CN108491861A - Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device - Google Patents
Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device Download PDFInfo
- Publication number
- CN108491861A CN108491861A CN201810157181.7A CN201810157181A CN108491861A CN 108491861 A CN108491861 A CN 108491861A CN 201810157181 A CN201810157181 A CN 201810157181A CN 108491861 A CN108491861 A CN 108491861A
- Authority
- CN
- China
- Prior art keywords
- data
- power transmission
- abnormal
- state quantity
- sequence
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 140
- 230000005540 biological transmission Effects 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000009466 transformation Effects 0.000 title claims abstract description 52
- 230000004927 fusion Effects 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 claims abstract description 83
- 241001269238 Data Species 0.000 claims abstract description 10
- 230000015654 memory Effects 0.000 claims description 31
- 238000004891 communication Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 abstract description 38
- 230000005856 abnormality Effects 0.000 abstract description 4
- 239000011159 matrix material Substances 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 230000002547 anomalous effect Effects 0.000 description 8
- 238000005259 measurement Methods 0.000 description 6
- 230000001052 transient effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a kind of power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and devices, wherein method includes:Obtain primary monitoring data;Various state quantity datas are ranked up respectively sequentially in time;Judge whether each state quantity data is candidate abnormal data;When state quantity data is candidate abnormal data, the candidate abnormal data sequence at current time is generated;It when candidate abnormal data sequence does not meet the cluster feature of preset normal data, obtains comprising multiple monitoring data sequences in the first time period including current time, and judges whether corresponding power transmission and transforming equipment exception occurs according to multiple monitoring data sequences.The recognition methods of power transmission and transformation equipment state abnormal patterns and device provided in an embodiment of the present invention based on multi-source multi-parameter fusion effectively reduce the complexity of recognizer and data store and calculate required space, can be used for the fast and effective identification of all kinds of power transmission and transforming equipment abnormalities.
Description
Technical field
The present invention relates to Signal and Information Processing technical fields, and in particular to a kind of defeated change based on multi-source multi-parameter fusion
Electric equipment abnormal state mode identification method and device.
Background technology
Power transmission and transforming equipment is most important power system device, thus its condition monitoring and fault diagnosis be always very by
The technical field of concern.Current most on-Line Monitor Device is carried out to power transmission and transforming equipment using certain level threshold value
Condition adjudgement, only alarm signal is just sent out when monitoring data are more than certain judge value.Due to the operation of each power transmission and transforming equipment
There are difference for the testing principle and acquisition precision of environment and different device so that certain sensor on certain power transmission and transforming equipment is applicable in
Threshold value, will appear not applicable situation on another power transmission and transforming equipment, and then report by mistake.In addition, power transmission and transforming equipment
Status information data stream is by largely continuously reaching, potential endless, continually changing multi source status information data form has
Sequence time series.With power transmission and transformation equipment state monitor system and production management system improve and perfect and electric network information,
The real time fusion of environment weather information, it is big, successional that power transmission and transformation equipment state information related data shows number of data streams
Feature.The quick excavation of status information real-time stream exceptional value and study of warning, on the one hand need to a large amount of structurings of equipment
Data flow anomaly state is excavated in real time, is on the other hand needed to image, video, vibration (including waveform, fingerprint), partial discharge
The unstructured datas feature such as (including waveform, collection of illustrative plates) and test report is quickly identified.This allows for existing defeated change
The complexity of electric equipment condition monitoring and fault diagnosis algorithm is higher, and real-time is poor, cannot meet power generation to power transmission and transformation
The needs of power transmission and transforming equipment abnormality quickly and effectively identified.
Invention content
In view of this, an embodiment of the present invention provides a kind of, the power transmission and transformation equipment state based on multi-source multi-parameter fusion is abnormal
Mode identification method and device, to solve, complexity existing for existing power transmission and transforming equipment anomalous identification algorithm is higher, real-time
The poor and poor problem of versatility.
According in a first aspect, an embodiment of the present invention provides a kind of power transmission and transformation equipment states based on multi-source multi-parameter fusion
Abnormal patterns recognition methods, including:Primary monitoring data is obtained, includes various states amount data in the primary monitoring data;
The various state quantity datas are ranked up respectively sequentially in time, generate the time series number of each state quantity data
According to;Judge whether each state quantity data is candidate abnormal number according to the data that the sliding window of preset length acquires are used
According to;When the state quantity data is candidate abnormal data, the candidate abnormal data sequence at current time is generated;The candidate is different
Regular data sequence includes the various states amount data under current time;It is default to judge whether the candidate abnormal data sequence meets
Normal data cluster feature;When the candidate abnormal data sequence does not meet the cluster feature of preset normal data,
It obtains comprising multiple monitoring data sequences in the first time period including current time, and according to the multiple monitoring data sequence
Row judge whether corresponding equipment exception occurs;Each monitoring data sequence in the multiple monitoring data sequence includes same
The various states amount data inscribed for the moment.
