CN107832896A - A kind of electric power factory equipment soft fault method for early warning and device - Google Patents
A kind of electric power factory equipment soft fault method for early warning and device Download PDFInfo
- Publication number
- CN107832896A CN107832896A CN201711228433.2A CN201711228433A CN107832896A CN 107832896 A CN107832896 A CN 107832896A CN 201711228433 A CN201711228433 A CN 201711228433A CN 107832896 A CN107832896 A CN 107832896A
- Authority
- CN
- China
- Prior art keywords
- data
- label vector
- real
- cluster
- cluster label
- 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.)
- Granted
Links
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
Abstract
The embodiment of the invention discloses a kind of electric power factory equipment soft fault method for early warning and device.The present invention is modeled with the fault condition data in the historical data of electric power factory equipment and nominal situation data and carries out cluster analysis, obtain cluster label vector corresponding to nominal situation data and fault condition data, the cluster label vector that obtains Real-time Monitoring Data is inputted in Clustering Model with Real-time Monitoring Data again, the cluster label vector of Real-time Monitoring Data cluster label vector corresponding with nominal situation data and fault condition data is matched, may determine that electric power factory equipment is normal operation or in soft fault evolution process, and get the fault type and pre-warning time of the occurent soft fault of the equipment, to prompt staff to be overhauled in time before failure formation, solves current electric power factory equipment fault early warning method early warning hysteresis, the technical problem that can not be effectively predicted before failure generation.
Description
Technical field
The present invention relates to electric power monitoring field, more particularly to a kind of electric power factory equipment soft fault method for early warning and device.
Background technology
The working environment residing for heat power equipment in thermal power plant is severe, and the generation of failure not only reduces the steady of production process
It is qualitative, also the security in production process can not be guaranteed.
Current Thermal Equipments of Thermal Power Plants fault early warning method is confined to when a failure occurs it, warn to failure and sentenced
Disconnected fault type, although having reminded the generation of staff's failure, failure can not be predicted before failure generation.
Therefore, current electric power factory equipment fault early warning method early warning hysteresis is result in, can not be had before failure generation
Imitate the technical problem of prediction.
The content of the invention
The invention provides a kind of electric power factory equipment soft fault method for early warning and device, solves current electric power factory equipment event
Hinder method for early warning early warning hysteresis, the technical problem that can not be effectively predicted before failure generation.
The invention provides a kind of electric power factory equipment soft fault method for early warning, including:
S1:With the time that failure starting is developed between time point and time of failure point in the historical data of electric power factory equipment
Section develops the period for failure, and the preset time point and failure starting before time point of developing is originated with failure developed between time point
Period be the nominal situation period, the failure for obtaining at least one of historical data electric power factory equipment soft fault develops the period
Fault condition data and the nominal situation data of nominal situation period, fault condition data and nominal situation data are subjected to standard
Change and handle and the fault condition data after standardization and nominal situation data are spliced into modeling data;
S2:Pass through optimal cluster class number of the silhouette coefficient algorithm computation modeling data in preset cluster class number hunting zone;
S3:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data, obtain nominal situation respectively
Cluster label vector corresponding to data and fault condition data, record corresponding to each cluster label vector corresponding to fault condition data
The fault type and pre-warning time scope of electric power factory equipment soft fault;
S4:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is inputted in Clustering Model and obtains prison in real time
The cluster label vector of data is surveyed, the cluster label vector of Real-time Monitoring Data cluster label vector corresponding with nominal situation data is entered
Row matching, judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data, if it is not,
Then the cluster label vector of Real-time Monitoring Data is matched with each cluster label vector in fault condition data, obtained real-time
The fault type and pre-warning time scope of electric power factory equipment soft fault corresponding to the cluster label vector of Monitoring Data.
Preferably, step S3 is specifically included:
S31:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data, obtain nominal situation respectively
Cluster label vector corresponding to data and fault condition data;
S32:Obtain and record electric power factory equipment soft fault corresponding to each cluster label vector corresponding to fault condition data
Fault type;
S33:The data acquisition time point of fault condition data corresponding to each cluster label vector is obtained, is calculated respectively each
Evolution duration between data acquisition time point and time of failure point, the most short evolution according to corresponding to each cluster label vector
Duration and most long evolution duration obtain and record the pre-warning time scope of each cluster label vector.
Preferably, step S4 is specifically included:
S41:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is inputted in Clustering Model and obtains prison in real time
The cluster label vector of data is surveyed, the cluster label vector of Real-time Monitoring Data cluster label vector corresponding with nominal situation data is entered
Row matching, judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data, if so,
Then electric power factory equipment normal operation, if it is not, then performing step S42;
S42:By each cluster label vector progress in the cluster label vector of Real-time Monitoring Data and fault condition data
Match somebody with somebody, judge whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to fault condition data, if so, then holding
Row step S43, if it is not, then performing step S44;
S43:Obtain the fault type of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data and pre-
Alert time range;
S44:It is abnormal by the status indication of electric power factory equipment.
Preferably, step S41 is specifically included:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is carried out
Standardization and the cluster label vector that Real-time Monitoring Data will be obtained in the Real-time Monitoring Data input Clustering Model after processing,
The cluster label vector of Real-time Monitoring Data cluster label vector corresponding with nominal situation data is matched, judges monitoring in real time
Whether the cluster label vector of data belongs to cluster label vector corresponding to nominal situation data, if so, then electric power factory equipment normal operation,
If it is not, then perform step S42.
Preferably, also include after step S4:Step S5;
S5:The return to step S4 after the first preset time.
