CN115186861A - Wind power plant dynamic sector management optimization method and system based on digital twinning - Google Patents
Wind power plant dynamic sector management optimization method and system based on digital twinning Download PDFInfo
- Publication number
- CN115186861A CN115186861A CN202210496509.4A CN202210496509A CN115186861A CN 115186861 A CN115186861 A CN 115186861A CN 202210496509 A CN202210496509 A CN 202210496509A CN 115186861 A CN115186861 A CN 115186861A
- Authority
- CN
- China
- Prior art keywords
- wind
- wake
- wake flow
- model
- generating set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
Abstract
The invention relates to a wind power plant dynamic sector management optimization method and system based on digital twins, wherein the method comprises the following steps: establishing a refined weather research and forecast model considering the surface condition of the wind power plant; establishing a wind power plant wake high-end dynamic pneumatic simulation and virtual blade coupling model, performing simulation calculation on wind field parameters of a position where a fan is placed, and scanning laser anemometry to verify the details of the wake obtained through calculation to obtain an accurate wake model for controlling the wind power plant; the online health monitoring and diagnosing system of the impeller based on machine hearing obtains the health state information of the fan, and participates in the control optimization of the fan under the health state of the unit; according to the wake flow influence condition, the wind power plant single machine adopts self-adaptive optimization control and the wind power plant group adopts dynamic wake flow control based on hearing. The wind power station dynamic sector management system has the basic characteristics of wind knowledge, field knowledge, machine knowledge and group control, realizes dynamic sector management of the wind power station, and effectively improves the intelligent monitoring and power generation profit capacity of the fan impeller of the offshore wind power station.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a dynamic sector management optimization method and system for a wind power plant based on digital twinning.
Background
The offshore wind energy resource is rich, the wind speed is high, the turbulence is small, the generating capacity is large, and the development of offshore wind power does not occupy land resources, which provides favorable conditions for the development of offshore wind power. However, because of the characteristics of large installed capacity, long offshore distance, severe operating environment, difficult inspection and maintenance and the like, especially the pneumatic coupling of the unit caused by the wake interference effect of the fan reduces the total wind energy capture amount of a wind field, increases the load fluctuation and vibration of the fan, easily causes the damage of parts and reduces the service life of the fan. The offshore wind farm has higher requirements on intelligent monitoring level and equipment reliability, and the traditional technical scheme of the onshore wind farm cannot meet the operation requirements. Meanwhile, in the long-term service process of the fan impeller, damage accumulation is easily caused due to material aging, corrosion and fatigue and long-term operation in outdoor severe environment, serious accidents that the whole fan collapses due to deformation tail edge cracking and even fracture of the blade can be caused, and huge economic loss and even casualties are caused, so that the on-line monitoring and health evaluation of the fan impeller are very necessary. The prior art is like unmanned aerial vehicle patrolling and examining, and because of offshore wind farm is far away, the operational environment is abominable, it is very difficult to carry out.
Disclosure of Invention
The invention aims to provide a dynamic sector management optimization method and system for a wind power plant based on a digital twin, so as to achieve the purposes of improving quality and efficiency, reducing power consumption cost, being unattended and being intelligent in operation and maintenance.
The invention provides a wind power plant dynamic sector management optimization method based on digital twins, which comprises the following steps:
step 1, establishing a mesoscale weather research and forecast model considering the earth surface condition of a wind power plant, and acquiring downscale refined numerical weather and wind speed and wind direction prediction data of the wind power plant;
step 2, establishing a wind farm wake high-end dynamic pneumatic simulation and virtual blade coupling model by taking the acquired wind farm downscaling refinement numerical weather and wind speed and wind direction prediction data as initial and boundary conditions based on wind farm topography and unit layout, performing simulation calculation on wind farm parameters at the position where a fan is placed to obtain wind farm fan and terrain wake numerical calculation results, and obtaining an accurate wake model for wind farm control by scanning laser wind measurement to verify the calculated wake details and realizing wake visualization;
step 3, acquiring the health state information of the fan impeller by an impeller online health monitoring and diagnosing system based on machine hearing, and entering step 4 under the state that the unit is healthy;
step 4, detecting and analyzing the wake flow interference state of a fan of the wind power plant in real time according to the wake flow model, and realizing maximum power by adopting a single-machine self-adaptive optimization control strategy when a unit has no wake flow influence; when the influence of wake flow interference is detected by combining the mechanical hearing equipment, a field group control strategy is implemented according to flow field details provided by a wake flow model, and during implementation of the field group control strategy, sound wave data acquired by the mechanical hearing equipment is used for correcting the wake flow model, so that the maximum full-field power is realized.
Further, the field group control strategy in step 4 includes:
and carrying out simulation analysis on the numerical model of the wind power plant according to the load state of the wind turbine, and if the simulation analysis result meets the expectation, sending a control instruction to the related wind turbine.
Further, the step 4 comprises:
for a land wind farm: the method comprises the following steps of analyzing full-field power output, noise and vibration data in different wind directions at the same wind speed by using annual historical data of healthy unit states and equipment temperature in a normal operation range, establishing a numerical model, determining the corresponding wind directions of sectors, and determining whether the forming reasons of the sectors are influenced by wake flow or terrain of an upstream wind generating set according to analysis of terrain and unit layout, wherein the method comprises the following steps:
when the noise and vibration data model embodies the characteristic that the wind generating set is influenced by the wake flow, judging that the wind generating set starts to be influenced by the wake flow;
under the condition that the upstream wind generating set generates wake flow influence to form a sector, correcting a wake flow model according to a noise sound wave and vibration data model, determining the wake flow influence and the full coverage or partial coverage of the sector according to the wake flow model, and comprising the following steps of:
when the wind speed is in the second zone corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable speed control and yaw control are adopted; when the sector influence range partially covers the wind generating set, adopting yaw control;
when the wind speed is in three zones corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable pitch control and yaw control are adopted; when the influence range of the sector partially covers the wind generating set, adopting yaw control;
under the condition that a sector is generated by terrain, according to the characteristics of noise sound waves and vibration data, the wake flow influence is determined, and the sector covers the wind generating set completely or partially, and the method comprises the following steps:
the affected wind generating set is stopped, so that overlarge load during operation is prevented, the failure rate is prevented from being increased, and the service life of the wind generating set is prevented from being reduced;
for offshore wind farms: the method comprises the following steps of analyzing full-field power output, noise and vibration data in different wind directions at the same wind speed by using one-year historical data of the state health of a unit and the temperature of equipment in a normal operation range, establishing a numerical model, and determining the wind direction corresponding to a wake pit, wherein the method comprises the following steps:
when the noise and vibration data model embodies the characteristic that the wind generating set is influenced by the wake flow, judging that the wind generating set starts to be influenced by the wake flow;
under the condition that an upstream wind generating set generates wake flow influence, correcting a wake flow model according to a noise and vibration numerical model, and determining the wake flow influence to be a full-coverage or partial-coverage wind generating set, wherein the method comprises the following steps of:
when the wind speed is in the second zone corresponding to the running state of the wind driven generator: the sector range is full coverage wind generating set, and variable speed control and yaw control are adopted; and when the sector range partially covers the wind generating set, adopting yaw control.
When the wind speed is in three zones corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable pitch control and yaw control are adopted; and when the influence range of the sector partially covers the wind generating set, adopting yaw control.
The invention also provides a wind power plant dynamic sector management optimization system based on digital twinning, which comprises the following steps:
the wind knowing module is used for establishing a mesoscale weather research and forecast model considering the earth surface condition of the wind power plant and acquiring downscaling refinement numerical weather and wind speed and wind direction prediction data of the wind power plant;
the field knowing module is used for establishing a wind farm wake high-end dynamic pneumatic simulation and virtual blade coupling model by taking the acquired wind farm downscaling refined numerical weather and wind speed and wind direction prediction data as initial and boundary conditions based on wind farm topography and unit layout, carrying out simulation calculation on wind farm parameters at the positions where the fans are placed to obtain wind farm fans and topographic wake numerical calculation results, and scanning laser wind measurement to verify the calculated wake details to obtain an accurate wake model for wind farm control and realize wake visualization;
the machine learning module is used for acquiring the health state information of the fan impeller and participating in fan control optimization in the healthy state of the unit by the online impeller health monitoring and diagnosing system based on machine hearing;
the control module is used for detecting and analyzing the wake flow interference state of a fan of the wind power plant in real time according to the wake flow model, and when the unit has no wake flow influence, a single-machine self-adaptive optimization control strategy is adopted to realize the maximum power; when the influence of wake flow interference is detected by combining the mechanical hearing equipment, a field group control strategy is implemented according to flow field details provided by a wake flow model, and during implementation of the field group control strategy, sound wave data acquired by the mechanical hearing equipment is used for correcting the wake flow model, so that the maximum full-field power is realized.
Further, the control module carries out simulation analysis on the numerical model of the wind power plant according to the load state of the fan, and if the simulation analysis result meets expectations, a control instruction is sent to the related fan.
By means of the scheme, the wind power plant dynamic sector management optimization method and system based on the digital twin are based on the basic characteristics of wind knowledge, field knowledge, machine knowledge and group control, wind power plant dynamic sector management is achieved, and the intelligent monitoring and power generation profit capacity of the fan impeller of the offshore wind power plant is effectively improved.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a digital twin based wind farm dynamic sector management optimization method of the present invention;
FIG. 2 is a block diagram of the architecture of the digital twin-based wind farm dynamic sector management optimization system of the present invention;
fig. 3 is a flow chart of wind and field knowledge in an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1, the present embodiment provides a method for optimizing management of a dynamic sector of a wind farm based on a digital twin, including:
step S1, establishing a mesoscale weather research and forecast model (downscale WRF wind field model) considering the surface condition of the wind power plant, and acquiring downscale refined numerical weather and wind speed and wind direction prediction data of the wind power plant. A new generation of mesoscale numerical weather and power prediction system is designed by embedding a numerical Weather Research and Forecast (WRF) downscaling model into a fan and wake model, so that the prediction accuracy is remarkably improved, and initial and boundary conditions are provided for subsequent field work.
And S2, establishing a wind farm wake high-end dynamic pneumatic simulation and virtual blade coupling model by taking the acquired wind farm downscaling refined numerical weather and wind speed and wind direction prediction data as initial and boundary conditions based on wind farm topography and unit layout, carrying out simulation calculation on wind farm parameters at the positions where the fans are placed to obtain wind farm fan and terrain wake numerical calculation results, and scanning laser wind measurement to verify the calculated wake details to obtain an accurate wake model for wind farm control and realize wake visualization.
And S3, acquiring the health state information of the fan impeller by the online health monitoring and diagnosing system of the impeller based on machine hearing, and entering the step S4 in the state of machine set health. The step has obvious help to the pertinence and efficiency improvement of the on-site operation and maintenance work; the prediction accuracy of the fault is high, and the number of hours of the unit fault can be obviously reduced.
S4, detecting and analyzing the wake flow interference state of a fan of the wind power plant in real time according to the wake flow model, and realizing maximum power by adopting a single-machine self-adaptive optimization control strategy (comprising variable pitch, variable speed and yaw) when a unit has no wake flow influence; when the influence of wake flow interference is detected by combining the mechanical hearing equipment, a field group control strategy is implemented according to flow field details provided by a wake flow model, and during the implementation of the field group control strategy, sound wave data acquired by the mechanical hearing equipment is used for correcting the wake flow model, so that the maximum full field power is realized.
Under the condition that the wind power plant has no wake flow influence, the maximum power is realized by adopting a single-machine self-adaptive optimization control system. When the wind power plant is influenced by the wake, the sound wave data acquired on the blades are used for judging whether the wind power plant is influenced by the wake or not, and the wake model in the step S2 is corrected to acquire more accurate wake information for controlling the wind power plant group. And the field group control takes the variable pitch angle, the rotor speed and the engine room yaw angle of the unit as input quantities to perform real-time online control.
Under the condition of not considering the wake flow, the self-adaptive optimization control is adopted, so that the generating efficiency of the unit can be obviously improved, the load of the unit is reduced, the vibration is reduced, and the safety of the unit is improved; the wind power plant group control adopts dynamic wake control based on hearing, sound wave data is used as a judgment basis for judging whether the sound wave data is influenced by the wake, and the sound wave data is used for correcting the wake model, so that the model accuracy can be obviously improved, and the control process is more accurate. The control precision of the whole field group is obviously improved, the power generation efficiency is obviously improved, and the load of a unit affected by wake flow in the downwind direction is obviously reduced, and the safety is obviously improved.
The wind power plant dynamic sector management optimization method based on the digital twin takes wind-known field-known machine-group control as a basic characteristic, achieves wind power plant dynamic sector management, and effectively improves the intelligent monitoring and power generation profitability of the fan impeller of the offshore wind power plant.
In this embodiment, the field group control strategy in step 4 includes:
and carrying out simulation analysis on the numerical model of the wind power plant according to the load state of the fan, and if the simulation analysis result meets expectations, sending a control instruction to the related fan.
In this embodiment, step S4 includes:
1. when the unit has no wake flow influence, the maximum power is realized by adopting a single-machine self-adaptive optimization control strategy.
2. For a land wind farm: the method comprises the steps of analyzing full-field power output, noise and vibration data in different wind directions at the same wind speed by using one-year historical data of unit state health and equipment temperature in a normal operation range, establishing a numerical model, determining the corresponding wind direction of a sector, and determining whether the sector forming reason is influenced by wake flow or terrain of an upstream wind generating set according to terrain and unit layout analysis.
And 2.1, when the noise and vibration data model shows the characteristic that the wind generating set is influenced by the wake flow, judging that the wind generating set starts to be influenced by the wake flow.
2.2, under the condition that the upstream wind generating set generates wake flow influence to form a sector, correcting a wake flow model according to a noise sound wave and vibration data model, and determining that the wake flow influence is generated and the sector is a full coverage or partial coverage wind generating set according to the wake flow model.
2.2.1, when the wind speed is in a second zone corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable speed control and yaw control are adopted; and when the influence range of the sector partially covers the wind generating set, adopting yaw control.
2.2.2, when the wind speed is in three regions corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable pitch control and yaw control are adopted; and when the influence range of the sector partially covers the wind generating set, adopting yaw control.
And 2.3, under the condition that a sector is generated by the terrain, determining the influence of the wake flow and the sector as the full coverage or partial coverage of the wind generating set according to the characteristics of noise sound waves and vibration data.
2.3.1, the affected wind generating set is stopped, so that the phenomena that the load is overlarge during operation, the failure rate is increased and the service life of the set is reduced are prevented.
3. For offshore wind farms: and analyzing full-field power output, noise and vibration data in different wind directions at the same wind speed by using the annual historical data of the state health of the unit and the temperature of the equipment in the normal operation range, establishing a numerical model, and determining the wind direction corresponding to the wake pit.
And 3.1, when the noise and vibration data model shows the characteristic that the wind generating set is influenced by the wake flow, judging that the wind generating set is influenced by the wake flow.
3.2, under the condition that the upstream wind generating set generates wake flow influence, correcting the wake flow model according to the noise and vibration numerical model, and determining that the wake flow influence fully covers or partially covers the wind generating set.
3.2.1, when the wind speed is in a second zone corresponding to the running state of the wind driven generator: the sector range is full coverage wind generating set, and variable speed control and yaw control are adopted; and when the sector range partially covers the wind generating set, adopting yaw control.
3.2.2, when the wind speed is in three regions corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable pitch control and yaw control are adopted; and when the influence range of the sector partially covers the wind generating set, adopting yaw control.
Referring to fig. 2 and 3, the invention further provides a wind farm dynamic sector management optimization system based on digital twinning, which includes:
the wind knowing module 10 (wind knowing system) is used for establishing a mesoscale weather research and forecast model (downscaling WRF wind field model) considering the surface condition of the wind power plant, and acquiring downscaling refinement numerical weather and wind speed and wind direction prediction data of the wind power plant;
and the field knowing module 20 (field knowing system) is used for establishing a wind farm wake high-end dynamic pneumatic simulation and virtual blade coupling model by taking the acquired wind farm downscaling refined numerical weather and wind speed and wind direction prediction data as initial and boundary conditions based on wind farm terrain and unit layout, performing simulation calculation on wind farm parameters at the positions where the fans are placed to obtain wind farm fans and terrain wake numerical calculation results, and scanning laser wind measurement to verify the calculated wake details to obtain an accurate wake model for wind farm control and realize wake visualization.
And a machine learning module 30 (machine learning system) for acquiring the health state information of the fan impeller based on the online health monitoring and diagnosing system of the impeller based on machine hearing, and entering step S4 in a state that the unit is healthy. The step has obvious help for pertinence and efficiency improvement of field operation and maintenance work; the prediction accuracy of the fault is high, and the number of hours of the unit fault can be obviously reduced.
The control module 40 (dynamic sector management system) is used for detecting and analyzing the wake flow interference state of the wind turbine of the wind power plant in real time according to the wake flow model, and when the unit has no wake flow influence, a single-machine self-adaptive optimization control strategy (comprising variable pitch, variable speed and yaw) is adopted to realize the maximum power; when the influence of wake flow interference is detected by combining the mechanical hearing equipment, a field group control strategy is implemented according to flow field details provided by a wake flow model, and during implementation of the field group control strategy, sound wave data acquired by the mechanical hearing equipment is used for correcting the wake flow model, so that the maximum full-field power is realized.
The wind power plant dynamic sector management optimization system based on the digital twin takes wind-known field-known machine-group control as a basic characteristic, realizes wind power plant dynamic sector management, and effectively improves the intelligent monitoring and power generation profitability of the fan impeller of the offshore wind power plant.
In this embodiment, the control module performs simulation analysis on the numerical model of the wind farm according to the load state of the wind turbine, and sends a control instruction to the relevant wind turbine if the simulation analysis result meets expectations.
The wind power plant dynamic sector management optimization system based on the digital twin takes wind-known field-known machine-group control as a basic characteristic, realizes wind power plant dynamic sector management, and effectively improves the intelligent monitoring and power generation profitability of the fan impeller of the offshore wind power plant.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (5)
1. A wind power plant dynamic sector management optimization method based on digital twinning is characterized by comprising the following steps:
step 1, establishing a mesoscale weather research and forecast model considering the earth surface condition of a wind power plant, and acquiring downscale refined numerical weather and wind speed and wind direction prediction data of the wind power plant;
step 2, establishing a wind farm wake high-end dynamic pneumatic simulation and virtual blade coupling model by taking the acquired wind farm downscaling refinement numerical weather and wind speed and wind direction prediction data as initial and boundary conditions based on wind farm topography and unit layout, performing simulation calculation on wind farm parameters at the position where a fan is placed to obtain wind farm fan and terrain wake numerical calculation results, and obtaining an accurate wake model for wind farm control by scanning laser wind measurement to verify the calculated wake details and realizing wake visualization;
step 3, acquiring the health state information of the fan impeller by an impeller online health monitoring and diagnosing system based on machine hearing, and entering step 4 under the state that the unit is healthy;
step 4, detecting and analyzing the wake flow interference state of a fan of the wind power plant in real time according to the wake flow model, and realizing maximum power by adopting a single-machine self-adaptive optimization control strategy when a unit has no wake flow influence; when the influence of wake flow interference is detected by combining the mechanical hearing equipment, a field group control strategy is implemented according to flow field details provided by a wake flow model, and during implementation of the field group control strategy, sound wave data acquired by the mechanical hearing equipment is used for correcting the wake flow model, so that the maximum full-field power is realized.
2. The method for optimizing dynamic sector management of a wind farm based on digital twins as claimed in claim 1, wherein the farm group control strategy in step 4 comprises:
and carrying out simulation analysis on the numerical model of the wind power plant according to the load state of the fan, and if the simulation analysis result meets expectations, sending a control instruction to the related fan.
3. The digital twin-based wind farm dynamic sector management optimization method according to claim 1, wherein the step 4 comprises:
for onshore wind farms: the method comprises the following steps of analyzing full-field power output, noise and vibration data in different wind directions at the same wind speed by using one-year historical data of the state health of a unit and the temperature of equipment in a normal operation range, establishing a numerical model, determining the wind direction corresponding to a sector, and determining whether the sector forming reason is influenced by the wake flow of an upstream wind generating set or the terrain according to the terrain and the unit layout analysis, wherein the historical data comprises the following steps:
when the noise and vibration data model embodies the characteristic that the wind generating set is influenced by the wake flow, judging that the wind generating set starts to be influenced by the wake flow;
under the condition that the upstream wind generating set generates wake flow influence to form a sector, correcting a wake flow model according to a noise sound wave and vibration data model, determining the wake flow influence and the sector as a full coverage or partial coverage wind generating set according to the wake flow model, and comprising the following steps of:
when the wind speed is in the second zone corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable speed control and yaw control are adopted; when the sector influence range partially covers the wind generating set, adopting yaw control;
when the wind speed is in three zones corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable pitch control and yaw control are adopted; when the influence range of the sector partially covers the wind generating set, adopting yaw control;
under the condition that a sector is generated by terrain, according to the characteristics of noise sound waves and vibration data, the wake flow influence is determined, and the sector covers the wind generating set completely or partially, and the method comprises the following steps:
the affected wind generating set is shut down, so that the phenomenon that the load is too large in operation, the failure rate is increased, and the service life of the set is reduced is prevented;
for offshore wind farms: the method comprises the following steps of analyzing full-field power output, noise and vibration data in different wind directions at the same wind speed by using one-year historical data of the state health of a unit and the temperature of equipment in a normal operation range, establishing a numerical model, and determining the wind direction corresponding to a wake pit, wherein the method comprises the following steps:
when the noise and vibration data model embodies the characteristic that the wind generating set is influenced by the wake flow, judging that the wind generating set starts to be influenced by the wake flow;
under the condition that an upstream wind generating set generates wake flow influence, correcting a wake flow model according to a noise and vibration numerical model, and determining the wake flow influence to be a full-coverage or partial-coverage wind generating set, wherein the method comprises the following steps of:
when the wind speed is in the second zone corresponding to the running state of the wind driven generator: the sector range is full coverage wind generating set, and variable speed control and yaw control are adopted; and when the sector range partially covers the wind generating set, adopting yaw control.
When the wind speed is in three zones corresponding to the running state of the wind driven generator: the sector influence range is full coverage of the wind generating set, and variable pitch control and yaw control are adopted; and when the influence range of the sector partially covers the wind generating set, adopting yaw control.
4. A wind power plant dynamic sector management optimization system based on digital twinning is characterized by comprising the following components:
the wind knowing module is used for establishing a mesoscale weather research and forecast model considering the earth surface condition of the wind power plant and acquiring downscaling refinement numerical weather and wind speed and wind direction prediction data of the wind power plant;
the wind field acquisition module is used for establishing a wind field wake high-end dynamic pneumatic simulation and virtual blade coupling model by taking the acquired wind field downscaling refinement numerical weather and wind speed and direction prediction data as initial and boundary conditions based on wind field topography and unit layout, carrying out simulation calculation on wind field parameters at the positions where the wind turbines are arranged to obtain wind field wind turbine and topography wake numerical calculation results, scanning laser wind measurement to verify the wake details obtained by calculation to obtain an accurate wake model for wind field control, and realizing wake visualization;
the machine learning module is used for acquiring the health state information of the fan impeller and participating in fan control optimization in the machine set health state by an impeller online health monitoring and diagnosis system based on machine hearing;
the control module is used for detecting and analyzing the wake flow interference state of a fan of the wind power plant in real time according to the wake flow model, and when the unit has no wake flow influence, a single-machine self-adaptive optimization control strategy is adopted to realize the maximum power; when the influence of wake flow interference is detected by combining the mechanical hearing equipment, a field group control strategy is implemented according to flow field details provided by a wake flow model, and during implementation of the field group control strategy, sound wave data acquired by the mechanical hearing equipment is used for correcting the wake flow model, so that the maximum full-field power is realized.
5. The digital twin-based wind farm dynamic sector management optimization system according to claim 4, wherein the control module performs wind farm numerical model simulation analysis according to a wind farm load state, and sends a control instruction to a relevant wind farm if a simulation analysis result meets an expectation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210496509.4A CN115186861A (en) | 2022-05-09 | 2022-05-09 | Wind power plant dynamic sector management optimization method and system based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210496509.4A CN115186861A (en) | 2022-05-09 | 2022-05-09 | Wind power plant dynamic sector management optimization method and system based on digital twinning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115186861A true CN115186861A (en) | 2022-10-14 |
Family
ID=83513001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210496509.4A Pending CN115186861A (en) | 2022-05-09 | 2022-05-09 | Wind power plant dynamic sector management optimization method and system based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115186861A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116306042A (en) * | 2023-05-22 | 2023-06-23 | 西安鑫风动力科技有限公司 | Digital construction system for electric field topography |
| CN116771596A (en) * | 2023-06-30 | 2023-09-19 | 渤海石油航务建筑工程有限责任公司 | Offshore wind farm wake flow steering control method and related equipment |
| WO2024041409A1 (en) * | 2022-08-26 | 2024-02-29 | 北京金风科创风电设备有限公司 | Method and apparatus for determining representative wind generating set, and control method and apparatus |
-
2022
- 2022-05-09 CN CN202210496509.4A patent/CN115186861A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024041409A1 (en) * | 2022-08-26 | 2024-02-29 | 北京金风科创风电设备有限公司 | Method and apparatus for determining representative wind generating set, and control method and apparatus |
| CN116306042A (en) * | 2023-05-22 | 2023-06-23 | 西安鑫风动力科技有限公司 | Digital construction system for electric field topography |
| CN116306042B (en) * | 2023-05-22 | 2023-09-15 | 华能新疆青河风力发电有限公司 | Digital construction system for electric field topography |
| CN116771596A (en) * | 2023-06-30 | 2023-09-19 | 渤海石油航务建筑工程有限责任公司 | Offshore wind farm wake flow steering control method and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115186861A (en) | Wind power plant dynamic sector management optimization method and system based on digital twinning | |
| US10612519B2 (en) | Optimal wind farm operation | |
| US9702345B2 (en) | Method of operating a wind turbine | |
| US10385829B2 (en) | System and method for validating optimization of a wind farm | |
| US7895018B2 (en) | Event monitoring via combination of signals | |
| US10371124B2 (en) | System and method for determining wind farm wake loss | |
| CN111794909B (en) | Sector regulation-oriented wind farm level yaw dynamic optimization method and system | |
| US10253758B2 (en) | System and method for optimizing wind farm performance | |
| CN103080540A (en) | Control of wind turbines in a wind park | |
| CN113033009B (en) | Real-time calculation method for wake flow loss of offshore wind farm in service | |
| EP3855019A1 (en) | System and method for operating a wind turbine | |
| CN111091298A (en) | Wind power plant flow field coupling characteristic evaluation and intelligent grouping method and system | |
| CN111340307B (en) | Method for predicting wind power generation power of fan and related device | |
| CN110761958B (en) | Blade stall diagnosis method and device of wind generating set | |
| CN111810357A (en) | System and method for mitigating damage to rotor blades of a wind turbine | |
| EP3608538A1 (en) | Model-based repowering solutions for wind turbines | |
| CN106677985A (en) | Wind turbine generator set evaluation system and predictive control service system thereof | |
| EP4060430A1 (en) | Systems and methods for operating power generating assets | |
| CN110008583B (en) | Wind power plant wind power resource condition prediction method and system | |
| EP3406897B1 (en) | System and method for determining wind farm wake loss | |
| Bao et al. | A data-driven approach for identification and compensation of wind turbine inherent yaw misalignment | |
| JP2019183734A (en) | Wind farm, and operation method and controller thereof | |
| EP3964708A1 (en) | Method and controller arrangement for operating a wind turbine farm | |
| JP7267815B2 (en) | Wind turbine cluster power generation evaluation device, wind turbine cluster power generation evaluation method, and program | |
| CN115680997A (en) | Wind turbine generator maximum power tracking control method capable of adapting to turbulence |
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 |