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
The temporal characteristics of the Condition Monitoring Data of power transmission and transforming equipment, the multidimensional characteristic of multi-source many reference amounts are considered, from status monitoring
Real-time and validity set out, a single state amount data are analyzed using time-based sliding window model respectively first, are known
Candidate abnormal data not therein;Secondly the candidate abnormal data sequence of the corresponding multi-source many reference amounts of candidate abnormal data is carried out
Clustering recognition.Screened due to using one-dimensional data in the early period of power transmission and transforming equipment anomalous identification, filtered out it is most of just
Normal data so that subsequent step is only to there may be abnormal multidimensional datas to carry out clustering recognition, so that algorithm is answered
Miscellaneous degree greatly reduces, and is conducive to the timely processing to real time data and identification.Due to the status information sample rate of power transmission and transforming equipment
It is very high so that the storage of primary monitoring data needs sizable memory space and processing space.The embodiment of the present invention provides
The power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion effectively reduce the complexity of recognizer
Space needed for degree and data storage and calculating, can be used for the fast and effective identification of all kinds of power transmission and transforming equipment abnormalities.In addition,
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion, by default
The cluster feature of normal data the Condition Monitoring Data of power transmission and transforming equipment is identified, there is stronger versatility.In reality
In the application of border, migration can be conveniently realized by replacing the cluster feature of preset normal data, be set with adapting to other power transmission and transformation
Standby operating mode.
With reference to first aspect, it in first aspect first embodiment, is acquired according to the sliding window of preset length is used
Data judge whether each state quantity data is candidate abnormal data, including:It is acquired using the sliding window of preset length
Include the data of multiple data points in second time period including current time;It is calculated according to the data of the multiple data point
Corresponding Mass median number;It is pre- to judge whether the difference between the state quantity data at current time and the Mass median number is more than
If first threshold;When the difference between the state quantity data and the Mass median number at current time is more than preset first threshold
When value, judge the state quantity data at current time for candidate abnormal data.
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
First with sliding window in the time series data that each state quantity data is constituted gathered data, secondly adopted using sliding window
The data that collect calculate for judge state quantity data whether abnormal Mass median number, have the characteristics that using flexible.Due to
Sliding window is variable so that by the collected data of sliding window is also variable, so that judging to be used each time
Mass median number be also variable, enhance the flexibility of judgement and identification.
First embodiment with reference to first aspect calculates institute in first aspect second embodiment according to following formula
State Mass median number:
Wherein,
Bt=| d (xi,t)-d(xi,t- 1), d (xi,t)=| xi,t-av(xi,t-w,xi,t-(w-1),…,xi,t),Indicate described average
Median, xi,tIndicate that the numerical value of i-th of state quantity data under t moment, w indicate the duration of the second time period.
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
Using a period, as to calculate the period corresponding average for the same state quantity data under Each point in time in second time period
Median realizes using one-dimensional state quantity data to the preliminary screening of the primary monitoring data of power transmission and transforming equipment, is conducive to
Reduce the complexity of algorithm.
With reference to first aspect, in first aspect third embodiment, according to the judgement pair of the multiple monitoring data sequence
Answer whether equipment exception occurs, including:Judge whether the multiple monitoring data sequence meets preset normal data respectively
Cluster feature;Count the quantity for the cluster feature that preset normal data is not met in the multiple monitoring data sequence;Judge
Whether the quantity of the cluster feature for not meeting preset normal data is more than preset second threshold;When it is described do not meet it is pre-
If the quantity of cluster feature of normal data when being more than preset second threshold, it is abnormal to judge that corresponding equipment occurs.
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
By judging whether monitoring data sequence exception and counts the quantity of abnormal monitoring data sequence one by one, and then determine power transmission and transformation
Whether equipment is abnormal, can avoid that single monitoring data sequence error in judgement is improved power transmission and transformation and set caused by noise spot
The accuracy of standby anomalous identification.
With reference to first aspect or any one of first aspect second embodiment-third embodiment embodiment, exist
In the 4th embodiment of first aspect, after the candidate abnormal data sequence for generating current time, and the candidate is judged
Before whether abnormal data sequence meets the cluster feature of preset normal data, further include:To the candidate abnormal data sequence
Row are standardized.
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
The excessive difference of each different types of measurement object numerically in candidate abnormal data sequence is eliminated by standardization,
The measurement object for avoiding certain numerical value smaller is annihilated in follow-up calculate, to lose it in power transmission and transforming equipment anomalous identification side
The function in face.In numerous monitoring data of power transmission and transforming equipment, each characteristic variable is there are attribute difference and has different measurements
Standard, if not pre-processed to the candidate abnormal data sequence being made of primary monitoring data, certain codomains are opposite
The attribute of smaller characteristic quantity in space is easy to be covered by the larger characteristic quantity of codomain.
4th embodiment with reference to first aspect, in the 5th embodiment of first aspect, according to following formula to described
Candidate abnormal data sequence is standardized:
Wherein,ci,fIndicate that normalized that treated is candidate different
The numerical value of i-th of state quantity data in regular data sequence, and ci,fThe corresponding time is f;xi,fIt indicates to inscribe when f candidate abnormal
The numerical value of i-th of state quantity data in data sequence.
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
Candidate abnormal data sequence is standardized using formula, reduces each quantity of state number in candidate abnormal data sequence
According to the difference in codomain, avoid the attribute of the relatively small characteristic quantity of certain codomains in space by the larger characteristic quantity of codomain
It is covered, is conducive to the accuracy for improving power transmission and transforming equipment anomalous identification.