The invention provides a kind of electric power factory equipment soft fault prior-warning device, it is characterised in that including:
Data acquisition module, for when failure starting evolution time point and failure occur in the historical data with electric power factory equipment
Between put between period for failure develop the period, with failure originate develop time point before preset time point and failure originate
Period between evolution time point is the nominal situation period, obtains at least one of historical data electric power factory equipment soft fault
Failure develops the fault condition data and the nominal situation data of nominal situation period of period, by fault condition data and normal work
Condition data are standardized and the fault condition data after standardization and nominal situation data are spliced into modeling number
According to;
Cluster class selecting module, for by silhouette coefficient algorithm computation modeling data in preset cluster class number hunting zone
Optimal cluster class number;
Cluster Analysis module, cluster analysis is carried out to modeling data for establishing Clustering Model according to optimal cluster class number, point
Not Huo Qu cluster label vector corresponding to nominal situation data and fault condition data, record each cluster corresponding to fault condition data
The fault type of electric power factory equipment soft fault corresponding to label vector and pre-warning time scope;
Status early warning module, for obtaining the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is inputted into cluster mould
The cluster label vector of Real-time Monitoring Data is obtained in type, the cluster label vector of Real-time Monitoring Data is corresponding with nominal situation data
Cluster label vector matched, judge whether the cluster label vector of Real-time Monitoring Data belongs to cluster corresponding to nominal situation data
Label vector, if it is not, then entering the cluster label vector of Real-time Monitoring Data and each cluster label vector in fault condition data
Row matching, obtain the fault type and pre-warning time of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data
Scope.
Preferably, Cluster Analysis module specifically includes:
Vectorial submodule, cluster analysis is carried out to modeling data for establishing Clustering Model according to optimal cluster class number, respectively
Obtain cluster label vector corresponding to nominal situation data and fault condition data;
Record sub module, set for power plant corresponding to obtaining and recording each cluster label vector corresponding to fault condition data
The fault type of standby soft fault
Scope submodule, for obtaining the data acquisition time point of fault condition data corresponding to each cluster label vector,
The evolution duration between each data acquisition time point and time of failure point is calculated respectively, according to each cluster label vector pair
The most short evolution duration and most long evolution duration answered obtain and record the pre-warning time scope of each cluster label vector.
Preferably, status early warning module specifically includes:
Normal submodule, for obtaining the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is inputted into Clustering Model
The middle cluster label vector for obtaining Real-time Monitoring Data, the cluster label vector of Real-time Monitoring Data is corresponding with nominal situation data
Cluster label vector is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster mark corresponding to nominal situation data
Note vector, if so, then electric power factory equipment normal operation, if it is not, then triggering judging submodule;
Judging submodule, for each cluster in the cluster label vector of Real-time Monitoring Data and fault condition data to be marked
Vector is matched, judge Real-time Monitoring Data cluster label vector whether belong to fault condition data corresponding to cluster mark to
Amount, if so, failure submodule is then triggered, if it is not, then triggering abnormal submodule;
Failure submodule, for obtaining the event of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data
Hinder type and pre-warning time scope;
Abnormal submodule, for being abnormal by the status indication of electric power factory equipment.
Preferably, normal submodule is specifically used for the Real-time Monitoring Data for obtaining electric power factory equipment, and Real-time Monitoring Data is entered
Row standardization and by after processing Real-time Monitoring Data input Clustering Model in obtain Real-time Monitoring Data cluster mark to
Amount, the cluster label vector of Real-time Monitoring Data cluster label vector corresponding with nominal situation data is matched, and is judged real-time
Whether the cluster label vector of Monitoring Data belongs to cluster label vector corresponding to nominal situation data, if so, then electric power factory equipment is run
Normally, if it is not, then triggering judging submodule.
Preferably, in addition to:Repeat module;
Module is repeated, for the triggering state warning module again after the first preset time.
As can be seen from the above technical solutions, the present invention has advantages below:
The invention provides a kind of electric power factory equipment soft fault method for early warning, including:S1:With the historical data of electric power factory equipment
The period that middle failure starting is developed between time point and time of failure point develops the period for failure, is originated and developed with failure
Preset time point before time point and the period between failure starting evolution time point are the nominal situation period, obtain history
The fault condition data of the failure differentiation period of at least one of data electric power factory equipment soft fault and nominal situation period are just
Normal floor data, fault condition data and nominal situation data are standardized and by the failure work after standardization
Condition data and nominal situation data are spliced into modeling data;S2:By silhouette coefficient algorithm computation modeling data in preset cluster class
Optimal cluster class number in number hunting zone;S3:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data,
Cluster label vector corresponding to nominal situation data and fault condition data is obtained respectively, is recorded each corresponding to fault condition data
The fault type of electric power factory equipment soft fault corresponding to cluster label vector and pre-warning time scope;S4:Obtain the reality of electric power factory equipment
When Monitoring Data, will Real-time Monitoring Data input Clustering Model in obtain Real-time Monitoring Data cluster label vector, will supervise in real time
The cluster label vector cluster label vector corresponding with nominal situation data for surveying data is matched, and judges the cluster of Real-time Monitoring Data
Whether label vector belongs to cluster label vector corresponding to nominal situation data, if it is not, then by the cluster of Real-time Monitoring Data mark to
Amount is matched with each cluster label vector in fault condition data, is obtained corresponding to the cluster label vector of Real-time Monitoring Data
The fault type and pre-warning time scope of electric power factory equipment soft fault.
The present invention is modeled and gone forward side by side with the fault condition data in the historical data of electric power factory equipment and nominal situation data
Row cluster analysis, cluster label vector corresponding to nominal situation data and fault condition data is obtained, then it is defeated with Real-time Monitoring Data
Enter to obtain the cluster label vector of Real-time Monitoring Data in Clustering Model, by the cluster label vector and nominal situation of Real-time Monitoring Data
Cluster label vector corresponding to data and fault condition data is matched, may determine that electric power factory equipment be normal operation or
In soft fault evolution process, and because electric power factory equipment corresponding to have recorded cluster label vector corresponding to fault condition data delays
Become the fault type and pre-warning time scope of failure, then the equipment can be got according to the cluster label vector of Real-time Monitoring Data
The fault type and pre-warning time of occurent soft fault, to prompt staff to be overhauled in time before failure formation,
Solves current electric power factory equipment fault early warning method early warning hysteresis, the technology that can not be effectively predicted before failure generation is asked
Topic.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is a kind of flow of one embodiment of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention
Schematic diagram;
Fig. 2 is a kind of stream of another embodiment of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention
Journey schematic diagram;
Fig. 3 is a kind of structure of one embodiment of electric power factory equipment soft fault prior-warning device provided in an embodiment of the present invention
Schematic diagram.
Embodiment
The embodiments of the invention provide a kind of electric power factory equipment soft fault method for early warning and device, solves current power plant
The early warning of equipment fault early-warning method lags, the technical problem that can not be effectively predicted before failure generation.
