CN110007171A - The screening method and system of transformer online monitoring data false alarm - Google Patents
The screening method and system of transformer online monitoring data false alarm Download PDFInfo
- Publication number
- CN110007171A CN110007171A CN201910265766.5A CN201910265766A CN110007171A CN 110007171 A CN110007171 A CN 110007171A CN 201910265766 A CN201910265766 A CN 201910265766A CN 110007171 A CN110007171 A CN 110007171A
- Authority
- CN
- China
- Prior art keywords
- transformer
- online monitoring
- monitoring data
- data
- failure
- 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
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
A kind of screening method of transformer online monitoring data false alarm of the present invention, comprising the following steps: obtain online monitoring data when transformer is in failure；Based on the online monitoring data got, the incidence relation between transformer online monitoring data transformers on-line monitoring amount is obtained；According to the incidence relation between transformer online monitoring amount, the characteristic feature of online monitoring data when identifying transformer fault, online monitoring data screening when being in failure based on characteristic feature analysis transformer go out to lead to the online monitoring data exceptional value of false alarm.The present invention is based on the strong incidence relations that Apriori association rule algorithm excavates each on-line monitoring amount, on-line monitoring when transformer fault with incidence relation measure its development trend answer it is with uniformity, it can determine whether that data outliers problem is caused by non-transformer fault reason if being unsatisfactory for the requirement, the screening that transformer online monitoring data outliers are realized with this avoids consequent malfunction diagnosis misjudgement, erroneous judgement.
Description
Technical field
The present invention relates to transformer big data technical field more particularly to a kind of transformer online monitoring data false alarms
Screening method and system.
Background technique
With the development of science and technology, entire power grid is just strided forward towards the direction of intelligent, information-based, networking and safe,
Also developing towards the direction as the core hub device transformer in power grid.For responsive message, intelligence, networking
And the development trend of safe, more and more sensors and monitoring device have been added on transformer, have been collected by analysis
The abnormal conditions of online monitoring data can carry out status assessment and fault diagnosis to transformer.However in addition to transformer is true
It breaks down and can lead to online monitoring data more than threshold value and other than alarming, degradation failure, the data of sensor and monitoring device
Exception, the external environmental interference etc. that transmission process occurs will also result in collected online monitoring data, and there are outlier problems.
If data outliers problem caused by these situations cannot be effectively handled, it will the occurrence of leading to false alarm, or even lead
Erroneous judgement, the misjudgement to transformer state are caused, Monitoring and forecasting system in real-time is hindered to play due effect, reduces operation maintenance personnel to transformer
The confidence of monitoring system.
Summary of the invention
The shortcomings that present invention is directed in the prior art, provide a kind of screening side of transformer online monitoring data false alarm
Method and system.
In order to solve the above-mentioned technical problem, the present invention is addressed by following technical proposals:
A kind of screening method of transformer online monitoring data false alarm, comprising the following steps:
Obtain online monitoring data when transformer is in failure；
Online monitoring data when analyzing the transformer fault got based on association rule algorithm is based on getting
Line monitoring data obtain the incidence relation between transformer online monitoring data transformers on-line monitoring amount；
According to the incidence relation between transformer online monitoring amount, the allusion quotation of online monitoring data when identifying transformer fault
Type feature, based on the characteristic feature analysis transformer be in failure when online monitoring data screening out cause false alarm
Line monitoring data exceptional value.
As an embodiment, the transformer online monitoring data include at least the gas data dissolved in oil
H2、CH4、C2H2、C2H4、C2H6、CO、CO2, oil temperature data, Partial Discharge Data.