According to second aspect, an embodiment of the present invention provides a kind of power transmission and transformation equipment states based on multi-source multi-parameter fusion
Abnormal patterns identification device, including:Input unit includes more in the primary monitoring data for obtaining primary monitoring data
Kind state quantity data;And it for being ranked up respectively to the various state quantity datas sequentially in time, generates each described
The time series data of state quantity data;First judging unit, for according to the number for using the sliding window of preset length to acquire
It is judged that whether each state quantity data is candidate abnormal data;When the state quantity data is candidate abnormal data, institute
It states the first judging unit to be additionally operable to generate the candidate abnormal data sequence at current time, candidate's abnormal data sequence includes working as
The various states amount data inscribed when preceding;Second judgment unit, for judging it is pre- whether the candidate abnormal data sequence meets
If normal data cluster feature;When the candidate abnormal data sequence does not meet the cluster feature of preset normal data
When, the second judgment unit is additionally operable to obtain multiple monitoring data sequences comprising in the first time period including current time
Row, and judge whether corresponding power transmission and transforming equipment exception, the multiple monitoring data occurs according to the multiple monitoring data sequence
Each monitoring data sequence in sequence includes the various states amount data under synchronization.
According to the third aspect, an embodiment of the present invention provides a kind of servers, including:At least one processor;And with
The memory of at least one processor communication connection;Wherein, be stored with can be by least one processing for the memory
The instruction that device executes, described instruction are executed by least one processor, so that at least one processor executes first
The power transmission and transformation equipment state based on multi-source multi-parameter fusion described in any one of aspect or first aspect embodiment
Abnormal patterns recognition methods.
It is described computer-readable an embodiment of the present invention provides a kind of computer readable storage medium according to fourth aspect
Storage medium stores computer instruction, and the computer instruction is for making the computer execute first aspect or first aspect
Any one embodiment described in the power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion.
Description of the drawings
The features and advantages of the present invention can be more clearly understood by reference to attached drawing, attached drawing is schematically without that should manage
Solution is carries out any restrictions to the present invention, in the accompanying drawings:
Fig. 1 shows that the power transmission and transformation equipment state abnormal patterns based on multi-source multi-parameter fusion in the embodiment of the present invention are known
The flow chart of one specific example of other method;
Fig. 2 shows the power transmission and transformation equipment state abnormal patterns knowledges based on multi-source multi-parameter fusion in the embodiment of the present invention
Step S103 is according to using the data that the sliding window of preset length acquires to judge whether each state quantity data is time in other method
Select the flow chart of a specific example of abnormal data;
Fig. 3 shows that the power transmission and transformation equipment state abnormal patterns based on multi-source multi-parameter fusion in the embodiment of the present invention are known
Step S201 is acquired using the sliding window of preset length comprising more in the second time period including current time in other method
The processing schematic diagram of one specific example of the data of a data point;
Fig. 4 shows that the power transmission and transformation equipment state abnormal patterns based on multi-source multi-parameter fusion in the embodiment of the present invention are known
Step S106 judges whether corresponding equipment an abnormal specific example occurs according to multiple monitoring data sequences in other method
Flow chart;
Fig. 5 shows that the power transmission and transformation equipment state abnormal patterns based on multi-source multi-parameter fusion in the embodiment of the present invention are known
The structural schematic diagram of one specific example of other device;
Fig. 6 shows the structural schematic diagram of a specific example of the server in the embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
There is the every other embodiment obtained under the premise of making creative work, shall fall within the protection scope of the present invention.
The power transmission and transformation equipment state abnormal patterns identification based on multi-source multi-parameter fusion that an embodiment of the present invention provides a kind of
Method, as shown in Figure 1, should power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion may include with
Lower step:
Step S101:Obtain primary monitoring data.Include various states amount data in primary monitoring data.It is specific real one
Apply in mode, by taking the anomalous identification of transformer equipment as an example, the primary monitoring data of acquisition may include for temperature, humidity,
CH4、C2H2、C2H6, the various states amount such as CO and total hydrocarbon detection and analysis data.
Step S102:Various state quantity datas are ranked up respectively sequentially in time, generate each state quantity data
Time series data.It, can be by each shape due to including various states amount data in the primary monitoring data of power transmission and transforming equipment
State amount data are ranked up and build corresponding time series respectively, and build a matrix using each time series, realize
To the statistics of the primary monitoring data of power transmission and transforming equipment.In a specific embodiment, whithin a period of time, a certain power transmission and transformation are set
Standby m members primary monitoring data can use the matrix in following formula (1) to indicate:
As shown in formula (1), matrix X (t) is by m time series X1(t)、X2(t)…Xm(t) it forms, corresponding power transmission and transformation are set
Standby m kind quantity of states.By formula (1) can easily extract power transmission and transforming equipment when a length of n time period t1~tnInterior original
Beginning monitoring data, every a line of matrix X (t) indicate that the time series of a state quantity data, each row of matrix X (t) indicate
Some time inscribes one group of primary monitoring data of power transmission and transforming equipment.
