CN109578226A - Wind turbines icing condition detection method based on icing detector and field group's intercommunication - Google Patents
Wind turbines icing condition detection method based on icing detector and field group's intercommunication Download PDFInfo
- Publication number
- CN109578226A CN109578226A CN201811323305.0A CN201811323305A CN109578226A CN 109578226 A CN109578226 A CN 109578226A CN 201811323305 A CN201811323305 A CN 201811323305A CN 109578226 A CN109578226 A CN 109578226A
- Authority
- CN
- China
- Prior art keywords
- icing
- unit
- neural network
- network model
- grade controller
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
- F03D80/40—Ice detection; De-icing means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The Wind turbines icing condition detection method based on icing detector and field group's intercommunication that the invention discloses a kind of detects that the icing related data of single unit sends field grade controller to using the icing detector installed on single unit；Field grade controller establishes the neural network model of unit icing by collecting the operation data of unit and the icing related data of acquisition；Other units in wind power plant obtain the model that model parameter establishes identification icing feature according to field grade controller training, the operation data of unit is input to and carries out that output is calculated in real time in the model, which is the no icing condition or icing thickness of unit；After unit identifies icing condition, the master control system of unit makes different grades of control measure or safe shutdown according to icing degree.The method of the present invention farthest protects the operation of entire wind power plant unit with least hardware, improves the reliability and safety of unit.
Description
Technical field
The present invention relates to the technical fields of wind-power electricity generation, refer in particular to a kind of wind based on icing detector and field group's intercommunication
Motor group icing condition detection method.
Background technique
It is known in the industry, major way of the wind-power electricity generation as wind energy utilization, be in current clean energy resource technology most it is mature and
Best one of the generation mode of development prospect.Blade is the important component of wind power generating set, but specific weather condition is drawn
The safety and efficient operation of the fan blade icing meeting fan of hair bring larger harm.Fan blade icing can change blower leaf
The pneumatic external form of piece and the operational efficiency for reducing blower.If blade icing can change the outer shape and aeroperformance of blade,
Increase blade drag, reduce lift, influences full machine maneuverability, stability；The transformation efficiency for eventually leading to wind energy reduces, serious
It can lead to the damage of blade, interruption of service occur, fan blade, which freezes to have become, guarantees what fan safe operation needed to solve
Pressing issues.Therefore, it is badly in need of a kind of scheme that can effectively detect unit icing now.
Summary of the invention
The purpose of the present invention is to overcome the shortcomings of the existing technology and deficiency, proposes a kind of based on icing detector and field
The Wind turbines icing condition detection method of group's intercommunication, this method is safe and reliable, accurate, farthest with least hardware
The operation for protecting entire wind power plant unit improves the reliability and safety of unit.
To achieve the above object, technical solution provided by the present invention are as follows: the wind based on icing detector and field group's intercommunication
Motor group icing condition detection method, specific as follows:
Using the icing detector installed on single unit, the icing related data of single unit is detected, including freeze
Speed, icing thickness, temperature and humidity information then send field grade controller to；
Field grade controller establishes unit knot in conjunction with the icing related data of acquisition by collecting the operation data of unit
The neural network model of ice, the input variable of neural network model include wind speed, wind direction, generator power, generator speed, paddle
Leaf angle, temperature, humidity, unit operational mode, set value of the power and speed setting value, the output of neural network model include knot
Ice-like state and icing thickness；Then the weight matrix parameter of neural network model is obtained by training, and neural network model
Characteristic parameter is updated to each unit in wind power plant by field grade controller, wherein neural network model can be based on history
Data carry out cyclic training, and neural network model parameter is regularly updated；
Other units in wind power plant obtain the mould that model parameter establishes identification icing feature according to field grade controller training
The operation data of unit is input to and carries out that output is calculated in real time in the model by type, which is the no knot of unit
Ice-like state or icing thickness, and in the case where being fitted without icing detector hardware, it still is able to identify unit icing shape
State；
After unit identifies icing condition, the master control system of unit is made different grades of control according to icing degree and is arranged
It applies or safe shutdown.
Compared with prior art, the present invention have the following advantages that with the utility model has the advantages that
The method of the present invention is intended in wind power plant with minimal hardware detection, the operation data based on unit, using neural network
Molding type detects the ice conditions of all blowers in wind power plant, and it is real to carry out under true ice condition compressor emergency shutdown processing
Now to the safeguard protection of unit, blade injury caused by avoiding blade from operating load under ice condition and transfinite, the accidents such as fracture
Appearance, have actual promotional value, be worthy to be popularized.
Detailed description of the invention
Fig. 1 is the functional block diagram of the method for the present invention.
Fig. 2 is the structure chart of neural network model.
Specific embodiment
The present invention is further explained in the light of specific embodiments.
As shown in Figure 1, the Wind turbines icing condition provided by the present embodiment based on icing detector and field group's intercommunication
Detection method, concrete condition are as follows:
Using the icing detector installed on single unit, the icing related data of single unit is detected, including freeze
The information such as speed, icing thickness, temperature and humidity then send field grade controller to.
Field grade controller establishes unit knot in conjunction with the icing related data of acquisition by collecting the operation data of unit
The neural network model of ice, Artificial Neural Network Structures are as shown in Fig. 2, the input variable of neural network model includes wind speed, wind
To, generator power, generator speed, blade angle, temperature, humidity, unit operational mode, set value of the power and revolving speed setting
Value etc., the output of neural network model includes icing condition and icing thickness etc.；Then neural network model is obtained by training
Weight matrix parameter, and the characteristic parameter of neural network model by field grade controller be updated to each machine in wind power plant
Group, wherein neural network model can carry out cyclic training based on historical data, enable neural network model parameter regular
It updates.
Other units in wind power plant obtain the mould that model parameter establishes identification icing feature according to field grade controller training
The operation data of unit is input to and carries out that output is calculated in real time in the model by type, which is the no knot of unit
Ice-like state or icing thickness, and in the case where being fitted without icing detector hardware, it still can identify unit icing shape
State.
After unit identifies icing condition, the master control system of unit is made different grades of control according to icing degree and is arranged
It applies or safe shutdown.
Embodiment described above is only the preferred embodiments of the invention, and but not intended to limit the scope of the present invention, therefore
All shapes according to the present invention change made by principle, should all be included within the scope of protection of the present invention.
Claims (1)
1. the Wind turbines icing condition detection method based on icing detector and field group's intercommunication, which is characterized in that specific as follows:
Using the icing detector installed on single unit, the icing related data of single unit is detected, including icing rate,
Icing thickness, temperature and humidity information then send field grade controller to；
Field grade controller establishes unit icing in conjunction with the icing related data of acquisition by collecting the operation data of unit
Neural network model, the input variable of neural network model include wind speed, wind direction, generator power, generator speed, blade angle
Degree, temperature, humidity, unit operational mode, set value of the power and speed setting value, the output of neural network model include icing shape
State and icing thickness；Then the weight matrix parameter of neural network model is obtained by training, and the feature of neural network model
Parameter is updated to each unit in wind power plant by field grade controller, wherein neural network model can be based on historical data
Cyclic training is carried out, neural network model parameter is regularly updated；
Other units in wind power plant obtain the model that model parameter establishes identification icing feature according to field grade controller training, will
The operation data of unit, which is input to, carries out that output is calculated in real time in the model, which is the no icing condition of unit
Or icing thickness, and in the case where being fitted without icing detector hardware, it still is able to identify unit icing condition；
After unit identifies icing condition, the master control system of unit according to icing degree make different grades of control measure or
Person's safe shutdown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811323305.0A CN109578226B (en) | 2018-11-08 | 2018-11-08 | Wind turbine icing state detection method based on intercommunication of icing detector and field group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811323305.0A CN109578226B (en) | 2018-11-08 | 2018-11-08 | Wind turbine icing state detection method based on intercommunication of icing detector and field group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109578226A true CN109578226A (en) | 2019-04-05 |
| CN109578226B CN109578226B (en) | 2020-05-01 |
Family
ID=65921761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811323305.0A Active CN109578226B (en) | 2018-11-08 | 2018-11-08 | Wind turbine icing state detection method based on intercommunication of icing detector and field group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109578226B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3730784A1 (en) * | 2019-04-25 | 2020-10-28 | Siemens Gamesa Renewable Energy A/S | A method for a computer-implemented analysis of operation data of one or more wind turbines |
| CN115857059A (en) * | 2022-11-24 | 2023-03-28 | 中国民航科学技术研究院 | Ice accumulation forecast management method, system, readable storage medium and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221083A (en) * | 2006-12-21 | 2008-07-16 | 通用电气公司 | Method and system for utilizing lateral tower acceleration to detect asymmetric icing |
| CN101876561A (en) * | 2008-12-22 | 2010-11-03 | 通用电气公司 | Be used for determining the method and system of possibility icing on the wind turbine blade |
| DE102015120306A1 (en) * | 2015-11-24 | 2017-05-24 | Wobben Properties Gmbh | Method for outputting control commands or event messages for a wind turbine or a wind farm and an evaluation device and a system therefor |
| CN104454386B (en) * | 2014-11-24 | 2017-08-29 | 北京金风科创风电设备有限公司 | Icing control method and device for wind generating set |
| CN108343566A (en) * | 2018-03-28 | 2018-07-31 | 长沙理工大学 | Blade icing fault online monitoring method and system based on running state of wind turbine generator |
-
2018
- 2018-11-08 CN CN201811323305.0A patent/CN109578226B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221083A (en) * | 2006-12-21 | 2008-07-16 | 通用电气公司 | Method and system for utilizing lateral tower acceleration to detect asymmetric icing |
| CN101876561A (en) * | 2008-12-22 | 2010-11-03 | 通用电气公司 | Be used for determining the method and system of possibility icing on the wind turbine blade |
| CN104454386B (en) * | 2014-11-24 | 2017-08-29 | 北京金风科创风电设备有限公司 | Icing control method and device for wind generating set |
| DE102015120306A1 (en) * | 2015-11-24 | 2017-05-24 | Wobben Properties Gmbh | Method for outputting control commands or event messages for a wind turbine or a wind farm and an evaluation device and a system therefor |
| CN108343566A (en) * | 2018-03-28 | 2018-07-31 | 长沙理工大学 | Blade icing fault online monitoring method and system based on running state of wind turbine generator |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3730784A1 (en) * | 2019-04-25 | 2020-10-28 | Siemens Gamesa Renewable Energy A/S | A method for a computer-implemented analysis of operation data of one or more wind turbines |
| CN115857059A (en) * | 2022-11-24 | 2023-03-28 | 中国民航科学技术研究院 | Ice accumulation forecast management method, system, readable storage medium and equipment |
| CN115857059B (en) * | 2022-11-24 | 2023-07-07 | 中国民航科学技术研究院 | Ice accumulation forecast management method, system, readable storage medium and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109578226B (en) | 2020-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101298864B (en) | Method of operating a wind turbine and wind turbine | |
| CN104807644A (en) | Fault early warning method and system for wind generation set variable-pitch system | |
| CN103608584B (en) | Method for running wind energy plant under ice-formation condition | |
| CN102606396B (en) | Method for managing and optimally controlling yawing sectors among multiple units in wind farm and system of method | |
| CN102817780B (en) | Device and method for controlling freezing of wind generating set | |
| CN104215640A (en) | Wind-generator blade defect damage inspection method and inspection system based on unmanned helicopter | |
| CN109578226A (en) | Wind turbines icing condition detection method based on icing detector and field group's intercommunication | |
| CN107735567A (en) | The initialization of wind turbine control function | |
| CN109737007A (en) | A kind of wind generating set yaw transfinites IPC variable Rate closing method | |
| CN202928617U (en) | Transmission line conducting wire icing and galloping on-line monitoring unit | |
| CN109595130A (en) | A kind of fan blade icing failure prediction method and system | |
| CN109236589B (en) | It is a kind of for assessing the method and device of fan blade deicing capital project | |
| CN208380747U (en) | A kind of pitch-controlled system of wind power generating set variable Rate feathering | |
| CN111350640A (en) | Pre-warning system and method for ice throwing risk of wind power plant in heavy ice area | |
| CN114623051A (en) | Intelligent identification and early warning method for icing state of wind power blade | |
| CN104484704A (en) | Wind power plant theoretical power determination method based on BP neural network | |
| CN105649896A (en) | Intelligent monitoring operation control system for wind turbine unit and control method thereof | |
| CN106351807A (en) | Wind turbine generator set blade coated ice removal method and ice removal system thereof | |
| CN103186699A (en) | Wind power generation wind resource site selection method based on economic coefficient | |
| CN202768252U (en) | Freezing control device of wind turbine generator system | |
| CN109322802A (en) | A kind of blade of wind-driven generator icing prediction technique and system | |
| CN204458201U (en) | A kind of wind generator set blade state monitoring apparatus | |
| CN103883483B (en) | A kind of 100W blade of wind-driven generator | |
| CN107784371B (en) | Nonlinear fitting-based intelligent self-adaptive control method for wind power yaw state | |
| CN212155056U (en) | Pre-warning system for ice throwing risk of wind power plant in heavy ice area |
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 |