune
Row data carry out feature extraction, to obtain the characteristic quantity of the operation data；By characteristic quantity input failure trained in advance
Prediction model, to predict the health status of the dry-type transformer.To the characteristic quantity of each operating parameter, for example, for handing over
Flow monitoring quantity (such as current data and voltage data) and extract power frequency period virtual value as characteristic quantity, for DC quantity (such as
Temperature, humidity) collection period average value is extracted as virtual value；It is extracted for high-speed sampling signal (such as Partial Discharge Data)
Characteristic quantity be degree of skewness, steepness, cross-correlation coefficient, discharge capacity factor, phase degree of asymmetry and modified cross-correlation coefficient
Two-dimentional spectrogram statistical parameter etc..
It illustratively, can history data based on the dry-type transformer, breakdown judge data, factory parameter
Deng training neural network, to obtain the fault prediction model, wherein breakdown judge data include the operation of dry-type transformer
The corresponding relationship of data and fault type.The corresponding relationship of operation data and fault type, may come from dry-type transformer
Empirical data of the parameter or senior industry technology personnel etc. of dispatching from the factory to breakdown judge.
In some embodiments, fault prediction model is three-layer neural network model, including input layer, hidden layer and output
Layer, wherein the number of nodes of the input layer is the sum of the characteristic quantity of the history data, the number of nodes of the hidden layer
For the sum of preset failure type, the number of nodes of the output layer is the sum of preset failure type.
Step 140, when prediction dry-type transformer is there are when potential faults, warning information is exported.
In this step, when predicting dry-type transformer there are alarm prompting is carried out when potential faults, to remind O&M people
Member is in time handled hidden danger.
In further embodiments, the operation data of the dry-type transformer and the health and fitness information of prediction can be shown.
The present invention provides a kind of failure prediction method of dry-type transformer, obtains the operation number of more dry-type transformers in real time
According to, and operation data is judged by fault prediction model trained in advance, to predict the failure of dry-type transformer
Hidden danger realizes the health status real-time monitoring to dry-type transformer, can find exist in dry-type transformer operation in time in this way
Potential faults, by by hidden danger eliminate at failure initial stage, failure can be reduced to the lesion larger of dry-type transformer, to reduce
Transformer fault bring economic loss and security risk.
A kind of failure prediction method of dry-type transformer provided by the invention is described in detail in previous embodiment, under
Face will be described in detail corresponding system in conjunction with attached drawing.Its realization principle and technical effect and preceding method embodiment phase
Together.
Fig. 2 is that a kind of process of the failure prediction system platform software for dry-type transformer that one embodiment of the invention provides is shown
It is intended to.
As shown in Fig. 2, a kind of failure prediction system software 200 of dry-type transformer of the invention includes: data acquisition mould
Block 210, filter module 220, prediction module 230 and output module 240.
Data acquisition module 210 can be used for obtaining the operation data of the dry-type transformer.
Filter module 220 can be used for being filtered the operation data.
In some embodiments, filter module 220 may further be used to carry out frequency and amplitude to the operation data
Analysis, to classify to the operation data；Based on operation data after the classification, the fortune is removed by Predetermined filter
Interference data in row data；Data reconstruction is carried out to the operation data for having removed interference data, the filtering can be obtained
Operation data afterwards.
Prediction module 230 can be used for the fault prediction model that the filtered operation data input is trained in advance,
To predict the operating status of the dry-type transformer.
In some embodiments, prediction module 230 may further be used to carry out the filtered operation data special
Sign is extracted, to obtain the characteristic quantity of the operation data；By characteristic quantity input fault prediction model trained in advance, with pre-
Survey the health status of the dry-type transformer.
Output module 240 can be used for when predicting that the dry-type transformer there are when potential faults, exports warning information.
Further, an exemplary embodiment, the plateform system software can also include model training according to the present invention
Module (not shown) can be used for history data based on the dry-type transformer, breakdown judge data, training mind
Through network, to obtain the fault prediction model, wherein breakdown judge data include the operation data and failure of dry-type transformer
The corresponding relationship of type.In some embodiments, the number of nodes of the input layer is the characteristic quantity of the history data
Sum, the number of nodes of the hidden layer are the sum of preset failure type, and the number of nodes of the output layer is preset failure type
Sum.
The present invention provides the failure prediction system and method for a kind of dry-type transformer, obtains more dry-type transformers in real time
Operation data, and data are judged by fault prediction model trained in advance, thus failure existing for early warning transformer
Hidden danger realizes the health status real-time monitoring to dry-type transformer, can find event present in dry-type transformer operation in time
Hinder hidden danger, hidden danger was eliminated at failure initial stage, reduces failure to the lesion larger of dry-type transformer, to reduce transformer fault
Bring economic loss and security risk.
Fig. 3 is a kind of structural schematic diagram of the failure prediction system for dry-type transformer that one embodiment of the invention provides.
As shown in figure 3, a kind of failure prediction system of dry-type transformer may include data monitoring terminal, data acquisition module
Block 1 to data acquisition module n, 485 buses, intelligent gateway, wireless network (for example, Ethernet), monitor supervision platform (as shown in Figure 2
Device).
The data monitoring terminal may include local discharge sensor, voltage sensor, current sensor, winding temperature
At least one of sensor, environment humidity sensor and vibrating sensor.
Wherein, local discharge sensor can be used for detecting dry-type transformer with the presence or absence of partial discharge phenomenon, it is preferable that
Local discharge sensor can use air type ultrasonic sensor, and air type ultrasonic sensor is packaged into rotating detector shape
Multiple local discharge sensors can be arranged in top and the week of dry-type transformer cabinet by formula, positioning accuracy 20cm
On casing body.
Voltage sensor and current sensor can be used for measuring the voltage and current of dry-type transformer respectively, it is preferable that
The voltage and current of the low-pressure side of dry-type transformer is selected to measure.
Winding temperature sensor can be used for measuring the temperature inside dry-type transformer winding, inside usual dry-type transformer
Winding can be embedded in sensor, can directly be measured using winding temperature sensor.
Environment humidity sensor can be used for measuring the temperature and humidity in dry-type transformer running environment.
Vibrating sensor can be used for monitoring dry-type transformer Oscillation Amplitude and acceleration in operation, it is preferable that vibration
Sensor is installed on the lower part of dry-type transformer ontology.
Further, data acquisition module may include A/D conversion module, communication module, power module and memory module.
Preferably, each dry-type transformer configures at least one data acquisition module.
Intelligent gateway may include RS485 communication module, ethernet module, protocol conversion module 333, controller module and
Power module.
Preferably, intelligent gateway can take GPRS mode with the communication between monitor supervision platform.
Monitor supervision platform (device as shown in Figure 2) is by data server, application server, web server, Communications service
Device, work station composition, in the application server, each server is connected transformer fault forecasting system software loading by cable
It connects.
For convenience of description, it describes to be divided into various units when system above with function or module describes respectively.Certainly, exist
Implement to realize the function of each unit or module in the same or multiple software and or hardware when this specification.
It should be understood by those skilled in the art that, the embodiment of this specification can provide as method, system or computer journey
Sequence product.Therefore, in terms of this specification can be used complete hardware embodiment, complete software embodiment or combine software and hardware
Embodiment form.Moreover, it wherein includes computer usable program code that this specification, which can be used in one or more,
The computer implemented in computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of program product.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute
It is in realize the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
System.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of system, the instruction system realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technology
For personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specification
Modification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.
Claims (10)
1. a kind of failure prediction method of dry-type transformer, which is characterized in that the described method includes:
Obtain the operation data of the dry-type transformer；
The operation data is filtered；
By filtered operation data input fault prediction model trained in advance, to predict the strong of the dry-type transformer
Health state；
When predicting that the dry-type transformer there are when potential faults, exports fault pre-alarming information.
2. the method according to claim 1, wherein the method also includes:
History data, breakdown judge data and equipment factory parameter based on the dry-type transformer, are trained nerve
Network, to obtain the fault prediction model,
Wherein, breakdown judge data include the operation data of dry-type transformer and the corresponding relationship of fault type.
3. according to the method described in claim 2, it is characterized in that, the fault prediction model be three-layer neural network model,
Including input layer, hidden layer and output layer,
Wherein, the number of nodes of the input layer is the sum of the characteristic quantity of the history data, the node of the hidden layer
Number is the sum of preset failure type, and the number of nodes of the output layer is the sum of preset failure type.
4. the method according to claim 1, wherein described be filtered to the operation data includes:
Frequency and amplitude analysis are carried out to the operation data, to classify to the operation data；
Based on operation data after the classification, the interference data in the operation data are removed by Predetermined filter；
Data reconstruction is carried out to the operation data for having removed interference data, the filtered operation data can be obtained.
5. the method according to claim 1, wherein described instruct the filtered operation data input in advance
Experienced fault prediction model, to predict that the operating status of the dry-type transformer includes:
Feature extraction is carried out to the filtered operation data, to obtain the characteristic quantity of the operation data；
By characteristic quantity input fault prediction model trained in advance, to predict the operating status of the dry-type transformer.
6. the method according to claim 1, wherein the method also includes:
Show the operation data of the dry-type transformer and the operating status of prediction.
7. a kind of fault prediction device of dry-type transformer, which is characterized in that described device includes:
Data acquisition module, for obtaining the operation data of the dry-type transformer；
Filter module, for being filtered to the operation data；
Prediction module, for the fault prediction model that the filtered operation data input is trained in advance, described in prediction
The health status of dry-type transformer；
Output module, for when predicting that the dry-type transformer there are when potential faults, exports fault pre-alarming information.
8. device according to claim 7, which is characterized in that described device further include:
Model training module, for history data, breakdown judge data and equipment factory based on the dry-type transformer
Parameter is trained neural network, to obtain the fault prediction model, wherein breakdown judge data include dry-type transformer
Operation data and fault type corresponding relationship.
9. device according to claim 7, which is characterized in that described device further include:
Display module, for showing the operation data of the dry-type transformer and the operating status of prediction.
10. a kind of failure prediction system of dry-type transformer, which is characterized in that the system comprises:
Data monitoring terminal, data acquisition module, intelligent gateway and the described in any item dry-type transformers of claim 7 to 9
Fault prediction device；
Wherein, the data monitoring terminal includes local discharge sensor, voltage sensor, current sensor, winding temperature biography
At least one of sensor, environment humidity sensor and vibrating sensor；
Data acquisition module includes A/D conversion module, communication module, power module and memory module；
The intelligent gateway includes RS485 communication module, ethernet module, protocol conversion module, controller module, power supply mould
Block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910366173.8A CN110221139A (en) | 2019-05-05 | 2019-05-05 | A kind of failure prediction method of dry-type transformer, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910366173.8A CN110221139A (en) | 2019-05-05 | 2019-05-05 | A kind of failure prediction method of dry-type transformer, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110221139A true CN110221139A (en) | 2019-09-10 |
Family
ID=67820295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910366173.8A Pending CN110221139A (en) | 2019-05-05 | 2019-05-05 | A kind of failure prediction method of dry-type transformer, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110221139A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110726957A (en) * | 2019-11-05 | 2020-01-24 | 国网江苏省电力有限公司宜兴市供电分公司 | Fault identification method of dry-type reactor |
| CN110766059A (en) * | 2019-10-14 | 2020-02-07 | 四川西部能源股份有限公司郫县水电厂 | Transformer fault prediction method, device and equipment |
| CN110929769A (en) * | 2019-11-14 | 2020-03-27 | 保定赛瑞电力科技有限公司 | Reactor mechanical fault joint detection model, method and device based on vibration and sound |
| CN111398723A (en) * | 2020-04-17 | 2020-07-10 | 上海数深智能科技有限公司 | Intelligent transformer fault diagnosis model method |
| CN111488947A (en) * | 2020-04-28 | 2020-08-04 | 深圳力维智联技术有限公司 | Fault detection method and device for power system equipment |
| CN111706499A (en) * | 2020-06-09 | 2020-09-25 | 成都数之联科技有限公司 | Predictive maintenance system and method for vacuum pump and automatic vacuum pump purchasing system |
| CN111830893A (en) * | 2019-12-03 | 2020-10-27 | 上海稳擎科技有限公司 | Equipment operation and maintenance monitoring system |
| CN112463362A (en) * | 2020-11-03 | 2021-03-09 | 江苏核电有限公司 | Multi-information edge calculation dry-type transformer fault mode identification system and method |
| CN112557793A (en) * | 2020-12-04 | 2021-03-26 | 广东电网有限责任公司 | Power plug-in health state detection method and device and storage medium |
| CN112880740A (en) * | 2021-01-21 | 2021-06-01 | 上海迈内能源科技有限公司 | Transformer running state on-line monitoring system and multi-parameter intelligent sensor thereof |
| CN113553927A (en) * | 2021-07-08 | 2021-10-26 | 国网福建省电力有限公司福州供电公司 | Running state analysis method, system, server and medium of dry-type transformer |
| WO2022000640A1 (en) * | 2020-06-28 | 2022-01-06 | 南京东创信通物联网研究院有限公司 | Monitoring and alarm system for transformer |
| CN114034344A (en) * | 2021-11-12 | 2022-02-11 | 广东电网有限责任公司江门供电局 | Transformer model measurement analysis method |
| CN114492636A (en) * | 2022-01-26 | 2022-05-13 | 上海交通大学 | Transformer winding state signal acquisition system |
| WO2022147853A1 (en) * | 2021-01-11 | 2022-07-14 | 大连理工大学 | Complex equipment power pack fault prediction method based on hybrid prediction model |
-
2019
- 2019-05-05 CN CN201910366173.8A patent/CN110221139A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| 国家电网公司武汉高压研究所: "《电力监测与故障诊断技术全书 变压器、电抗器、互感器卷 下》", 30 September 2005 * |
| 李祥飞等: "一种检测电力变压器局放信号的离散小波算法", 《中南工业大学学报》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766059A (en) * | 2019-10-14 | 2020-02-07 | 四川西部能源股份有限公司郫县水电厂 | Transformer fault prediction method, device and equipment |
| CN110726957A (en) * | 2019-11-05 | 2020-01-24 | 国网江苏省电力有限公司宜兴市供电分公司 | Fault identification method of dry-type reactor |
| CN110929769A (en) * | 2019-11-14 | 2020-03-27 | 保定赛瑞电力科技有限公司 | Reactor mechanical fault joint detection model, method and device based on vibration and sound |
| CN110929769B (en) * | 2019-11-14 | 2023-02-10 | 国网吉林省电力有限公司超高压公司 | Reactor mechanical fault joint detection model, method and device based on vibration and sound |
| CN111830893A (en) * | 2019-12-03 | 2020-10-27 | 上海稳擎科技有限公司 | Equipment operation and maintenance monitoring system |
| CN111398723A (en) * | 2020-04-17 | 2020-07-10 | 上海数深智能科技有限公司 | Intelligent transformer fault diagnosis model method |
| CN111488947A (en) * | 2020-04-28 | 2020-08-04 | 深圳力维智联技术有限公司 | Fault detection method and device for power system equipment |
| CN111488947B (en) * | 2020-04-28 | 2024-02-02 | 深圳力维智联技术有限公司 | Fault detection method and device for power system equipment |
| CN111706499B (en) * | 2020-06-09 | 2022-03-01 | 成都数之联科技有限公司 | Predictive maintenance system and method for vacuum pump and automatic vacuum pump purchasing system |
| CN111706499A (en) * | 2020-06-09 | 2020-09-25 | 成都数之联科技有限公司 | Predictive maintenance system and method for vacuum pump and automatic vacuum pump purchasing system |
| WO2022000640A1 (en) * | 2020-06-28 | 2022-01-06 | 南京东创信通物联网研究院有限公司 | Monitoring and alarm system for transformer |
| CN112463362A (en) * | 2020-11-03 | 2021-03-09 | 江苏核电有限公司 | Multi-information edge calculation dry-type transformer fault mode identification system and method |
| CN112557793A (en) * | 2020-12-04 | 2021-03-26 | 广东电网有限责任公司 | Power plug-in health state detection method and device and storage medium |
| WO2022147853A1 (en) * | 2021-01-11 | 2022-07-14 | 大连理工大学 | Complex equipment power pack fault prediction method based on hybrid prediction model |
| CN112880740A (en) * | 2021-01-21 | 2021-06-01 | 上海迈内能源科技有限公司 | Transformer running state on-line monitoring system and multi-parameter intelligent sensor thereof |
| CN113553927A (en) * | 2021-07-08 | 2021-10-26 | 国网福建省电力有限公司福州供电公司 | Running state analysis method, system, server and medium of dry-type transformer |
| CN114034344A (en) * | 2021-11-12 | 2022-02-11 | 广东电网有限责任公司江门供电局 | Transformer model measurement analysis method |
| CN114492636A (en) * | 2022-01-26 | 2022-05-13 | 上海交通大学 | Transformer winding state signal acquisition system |
| CN114492636B (en) * | 2022-01-26 | 2023-11-24 | 上海交通大学 | Transformer winding state signal acquisition system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221139A (en) | A kind of failure prediction method of dry-type transformer, apparatus and system | |
| CN108591104B (en) | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN106698197B (en) | Container crane inline diagnosis and preventative maintenance system based on big data | |
| CN105809255B (en) | A kind of thermal power plant's rotating machinery health control method and system based on Internet of Things | |
| CN106006344B (en) | Staircase On-line Fault early warning system and method for diagnosing faults | |
| CN107515372A (en) | A kind of switchgear defect intelligent detection and analysis system | |
| CN108388950A (en) | Intelligent transformer O＆M method and system based on big data | |
| CN108375732A (en) | Motor monitoring and pre-alarming method and system | |
| CN107329079A (en) | A kind of primary cut-out on-line monitoring and synthetic fault diagnosis system | |
| CN107146018A (en) | Data Management Analysis method and system based on electric network state monitoring system | |
| CN108073551A (en) | A kind of high-tension switch cabinet on-line fault diagnosis method based on Multi-Agent model | |
| CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
| CN202404166U (en) | On-line monitoring system for vibration performance of transformer | |
| CN101825894A (en) | SF6 high-voltage circuit breaker state intelligent monitoring and health management system | |
| CN108689271A (en) | A kind of online elevator multiplies fortune quality detecting system and method | |
| CN102270879A (en) | Equipment audio monitoring system of unattended substation | |
| CN103901330A (en) | Partial discharge on-line monitoring method for XLPE cable | |
| CN201725208U (en) | Intelligent monitoring and health managing system for sulfur hexafluoride high-voltage circuit breaker state | |
| CN106154978A (en) | A kind of dynamic equipment condition monitoring and fault diagnosis security system | |
| CN114881808B (en) | Big data-based accurate identification method for electric power larceny and electric power larceny prevention system | |
| CN114383652A (en) | Method, system and device for identifying potential fault online risk of power distribution network | |
| CN107656156A (en) | A kind of equipment fault diagnosis and running status appraisal procedure and system based on cloud platform | |
| CN112363029A (en) | Equipment corona discharge online monitoring system and monitoring method thereof | |
| CN105158610B (en) | A kind of screening processing method of transformer state warning data dubious value |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
| RJ01 | Rejection of invention patent application after publication |