Step S103:Judge whether each state quantity data is time according to the data that the sliding window of preset length acquires are used
Select abnormal data.In a specific embodiment, using sliding window respectively to each state quantity data in matrix X (t)
Time series handled, to identify the candidate abnormal data in each time series.Fig. 2 shows step S103 according to making
The data acquired with the sliding window of preset length judge each state quantity data whether be candidate abnormal data specific method, should
Method includes the following steps:
Step S201:Using the sliding window acquisition of preset length comprising more in the second time period including current time
The data of a data point.With the time series X in matrix X (t)1(t) for, as shown in figure 3, SW [t-w:T] it is data flow X1
(t) sliding window that a time interval on is w, the unit of wherein t and w is identical, and t > w.xt-w,xt-w+1,...,xt-1,
xtFor the data point that length of window is w continuous sampling in the sliding window of w.Since initial time, sliding window successively with
Unit interval is slided with time shaft, until traversal full number is according to stream sequence X1(t).Wherein, second time period is that window is long
Degree is w.
Step S202:Corresponding Mass median number is calculated according to the data of multiple data points.In a specific embodiment,
Mass median number is calculated according to following formula (2):
Wherein,
Bt=| d (xi,t)-d(xi,t-1), d (xi,t)=| xi,t-av(xi,t-w,xi,t-(w-1),…,xi,t),Indicate Mass median number,
xi,tIndicate that the numerical value of i-th of state quantity data under t moment, w indicate the duration of second time period.
Step S203:It is preset to judge whether the difference between the state quantity data at current time and Mass median number is more than
First threshold.
Step S204:When the difference between the state quantity data and Mass median number at current time is more than preset first threshold
When value, judge the state quantity data at current time for candidate abnormal data.In a specific embodiment, τ is set as the first threshold
Value, ifThen sliding window moves backward a unit along time series;IfThen
Mark the data point x of t momenti,t, and by xi,tCandidate abnormal data set D is added, uses simultaneouslyInstead of the data point x of t momenti,t
To the distance d (x at data set space centeri,t)。
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
First with sliding window in the time series data that each state quantity data is constituted gathered data, secondly adopted using sliding window
The data that collect calculate for judge state quantity data whether abnormal Mass median number, have the characteristics that using flexible.Due to
Sliding window is variable so that by the collected data of sliding window is also variable, so that judging to be used each time
Mass median number be also variable, enhance the flexibility of judgement and identification.
Step S104:When state quantity data is candidate abnormal data, the candidate abnormal data sequence at current time is generated.
Candidate abnormal data sequence includes the various states amount data under current time.In a specific embodiment, as judgement xi,tFor
When candidate abnormal data, the corresponding row [x of t moment can be extracted in matrix X (t)1,t,x2,t,…,xi,t,…,xm,t]T, will
[x1,t,x2,t,…,xi,t,…,xm,t]TCandidate abnormal data sequence as current time t.
Step S105:Judge whether candidate abnormal data sequence meets the cluster feature of preset normal data.In a tool
In body embodiment, can be directed to all parameter normal conditions under historical data, by k-means algorithms to multivariate data into
The cluster Loop partition of row k, obtains normal data clustering cluster race Y and each of which cluster center, using clustering cluster race Y as it is preset just
The cluster feature of regular data.
Step S106:When candidate abnormal data sequence does not meet the cluster feature of preset normal data, acquisition includes
Multiple monitoring data sequences in first time period including current time, and judge that correspondence is defeated according to multiple monitoring data sequences
Whether transformer equipment there is exception.Each monitoring data sequence in multiple monitoring data sequences includes under synchronization
Various states amount data.When the cluster feature of candidate abnormal data sequence and preset normal data is not inconsistent, it is believed that wait
It selects abnormal data sequence that may characterize power transmission and transforming equipment and there is exception, but be noise spot there is also candidate abnormal data sequence
May, there is exception to confirm whether candidate abnormal data sequence characterizes power transmission and transforming equipment, can utilize preset normal
The cluster feature of data respectively pair with current time it is neighbouring other it is several when multiple monitoring data sequences for inscribing be identified,
And then judge within this period power transmission and transforming equipment whether operation exception.It in a specific embodiment, can be according to normal
The quantity k of clustering cluster determines the length of first time period in the clustering cluster race Y of data, such as before and after can choosing current time
Each k/2 monitoring data sequence.
In another specific implementation mode, gives step S106 and judge corresponding power transmission and transformation according to multiple monitoring data sequences
Whether equipment there is a kind of abnormal specific method, as shown in figure 4, this method may comprise steps of:
Step S401:Judge whether multiple monitoring data sequences meet the cluster feature of preset normal data respectively;
Step S402:Count the quantity for the cluster feature that preset normal data is not met in multiple monitoring data sequences;
Step S403:Judge whether the quantity for not meeting the cluster feature of preset normal data is more than preset second threshold
Value;
Step S404:When not meeting the quantity of cluster feature of preset normal data more than preset second threshold,
The corresponding equipment of judgement occurs abnormal.
When multiple continuous monitoring data sequences in abnormal candidate abnormal data sequence time adjacent segments are all or big
When majority is not belonging to k clustering cluster of preset normal data, it can be determined that abnormal operation shape occurs in the power transmission and transforming equipment
State can be inferred that the time of origin of power transmission and transforming equipment exception according to the generation time section of above-mentioned multiple monitoring data sequences.When
When only a few is not belonging to k clustering cluster of preset normal data in above-mentioned multiple monitoring data sequences, it is believed that
These abnormal monitoring data sequences are noise spot.In order to avoid erroneous judgement, need that second threshold is arranged, and utilize second threshold pair
Abnormal quantity in monitoring data sequence is judged.