To enable goal of the invention, feature, the advantage of the present invention more obvious and understandable, below in conjunction with the present invention
Accompanying drawing in embodiment, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that disclosed below
Embodiment be only part of the embodiment of the present invention, and not all embodiment.Based on the embodiment in the present invention, this area
All other embodiment that those of ordinary skill is obtained under the premise of creative work is not made, belongs to protection of the present invention
Scope.
Referring to Fig. 1, the embodiments of the invention provide a kind of one embodiment of electric power factory equipment soft fault method for early warning,
Including:
Step 101:Developed with failure starting in the historical data of electric power factory equipment between time point and time of failure point
Period for failure develop the period, with failure originate develop time point before preset time point and failure starting develop the time
Period between point is the nominal situation period, and the failure for obtaining at least one of historical data electric power factory equipment soft fault develops
The fault condition data of period and the nominal situation data of nominal situation period, fault condition data and nominal situation data are entered
Fault condition data after standardization and nominal situation data are simultaneously spliced into modeling data by row standardization;
It should be noted that, it is necessary to establish electric power factory equipment soft fault before electric power factory equipment soft fault early warning is carried out
Early-warning Model, so needing to get fault condition data in historical data and nominal situation data are built as modeling data
Formwork erection type.
Step 102:Pass through optimal cluster class of the silhouette coefficient algorithm computation modeling data in preset cluster class number hunting zone
Number;
, can be with it should be noted that silhouette coefficient algorithm (Silhouette parsers) is a kind of Cluster Evaluation algorithm
Clustering Effect quality is evaluated by calculating silhouette coefficient, two kinds of factors of silhouette coefficient algorithm combination cohesion degree and separating degree can be with
For being used for evaluating algorithms of different or algorithm different running method produces cluster result on the basis of identical initial data
Raw influence;
The optimal cluster for getting modeling data in preset cluster class number hunting zone can be calculated by silhouette coefficient algorithm
Class number.
Step 103:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data, obtained respectively normal
Cluster label vector corresponding to floor data and fault condition data, record each cluster label vector pair corresponding to fault condition data
The fault type and pre-warning time scope for the electric power factory equipment soft fault answered;
It should be noted that nominal situation data and fault condition data pair can be obtained after analyzing modeling data
The cluster label vector answered, and record electric power factory equipment soft fault corresponding to each cluster label vector corresponding to fault condition data
Fault type and pre-warning time scope.
Step 104:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is inputted in Clustering Model and obtained in fact
When Monitoring Data cluster label vector, by the cluster label vector of Real-time Monitoring Data cluster corresponding with nominal situation data mark to
Amount is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data,
If it is not, then perform step 105;
It should be noted that after Real-time Monitoring Data is inputted into Clustering Model, the cluster mark monitored in real time can be got
Vector, it may determine that Real-time Monitoring Data belongs to nominal situation data either fault condition data by cluster label vector.
Step 105:The cluster label vector of Real-time Monitoring Data and each cluster label vector in fault condition data are entered
Row matching, obtain the fault type and pre-warning time of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data
Scope.
It should be noted that when judging Real-time Monitoring Data for fault condition data, then can be by itself and fault condition
Cluster label vector is matched corresponding to data, obtains the gradual event of electric power factory equipment corresponding to the cluster label vector of Real-time Monitoring Data
The fault type and pre-warning time scope of barrier.
It is modeled, is obtained by the fault condition data before power plant's soft fault and nominal situation data in the present embodiment
Cluster label vector corresponding to nominal situation data and fault condition data is taken, then is inputted in Clustering Model and obtained with Real-time Monitoring Data
The cluster label vector of Real-time Monitoring Data is taken, by the cluster label vector of Real-time Monitoring Data and nominal situation data and fault condition
Cluster label vector is matched corresponding to data, may determine that electric power factory equipment is normal operation or developed in soft fault
Cheng Zhong, and because have recorded the failure classes of electric power factory equipment soft fault corresponding to cluster label vector corresponding to fault condition data
Type and pre-warning time scope, then it is occurent gradual the equipment can be got according to the cluster label vector of Real-time Monitoring Data
The fault type and pre-warning time of failure, to prompt staff to be overhauled in time before failure formation, solves current electricity
The early warning of plant fault early warning method lags, the technical problem that can not be effectively predicted before failure generation.
It is a kind of one embodiment of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention above, below
For a kind of another embodiment of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention.
Referring to Fig. 2, the embodiments of the invention provide a kind of another of electric power factory equipment soft fault method for early warning implementation
Example, including:
Step 201:Developed with failure starting in the historical data of electric power factory equipment between time point and time of failure point
Period for failure develop the period, with failure originate develop time point before preset time point and failure starting develop the time
Period between point is the nominal situation period, and the failure for obtaining at least one of historical data electric power factory equipment soft fault develops
The fault condition data of period and the nominal situation data of nominal situation period, fault condition data and nominal situation data are entered
Fault condition data after standardization and nominal situation data are simultaneously spliced into modeling data by row standardization;
It should be noted that soft fault A occur at 12 points for such as electric power factory equipment, observation data find that start gradual event at 11 points
Barrier develops, then develops the period by failure of 11 points to 12 points of period;
It is normal time that can set the preset time point before failure starting evolution time point according to engineering actual demand
Point, it is normal time point as given tacit consent to half an hour before failure starting is developed, then using 10 thirty to 11 points of period as normal work
The condition period;
Obtain the fault condition data and the nominal situation of 10 thirty to 11 points of period of 11 points to 12 points of period
Data are simultaneously standardized and spliced, then obtain modeling data.
Step 202:Pass through optimal cluster class of the silhouette coefficient algorithm computation modeling data in preset cluster class number hunting zone
Number;
It should be noted that such as preset cluster class number hunting zone is [2,8], then can be calculated most by silhouette coefficient algorithm
Good cluster class number, such as optimal cluster class number are 5.
Step 203:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data, obtained respectively normal
Cluster label vector corresponding to floor data and fault condition data;
It should be noted that after such as being clustered, nominal situation data are divided into two classes, and cluster label vector is A1 and A2,
Fault condition data are divided into three classes, and cluster label vector is B1, B2 and B3.