As an embodiment,
The online monitoring data when transformer fault got is analyzed based on association rule algorithm, and it is online to obtain transformer
Incidence relation between monitoring quantity, specifically:
Online monitoring data when being in malfunction to collected transformer carries out boolean's sliding-model control, obtains phase
The threshold range answered；
Based on the threshold range obtained after boolean's sliding-model control, the transformer being collected into is in online prison when failure
Measured data establishes what online monitoring data library D i.e. association rule algorithm when transformer is in failure was analyzed as object is excavated
Library to be excavated, it is assumed that excavating in library has n group fault data, then D={ T1, T2 ..., Tn }, for each affairs T, then by 9
Line monitoring data composition, here, affairs T is the intersection of fault data, T={ I1, I2 ..., I9 }, wherein Ii indication transformer
The random subset A of value of the on-line monitoring amount after boolean's sliding-model control, T is known as item collection；
The calculation method of support and confidence level is defined, minimum support threshold value and Minimum confidence threshold are set；
Online monitoring data library D when scanning the transformer fault obtains 1 rank candidate and obtains corresponding support
Degree determines the frequent candidate of 1 rank for being greater than minimum support threshold value according to the minimum support threshold value of setting, by closing two-by-two
And 1 rank, 2 rank candidates of frequent candidate formation, it obtains support and 2 ranks is determined according to the minimum support threshold value of setting
Frequent candidate recycles this process, until reaching maximum number of iterations or again without new frequent item set, determining frequent episode
Collection；
The confidence level of the frequent item set is calculated, and defeated from affiliated frequent item set according to the Minimum confidence threshold of setting
It is greater than the correlation rule of Minimum confidence threshold out, the correlation rule of the output is that the association between online monitoring data is closed
System.
As an embodiment, the calculation method for defining support and confidence level, specific as follows:
For item collection A, the support is defined as:
ForCorrelation rule, the support is defined as:
ForCorrelation rule, the confidence level is defined as:
As an embodiment, the on-line monitoring analyzed based on the characteristic feature when transformer is in failure
Data screening goes out to lead to the online monitoring data exceptional value of false alarm, specifically: transformer is in on-line monitoring number when failure
According to characteristic feature and transformer be in failure when the online monitoring data development trend having the same of incidence relation that has.
A kind of screening system of transformer online monitoring data false alarm, including data acquisition module, incidence relation obtain
Module and anomaly analysis module；
The data acquisition module, for obtaining online monitoring data when transformer is in failure；
The incidence relation obtains module, when for analyzing the transformer fault got based on association rule algorithm
Line monitoring data are obtained between transformer online monitoring data transformers on-line monitoring amount based on the online monitoring data got
Incidence relation；
The anomaly analysis module, for identifying transformer according to the incidence relation between transformer online monitoring amount
The characteristic feature of online monitoring data when failure is in on-line monitoring number when failure based on characteristic feature analysis transformer
Go out to lead to the online monitoring data exceptional value of false alarm according to screening.
As an embodiment, the data acquisition module is used for:
The transformer online monitoring data include at least the gas data H dissolved in oil2、CH4、C2H2、C2H4、C2H6、
CO、CO2, oil temperature data, Partial Discharge Data.
As an embodiment, the incidence relation obtains module and is arranged to:
Online monitoring data when being in failure to collected transformer carries out boolean's sliding-model control, obtains corresponding
Threshold range；
Based on the threshold range obtained after boolean's sliding-model control, the transformer being collected into is in online prison when failure
Measured data establishes what online monitoring data library D i.e. association rule algorithm when transformer is in failure was analyzed as object is excavated
Library to be excavated, it is assumed that excavating in library has n group fault data, then D={ T1, T2 ..., Tn }, for each affairs T, then by 9
Line monitoring data composition, here, affairs T is the intersection of fault data, T={ I1, I2 ..., I9 }, wherein Ii indication transformer
The random subset A of value of the on-line monitoring amount after boolean's sliding-model control, T is known as item collection；
The calculation method of support and confidence level is defined, minimum support threshold value and Minimum confidence threshold are set；
Online monitoring data library D when scanning the transformer fault obtains 1 rank candidate and obtains corresponding support
Degree determines the frequent candidate of 1 rank for being greater than minimum support threshold value according to the minimum support threshold value of setting, by closing two-by-two
And 1 rank, 2 rank candidates of frequent candidate formation, it obtains support and 2 ranks is determined according to the minimum support threshold value of setting
Frequent candidate recycles this process, until reaching maximum number of iterations or again without new frequent item set, determining frequent episode
Collection；
The confidence level of the frequent item set is calculated, and defeated from affiliated frequent item set according to the Minimum confidence threshold of setting
It is greater than the correlation rule of Minimum confidence threshold out, the correlation rule of the output is that the association between online monitoring data is closed
System.