In practical applications, the on-line monitoring project of power transmission and transforming equipment is often more, monitors the characteristic value of gained in numerical value
With often there is prodigious difference in measurement unit, this is allowed for may in candidate abnormal data sequence and monitoring data sequence
There is the phenomenon that data failure, such as the smaller measurement object of certain numerical value is annihilated in follow-up calculate, to lose its
Function in terms of power transmission and transforming equipment anomalous identification.In order to eliminate each different types of measurement object in candidate abnormal data sequence
Excessive difference numerically, in a specific embodiment, can according to following formula (3) to candidate abnormal data sequence into
Row standardization:
Wherein,ci,fIndicate that normalized that treated is candidate different
The numerical value of i-th of state quantity data in regular data sequence, and ci,fThe corresponding time is f;xi,fIt indicates to inscribe when f candidate abnormal
The numerical value of i-th of state quantity data in data sequence.
In addition to candidate abnormal data sequence needs are standardized to reduce in sequence each characteristic value in codomain
Larger difference outside, the monitoring data sequence in step S106 similarly needs standardization, can generate formula (1) institute
After the primary monitoring data matrix shown, each row in matrix are standardized respectively according to formula (3).
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion,
The temporal characteristics of the Condition Monitoring Data of power transmission and transforming equipment, the multidimensional characteristic of multi-source many reference amounts are considered, from status monitoring
Real-time and validity set out, a single state amount data are analyzed using time-based sliding window model respectively first, are known
Candidate abnormal data not therein;Secondly the candidate abnormal data sequence of the corresponding multi-source many reference amounts of candidate abnormal data is carried out
Clustering recognition.Screened due to using one-dimensional data in the early period of power transmission and transforming equipment anomalous identification, filtered out it is most of just
Normal data so that subsequent step is only to there may be abnormal multidimensional datas to carry out clustering recognition, so that algorithm is answered
Miscellaneous degree greatly reduces, and is conducive to the timely processing to real time data and identification.Due to the status information sample rate of power transmission and transforming equipment
It is very high so that the storage of primary monitoring data needs sizable memory space and processing space.The embodiment of the present invention provides
The power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion effectively reduce the complexity of recognizer
Space needed for degree and data storage and calculating, can be used for the fast and effective identification of all kinds of power transmission and transforming equipment abnormalities.In addition,
Power transmission and transformation equipment state abnormal patterns recognition methods provided in an embodiment of the present invention based on multi-source multi-parameter fusion, by default
The cluster feature of normal data the Condition Monitoring Data of power transmission and transforming equipment is identified, there is stronger versatility.In reality
In the application of border, migration can be conveniently realized by replacing the cluster feature of preset normal data, be set with adapting to other power transmission and transformation
Standby operating mode.
Correspondingly, referring to FIG. 5, the embodiment of the present invention additionally provides a kind of power transmission and transformation based on multi-source multi-parameter fusion sets
Standby abnormal state pattern recognition device, should the power transmission and transformation equipment state abnormal patterns identification device packet based on multi-source multi-parameter fusion
Include input unit 501, the first judging unit 502 and second judgment unit 503.
Wherein, input unit 501 is used to obtain primary monitoring data, and sequentially in time respectively to primary monitoring data
In include various state quantity datas be ranked up, generate the time series data of each state quantity data;Particular content please refer to
Described in step S101 to step S102 in above method embodiment.
First judging unit 502 is used for according to using the data that the sliding window of preset length acquires to judge each quantity of state number
According to whether being candidate abnormal data;Particular content please refer to described in the step S103 in above method embodiment.
When the state quantity data is candidate abnormal data, the first judging unit 502 is additionally operable to generate current time
Candidate abnormal data sequence, candidate abnormal data sequence include the various states amount data under current time;Particular content please be detailed
See described in the step S104 in above method embodiment.
Second judgment unit 503 is used to judge whether candidate abnormal data sequence to meet the cluster spy of preset normal data
Sign;Particular content please refer to described in the step S105 in above method embodiment.
When candidate abnormal data sequence does not meet the cluster feature of preset normal data, second judgment unit 503 is also
For obtaining comprising multiple monitoring data sequences in the first time period including current time, and according to multiple monitoring data sequences
Row judge whether corresponding power transmission and transforming equipment exception occurs, each monitoring data sequence in multiple monitoring data sequences includes
Various states amount data under synchronization.Particular content please refer to described in the step S106 in above method embodiment.
The embodiment of the present invention additionally provides a kind of server, as shown in fig. 6, the server may include 601 He of processor
Memory 602, wherein processor 601 can be connected with memory 602 by bus or other modes, with by total in Fig. 6
For line connection.
Processor 601 can be central processing unit (Central Processing Unit, CPU).Processor 601 may be used also
Think other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 602 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program and module, such as the power transmission and transforming equipment based on multi-source multi-parameter fusion in the embodiment of the present invention
Corresponding program instruction/the module of abnormal state mode identification method is (for example, input unit shown in fig. 5 501, first judges list
Member 502 and second judgment unit 503).Processor 601 is by running storage non-transient software program in the memory 602, referring to
It enables and module is realized in above method embodiment to execute various function application and the data processing of processor
Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion.