Step 204:Obtain and to record electric power factory equipment corresponding to each cluster label vector corresponding to fault condition data gradual
The fault type of failure;
It should be noted that have chosen three kinds of failures when obtaining modeling data as described above, respective cluster label vector be B1,
One in B2 or B3.
Step 205:The data acquisition time point of fault condition data corresponding to each cluster label vector is obtained, is calculated respectively
Evolution duration between each data acquisition time point and time of failure point, it is most short according to corresponding to each cluster label vector
Evolution duration and most long evolution duration obtain and record the pre-warning time scope of each cluster label vector;
It should be noted that each cluster label vector includes a series of data, therefore such as B1 cluster label vector bags
Containing b1, b2, b3 and b4 data, b1 data acquisition times be 11 points 11 minutes, b2 data acquisition times be 11 points 21 minutes, b3 data adopt
Collection the time be 11 points 31 minutes with b4 data acquisition times be 11 points 41 minutes, then during most short evolution a length of 11: 41 assign to 12 points when
Between difference be 19 minutes, a length of 11: 11 time differences for assigning at 12 points were 49 minutes during most long evolution, then pre-warning time scope is
[19,49], i.e., when Real-time Monitoring Data is B1 cluster label vectors, it can be broken down in the range of [19,49] minute.
Step 206:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is inputted in Clustering Model and obtained in fact
When Monitoring Data cluster label vector, by the cluster label vector of Real-time Monitoring Data cluster corresponding with nominal situation data mark to
Amount is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data,
If so, step 207 is then performed, if it is not, then performing step 208;
It should be noted that by Real-time Monitoring Data input Clustering Model in obtain Real-time Monitoring Data cluster mark to
Amount, and judges whether it is cluster label vector corresponding to nominal situation data, if the cluster label vector of Real-time Monitoring Data is A1, then
Step 207 is performed, if the cluster label vector of Real-time Monitoring Data be B1, then execution step 208.
Step 207:Electric power factory equipment normal operation;
It should be noted that the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data
Then illustrate electric power factory equipment normal operation.
Step 208:The cluster label vector of Real-time Monitoring Data and each cluster label vector in fault condition data are entered
Row matching, judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to fault condition data, if so,
Step 209 is then performed, if it is not, then performing step 210;
It should be noted that when the cluster label vector for judging Real-time Monitoring Data is not cluster mark corresponding to nominal situation data
Note vector, then the cluster label vector for judging Real-time Monitoring Data is cluster label vector corresponding to fault condition data, strictly according to the facts
When Monitoring Data cluster label vector be B1, then perform step 209, if the cluster label vector of Real-time Monitoring Data is C1, then hold
Row step 210.
Step 209:Obtain the fault type of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data
With pre-warning time scope;
It should be noted that when the cluster label vector of Real-time Monitoring Data is B1, it is that fault condition data are corresponding to be judged
Cluster label vector when, then get the fault type of electric power factory equipment soft fault corresponding to B1 and pre-warning time scope [19,
49];
Step 210:It is abnormal by the status indication of electric power factory equipment;
It should be noted that when the cluster label vector of Real-time Monitoring Data is C1, C1 is not after modeling data clusters
The cluster label vector drawn, now electric power factory equipment may be up, but data are different from above-mentioned nominal situation data, electricity
Plant may also be exception in the failure evolution process of other soft faults, therefore by the status indication of electric power factory equipment, with
Staff is reminded to be checked, then can also be by C1 if electric power factory equipment is just in the failure evolution process of other soft faults
Cluster label vector is corresponded to as fault condition data to recorded in database.
Step 211:The return to step 206 after the first preset time.
It should be noted that in actual production process, it is necessary to cyclicity carry out detection judgement, such as set half an hour check
Once, then the first preset time is 30 minutes.
It is modeled, is obtained by the fault condition data before power plant's soft fault and nominal situation data in the present embodiment
Cluster label vector corresponding to nominal situation data and fault condition data is taken, then is inputted in Clustering Model and obtained with Real-time Monitoring Data
The cluster label vector of Real-time Monitoring Data is taken, by the cluster label vector of Real-time Monitoring Data and nominal situation data and fault condition
Cluster label vector is matched corresponding to data, may determine that electric power factory equipment is normal operation or developed in soft fault
Cheng Zhong, and because have recorded the failure classes of electric power factory equipment soft fault corresponding to cluster label vector corresponding to fault condition data
Type and pre-warning time scope, then it is occurent gradual the equipment can be got according to the cluster label vector of Real-time Monitoring Data
The fault type and pre-warning time of failure, to prompt staff to be overhauled in time before failure formation, solves current electricity
The early warning of plant fault early warning method lags, the technical problem that can not be effectively predicted before failure generation;
It is a kind of another embodiment of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention above, with
It is an a kind of application examples of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention down.
The embodiments of the invention provide an a kind of application examples of electric power factory equipment soft fault method for early warning, including:
By taking the fault pre-alarming of the coal pulverizer in fired power generating unit as an example, 2 sections of coal-grindings of the coal pulverizer of certain 1000MW unit are chosen
Machine fault data carries out fault early warning system modeling, sampling interval 1s;
8 variables are chosen to establish Early-warning Model, are respectively:Coal pulverizer electric current, primary air pressure, an air temperature, mill
Coal machine outlet temperature, a wind flow, cold-air flap aperture, hot air disperser aperture and coal-supplying amount;
Fault data section A is the disconnected coal fault data of coal pulverizer, and failure develops when a length of 1353s of period;
Fault data section B is coal pulverizer spontaneous combustion fault data, and failure develops when a length of 1000s of period;
In order to which the difference after terminating when coal pulverizer breaks down with coal pulverizer normal operation and failure can be distinguished, in disconnected coal
Fault data starts to take 500s forward as the coal pulverizer nominal situation period when developing;
It is that coal pulverizer breaks coal fault data to choose 1 section in addition, referred to as fault data section C, failure develop the period when it is a length of
1000s, the checking data as fault early warning system;
The hunting zone for determining cluster class number is [2,7], using Silhouette analyze data sections A, data segment B and coal pulverizer
The modeling data of the data segment combination of nominal situation period, cluster class number are defined as 6;
Coal pulverizer evolution process is portrayed at the cluster center of each cluster, as shown in table 1:
The cluster center of the coal pulverizer fault cluster model of table 1
Wherein μ 0 is that cluster center, μ 1, μ 2 and the μ 3 of coal pulverizer normal operation are respectively the disconnected coal failure phase 1,2,3 of coal pulverizer
Cluster center, μ 4 and μ 5 are respectively the cluster center of coal pulverizer spontaneous combustion failure phase 4 and 5;
The cluster mark result such as table 2 of the disconnected coal fault data of coal pulverizer and coal pulverizer spontaneous combustion fault data, coal pulverizer occurs disconnected
When coal failure and spontaneous combustion failure, different evolving stages can be divided into;
Wherein, the break cluster label vector of coal failure of coal pulverizer be (0,1,2,3), the cluster label vector of spontaneous combustion failure be (0,
4,5).The time that each stage by counting each failure occurs to coal pulverizer failure, the time model predicted during as fault alarm
Enclose, final result collects as shown in table 2:
Each stage pre-warning time range table of 2 each failure of table
Data segment C after standardization, is sent into Clustering Model, corresponding cluster label vector as live real time data
For (0,1,2,3), it can be determined that its fault type is the disconnected coal failure of coal pulverizer;
It is as shown in table 3 to obtain each stage time of failure corresponding to data segment C in practice:
The coal pulverizer fault data section C of table 3 actually each stage to time of failure scope
Therefore checking data segment C's is close with fault pre-alarming time range to time of failure scope, therefore
It can be seen that electric power factory equipment soft fault method for early warning proposed by the present invention can predict the generation of electric power factory equipment soft fault, and in advance
Pre-warning time accuracy height is measured out, prediction result is true and reliable;
And with the increase of modeling data, electric power factory equipment soft fault method for early warning proposed by the present invention is predicted accurate
Property also can be with improve.
It is an a kind of application examples of electric power factory equipment soft fault method for early warning provided in an embodiment of the present invention above, below
For a kind of one embodiment of electric power factory equipment soft fault prior-warning device provided in an embodiment of the present invention.
Referring to Fig. 3, the embodiments of the invention provide a kind of one embodiment of electric power factory equipment soft fault prior-warning device,
Including:
Data acquisition module 301, develop time point and failure hair for failure starting in the historical data with electric power factory equipment
Period between raw time point develops the period for failure, preset time point and failure before time point of being developed with failure starting
Period between starting evolution time point is the nominal situation period, obtains the gradual event of at least one of historical data electric power factory equipment
The failure of barrier develops the fault condition data and the nominal situation data of nominal situation period of period, by fault condition data and just
Normal floor data is standardized and the fault condition data after standardization and nominal situation data is spliced into and built
Modulus evidence;
Cluster class selecting module 302, for by silhouette coefficient algorithm computation modeling data in preset cluster class number hunting zone
Interior optimal cluster class number;
Cluster Analysis module 303, cluster analysis is carried out to modeling data for establishing Clustering Model according to optimal cluster class number,
Cluster label vector corresponding to nominal situation data and fault condition data is obtained respectively, is recorded each corresponding to fault condition data
The fault type of electric power factory equipment soft fault corresponding to cluster label vector and pre-warning time scope;
Status early warning module 304, for obtaining the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is inputted and clustered
The cluster label vector of Real-time Monitoring Data is obtained in model, by the cluster label vector of Real-time Monitoring Data and nominal situation data pair
The cluster label vector answered is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to corresponding to nominal situation data
Cluster label vector, if it is not, then by each cluster label vector in the cluster label vector of Real-time Monitoring Data and fault condition data
Matched, when obtaining the fault type of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data and early warning
Between scope.
Further, Cluster Analysis module 303 specifically includes:
Vectorial submodule 3031, cluster analysis is carried out to modeling data for establishing Clustering Model according to optimal cluster class number,
Cluster label vector corresponding to nominal situation data and fault condition data is obtained respectively;
Record sub module 3032, it is electric corresponding to each cluster label vector corresponding to fault condition data for obtaining and recording
The fault type of plant soft fault;
Scope submodule 3033, for obtaining the data acquisition time of fault condition data corresponding to each cluster label vector
Point, calculate the evolution duration between each data acquisition time point and time of failure point respectively, according to each cluster mark to
Most short evolution duration and most long evolution duration obtain and record the pre-warning time scope of each cluster label vector corresponding to amount.
Further, status early warning module 304 specifically includes:
Normal submodule 3041, for obtaining the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is inputted and clustered
The cluster label vector of Real-time Monitoring Data is obtained in model, by the cluster label vector of Real-time Monitoring Data and nominal situation data pair
The cluster label vector answered is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to corresponding to nominal situation data
Cluster label vector, if so, then electric power factory equipment normal operation, if it is not, then triggering judging submodule 3042;
Judging submodule 3042, for by each cluster in the cluster label vector of Real-time Monitoring Data and fault condition data
Label vector is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster corresponding to fault condition data and mark
Vector, if so, failure submodule 3043 is then triggered, if it is not, then triggering abnormal submodule 3044;
Failure submodule 3043, for obtaining electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data
Fault type and pre-warning time scope;
Abnormal submodule 3044, for being abnormal by the status indication of electric power factory equipment.
Further, normal submodule 3041 is specifically used for the Real-time Monitoring Data for obtaining electric power factory equipment, will monitor in real time
Data are standardized and the cluster of Real-time Monitoring Data will be obtained in the Real-time Monitoring Data input Clustering Model after processing
Label vector, the cluster label vector of Real-time Monitoring Data cluster label vector corresponding with nominal situation data is matched, sentenced
Whether the cluster label vector of disconnected Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data, if so, then power plant sets
Standby normal operation, if it is not, then triggering judging submodule 3042.
Further, in addition to:Repeat module 305;
Module 305 is repeated, for the triggering state warning module 304 again after the first preset time.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and module, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it can be passed through
Its mode is realized.For example, device embodiment described above is only schematical, for example, the division of the module, only
Only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple module or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.It is another, it is shown or discussed
Mutual coupling or direct-coupling or communication connection can be the INDIRECT COUPLINGs or logical by some interfaces, device or module
Letter connection, can be electrical, mechanical or other forms.
The module illustrated as separating component can be or may not be physically separate, show as module
The part shown can be or may not be physical module, you can with positioned at a place, or can also be distributed to multiple
On mixed-media network modules mixed-media.Some or all of module therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional module in each embodiment of the present invention can be integrated in a processing module, can also
That modules are individually physically present, can also two or more modules be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.
If the integrated module is realized in the form of software function module and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to be contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the present invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
Described above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those within the art that:It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent substitution is carried out to which part technical characteristic;And these
Modification is replaced, and the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
- A kind of 1. electric power factory equipment soft fault method for early warning, it is characterised in that including:S1:Using failure starting is developed between time point and time of failure point in the historical data of electric power factory equipment period as Failure develop the period, with failure originate develop time point before preset time point and failure starting develop time point between when Between section be the nominal situation period, the failure for obtaining at least one of historical data electric power factory equipment soft fault develops the failure of period Fault condition data and nominal situation data are standardized place by floor data and the nominal situation data of nominal situation period Manage and the fault condition data after standardization and nominal situation data are spliced into modeling data;S2:Pass through optimal cluster class number of the silhouette coefficient algorithm computation modeling data in preset cluster class number hunting zone;S3:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data, obtain nominal situation data respectively With fault condition data corresponding to cluster label vector, record fault condition data corresponding to power plant corresponding to each cluster label vector The fault type and pre-warning time scope of equipment soft fault;S4:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is inputted in Clustering Model and obtains monitoring number in real time According to cluster label vector, corresponding with the nominal situation data cluster label vector of the cluster label vector of Real-time Monitoring Data is carried out Match somebody with somebody, judge whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data, if it is not, then will The cluster label vector of Real-time Monitoring Data is matched with each cluster label vector in fault condition data, obtains monitoring in real time The fault type and pre-warning time scope of electric power factory equipment soft fault corresponding to the cluster label vector of data.
- 2. a kind of electric power factory equipment soft fault method for early warning according to claim 1, it is characterised in that step S3 is specifically wrapped Include:S31:Clustering Model is established according to optimal cluster class number cluster analysis is carried out to modeling data, obtain nominal situation data respectively With fault condition data corresponding to cluster label vector;S32:Obtain and record the event of electric power factory equipment soft fault corresponding to each cluster label vector corresponding to fault condition data Hinder type;S33:The data acquisition time point of fault condition data corresponding to each cluster label vector is obtained, calculates each data respectively Evolution duration between acquisition time and time of failure point, the most short evolution duration according to corresponding to each cluster label vector Most long evolution duration obtains and records the pre-warning time scope of each cluster label vector.
- 3. a kind of electric power factory equipment soft fault method for early warning according to claim 1, it is characterised in that step S4 is specifically wrapped Include:S41:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is inputted in Clustering Model and obtains monitoring number in real time According to cluster label vector, corresponding with the nominal situation data cluster label vector of the cluster label vector of Real-time Monitoring Data is carried out Match somebody with somebody, judge whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to nominal situation data, if so, then electric Plant normal operation, if it is not, then performing step S42;S42:The cluster label vector of Real-time Monitoring Data is matched with each cluster label vector in fault condition data, sentenced Whether the cluster label vector of disconnected Real-time Monitoring Data belongs to cluster label vector corresponding to fault condition data, if so, then performing step Rapid S43, if it is not, then performing step S44;S43:When obtaining the fault type of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data and early warning Between scope;S44:It is abnormal by the status indication of electric power factory equipment.
- 4. a kind of electric power factory equipment soft fault method for early warning according to claim 3, it is characterised in that step S41 is specific Including:The Real-time Monitoring Data of electric power factory equipment is obtained, Real-time Monitoring Data is standardized and will be real-time after processing The cluster label vector of Real-time Monitoring Data is obtained in Monitoring Data input Clustering Model, by the cluster label vector of Real-time Monitoring Data Cluster label vector corresponding with nominal situation data is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to just Cluster label vector corresponding to normal floor data, if so, then electric power factory equipment normal operation, if it is not, then performing step S42.
- 5. a kind of electric power factory equipment soft fault method for early warning according to claim 1, it is characterised in that after step S4 also Including:Step S5;S5:The return to step S4 after the first preset time.
- A kind of 6. electric power factory equipment soft fault prior-warning device, it is characterised in that including:Data acquisition module, for failure starting evolution time point and time of failure point in the historical data with electric power factory equipment Between period for failure develop the period, with failure originate develop time point before preset time point and failure starting develop Period between time point is the nominal situation period, obtains the failure of at least one of historical data electric power factory equipment soft fault The fault condition data and the nominal situation data of nominal situation period of period are developed, by fault condition data and nominal situation number According to being standardized and the fault condition data after standardization and nominal situation data be spliced into modeling data;Cluster class selecting module, for optimal in preset cluster class number hunting zone by silhouette coefficient algorithm computation modeling data Cluster class number;Cluster Analysis module, cluster analysis is carried out to modeling data for establishing Clustering Model according to optimal cluster class number, obtained respectively Cluster label vector corresponding to nominal situation data and fault condition data is taken, records each cluster mark corresponding to fault condition data The fault type of electric power factory equipment soft fault corresponding to vector and pre-warning time scope;Status early warning module, for obtaining the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is inputted in Clustering Model The cluster label vector of Real-time Monitoring Data is obtained, by the cluster label vector of Real-time Monitoring Data cluster corresponding with nominal situation data Label vector is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to cluster corresponding to nominal situation data and mark Vector, if it is not, then by each cluster label vector progress in the cluster label vector of Real-time Monitoring Data and fault condition data Match somebody with somebody, obtain the fault type of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data and pre-warning time model Enclose.
- A kind of 7. electric power factory equipment soft fault prior-warning device according to claim 6, it is characterised in that Cluster Analysis module Specifically include:Vectorial submodule, cluster analysis is carried out to modeling data for establishing Clustering Model according to optimal cluster class number, obtained respectively Cluster label vector corresponding to nominal situation data and fault condition data;Record sub module, delay for electric power factory equipment corresponding to obtaining and recording each cluster label vector corresponding to fault condition data Become the fault type of failure;Scope submodule, for obtaining the data acquisition time point of fault condition data corresponding to each cluster label vector, respectively The evolution duration between each data acquisition time point and time of failure point is calculated, according to corresponding to each cluster label vector Most short evolution duration and most long evolution duration obtain and record the pre-warning time scope of each cluster label vector.