As an embodiment, the incidence relation obtains module and is arranged to:
For item collection A, the support is defined as:
ForCorrelation rule, the support is defined as:
ForCorrelation rule, the confidence level is defined as:
As an embodiment, the incidence relation obtains module and is arranged to: when transformer is in failure
The online monitoring data for the incidence relation that the characteristic feature of line monitoring data has when being in failure with transformer is having the same
Development trend.
The present invention is due to using above technical scheme, with significant technical effect:
The incidence relation between transformer online monitoring amount is excavated the present invention is based on Apriori association rule algorithm to carry out online
Monitoring data outlier detection significantly improves the confidence level of online monitoring data, improves transformer operation maintenance personnel to online
The confidence of monitoring system；The quality of online monitoring data can be effectively ensured, be the basis of subsequent data analysis and status assessment；Energy
Success separates outlier problem caused by external other factors from data exception caused by transformer fault, captures
The exceptional values problem such as other external disturbances, it is ensured that the accuracy of subsequent data analysis.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is overall flow schematic diagram of the invention；
Fig. 2 is overall structure diagram of the invention.
Specific embodiment
The present invention will be further described in detail below with reference to the embodiments, following embodiment be explanation of the invention and
The invention is not limited to following embodiments.
Embodiment 1:
A kind of screening method of transformer online monitoring data false alarm, as shown in Figure 1, comprising the following steps:
S100, online monitoring data when transformer is in failure is obtained；
S200, based on association rule algorithm analyze get transformer fault when online monitoring data be based on get
Online monitoring data, obtain the incidence relation between transformer online monitoring data transformers on-line monitoring amount；
S300, according to the incidence relation between transformer online monitoring amount, monitor number on-line when identifying transformer fault
According to characteristic feature, based on the characteristic feature analysis transformer be in failure when online monitoring data screening out cause to report by mistake
Alert online monitoring data exceptional value.
In the prior art, transformer, which breaks down, can lead to online monitoring data more than threshold value and other than alarming, sensor
Exception, the external environmental interference etc. occurred with the degradation failure of monitoring device, data transmission procedure will also result in it is collected
There are outlier problems for line monitoring data, if data outliers problem caused by these situations cannot be effectively handled, it will lead
The occurrence of causing false alarm even results in erroneous judgement, misjudgement to transformer state, hinders Monitoring and forecasting system in real-time to play due
Effect reduces operation maintenance personnel to the confidence of transformer monitoring systems.The purpose of the application is exactly in order to solve problem above, to provide
A kind of screening method of transformer online monitoring data false alarm.The application is based on Apriori association rule algorithm and excavates respectively
The incidence relation of on-line monitoring amount, the on-line monitoring when transformer fault with incidence relation, which measures its development trend, should have one
Cause property, can determine whether that data outliers problem is caused by non-transformer fault reason if being unsatisfactory for the requirement, realizes transformation with this
The screening of device online monitoring data exceptional value avoids consequent malfunction diagnosis misjudgement, erroneous judgement.
In the step s 100, the transformer online monitoring data include at least the gas data H dissolved in oil2、CH4、
C2H2、C2H4、C2H6、CO、CO2, oil temperature data, Partial Discharge Data.
In step s 200, incidence relation is the pass that each online monitoring data is excavated using Apriori association rule algorithm
Connection relationship, described that incidence relation between transformer online monitoring data is obtained based on the volume online monitoring data got, tool
Body are as follows:
Online monitoring data when being in failure to collected transformer carries out boolean's sliding-model control, obtains corresponding
Threshold range；
Based on the threshold range obtained after boolean's sliding-model control, the transformer being collected into is in online prison when failure
Measured data establishes what online monitoring data library D i.e. association rule algorithm when transformer is in failure was analyzed as object is excavated
Library to be excavated, it is assumed that excavating in library has n group fault data, then D={ T1, T2 ..., Tn }, for each affairs T, then by 9
Line monitoring data composition, here, affairs T is the intersection of fault data, T={ I1, I2 ..., I9 }, wherein Ii indication transformer
The random subset A of value of the on-line monitoring amount after boolean's sliding-model control, T is known as item collection；
The calculation method of support and confidence level is defined, minimum support threshold value and Minimum confidence threshold are set；
Online monitoring data library D when scanning the transformer fault obtains 1 rank candidate and obtains corresponding support
Degree determines the frequent candidate of 1 rank for being greater than minimum support threshold value according to the minimum support threshold value of setting, by closing two-by-two
And 1 rank, 2 rank candidates of frequent candidate formation, it obtains support and 2 ranks is determined according to the minimum support threshold value of setting
Frequent candidate recycles this process, until reaching maximum number of iterations or again without new frequent item set, determining frequent episode
Collection；
The confidence level of the frequent item set is calculated, and defeated from affiliated frequent item set according to the Minimum confidence threshold of setting
It is greater than the correlation rule of Minimum confidence threshold out, the correlation rule of the output is that the association between online monitoring data is closed
System.
In this application, defining online monitoring data within the scope of normality threshold is 0, is otherwise 1, the following table 1 lists change
Boolean's discretization reference standard of each online monitoring data of depressor；
1. transformer online monitoring amount boolean's discretization reference standard of table
More specifically, in step s 200, the calculation method for defining support and confidence level, specific as follows:
For item collection A, the support is defined as:
ForCorrelation rule, the support is defined as:
ForCorrelation rule, the confidence level is defined as:
In step S300, the online monitoring data sieve analyzed based on the characteristic feature when transformer is in failure
The online monitoring data exceptional value for leading to false alarm is found, specifically: the allusion quotation of online monitoring data when transformer is in failure
Type feature and transformer are in the online monitoring data development trend having the same for the incidence relation having when failure.
It is assumed that as when going out transformer fault by association rule mining between oil temperature and acetylene there are incidence relation, when If then oil temperature is more than threshold value when transformer fault, corresponding acetylene contains
Amount also can be more than threshold value.If temperature of oil in transformer is more than threshold value at this time, but observes discovery acetylene and be less than threshold value, then can exclude
Transformer fault causes oil temperature abnormal, should check that oil temperature sensor does further investigation.
Method of the invention excavates the strong incidence relation of each on-line monitoring amount based on Apriori association rule algorithm, works as change
On-line monitoring when depressor failure with incidence relation measures its development trend and answers with uniformity, can sentence if being unsatisfactory for the requirement
Disconnected data outliers problem is caused by non-transformer fault reason, and the sieve of transformer online monitoring data outliers is realized with this
It looks into, avoids consequent malfunction diagnosis misjudgement, erroneous judgement.
Embodiment 2:
A kind of screening system of transformer online monitoring data false alarm, as shown in Fig. 2, include data acquisition module 100,
Incidence relation obtains module 200 and anomaly analysis module 300；
The data acquisition module 100, for obtaining online monitoring data when transformer is in failure；
The incidence relation obtains module 200, when for analyzing the transformer fault got based on association rule algorithm
Online monitoring data based on the online monitoring data got, obtain transformer online monitoring data transformers on-line monitoring amount
Between incidence relation；
The anomaly analysis module 300, for identifying transformation according to the incidence relation between transformer online monitoring amount
The characteristic feature of online monitoring data when device failure is in on-line monitoring when failure based on characteristic feature analysis transformer
Data screening goes out to lead to the online monitoring data exceptional value of false alarm.
More specifically, the data acquisition module 100 is used for: the transformer online monitoring data include at least oil
The gas data H of middle dissolution2、CH4、C2H2、C2H4、C2H6、CO、CO2, oil temperature data, Partial Discharge Data.
The incidence relation obtains module 200 and is arranged to: on-line monitoring when failure is in collected transformer
Data carry out boolean's sliding-model control, obtain corresponding threshold range；
Based on the threshold range obtained after boolean's sliding-model control, the transformer being collected into is in online prison when failure
Measured data establishes what online monitoring data library D i.e. association rule algorithm when transformer is in failure was analyzed as object is excavated
Library to be excavated, it is assumed that excavating in library has n group fault data, then D={ T1, T2 ..., Tn }, for each affairs T, then by 9
Line monitoring data composition, here, affairs T is the intersection of fault data, T={ I1, I2 ..., I9 }, wherein Ii indication transformer
The random subset A of value of the on-line monitoring amount after boolean's sliding-model control, T is known as item collection；
The calculation method of support and confidence level is defined, minimum support threshold value and Minimum confidence threshold are set；
Online monitoring data library D when scanning the transformer fault obtains 1 rank candidate and obtains corresponding support
Degree determines the frequent candidate of 1 rank for being greater than minimum support threshold value according to the minimum support threshold value of setting, by closing two-by-two
And 1 rank, 2 rank candidates of frequent candidate formation, it obtains support and 2 ranks is determined according to the minimum support threshold value of setting
Frequent candidate recycles this process, until reaching maximum number of iterations or again without new frequent item set, determining frequent episode
Collection；
The confidence level of the frequent item set is calculated, and defeated from affiliated frequent item set according to the Minimum confidence threshold of setting
It is greater than the correlation rule of Minimum confidence threshold out, the correlation rule of the output is that the association between online monitoring data is closed
System.
In this application, defining online monitoring data within the scope of normality threshold is 0, is otherwise 1, the following table 2 lists change
Boolean's discretization reference standard of each online monitoring data of depressor；
2. transformer online monitoring amount boolean's discretization reference standard of table
For above step, more specifically, the incidence relation obtains module 200 and is arranged to: for item collection A, institute
State support is defined as:
ForCorrelation rule, the support is defined as:
ForCorrelation rule, the confidence level is defined as:
Further, the incidence relation obtains module 300 and is arranged to: transformer is in on-line monitoring when failure
The development having the same of the online monitoring data for the incidence relation that the characteristic feature of data has when being in failure with transformer becomes
Gesture.
It is assumed that as when going out transformer fault by association rule mining between oil temperature and acetylene there are incidence relation, when If then oil temperature is more than threshold value when transformer fault, corresponding acetylene contains
Amount also can be more than threshold value.If temperature of oil in transformer is more than threshold value at this time, but observes discovery acetylene and be less than threshold value, then can exclude
Transformer fault causes oil temperature abnormal, should check that oil temperature sensor does further investigation.
System of the invention excavates the strong incidence relation of each on-line monitoring amount based on Apriori association rule algorithm, works as change
On-line monitoring when depressor failure with incidence relation measures its development trend and answers with uniformity, can sentence if being unsatisfactory for the requirement
Disconnected data outliers problem is caused by non-transformer fault reason, and the sieve of transformer online monitoring data outliers is realized with this
It looks into, avoids consequent malfunction diagnosis misjudgement, erroneous judgement.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, apparatus or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the present invention, the flow chart of terminal device (system) and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminal devices with
A machine is generated, so that generating by the instruction that computer or the processor of other programmable data processing terminal devices execute
For realizing the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram
Device.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
It should be understood that
" one embodiment " or " embodiment " mentioned in specification means the special characteristic described in conjunction with the embodiments, structure
Or characteristic is included at least one embodiment of the present invention.Therefore, the phrase " reality that specification various places throughout occurs
Apply example " or " embodiment " the same embodiment might not be referred both to.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
In addition, it should be noted that, the specific embodiments described in this specification, the shape of parts and components are named
Title etc. can be different.The equivalent or simple change that all structure, feature and principles described according to the invention patent design are done, is wrapped
It includes in the scope of protection of the patent of the present invention.Those skilled in the art can be to described specific implementation
Example is done various modifications or additions or is substituted in a similar manner, and without departing from structure of the invention or surmounts this
Range as defined in the claims, is within the scope of protection of the invention.
Claims (10)
1. a kind of screening method of transformer online monitoring data false alarm, which comprises the following steps:
Obtain online monitoring data when transformer is in failure；
The online monitoring data when transformer fault got is analyzed based on association rule algorithm, obtains transformer online monitoring
Incidence relation between amount；
According to the incidence relation between transformer online monitoring amount, the typical case of online monitoring data is special when identifying transformer fault
Sign, online monitoring data screening when being in failure based on characteristic feature analysis transformer go out to lead to the online prison of false alarm
Measured data exceptional value.
2. the screening method of transformer online monitoring data false alarm according to claim 1, which is characterized in that the change
Depressor online monitoring data includes at least the gas data H dissolved in oil2、CH4、C2H2、C2H4、C2H6、CO、CO2, oil temperature data,
Partial Discharge Data.
3. the screening method of transformer online monitoring data false alarm according to claim 1, which is characterized in that based on pass
Connection rule-based algorithm analyzes the online monitoring data when transformer fault got, obtains the pass between transformer online monitoring amount
Connection relationship, specifically:
Online monitoring data when being in malfunction to collected transformer carries out boolean's sliding-model control, obtains corresponding
Threshold range；
Based on the threshold range obtained after boolean's sliding-model control, the transformer being collected into is in on-line monitoring number when failure
According to as object is excavated, establishing that online monitoring data library D i.e. association rule algorithm when transformer be in failure analyzes wait dig
Dig library, it is assumed that excavating in library has n group fault data, then D={ T1, T2 ..., Tn }, for each affairs T, then by 9 online prisons
Measured data composition, here, affairs T is the intersection of fault data, T={ I1, I2 ..., I9 }, wherein Ii indication transformer is online
The random subset A of value of the monitoring quantity after boolean's sliding-model control, T is known as item collection；
The calculation method of support and confidence level is defined, minimum support threshold value and Minimum confidence threshold are set；
Online monitoring data library D when scanning the transformer fault obtains 1 rank candidate and obtains corresponding support, root
The frequent candidate of 1 rank for being greater than minimum support threshold value is determined according to the minimum support threshold value of setting, by merging 1 rank two-by-two
Frequent candidate forms 2 rank candidates, obtains support and determines that 2 ranks are frequently waited according to the minimum support threshold value of setting
Set of choices recycles this process, until reaching maximum number of iterations or again without new frequent item set, determining frequent item set；
The confidence level of the frequent item set is calculated, and is exported from affiliated frequent item set greatly according to the Minimum confidence threshold of setting
In the correlation rule of Minimum confidence threshold, the correlation rule of the output is the incidence relation between online monitoring data.
4. the screening method of transformer online monitoring data false alarm according to claim 3, which is characterized in that described fixed
The calculation method of adopted support and confidence level, specific as follows:
For item collection A, the support is defined as:
ForCorrelation rule, the support is defined as:
ForCorrelation rule, the confidence level is defined as:
5. the screening method of transformer online monitoring data false alarm according to claim 1, which is characterized in that the base
Online monitoring data screening when characteristic feature analysis transformer is in failure goes out to lead to the on-line monitoring number of false alarm
According to exceptional value, specifically: the characteristic feature of online monitoring data when transformer is in failure has when being in failure with transformer
The online monitoring data of some incidence relations development trend having the same.
6. a kind of screening system of transformer online monitoring data false alarm, which is characterized in that including data acquisition module, association
Relationship obtains module and anomaly analysis module；
The data acquisition module, for obtaining online monitoring data when transformer is in failure；
The incidence relation obtains module, for analyzing the online prison when transformer fault got based on association rule algorithm
Measured data obtains the incidence relation between transformer online monitoring amount；
The anomaly analysis module, for identifying transformer fault according to the incidence relation between transformer online monitoring amount
When online monitoring data characteristic feature, online monitoring data when be in failure based on characteristic feature analysis transformer sieves
Find the online monitoring data exceptional value for leading to false alarm.
7. the screening system of transformer online monitoring data false alarm according to claim 6, which is characterized in that the number
It is used for according to module is obtained:
The transformer online monitoring data include at least the gas data H dissolved in oil2、CH4、C2H2、C2H4、C2H6、CO、
CO2, oil temperature data, Partial Discharge Data.
8. the screening system of transformer online monitoring data false alarm according to claim 6, which is characterized in that the pass
Connection relationship obtains module and is arranged to:
Online monitoring data when being in failure to collected transformer carries out boolean's sliding-model control, obtains corresponding threshold value
Range；
Based on the threshold range obtained after boolean's sliding-model control, the transformer being collected into is in on-line monitoring number when failure
According to as object is excavated, establishing that online monitoring data library D i.e. association rule algorithm when transformer be in failure analyzes wait dig
Dig library, it is assumed that excavating in library has n group fault data, then D={ T1, T2 ..., Tn }, for each affairs T, then by 9 online prisons
Measured data composition, here, affairs T is the intersection of fault data, T={ I1, I2 ..., I9 }, wherein Ii indication transformer is online
The random subset A of value of the monitoring quantity after boolean's sliding-model control, T is known as item collection；
The calculation method of support and confidence level is defined, minimum support threshold value and Minimum confidence threshold are set；
Online monitoring data library D when scanning the transformer fault obtains 1 rank candidate and obtains corresponding support, root
The frequent candidate of 1 rank for being greater than minimum support threshold value is determined according to the minimum support threshold value of setting, by merging 1 rank two-by-two
Frequent candidate forms 2 rank candidates, obtains support and determines that 2 ranks are frequently waited according to the minimum support threshold value of setting
Set of choices recycles this process, until reaching maximum number of iterations or again without new frequent item set, determining frequent item set；
The confidence level of the frequent item set is calculated, and is exported from affiliated frequent item set greatly according to the Minimum confidence threshold of setting
In the correlation rule of Minimum confidence threshold, the correlation rule of the output is the incidence relation between online monitoring data.
9. the screening system of transformer online monitoring data false alarm according to claim 8, which is characterized in that the pass
Connection relationship obtains module and is arranged to:
For item collection A, the support is defined as:
ForCorrelation rule, the support is defined as:
ForCorrelation rule, the confidence level is defined as:
10. the screening system of transformer online monitoring data false alarm according to claim 6, which is characterized in that described
Online monitoring data screening when being in failure based on characteristic feature analysis transformer goes out to lead to the on-line monitoring of false alarm
Data outliers, specifically: when the characteristic feature and transformer of online monitoring data when transformer is in failure are in failure
The online monitoring data for the incidence relation having development trend having the same.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910265766.5A CN110007171A (en) | 2019-04-03 | 2019-04-03 | The screening method and system of transformer online monitoring data false alarm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910265766.5A CN110007171A (en) | 2019-04-03 | 2019-04-03 | The screening method and system of transformer online monitoring data false alarm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110007171A true CN110007171A (en) | 2019-07-12 |
Family
ID=67169641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910265766.5A Pending CN110007171A (en) | 2019-04-03 | 2019-04-03 | The screening method and system of transformer online monitoring data false alarm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110007171A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112763848A (en) * | 2020-12-28 | 2021-05-07 | 国网北京市电力公司 | Method and device for determining power system fault |
| CN114353869A (en) * | 2021-12-25 | 2022-04-15 | 华荣科技股份有限公司 | Online monitoring method and system for mobile equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080201772A1 (en) * | 2007-02-15 | 2008-08-21 | Maxim Mondaeev | Method and Apparatus for Deep Packet Inspection for Network Intrusion Detection |
| CN105891629A (en) * | 2016-03-31 | 2016-08-24 | 广西电网有限责任公司电力科学研究院 | Transformer equipment fault identification method |
| CN106557546A (en) * | 2016-10-20 | 2017-04-05 | 中国电力科学研究院 | A kind of method and system extra-high voltage online monitoring data excavated and is evaluated |
| CN106909664A (en) * | 2017-02-28 | 2017-06-30 | 国网福建省电力有限公司 | A kind of power equipment data stream failure recognition methods |
| CN108304349A (en) * | 2018-02-13 | 2018-07-20 | 贵州电网有限责任公司 | A kind of power transmission and transforming equipment characteristic parameter discretization method |
| CN109034604A (en) * | 2018-07-23 | 2018-12-18 | 长沙理工大学 | Distribution network fault association rule analysis method considering equipment state and air temperature |
-
2019
- 2019-04-03 CN CN201910265766.5A patent/CN110007171A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080201772A1 (en) * | 2007-02-15 | 2008-08-21 | Maxim Mondaeev | Method and Apparatus for Deep Packet Inspection for Network Intrusion Detection |
| CN105891629A (en) * | 2016-03-31 | 2016-08-24 | 广西电网有限责任公司电力科学研究院 | Transformer equipment fault identification method |
| CN106557546A (en) * | 2016-10-20 | 2017-04-05 | 中国电力科学研究院 | A kind of method and system extra-high voltage online monitoring data excavated and is evaluated |
| CN106909664A (en) * | 2017-02-28 | 2017-06-30 | 国网福建省电力有限公司 | A kind of power equipment data stream failure recognition methods |
| CN108304349A (en) * | 2018-02-13 | 2018-07-20 | 贵州电网有限责任公司 | A kind of power transmission and transforming equipment characteristic parameter discretization method |
| CN109034604A (en) * | 2018-07-23 | 2018-12-18 | 长沙理工大学 | Distribution network fault association rule analysis method considering equipment state and air temperature |
Non-Patent Citations (2)
| Title |
|---|
| 林峻 等: "考虑时间序列关联的变压器在线监测数据清洗", 《电网技术》 * |
| 郑元兵 等: "变压器故障特征量可信度的关联规则分析", 《高电压技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112763848A (en) * | 2020-12-28 | 2021-05-07 | 国网北京市电力公司 | Method and device for determining power system fault |
| CN114353869A (en) * | 2021-12-25 | 2022-04-15 | 华荣科技股份有限公司 | Online monitoring method and system for mobile equipment and readable storage medium |
| CN114353869B (en) * | 2021-12-25 | 2024-02-20 | 华荣科技股份有限公司 | Online monitoring method and system for mobile equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10235231B2 (en) | Anomaly fusion on temporal casualty graphs | |
| US8275735B2 (en) | Diagnostic system | |
| KR101713985B1 (en) | Method and apparatus for prediction maintenance | |
| JPH06236207A (en) | Method and apparatus for diagnosis of trouble | |
| CN109948808A (en) | The banking process in substation equipment fault case library, fault diagnosis method and system | |
| CN117114454B (en) | DC sleeve state evaluation method and system based on Apriori algorithm | |
| KR102319083B1 (en) | Artificial intelligence based fire prevention device and method | |
| JP4635194B2 (en) | Anomaly detection device | |
| JP7031743B2 (en) | Anomaly detection device | |
| CN112799898A (en) | Interconnection system fault node positioning method and system based on distributed fault detection | |
| CN106096789A (en) | A kind of based on machine learning techniques can be from the abnormal industry control security protection of perception and warning system | |
| CN117041029A (en) | Network equipment fault processing method and device, electronic equipment and storage medium | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| CN110007171A (en) | The screening method and system of transformer online monitoring data false alarm | |
| KR101444250B1 (en) | System for monitoring access to personal information and method therefor | |
| JP2010049359A (en) | Plant monitoring device and plant monitoring method | |
| CN116975728A (en) | Safety management method and system for coal bed methane drilling engineering | |
| Yu et al. | A continuous learning monitoring strategy for multi-condition of nuclear power plant | |
| CN106652393B (en) | False alarm determination method and device | |
| US12038742B2 (en) | Method for alarm handling in a processing system | |
| CN112769615B (en) | Anomaly analysis method and device | |
| CN112445684A (en) | Real-time fault diagnosis and early warning method and device and computer storage medium | |
| US11665193B2 (en) | Method for managing plant, plant design device, and plant management device | |
| CN114942364A (en) | Substation fault diagnosis method and system based on knowledge graph technology | |
| Singer et al. | A pattern-recognition-based, fault-tolerant monitoring and diagnostic technique |
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: 20190712 |
|
| RJ01 | Rejection of invention patent application after publication |