Memory 602 may include storing program area and storage data field, wherein storing program area can store operation system
System, the required application program of at least one function;Storage data field can store the data etc. that processor 601 is created.In addition,
Memory 602 may include high-speed random access memory, can also include non-transient memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-transient solid-state memories.In some embodiments, it includes opposite that memory 602 is optional
In the remotely located memory of processor 601, these remote memories can pass through network connection to processor 601.Above-mentioned net
The example of network includes but not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 602, when being executed by the processor 601, are held
The power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion in row embodiment as shown in Figs 1-4.
Above-mentioned server detail can correspond to refering to fig. 1 to corresponding associated description in embodiment shown in Fig. 4 and
Effect is understood that details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of flow in above-described embodiment method
It crosses computer program and is completed to instruct relevant hardware, the program can be stored in a computer read/write memory medium
In, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic disc,
CD, read-only memory (Read-Only Memory, ROM), random access memory (RandomAccess Memory,
RAM), flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation:) or solid state disk (Solid- HDD
State Drive, SSD) etc.;The storage medium can also include the combination of the memory of mentioned kind.
The embodiment of the present invention additionally provides a kind of computer storage media, and the computer storage media is stored with computer
Executable instruction, the computer executable instructions can perform in above-mentioned any means embodiment based on multi-source multi-parameter fusion
Power transmission and transformation equipment state abnormal patterns recognition methods.Wherein, the storage medium can be magnetic disc, CD, read-only memory
(Read-Only Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory
(Flash Memory), hard disk (Hard Disk Drive, abbreviation:HDD) or solid state disk (Solid-State Drive,
SSD) etc.;The storage medium can also include the combination of the memory of mentioned kind.
Although being described in conjunction with the accompanying the embodiment of the present invention, those skilled in the art can not depart from the present invention
Spirit and scope in the case of various modifications and variations can be made, such modifications and variations are each fallen within by appended claims institute
Within the scope of restriction.
Claims (9)
1. a kind of power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion, which is characterized in that including:
Primary monitoring data is obtained, includes various states amount data in the primary monitoring data;
The various state quantity datas are ranked up respectively sequentially in time, generate the time sequence of each state quantity data
Column data;
Judge whether each state quantity data is candidate abnormal number according to the data that the sliding window of preset length acquires are used
According to;
When the state quantity data is candidate abnormal data, the candidate abnormal data sequence at current time is generated;The candidate
Abnormal data sequence includes the various states amount data under current time;
Judge whether the candidate abnormal data sequence meets the cluster feature of preset normal data;
When the candidate abnormal data sequence does not meet the cluster feature of preset normal data, acquisition exists comprising current time
Multiple monitoring data sequences in interior first time period, and whether corresponding equipment is judged according to the multiple monitoring data sequence
Occur abnormal;Each monitoring data sequence in the multiple monitoring data sequence includes the various states under synchronization
Measure data.
2. the power transmission and transformation equipment state abnormal patterns recognition methods according to claim 1 based on multi-source multi-parameter fusion,
It is characterized in that, according to using the data that the sliding window of preset length acquires to judge whether each state quantity data is candidate
Abnormal data, including:
Include the number of multiple data points in the second time period including current time using the sliding window acquisition of preset length
According to;
Corresponding Mass median number is calculated according to the data of the multiple data point;
Judge whether the difference between the state quantity data at current time and the Mass median number is more than preset first threshold;
When the difference between the state quantity data at current time and the Mass median number is more than preset first threshold, judgement
The state quantity data at current time is candidate abnormal data.
3. the power transmission and transformation equipment state abnormal patterns recognition methods according to claim 2 based on multi-source multi-parameter fusion,
It is characterized in that, calculating the Mass median number according to following formula:
Wherein,Bt=
|d(xi,t)-d(xi,t-1)|, d (xi,t)=| xi,t-av(xi,t-w,xi,t-(w-1),…,xi,t) |,Indicate the Mass median
Number, xi,tIndicate that the numerical value of i-th of state quantity data under t moment, w indicate the duration of the second time period.
4. the power transmission and transformation equipment state abnormal patterns according to any one of claim 1-3 based on multi-source multi-parameter fusion
Recognition methods, which is characterized in that judge whether corresponding equipment exception occurs according to the multiple monitoring data sequence, including:
Judge whether the multiple monitoring data sequence meets the cluster feature of preset normal data respectively;
Count the quantity for the cluster feature that preset normal data is not met in the multiple monitoring data sequence;
Whether the quantity that the cluster feature of preset normal data is not met described in judgement is more than preset second threshold;
When the quantity of the cluster feature for not meeting preset normal data is more than preset second threshold, judgement correspondence is set
It is standby exception occur.
5. the power transmission and transformation equipment state abnormal patterns based on multi-source multi-parameter fusion according to any one of claim 1-4
Recognition methods, which is characterized in that after the candidate abnormal data sequence for generating current time, and judge described candidate abnormal
Before whether data sequence meets the cluster feature of preset normal data, further include:
The candidate abnormal data sequence is standardized.
6. the power transmission and transformation equipment state abnormal patterns recognition methods according to claim 5 based on multi-source multi-parameter fusion,
It is characterized in that, being standardized to the candidate abnormal data sequence according to following formula:
Wherein,ci,fIndicate normalized treated candidate abnormal number
According to the numerical value of i-th of state quantity data in sequence, and ci,fThe corresponding time is f;xi,fIt indicates to inscribe candidate abnormal data when f
The numerical value of i-th of state quantity data in sequence.
7. a kind of power transmission and transformation equipment state abnormal patterns identification device based on multi-source multi-parameter fusion, which is characterized in that including:
Input unit includes various states amount data in the primary monitoring data for obtaining primary monitoring data;And it uses
In being ranked up respectively to the various state quantity datas sequentially in time, the time series of each state quantity data is generated
Data;
First judging unit, for according to using the data that the sliding window of preset length acquires to judge each state quantity data
Whether it is candidate abnormal data;When the state quantity data is candidate abnormal data, first judging unit is additionally operable to give birth to
At the candidate abnormal data sequence at current time, candidate's abnormal data sequence includes the various states amount number under current time
According to;
Second judgment unit, for judging that the cluster whether candidate abnormal data sequence meets preset normal data is special
Sign;When the candidate abnormal data sequence does not meet the cluster feature of preset normal data, the second judgment unit is also
For obtaining comprising multiple monitoring data sequences in the first time period including current time, and according to the multiple monitoring number
Judge whether corresponding equipment exception occurs according to sequence, each monitoring data sequence in the multiple monitoring data sequence is wrapped
Include the various states amount data under synchronization.
8. a kind of server, which is characterized in that including:
At least one processor;And
The memory being connect at least one processor communication;Wherein, be stored with can be by described at least one for the memory
The instruction that a processor executes, described instruction is executed by least one processor, so that at least one processor is held
Power transmission and transformation equipment state abnormal patterns identification side based on multi-source multi-parameter fusion of the row as described in any one of claim 1-6
Method.
9. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer to refer to
It enables, the computer instruction is used to make the computer to execute more joining based on multi-source as described in any one of claim 1-6
Measure the power transmission and transformation equipment state abnormal patterns recognition methods of fusion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810157181.7A CN108491861A (en) | 2018-02-24 | 2018-02-24 | Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810157181.7A CN108491861A (en) | 2018-02-24 | 2018-02-24 | Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108491861A true CN108491861A (en) | 2018-09-04 |
Family
ID=63340619
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810157181.7A Pending CN108491861A (en) | 2018-02-24 | 2018-02-24 | Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108491861A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239265A (en) * | 2018-09-11 | 2019-01-18 | 清华大学合肥公共安全研究院 | Monitoring device fault detection method and device |
CN109739838A (en) * | 2018-12-06 | 2019-05-10 | 中科恒运股份有限公司 | Method for processing abnormal data and device |
CN110032495A (en) * | 2019-03-28 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Data exception detection method and device |
CN111612179A (en) * | 2020-05-20 | 2020-09-01 | 上海凯宝药业股份有限公司 | Automatic management system of phlegm-heat-clearing production equipment |
CN111723831A (en) * | 2019-03-20 | 2020-09-29 | 北京嘀嘀无限科技发展有限公司 | Data fusion method and device |
CN112231341A (en) * | 2020-09-03 | 2021-01-15 | 山东师范大学 | Cloud platform anomaly detection method and system based on multi-data channel analysis |
CN112381130A (en) * | 2020-11-10 | 2021-02-19 | 国网上海市电力公司 | Cluster analysis-based power distribution room multivariate data anomaly detection method |
CN112906787A (en) * | 2021-02-10 | 2021-06-04 | 宁波诺丁汉新材料研究院有限公司 | Industrial boiler fault identification method and system |
CN113537528A (en) * | 2021-07-28 | 2021-10-22 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
CN113922500A (en) * | 2021-09-17 | 2022-01-11 | 国网山西省电力公司输电检修分公司 | Power transmission line state multi-source monitoring data access method and device |
CN114722891A (en) * | 2022-02-11 | 2022-07-08 | 杭州致成电子科技有限公司 | Transformer area state classification method |
CN114881167A (en) * | 2022-05-24 | 2022-08-09 | 北京百度网讯科技有限公司 | Abnormality detection method, abnormality detection device, electronic apparatus, and medium |
CN115412923A (en) * | 2022-10-28 | 2022-11-29 | 河北省科学院应用数学研究所 | Multi-source sensor data credible fusion method, system, equipment and storage medium |
CN116448219A (en) * | 2023-06-16 | 2023-07-18 | 跨越速运集团有限公司 | Oil level abnormality detection method, apparatus, device, and computer-readable storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140146077A1 (en) * | 2012-11-29 | 2014-05-29 | International Business Machines Corporation | Identifying relationships between entities |
CN105512474A (en) * | 2015-12-02 | 2016-04-20 | 国网山东省电力公司电力科学研究院 | Transformer state monitoring data anomaly detection method |
-
2018
- 2018-02-24 CN CN201810157181.7A patent/CN108491861A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140146077A1 (en) * | 2012-11-29 | 2014-05-29 | International Business Machines Corporation | Identifying relationships between entities |
CN105512474A (en) * | 2015-12-02 | 2016-04-20 | 国网山东省电力公司电力科学研究院 | Transformer state monitoring data anomaly detection method |
Non-Patent Citations (1)
Title |
---|
严英杰 等: "《基于滑动窗口和聚类算法的变压器状态异常检测》", 《高电压技术》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109239265A (en) * | 2018-09-11 | 2019-01-18 | 清华大学合肥公共安全研究院 | Monitoring device fault detection method and device |
US11385122B2 (en) * | 2018-09-11 | 2022-07-12 | Hefei Institute For Public Safety Research, Tsinghua University | Method and device for detecting fault of monitoring device |
CN109239265B (en) * | 2018-09-11 | 2021-01-22 | 清华大学合肥公共安全研究院 | Fault detection method and device for monitoring equipment |
CN109739838A (en) * | 2018-12-06 | 2019-05-10 | 中科恒运股份有限公司 | Method for processing abnormal data and device |
CN111723831A (en) * | 2019-03-20 | 2020-09-29 | 北京嘀嘀无限科技发展有限公司 | Data fusion method and device |
CN111723831B (en) * | 2019-03-20 | 2023-11-14 | 北京嘀嘀无限科技发展有限公司 | Data fusion method and device |
CN110032495A (en) * | 2019-03-28 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Data exception detection method and device |
CN110032495B (en) * | 2019-03-28 | 2023-08-25 | 创新先进技术有限公司 | Data anomaly detection method and device |
CN111612179A (en) * | 2020-05-20 | 2020-09-01 | 上海凯宝药业股份有限公司 | Automatic management system of phlegm-heat-clearing production equipment |
CN112231341A (en) * | 2020-09-03 | 2021-01-15 | 山东师范大学 | Cloud platform anomaly detection method and system based on multi-data channel analysis |
CN112381130A (en) * | 2020-11-10 | 2021-02-19 | 国网上海市电力公司 | Cluster analysis-based power distribution room multivariate data anomaly detection method |
CN112906787A (en) * | 2021-02-10 | 2021-06-04 | 宁波诺丁汉新材料研究院有限公司 | Industrial boiler fault identification method and system |
CN112906787B (en) * | 2021-02-10 | 2023-09-15 | 宁波诺丁汉新材料研究院有限公司 | Industrial boiler fault identification method and system |
CN113537528A (en) * | 2021-07-28 | 2021-10-22 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
CN113537528B (en) * | 2021-07-28 | 2022-05-03 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
CN113922500A (en) * | 2021-09-17 | 2022-01-11 | 国网山西省电力公司输电检修分公司 | Power transmission line state multi-source monitoring data access method and device |
CN114722891A (en) * | 2022-02-11 | 2022-07-08 | 杭州致成电子科技有限公司 | Transformer area state classification method |
CN114881167A (en) * | 2022-05-24 | 2022-08-09 | 北京百度网讯科技有限公司 | Abnormality detection method, abnormality detection device, electronic apparatus, and medium |
CN115412923A (en) * | 2022-10-28 | 2022-11-29 | 河北省科学院应用数学研究所 | Multi-source sensor data credible fusion method, system, equipment and storage medium |
CN116448219A (en) * | 2023-06-16 | 2023-07-18 | 跨越速运集团有限公司 | Oil level abnormality detection method, apparatus, device, and computer-readable storage medium |
CN116448219B (en) * | 2023-06-16 | 2023-08-29 | 跨越速运集团有限公司 | Oil level abnormality detection method, apparatus, device, and computer-readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108491861A (en) | Power transmission and transformation equipment state abnormal patterns recognition methods based on multi-source multi-parameter fusion and device | |
CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
Borghesi et al. | Anomaly detection using autoencoders in high performance computing systems | |
CN111143438B (en) | Workshop field data real-time monitoring and anomaly detection method based on stream processing | |
US11657121B2 (en) | Abnormality detection device, abnormality detection method and computer readable medium | |
CN108415810B (en) | Hard disk state monitoring method and device | |
CN110942137A (en) | Power grid information operation and maintenance monitoring method based on deep learning | |
CN108919059A (en) | A kind of electric network failure diagnosis method, apparatus, equipment and readable storage medium storing program for executing | |
CN112270312A (en) | Fan bearing fault diagnosis method and system, computer equipment and storage medium | |
CN111949429A (en) | Server fault monitoring method and system based on density clustering algorithm | |
US20090182994A1 (en) | Two-level representative workload phase detection method, apparatus, and computer usable program code | |
CN112951311A (en) | Hard disk fault prediction method and system based on variable weight random forest | |
Atzmueller et al. | Anomaly detection and structural analysis in industrial production environments | |
KR102158100B1 (en) | Auto monitoring method and apparatus by using anomaly detection | |
CN111314110B (en) | Fault early warning method for distributed system | |
CN112345972A (en) | Power failure event-based power distribution network line transformation relation abnormity diagnosis method, device and system | |
CN111614504A (en) | Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis | |
WO2019073512A1 (en) | System analysis method, system analysis device, and program | |
CN116775436A (en) | Chip fault prediction method, device, computer equipment and storage medium | |
CN110502424A (en) | A kind of performance data processing method of application software, device, system and terminal | |
CN116400249A (en) | Detection method and device for energy storage battery | |
CN116108376A (en) | Monitoring system and method for preventing electricity stealing, electronic equipment and medium | |
CN115543702A (en) | Multi-source solid state disk collaborative fault diagnosis method, system, equipment and medium | |
CN116415129A (en) | Method, device and computing equipment for assessing the health of a doctor blade of a paper machine | |
CN111078440A (en) | Disk error detection method, device and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |