CN109657982A - A kind of fault early warning method and device - Google Patents
A kind of fault early warning method and device Download PDFInfo
- Publication number
- CN109657982A CN109657982A CN201811565315.5A CN201811565315A CN109657982A CN 109657982 A CN109657982 A CN 109657982A CN 201811565315 A CN201811565315 A CN 201811565315A CN 109657982 A CN109657982 A CN 109657982A
- Authority
- CN
- China
- Prior art keywords
- data
- variety
- history
- wind
- driven generator
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 76
- 241001269238 Data Species 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims description 19
- 238000013135 deep learning Methods 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 claims description 2
- 238000012407 engineering method Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Wind Motors (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the present invention proposes a kind of fault early warning method and device, is related to technical field of wind power generator.The fault early warning method is used to carry out wind-driven generator fault pre-alarming, which includes: a variety of history normal operation data and a variety of historical failure operation datas for obtaining wind-driven generator;A variety of history are operated normally into data and a variety of historical failure operation datas carry out Feature Selection and obtain data characteristics;Data characteristics progress model training is obtained into training pattern;The real-time running data of wind-driven generator is input to training pattern and obtains warning information.The fault early warning method realizes the fault pre-alarming function of wind-driven generator by a variety of data of wind-driven generator, and then improves early warning accuracy rate.
Description
Technical field
The present invention relates to technical field of wind power generator, in particular to a kind of fault early warning method and device.
Background technique
The fault early warning method of current wind-driven generator is mostly based on a kind of data in source to realize to wind-power electricity generation
The fault pre-alarming of machine is not high to the accuracy rate of the fault pre-alarming of wind-driven generator since data source is single.
Summary of the invention
The purpose of the present invention is to provide a kind of fault early warning method and device, which passes through wind-power electricity generation
A variety of data of machine realize the fault pre-alarming function of wind-driven generator, and then improve early warning accuracy rate.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of fault early warning method, for carrying out failure to wind-driven generator
Early warning, which comprises a variety of history for obtaining the wind-driven generator operate normally data and the operation of a variety of historical failures
Data;A variety of history are operated normally into data and a variety of historical failure operation datas carry out Feature Selection and obtain data
Feature;Data characteristics progress model training is obtained into training pattern;The real-time running data of the wind-driven generator is defeated
Enter to the training pattern and obtains warning information.
Further, a variety of history for obtaining the wind-driven generator operate normally data and a variety of historical failures fortune
The step of row data includes: a variety of history normal operation data and a variety of history that the wind-driven generator is obtained from database
Failure operation data;The real-time running data by the wind-driven generator is input to the training pattern and obtains warning information
The step of after, the method also includes: the real-time running data is operated normally into data as new history or new is gone through
History failure operation data are stored into the database, to be updated to the training pattern.
Further, a variety of history operate normally data and a variety of historical failure operation datas include
SCADA signal, blower sound transducer signal and CMS vibration monitoring signal.
Further, a variety of history operate normally data and a variety of historical failure operation datas according to default ratio
Example obtains.
Further, described to operate normally data and a variety of historical failure operation datas according to by a variety of history
Carrying out the step of Feature Selection obtains data characteristics includes: to operate normally number to a variety of history according to the method for Feature Engineering
Data characteristics is obtained according to Feature Selection is carried out with a variety of historical failure operation datas.
Further, described the step of data characteristics progress model training is obtained training pattern includes: according to machine
Data characteristics progress model training is obtained training pattern by device learning method.
Further, described the step of data characteristics progress model training is obtained training pattern includes: according to depth
Data characteristics progress model training is obtained training pattern by degree learning method.
Second aspect, the embodiment of the invention also provides a kind of fault pre-alarming devices, for carrying out event to wind-driven generator
Hinder early warning, described device includes: acquisition module, and a variety of history for obtaining the wind-driven generator operate normally data and more
Kind historical failure operation data;Characteristic selecting module, for a variety of history to be operated normally data and a variety of history
Failure operation data carry out Feature Selection and obtain data characteristics;Model training module, for the data characteristics to be carried out model
Training obtains training pattern;Warning module, for the real-time running data of the wind-driven generator to be input to the trained mould
Type obtains warning information.
Further, the acquisition module, a variety of history for obtaining the wind-driven generator from database are normal
Operation data and a variety of historical failure operation datas;Described device further include: update module is used for the real-time running data
Data are operated normally as new history or new historical failure operation data is stored into the database, so as to the instruction
Practice model to be updated.
Further, a variety of history operate normally data and a variety of historical failure operation datas include
SCADA signal, blower sound transducer signal and CMS vibration monitoring signal.
A kind of fault early warning method and device provided in an embodiment of the present invention, the fault early warning method include obtaining wind-force hair
A variety of history of motor operate normally data and a variety of historical failure operation datas;A variety of history are operated normally into data and a variety of
Historical failure operation data carries out Feature Selection and obtains data characteristics;Data characteristics progress model training is obtained into training pattern;
The real-time running data of wind-driven generator is input to training pattern and obtains warning information.As it can be seen that this fault early warning method passes through
It obtains a variety of history normal operation data and a variety of historical failure operation datas carries out Feature Selection and obtain data characteristics, Jin Ergen
Training pattern is obtained according to data characteristics, then is brought real-time running data into training pattern and be can be achieved with failure to wind-driven generator
Early warning accuracy rate can be improved due to operating normally data and a variety of historical failure operation datas using a variety of history in early warning.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the application environment schematic diagram of fault early warning method and device provided in an embodiment of the present invention;
Fig. 2 shows the structural block diagrams of server provided in an embodiment of the present invention;
Fig. 3 shows the flow diagram of fault early warning method provided in an embodiment of the present invention;
Fig. 4 shows the structural block diagram of fault pre-alarming device provided in an embodiment of the present invention.
Icon: 1- server;10- memory;20- processor;30- communication unit;40- fault pre-alarming device;41- is obtained
Module;42- characteristic selecting module;43- model training module;44- warning module;45- update module;2- client;3- monitoring
Server;4- wind-driven generator.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
The embodiment of the invention provides a kind of fault early warning method and device, the fault early warning method and device application environment
As shown in Figure 1, server 1, client 2 and monitoring server 3 are located in wireless network or finite element network, pass through the wireless network
Or finite element network, server 1 and client 2 and monitoring server 3 carry out data interaction, monitoring server 3 is gone back and wind-power electricity generation
Machine 4 is electrically connected.
The fault early warning method and device that the embodiment of the present invention proposes are applicable to server 1.The server 1 can be,
But it is not limited to host (Host), is also possible to cloud server etc..The client 2 may be, but not limited to, smart phone, individual
Computer (personal computer, PC), tablet computer, personal digital assistant (personal digital assistant,
PDA), mobile internet surfing equipment (mobile Internet device, MID) etc..The monitoring server 3 includes that data are acquired and supervised
Depending on control system (Supervisory Control And Data Acquisition, SCADA), CMS vibration monitor system, survey
Wind tower system, wind power prediction system etc., for monitoring the signal and state of 4 reality output of wind-driven generator, CMS vibration monitoring
The main shaft, gear-box, generator that system is used to monitor wind-driven generator 4 by installing vibrating sensor in wind-driven generator 4
CMS vibration monitoring signal, and CMS vibration monitoring signal is sent to server 1, server 1 deposits CMS vibration monitoring signal
It puts into database, for anemometer tower system by acquiring the signal of wind field anemometer tower and being sent to server 1, wind power system is pair
Wind speed and power are made in short term, and ultra-short term prediction, prediction result data are sent to server 1.
As shown in Fig. 2, being the block diagram of server 1 shown in FIG. 1.The server 1 includes memory 10, processor
20, communication unit 30 and fault pre-alarming device 40.
Memory 10, processor 20, communication unit 30 and fault pre-alarming device 40 are directly or indirectly electrical between each other
Connection, to realize the transmission or interaction of data.For example, these elements can pass through one or more communication bus or letter between each other
Number line, which is realized, to be electrically connected.Fault pre-alarming device 40 includes that at least one can be stored in the form of software or firmware (firmware)
In memory 10 or the software function module that is solidificated in the operating system (operating system, OS) of server 1.Place
Reason device 20 is for executing the executable module stored in memory 10, such as software function mould included by fault pre-alarming device 40
Block and computer program etc..
Wherein, the memory 10 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Processor 20 can be general processor, including central processing unit (Central Processing Unit, CPU), network processes
Device (Network Processor, NP) etc.;It can also be digital signal processor (DSP), specific integrated circuit (ASIC), show
At programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware
Component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor can
To be that microprocessor or the processor 20 are also possible to any conventional processor etc..Wherein, the memory 10 is for depositing
Store up program and database, the processor 20 executes described program after receiving and executing instruction.The communication unit 30 is used
In the communication connection established by the network between the server 1 and client 2 and monitoring server 3, and for passing through
The network sending and receiving data.
It is appreciated that structure shown in Fig. 2 is only to illustrate, server 1 may also include more or less than shown in Fig. 2
Component, or with the configuration different from shown in Fig. 2.Each component shown in Fig. 2 can use hardware, software, or its combination
It realizes.
As shown in figure 3, being the flow diagram of fault early warning method provided in an embodiment of the present invention, the fault early warning method
For to wind-driven generator 4 carry out fault pre-alarming, it should be noted that fault early warning method of the present invention not with Fig. 3 with
And specific order as described below is limitation.It should be appreciated that in other embodiments, fault early warning method of the present invention its
The sequence of middle part steps can be exchanged with each other according to actual needs or part steps therein also can be omitted or delete.
Detailed process shown in Fig. 3 will be described in detail below.Referring to Fig. 3, the present embodiment describes the processing of server 1
Process, which comprises
Step S1, a variety of history for obtaining the wind-driven generator 4 operate normally data and a variety of historical failures operation number
According to.
In the present embodiment, a variety of history that the wind-driven generator 4 is obtained from database operate normally data and more
Kind historical failure operation data.
Wherein, a variety of history operate normally data and a variety of historical failure operation datas include SCADA letter
Number, blower sound transducer signal and CMS vibration monitoring signal.In the present embodiment, a variety of history operate normally data and more
Kind historical failure operation data is not limited to SCADA signal, blower sound transducer signal and CMS vibration monitoring signal, more
Kind history operates normally data and a variety of historical failure operation datas refer to the various data-signals that wind-driven generator 4 generates.Example
It such as, can also include tach signal, dtc signal and pitch angle signal etc..
It is appreciated that a variety of history of wind-driven generator 4 operate normally the number of data and a variety of historical failure operation datas
According to from multi-signal, including but not limited to SCADA signal, blower sound transducer signal and CMS vibration monitoring signal etc..
For example, when need whether to transfinite to the vibration of the gear-box of wind-driven generator 4 carry out fault pre-alarming when, a variety of history are just
Normal operation data and a variety of historical failure operation datas then include CMS vibration monitoring signal, blower sound transducer signal and
Power of fan signal.
In the present embodiment, a variety of history operate normally data and a variety of historical failure operation datas are obtained according to preset ratio
It takes.It is appreciated that a variety of history for obtaining wind-driven generator 4 from database operate normally data and the operation of a variety of historical failures
It can be obtained according to the ratio of 1:1 when data, i.e., a variety of history operate normally the ratio of data and a variety of historical failure operation datas
Example is 1:1.
A variety of history are operated normally data and a variety of historical failure operation datas carry out feature choosing by step S2
Obtain data characteristics.
In the present embodiment, data are operated normally to a variety of history according to the method for Feature Engineering and described a variety of gone through
History failure operation data carry out Feature Selection and obtain data characteristics.
It is appreciated that a variety of history that first will acquire operate normally data and a variety of historical failure operation datas carry out data
Cleaning, i.e. a variety of history of the removal containing NAN value operate normally data or a variety of historical failure operation datas, and will be remaining more
Kind history operates normally data and a variety of historical failure operation datas are normalized to obtain the first processing data;Then right
It handles data and carries out Data Dimensionality Reduction processing, PCA method can be used, dimension-reduction treatment is carried out to processing data, choose linear uncorrelated
Second processing data;It is related to result that each second processing data are assessed using correlation coefficient process to second processing data again
Property, the strongest certain amount of second processing data of correlation are left as data characteristics, Python engineering can be used
The SelectKBest function practised in library realizes correlation coefficient process, and wherein specific quantity can be set to 30.
Data characteristics progress model training is obtained training pattern by step S3.
In the present embodiment, data characteristics is labeled according to pre-set rule, it is normal to distinguish a variety of history
The data characteristics of the data characteristics of operation data and a variety of historical failure operation datas.Wherein it is possible to normally be transported in a variety of history
It is labeled as 0 after the data characteristics of row data, is labeled as 1 after the data characteristics of a variety of historical failure operation datas.
The data characteristics being labeled is subjected to model training and then obtains training pattern.In the present embodiment, Ke Yigen
Data characteristics progress model training is obtained into training pattern according to machine learning method, can also be incited somebody to action according to deep learning method
The data characteristics carries out model training and obtains training pattern.
It is appreciated that the data characteristics being labeled can be chosen to the side of decision tree, random forest or gradient decline tree
Method carries out model training and obtains multiple models, then selects the highest model of accuracy rate as training pattern from multiple models.
The real-time running data of the wind-driven generator 4 is input to the training pattern and obtains warning information by step S4.
In the present embodiment, the real-time running data of wind-driven generator 4 is input in training pattern and obtains training result,
If the deviation of training result and setting value is more than preset range, then it is assumed that exception occurs in wind-driven generator 4, and then generates early warning letter
Breath;If the deviation of training result and setting value is within a preset range, then it is assumed that the situation without exception of wind-driven generator 4 occurs.It will not
Generate warning information.
Further, in the present embodiment, using the real-time running data as new history normal operation data or newly
Historical failure operation data store into the database, to be updated to the training pattern.
It is appreciated that after step s4, the real-time running data in step S4 can be saved into data as newly
History operates normally data or new historical failure operation data, sentences inputting next real-time running data in training pattern
Disconnected wind-driven generator 4 whether faulty generation when, a upper real-time running data may be operated normally as history data or
Historical failure operation data carries out Feature Selection, and then obtains new data characteristics, in order to carry out model training obtain it is new
Training pattern realizes the update of training pattern with this.
In the present embodiment, it is possible to specify daily specific time is trained the update of model.Wherein, specific time
It can be daily 0 point.
In the present embodiment, if bringing training pattern into real-time running data has obtained warning information, this is real-time
When operation data is saved to database, which is new historical failure operation data;If to real-time running data
It brings training pattern into and does not obtain warning information, then when saving the real-time running data to database, the real-time running data
Data are operated normally for new history.
As shown in figure 4, being the structural schematic diagram of fault pre-alarming device 40 provided in an embodiment of the present invention, the fault pre-alarming
Device 40 is used to carry out fault pre-alarming to wind-driven generator 4, it should be noted that fault pre-alarming device provided by the present embodiment
40 its basic principle and the technical effect of generation are identical as preceding method embodiment, to briefly describe, do not refer in the present embodiment
Part can refer to the corresponding contents in preceding method embodiment.The fault pre-alarming device 40 includes obtaining module 41, feature choosing
Modulus block 42, model training module 43 and warning module 44.
The a variety of history normal operation data and a variety of history for obtaining module 41 and being used to obtain the wind-driven generator 4
Failure operation data.
It is appreciated that the acquisition module 41 can execute above-mentioned steps S1.
The characteristic selecting module 42 is used to a variety of history operating normally data and a variety of historical failures are transported
Row data carry out Feature Selection and obtain data characteristics.
It is appreciated that the characteristic selecting module 42 can execute above-mentioned steps S2.
The model training module 43 is used to data characteristics progress model training obtaining training pattern.
It is appreciated that the model training module 43 can execute above-mentioned steps S3.
Warning module 44 be used for by the real-time running data of the wind-driven generator 4 be input to the training pattern obtain it is pre-
Alert information.
It is appreciated that the warning module 44 can execute above-mentioned steps S4.
Further, in the present embodiment, which further includes update module 45, for making the real-time running data
Data are operated normally for new history or new historical failure operation data is stored into the database, so as to the training
Model is updated.
In conclusion fault early warning method provided in an embodiment of the present invention and device, which includes obtaining
A variety of history of wind-driven generator operate normally data and a variety of historical failure operation datas;A variety of history are operated normally into data
Feature Selection, which is carried out, with a variety of historical failure operation datas obtains data characteristics;Data characteristics progress model training is trained
Model;The real-time running data of wind-driven generator is input to training pattern and obtains warning information.As it can be seen that this fault early warning method
It carries out Feature Selection by obtaining a variety of history normal operation data and a variety of historical failure operation datas and obtains data characteristics, into
And training pattern is obtained according to data characteristics, then bring real-time running data into training pattern and can be achieved with to wind-driven generator
It is accurate that early warning can be improved due to operating normally data and a variety of historical failure operation datas using a variety of history in fault pre-alarming
Rate.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
Claims (10)
1. a kind of fault early warning method, for carrying out fault pre-alarming to wind-driven generator, which is characterized in that the described method includes:
The a variety of history for obtaining the wind-driven generator operate normally data and a variety of historical failure operation datas;
A variety of history are operated normally into data and a variety of historical failure operation datas carry out Feature Selection and obtain data
Feature;
Data characteristics progress model training is obtained into training pattern;
The real-time running data of the wind-driven generator is input to the training pattern and obtains warning information.
2. fault early warning method as described in claim 1, which is characterized in that acquisition a variety of of wind-driven generator go through
History operates normally data and the step of a variety of historical failure operation datas includes:
A variety of history that the wind-driven generator is obtained from database operate normally data and a variety of historical failure operation datas;
The real-time running data by the wind-driven generator be input to the step of training pattern obtains warning information it
Afterwards, the method also includes:
Data or the storage of new historical failure operation data are operated normally to institute using the real-time running data as new history
It states in database, to be updated to the training pattern.
3. fault early warning method as described in claim 1, which is characterized in that a variety of history operate normally data and described
A variety of historical failure operation datas include SCADA signal, blower sound transducer signal and CMS vibration monitoring signal.
4. fault early warning method as described in claim 1, which is characterized in that a variety of history operate normally data and described
A variety of historical failure operation datas are obtained according to preset ratio.
5. fault early warning method as described in claim 1, which is characterized in that described that a variety of history are operated normally data
Carrying out the step of Feature Selection obtains data characteristics with a variety of historical failure operation datas includes:
According to Feature Engineering method to a variety of history operate normally data and a variety of historical failure operation datas into
Row Feature Selection obtains data characteristics.
6. fault early warning method as described in claim 1, which is characterized in that described that the data characteristics is carried out model training
The step of obtaining training pattern include:
Data characteristics progress model training is obtained into training pattern according to machine learning method.
7. fault early warning method as described in claim 1, which is characterized in that described that the data characteristics is carried out model training
The step of obtaining training pattern include:
Data characteristics progress model training is obtained into training pattern according to deep learning method.
8. a kind of fault pre-alarming device, for carrying out fault pre-alarming to wind-driven generator, which is characterized in that described device includes:
Module is obtained, a variety of history for obtaining the wind-driven generator operate normally data and a variety of historical failures operation number
According to;
Characteristic selecting module, for a variety of history to be operated normally data and a variety of historical failure operation data progress
Feature Selection obtains data characteristics;
Model training module, for data characteristics progress model training to be obtained training pattern;
Warning module obtains early warning letter for the real-time running data of the wind-driven generator to be input to the training pattern
Breath.
9. fault pre-alarming device as claimed in claim 8, which is characterized in that the acquisition module, for being obtained from database
A variety of history of the wind-driven generator are taken to operate normally data and a variety of historical failure operation datas;
Described device further include: update module, for using the real-time running data as new history operate normally data or
New historical failure operation data is stored into the database, to be updated to the training pattern.
10. fault pre-alarming device as claimed in claim 8, which is characterized in that a variety of history operate normally data and institute
Stating a variety of historical failure operation datas includes SCADA signal, blower sound transducer signal and CMS vibration monitoring signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811565315.5A CN109657982B (en) | 2018-12-20 | 2018-12-20 | Fault early warning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811565315.5A CN109657982B (en) | 2018-12-20 | 2018-12-20 | Fault early warning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109657982A true CN109657982A (en) | 2019-04-19 |
CN109657982B CN109657982B (en) | 2022-02-11 |
Family
ID=66115235
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811565315.5A Active CN109657982B (en) | 2018-12-20 | 2018-12-20 | Fault early warning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109657982B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111079855A (en) * | 2019-12-27 | 2020-04-28 | 三一重能有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting console |
CN112393931A (en) * | 2019-08-13 | 2021-02-23 | 北京国双科技有限公司 | Detection method, detection device, electronic equipment and computer readable medium |
CN112578794A (en) * | 2020-12-12 | 2021-03-30 | 云南昆船智能装备有限公司 | AGV fault detection method based on machine learning, storage medium and system |
CN112632805A (en) * | 2021-03-15 | 2021-04-09 | 国能大渡河大数据服务有限公司 | Analysis early warning method, system, terminal and medium for crossing vibration area of unit |
CN112688836A (en) * | 2021-03-11 | 2021-04-20 | 南方电网数字电网研究院有限公司 | Energy routing equipment online dynamic sensing method based on deep self-coding network |
CN112906177A (en) * | 2019-12-04 | 2021-06-04 | 财团法人资讯工业策进会 | Apparatus and method for generating a motor diagnostic model |
CN113670790A (en) * | 2021-07-30 | 2021-11-19 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Method and device for determining working state of ceramic filter |
CN114330569A (en) * | 2021-12-30 | 2022-04-12 | 山东浪潮科学研究院有限公司 | Method and equipment for detecting fan unit component fault and storage medium |
CN117250942A (en) * | 2023-11-15 | 2023-12-19 | 成都态坦测试科技有限公司 | Fault prediction method, device, equipment and storage medium for determining model |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
WO2013077794A1 (en) * | 2011-11-23 | 2013-05-30 | Aktiebolaget Skf | A method and an arrangement for monitoring the condition of a rotating system |
US8781982B1 (en) * | 2011-09-23 | 2014-07-15 | Lockheed Martin Corporation | System and method for estimating remaining useful life |
CN104102773A (en) * | 2014-07-05 | 2014-10-15 | 山东鲁能软件技术有限公司 | Equipment fault warning and state monitoring method |
CN104200396A (en) * | 2014-08-26 | 2014-12-10 | 燕山大学 | Wind driven generator part fault early warning method |
US20160266206A1 (en) * | 2015-03-11 | 2016-09-15 | Siemens Energy, Inc. | Generator neutral ground monitoring device utilizing direct current component measurement and analysis |
CN106662072A (en) * | 2014-11-18 | 2017-05-10 | Abb瑞士股份有限公司 | Wind turbine condition monitoring method and system |
CN107291991A (en) * | 2017-05-25 | 2017-10-24 | 华侨大学 | A kind of Wind turbines early defect method for early warning based on dynamic network mark |
CN107403189A (en) * | 2017-06-30 | 2017-11-28 | 南京理工大学 | A kind of windage yaw discharge method for early warning based on Naive Bayes Classifier |
CN107483252A (en) * | 2017-08-22 | 2017-12-15 | 深圳企管加企业服务有限公司 | Calculator room equipment fault early warning system based on Internet of Things |
-
2018
- 2018-12-20 CN CN201811565315.5A patent/CN109657982B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
US8781982B1 (en) * | 2011-09-23 | 2014-07-15 | Lockheed Martin Corporation | System and method for estimating remaining useful life |
WO2013077794A1 (en) * | 2011-11-23 | 2013-05-30 | Aktiebolaget Skf | A method and an arrangement for monitoring the condition of a rotating system |
CN104102773A (en) * | 2014-07-05 | 2014-10-15 | 山东鲁能软件技术有限公司 | Equipment fault warning and state monitoring method |
CN104200396A (en) * | 2014-08-26 | 2014-12-10 | 燕山大学 | Wind driven generator part fault early warning method |
CN106662072A (en) * | 2014-11-18 | 2017-05-10 | Abb瑞士股份有限公司 | Wind turbine condition monitoring method and system |
US20160266206A1 (en) * | 2015-03-11 | 2016-09-15 | Siemens Energy, Inc. | Generator neutral ground monitoring device utilizing direct current component measurement and analysis |
CN107291991A (en) * | 2017-05-25 | 2017-10-24 | 华侨大学 | A kind of Wind turbines early defect method for early warning based on dynamic network mark |
CN107403189A (en) * | 2017-06-30 | 2017-11-28 | 南京理工大学 | A kind of windage yaw discharge method for early warning based on Naive Bayes Classifier |
CN107483252A (en) * | 2017-08-22 | 2017-12-15 | 深圳企管加企业服务有限公司 | Calculator room equipment fault early warning system based on Internet of Things |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112393931A (en) * | 2019-08-13 | 2021-02-23 | 北京国双科技有限公司 | Detection method, detection device, electronic equipment and computer readable medium |
CN112906177A (en) * | 2019-12-04 | 2021-06-04 | 财团法人资讯工业策进会 | Apparatus and method for generating a motor diagnostic model |
CN111079855B (en) * | 2019-12-27 | 2023-08-11 | 三一重能股份有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting control console |
CN111079855A (en) * | 2019-12-27 | 2020-04-28 | 三一重能有限公司 | Fire-fighting method and device for wind turbine generator, storage medium and fire-fighting console |
CN112578794A (en) * | 2020-12-12 | 2021-03-30 | 云南昆船智能装备有限公司 | AGV fault detection method based on machine learning, storage medium and system |
CN112578794B (en) * | 2020-12-12 | 2023-09-01 | 云南昆船智能装备有限公司 | AGV fault detection method, storage medium and system based on machine learning |
CN112688836A (en) * | 2021-03-11 | 2021-04-20 | 南方电网数字电网研究院有限公司 | Energy routing equipment online dynamic sensing method based on deep self-coding network |
CN112632805A (en) * | 2021-03-15 | 2021-04-09 | 国能大渡河大数据服务有限公司 | Analysis early warning method, system, terminal and medium for crossing vibration area of unit |
CN112632805B (en) * | 2021-03-15 | 2021-06-01 | 国能大渡河大数据服务有限公司 | Analysis early warning method, system, terminal and medium for crossing vibration area of unit |
CN113670790A (en) * | 2021-07-30 | 2021-11-19 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Method and device for determining working state of ceramic filter |
CN113670790B (en) * | 2021-07-30 | 2024-03-22 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Method and device for determining working state of ceramic filter |
CN114330569A (en) * | 2021-12-30 | 2022-04-12 | 山东浪潮科学研究院有限公司 | Method and equipment for detecting fan unit component fault and storage medium |
CN117250942A (en) * | 2023-11-15 | 2023-12-19 | 成都态坦测试科技有限公司 | Fault prediction method, device, equipment and storage medium for determining model |
CN117250942B (en) * | 2023-11-15 | 2024-02-27 | 成都态坦测试科技有限公司 | Fault prediction method, device, equipment and storage medium for determining model |
Also Published As
Publication number | Publication date |
---|---|
CN109657982B (en) | 2022-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657982A (en) | A kind of fault early warning method and device | |
CN108520080A (en) | Automatic system of marine diesel-generator failure predication and health status online evaluation system and method | |
CN104200396B (en) | A kind of wind turbine component fault early warning method | |
CN110991666A (en) | Fault detection method, model training method, device, equipment and storage medium | |
US20170024649A1 (en) | Anomaly detection system and method for industrial asset | |
CN112149329B (en) | Method, system, equipment and storage medium for previewing state of key equipment of nuclear power plant | |
CN107450524A (en) | Predict the method, apparatus and computer-readable recording medium of industrial equipment failure | |
JP2015516530A (en) | Method and system for real-time performance recovery recommendations for centrifugal compressors | |
Jeong et al. | Integrated decision-support system for diagnosis, maintenance planning, and scheduling of manufacturing systems | |
EP3336349B1 (en) | Method and system for configuring wind turbines | |
JP6086875B2 (en) | Power generation amount prediction device and power generation amount prediction method | |
CN109855873A (en) | The method for diagnosing faults and device of steam turbine main shaft | |
CN113435703A (en) | Wind turbine generator system fault analysis system based on SCADA data modeling | |
CN115129607A (en) | Power grid safety analysis machine learning model test method, device, equipment and medium | |
CN108009063A (en) | The method of a kind of electronic equipment fault threshold detection | |
US11308408B2 (en) | Fault signal recovery system and method | |
CN110162743A (en) | A kind of data administering method based on k neighborhood nonlinear state Eq algorithm | |
Gong et al. | Machine learning-enhanced loT and wireless sensor networks for predictive analysis and maintenance in wind turbine systems | |
CN113220946A (en) | Fault link searching method, device, equipment and medium based on reinforcement learning | |
CN105353306B (en) | Motor fault diagnosis method and device and electric appliance | |
CN117057772A (en) | Real-time tracking display method and system for equipment fault detection and maintenance | |
US11188064B1 (en) | Process flow abnormality detection system and method | |
Liansheng et al. | SDR: Sensor data recovery for system condition monitoring | |
US20180087489A1 (en) | Method for windmill farm monitoring | |
CN116222753A (en) | Rotor system fault sensitivity feature extraction method and system |
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 |