- A kind of 8. electric power factory equipment soft fault prior-warning device according to claim 6, it is characterised in that status early warning module Specifically include:Normal submodule, for obtaining the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is inputted in Clustering Model and obtained The cluster label vector of Real-time Monitoring Data is taken, by the cluster label vector of Real-time Monitoring Data cluster mark corresponding with nominal situation data Note vector matched, judge Real-time Monitoring Data cluster label vector whether belong to nominal situation data corresponding to cluster mark to Amount, if so, then electric power factory equipment normal operation, if it is not, then triggering judging submodule;Judging submodule, for by each cluster label vector in the cluster label vector of Real-time Monitoring Data and fault condition data Matched, judge whether the cluster label vector of Real-time Monitoring Data belongs to cluster label vector corresponding to fault condition data, if It is failure submodule then to be triggered, if it is not, then triggering abnormal submodule;Failure submodule, for obtaining the failure classes of electric power factory equipment soft fault corresponding to the cluster label vector of Real-time Monitoring Data Type and pre-warning time scope;Abnormal submodule, for being abnormal by the status indication of electric power factory equipment.
- A kind of 9. electric power factory equipment soft fault prior-warning device according to claim 8, it is characterised in that normal submodule tool Body is used to obtain the Real-time Monitoring Data of electric power factory equipment, Real-time Monitoring Data is standardized and will be real-time after processing The cluster label vector of Real-time Monitoring Data is obtained in Monitoring Data input Clustering Model, by the cluster label vector of Real-time Monitoring Data Cluster label vector corresponding with nominal situation data is matched, and judges whether the cluster label vector of Real-time Monitoring Data belongs to just Cluster label vector corresponding to normal floor data, if so, then electric power factory equipment normal operation, if it is not, then triggering judging submodule.
- 10. a kind of electric power factory equipment soft fault prior-warning device according to claim 6, it is characterised in that also include:Repeat Execution module;Module is repeated, for the triggering state warning module again after the first preset time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711228433.2A CN107832896B (en) | 2017-11-29 | 2017-11-29 | Power plant equipment slow-changing fault early warning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711228433.2A CN107832896B (en) | 2017-11-29 | 2017-11-29 | Power plant equipment slow-changing fault early warning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107832896A true CN107832896A (en) | 2018-03-23 |
CN107832896B CN107832896B (en) | 2021-03-12 |
Family
ID=61646601
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711228433.2A Active CN107832896B (en) | 2017-11-29 | 2017-11-29 | Power plant equipment slow-changing fault early warning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107832896B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109299201A (en) * | 2018-11-05 | 2019-02-01 | 远光软件股份有限公司 | Power plant's production subsystem method for monitoring abnormality and device based on two-phase analyzing method |
CN109300285A (en) * | 2018-11-30 | 2019-02-01 | 联想(北京)有限公司 | Method for early warning and device |
CN110266541A (en) * | 2019-06-25 | 2019-09-20 | 湖南科技学院 | Equipment safety monitoring system based on cloud computing |
CN110262460A (en) * | 2019-07-01 | 2019-09-20 | 山东浪潮人工智能研究院有限公司 | A kind of combination Clustering carries out the concrete piston failure prediction method of feature extraction |
CN110391936A (en) * | 2019-07-25 | 2019-10-29 | 长沙学院 | A kind of novel clustering algorithm based on timing alarm |
CN110658905A (en) * | 2019-09-23 | 2020-01-07 | 珠海格力电器股份有限公司 | Early warning method, early warning system and early warning device for equipment running state |
CN110738255A (en) * | 2019-10-15 | 2020-01-31 | 和尘自仪(嘉兴)科技有限公司 | device state monitoring method based on clustering algorithm |
CN111046942A (en) * | 2019-12-09 | 2020-04-21 | 交控科技股份有限公司 | Turnout fault judgment method and device |
CN111046583A (en) * | 2019-12-27 | 2020-04-21 | 中国铁道科学研究院集团有限公司通信信号研究所 | Switch machine fault diagnosis method based on DTW algorithm and ResNet network |
CN111104959A (en) * | 2018-10-25 | 2020-05-05 | 激发认知有限公司 | Method and apparatus for machine learning classifier generation |
CN114088389A (en) * | 2021-12-10 | 2022-02-25 | 华润电力技术研究院有限公司 | Data processing method and related device for gearbox |
CN116361351A (en) * | 2022-12-01 | 2023-06-30 | 重庆科创职业学院 | Data mining method for health management of industrial equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6834256B2 (en) * | 2002-08-30 | 2004-12-21 | General Electric Company | Method and system for determining motor reliability |
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN105425150A (en) * | 2015-11-09 | 2016-03-23 | 江苏科技大学 | Motor fault diagnosis method based on RBF and PCA-SVDD |
CN105573290A (en) * | 2015-12-16 | 2016-05-11 | 浙江中烟工业有限责任公司 | Cigarette factory superspeed carton packaging machine multi-condition process online monitoring and fault diagnosis method |
CN106407589A (en) * | 2016-09-29 | 2017-02-15 | 北京岳能科技股份有限公司 | Wind turbine state evaluation and prediction method and system |
CN106779200A (en) * | 2016-12-07 | 2017-05-31 | 东北大学 | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data |
CN106936627A (en) * | 2016-09-28 | 2017-07-07 | 清华大学 | A kind of thermal power generating equipment performance monitoring method based on big data analysis mining |
CN107346466A (en) * | 2017-05-26 | 2017-11-14 | 国网山东省电力公司淄博供电公司 | A kind of control method and device of electric power dispatching system |
-
2017
- 2017-11-29 CN CN201711228433.2A patent/CN107832896B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6834256B2 (en) * | 2002-08-30 | 2004-12-21 | General Electric Company | Method and system for determining motor reliability |
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN105425150A (en) * | 2015-11-09 | 2016-03-23 | 江苏科技大学 | Motor fault diagnosis method based on RBF and PCA-SVDD |
CN105573290A (en) * | 2015-12-16 | 2016-05-11 | 浙江中烟工业有限责任公司 | Cigarette factory superspeed carton packaging machine multi-condition process online monitoring and fault diagnosis method |
CN106936627A (en) * | 2016-09-28 | 2017-07-07 | 清华大学 | A kind of thermal power generating equipment performance monitoring method based on big data analysis mining |
CN106407589A (en) * | 2016-09-29 | 2017-02-15 | 北京岳能科技股份有限公司 | Wind turbine state evaluation and prediction method and system |
CN106779200A (en) * | 2016-12-07 | 2017-05-31 | 东北大学 | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data |
CN107346466A (en) * | 2017-05-26 | 2017-11-14 | 国网山东省电力公司淄博供电公司 | A kind of control method and device of electric power dispatching system |
Non-Patent Citations (1)
Title |
---|
李舰等: "《数据科学中的R语言》", 30 July 2015, 西安交通大学出版社 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104959A (en) * | 2018-10-25 | 2020-05-05 | 激发认知有限公司 | Method and apparatus for machine learning classifier generation |
CN109299201A (en) * | 2018-11-05 | 2019-02-01 | 远光软件股份有限公司 | Power plant's production subsystem method for monitoring abnormality and device based on two-phase analyzing method |
CN109299201B (en) * | 2018-11-05 | 2020-09-04 | 远光软件股份有限公司 | Power plant production subsystem abnormity monitoring method and device based on two-stage clustering |
CN109300285A (en) * | 2018-11-30 | 2019-02-01 | 联想(北京)有限公司 | Method for early warning and device |
CN109300285B (en) * | 2018-11-30 | 2021-07-16 | 联想(北京)有限公司 | Early warning method and device |
CN110266541A (en) * | 2019-06-25 | 2019-09-20 | 湖南科技学院 | Equipment safety monitoring system based on cloud computing |
CN110262460A (en) * | 2019-07-01 | 2019-09-20 | 山东浪潮人工智能研究院有限公司 | A kind of combination Clustering carries out the concrete piston failure prediction method of feature extraction |
CN110262460B (en) * | 2019-07-01 | 2020-07-03 | 浪潮集团有限公司 | Concrete piston fault prediction method for extracting features by combining clustering idea |
CN110391936A (en) * | 2019-07-25 | 2019-10-29 | 长沙学院 | A kind of novel clustering algorithm based on timing alarm |
CN110391936B (en) * | 2019-07-25 | 2022-03-01 | 长沙学院 | Clustering method based on time sequence alarm |
CN110658905A (en) * | 2019-09-23 | 2020-01-07 | 珠海格力电器股份有限公司 | Early warning method, early warning system and early warning device for equipment running state |
CN110658905B (en) * | 2019-09-23 | 2023-08-04 | 珠海格力电器股份有限公司 | Early warning method, early warning system and early warning device for equipment operation state |
CN110738255A (en) * | 2019-10-15 | 2020-01-31 | 和尘自仪(嘉兴)科技有限公司 | device state monitoring method based on clustering algorithm |
CN111046942A (en) * | 2019-12-09 | 2020-04-21 | 交控科技股份有限公司 | Turnout fault judgment method and device |
CN111046583A (en) * | 2019-12-27 | 2020-04-21 | 中国铁道科学研究院集团有限公司通信信号研究所 | Switch machine fault diagnosis method based on DTW algorithm and ResNet network |
CN111046583B (en) * | 2019-12-27 | 2023-12-08 | 中国铁道科学研究院集团有限公司通信信号研究所 | Point machine fault diagnosis method based on DTW algorithm and ResNet network |
CN114088389A (en) * | 2021-12-10 | 2022-02-25 | 华润电力技术研究院有限公司 | Data processing method and related device for gearbox |
CN116361351A (en) * | 2022-12-01 | 2023-06-30 | 重庆科创职业学院 | Data mining method for health management of industrial equipment |
Also Published As
Publication number | Publication date |
---|---|
CN107832896B (en) | 2021-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107832896A (en) | A kind of electric power factory equipment soft fault method for early warning and device | |
CN105551549B (en) | A kind of nuclear power generating equipment operation conditions on-line monitoring method and system | |
CN109886475B (en) | Information security situation perception system of measurement automation system based on AI | |
CN110298455A (en) | A kind of mechanical equipment fault intelligent early-warning method based on multivariable estimation prediction | |
CN106019195B (en) | Electric power measurement automation verification assembly line fault diagnosis system | |
CN110414155A (en) | A kind of detection of fan part temperature anomaly and alarm method with single measuring point | |
CN107612756A (en) | A kind of operation management system with intelligent trouble analyzing and processing function | |
CN108445410A (en) | A kind of method and device of monitoring accumulator group operating status | |
CN110619587B (en) | Method and system for foundation pit monitoring intelligent early warning and data evidence storage | |
CN107369303A (en) | Factory's intelligent diagnosing method, apparatus and system | |
CN106646030A (en) | Power grid fault diagnosis method and device based on multiple data sources and expert rule base | |
CN106406270A (en) | System level fault diagnosis for the air management system of an aircraft | |
CN107271839A (en) | Method and control device for the vehicle-mounted electrical system that monitors vehicle | |
EP3553044A1 (en) | System and method of remote object monitoring | |
CN108039987A (en) | Critical infrastructures fragility assessment method based on multi-layer-coupled relational network | |
CN109889512A (en) | A kind of method for detecting abnormality and device of charging pile CAN message | |
CN112632845B (en) | Data-based mini-reactor online fault diagnosis method, medium and equipment | |
CN109557468A (en) | BMS passively balanced abatement detecting method, device and equalizing circuit | |
CN105243180A (en) | Electromechanical device fault early warning method and system | |
CN109344610A (en) | The detection method and device of sequence attack | |
CN115018220A (en) | Household appliance fault prediction method and system based on knowledge graph | |
CN111260127A (en) | Fault prediction system and method based on full-machine digital twin model | |
CN111306051B (en) | Probe type state monitoring and early warning method, device and system for oil transfer pump unit | |
CN106652393A (en) | Method for determining false alarm | |
CN117110794A (en) | Intelligent diagnosis system and method for cable faults |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |