CN103161668A - Intelligent wind turbine generator working condition identification system and method - Google Patents
Intelligent wind turbine generator working condition identification system and method Download PDFInfo
- Publication number
- CN103161668A CN103161668A CN2013100564955A CN201310056495A CN103161668A CN 103161668 A CN103161668 A CN 103161668A CN 2013100564955 A CN2013100564955 A CN 2013100564955A CN 201310056495 A CN201310056495 A CN 201310056495A CN 103161668 A CN103161668 A CN 103161668A
- Authority
- CN
- China
- Prior art keywords
- operating mode
- wind
- parameter
- generator
- zone
- 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
Images
Classifications
-
- 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
- Wind Motors (AREA)
Abstract
The invention discloses an intelligent wind turbine generator working condition identification method which is used for identifying working conditions of a wind turbine generator comprising a plurality of subsystems. The method includes the steps of obtaining a plurality of parameters of the wind turbine generator; dividing the parameters into global parameters and local parameters; extracting eigen values of the plurality of parameters; and obtaining an eigen value vector of each parameter according to the eigen value of each parameter; and classifying the eigen value vectors of the plurality of parameters into global working conditions and subsystem working conditions through a first layer self-organizing map neural network and a second layer self-organizing map neural network to obtain a working condition identification result of the wind turbine generator. The plurality of parameters of the wind turbine generator are adopted to analyze the wind turbine generator working conditions, the wind turbine generator working conditions are divided into the plurality of global working conditions and subsystem working conditions, wind turbine generator working condition identification stability can be improved, and monitoring precision for wind turbine generator running is improved.
Description
Technical field
The present invention relates to wind power generation field, relate in particular to a kind of Intelligent wind power unit operating mode identification system and method.
Background technique
Wind energy more and more is subject to the attention of countries in the world as a kind of renewable energy sources of cleaning.Its amount of accumulateing is huge, and the wind energy in the whole world is about 2.74 * 10
9MW, wherein available wind energy is 2 * 10
7MW is than also large 10 times of the water energy total amounts that can develop on the earth.
The kinetic energy of keeping watch is transformed into mechanical kinetic energy, then mechanical energy is converted into electric power kinetic energy, Here it is wind-power electricity generation.The principle of wind-power electricity generation is to utilize wind-force to drive the air vane rotation, then sees through booster engine with the speed lifting of rotation, impels the generator generating.According to present windmill technology, be approximately the gentle breeze speed (degree of gentle breeze) of three meters of per seconds, just can begin generating.Wind-power electricity generation forms one upsurge just in the world, because wind-power electricity generation does not need to use fuel, also can not produce radiation or atmospheric pollution.The needed device of wind-power electricity generation is called wind power generating set.This wind power generating set can be divided wind wheel (comprising tail vane), motor and steel tower three parts substantially.
Along with development and the large-scale commercial operation of wind generating technology, because wind turbine forms this height, the maintenance maintenance expense is high and the operation life-span is long, so the stability of wind-powered electricity generation unit and safety issue obtain paying close attention to more and more widely.Special Large-scale Wind Turbines, it is usually operated under the weather conditions and alternate load operating mode of very severe, and is round-the-clock operation.Therefore, the wind-powered electricity generation unit is carried out condition monitoring, can effectively avoid the generation of wind-powered electricity generation unit fault, reach and under outage state, operational outfit is not effectively being monitored.At present, various wind-powered electricity generation supervisory systems are widely used in supporting and ensureing the normal operation of wind-powered electricity generation unit.Yet, single or several parameters that the monitoring strategies that these wind-powered electricity generation supervisory systems of prior art adopt is based on the wind-powered electricity generation unit more are according to (as wind speed, motor speed and active power etc.), the wind-powered electricity generation unit is divided into several different operating modes, then controls the selection of adjusting of parameter and monitoring threshold according to different operating modes.But in fact, only divide the operating conditions of wind-powered electricity generation unit by limited parameter threshold, can not effectively describe wind power generating set operating conditions complicated and changeable.Therefore adopt probably the making false judgment and mistake such as false alarm etc. occurs in the actual monitored process of wind-powered electricity generation supervisory system of this monitoring strategies of prior art, this will directly have influence on the normal operation of wind-powered electricity generation unit.And, because the wind-powered electricity generation unit that reality is used is integrated by a plurality of subtense angles, different subtense angles its response is different to different operating mode, therefore when the supervisory system of effective wind-powered electricity generation unit reasonable in design, need also to consider that wherein subtense angle is to the response of different operating modes.
Therefore, those skilled in the art is devoted to develop a kind of Intelligent wind power unit operating mode identification system and method, adopts a plurality of parameters of wind-powered electricity generation unit to carry out the operating mode identification.
Summary of the invention
Because the defects of prior art, technical problem to be solved by this invention is to provide a kind of Intelligent wind power unit operating mode identification system and method, and a plurality of parameters by adopting the wind-powered electricity generation unit also use self-organizing map neural network to realize the operating mode identification of wind-powered electricity generation unit.
For achieving the above object, the invention provides a kind of Intelligent wind power unit operating mode discrimination method, it is characterized in that, the wind-powered electricity generation unit comprises a plurality of subtense angles, and described discrimination method comprises step:
Use sensor to obtain a plurality of parameters of described wind-powered electricity generation unit, described parameter comprises the enviromental parameter of described wind-powered electricity generation unit and the unit parameter of described wind-powered electricity generation unit;
Be global parameter and local parameter with described a plurality of parametric classifications, described global parameter is all relevant to described a plurality of subtense angles, and described local parameter is only relevant to a part in described a plurality of subtense angles;
Extract the eigenvalue of described a plurality of parameters, described eigenvalue comprise the statistics eigenvalue and the time, the frequency domain character value;
Obtain the feature value vector of each described parameter according to the eigenvalue of each described parameter;
The feature value vector input first layer self-organizing map neural network of described a plurality of parameters that will be relevant to same described subtense angle obtains the output vector relevant with described subtense angle; Will to described a plurality of subtense angles respectively relevant each described output vector as mixed vector and described mixed vector input second layer self-organizing map neural network is obtained the identification result of the operating mode of described wind-powered electricity generation unit.
Further, described subtense angle comprises wheel hub subtense angle, drive subsystem, generator subtense angle, electrical control subtense angle and column foot subtense angle.
Further, described operating mode comprises a plurality of overall operating modes and a plurality of subtense angle operating mode; Described overall operating mode represents the overall operation state of described wind-powered electricity generation unit, comprises shutdown, startup, underload, fully loaded and overload; Described subtense angle operating mode represents the running state of described subsystems, comprise the low speed of wheel hub subtense angle, at a high speed, rated speed, stall and locking.
Further, use regular polygon to show the identification result of described operating mode;
It is regional that the line on the center of described regular polygon and each summit of described regular polygon is divided into a plurality of leg-of-mutton overall operating modes with described regular polygon, and described overall operating mode zone is corresponding one by one with described overall operating mode;
Each described overall operating mode zone all is divided into a plurality of subtense angle operating modes zones from the center of described regular polygon to the line on the leg-of-mutton base in described overall operating mode zone; In each described overall operating mode zone, described subtense angle operating mode zone is corresponding one by one with described subtense angle operating mode;
The line that each described overall operating mode zone all is parallel to the leg-of-mutton base in described overall operating mode zone is divided into a plurality of stepped zones, and the severe degree of operating mode that the center of the described regular polygon of distance described stepped zone far away is corresponding is higher;
The identification result of the described operating mode that shows when needs is when being in an overall operating mode of a severe degree of operating mode, and is selected to the stepped zone to should the severe degree of operating mode in overall operating mode zone that should overall operating mode in described regular polygon; The identification result of the described operating mode that shows when needs is when being in a sub-systems operating mode of a severe degree of operating mode, and is selected to the stepped zone to should the severe degree of operating mode in subtense angle operating mode zone that should the subtense angle operating mode in described regular polygon.
Further, in described regular polygon, the color in the described zone of choosing is different from the color in not selected zone.
further, described enviromental parameter comprises wind speed, wind direction and the ambient temperature at place, described wind-powered electricity generation unit place, described unit parameter comprises the generator U phase voltage of described wind-powered electricity generation unit, generator V phase voltage, generator W phase voltage, generator U phase current, generator V phase current, generator W phase current, mains frequency, motor power factor, output power, wind speed round, generator speed, generator-temperature detection, the controller temperature, the main bearing temperature, the gear box lubricating oil temperature, the Hydraulic System Oil temperature, the lubricant oil liquid level, the hydraulic oil liquid level, the cable torsion angle, blade angle, the position, cabin, generated energy, consumes power, program runtime, the wheel hub number of starts, yaw angle, driftage left-hand rotation number of times, driftage right-hand rotation number of times, driftage power, angle of inclination and Ta Nei temperature.
Further, described wind speed, described wind direction and described ambient temperature described is categorized as described global parameter; Described wind speed round and described blade angle described is categorized as described local parameter, and it is relevant to described wheel hub subtense angle; Described gear box lubricating oil temperature described is categorized as described local parameter, and it is relevant to described drive subsystem; Described output power, described generator U phase voltage, described generator V phase voltage, described generator W phase voltage, described generator U phase current, described generator V phase current, described generator W phase current, described generator-temperature detection, described mains frequency and described consumes power described is categorized as described local parameter, and it is relevant to described generator subtense angle; Temperature described is categorized as described local parameter in described yaw angle, described driftage left-hand rotation number of times, described driftage right-hand rotation number of times, described driftage power, described angle of inclination and described tower, and it is relevant to described column foot subtense angle.
Further, the process that obtains the feature value vector of each described parameter according to the eigenvalue of each described parameter comprises that the eigenvalue to each described parameter is weighted calculating; The neuron weights that use in described weighted calculation obtain by the described first layer self-organizing map neural network of training and described second layer self-organizing map neural network.
Further, the present invention also provides a kind of Intelligent wind power unit operating mode identification system, use above-mentioned Intelligent wind power unit operating mode discrimination method, it is characterized in that, comprise data acquisition module, choice of parameters diversity module, characteristic extracting module and operating mode recognition module; Described data acquisition module uses sensor to obtain described a plurality of parameters of described wind-powered electricity generation unit; Described choice of parameters diversity module is described global parameter and described local parameter with described a plurality of parametric classifications; Described characteristic extracting module is extracted the eigenvalue of described a plurality of parameters; Described operating mode recognition module obtains the feature value vector of each described parameter according to the eigenvalue of each described parameter, and uses described first layer self-organizing map neural network and described second layer self-organizing map neural network to obtain the identification result of the operating mode of described wind-powered electricity generation unit.
In better embodiment of the present invention, a kind of Intelligent wind power unit operating mode identification system and method thereof are provided.Wherein, Intelligent wind power unit operating mode identification system of the present invention comprises data acquisition module, choice of parameters diversity module, characteristic extracting module and operating mode recognition module.Data acquisition module uses sensor to obtain a plurality of parameters of wind-powered electricity generation unit; The choice of parameters diversity module is global parameter and local parameter with a plurality of parametric classifications; Characteristic extracting module is extracted the eigenvalue of a plurality of parameters; The operating mode recognition module obtains the feature value vector of parameters according to the eigenvalue of parameters, and uses first layer self-organizing map neural network and second layer self-organizing map neural network to obtain the identification result of the operating mode of wind-powered electricity generation unit.The wind-powered electricity generation unit comprises a plurality of subtense angles of wheel hub subtense angle, drive subsystem, generator subtense angle, electrical control subtense angle and column foot subtense angle, and the operating mode of wind-powered electricity generation unit comprises a plurality of overall operating modes and a plurality of subtense angle operating mode.Intelligent wind power unit operating mode discrimination method of the present invention comprises step: use sensor to obtain a plurality of parameters of wind-powered electricity generation unit; Be global parameter and local parameter with a plurality of parametric classifications; Extract the eigenvalue of a plurality of parameters; Obtain the feature value vector of parameters according to the eigenvalue of parameters; The feature value vector input first layer self-organizing map neural network of a plurality of parameters that will be relevant to same subtense angle obtains the output vector relevant with this subtense angle; Will to a plurality of subtense angles respectively relevant each output vector as mixed vector and this mixed vector input second layer self-organizing map neural network is obtained the identification result of the operating mode of wind-powered electricity generation unit.Wherein, the process that obtains the feature value vector of parameters according to the eigenvalue of parameters comprises that the eigenvalue to parameters is weighted calculating, and the neuron weights that use in weighted calculation obtain by training first layer self-organizing map neural network and second layer self-organizing map neural network.The identification result that obtains operating mode shows by the regular polygon in the overall operating mode zone that comprises the overall operating mode of a plurality of correspondences, and each overall operating mode zone all is divided into the subtense angle operating mode zone of a plurality of corresponding subtense angle operating modes and the stepped zone of the severe degree of a plurality of corresponding operating mode; Choose the stepped zone in overall operating mode zone to represent that the operating mode of wind-powered electricity generation unit is the overall operating mode that is in the corresponding severe degree of operating mode, choose the stepped zone in subtense angle operating mode zone to represent that the operating mode of wind-powered electricity generation unit is the subtense angle operating mode that is in the severe degree of operating mode of correspondence.
This shows, Intelligent wind power unit operating mode identification system of the present invention and method thereof adopt a plurality of parameters of wind-powered electricity generation unit to analyze the operating mode of wind-powered electricity generation unit, according to parameter, the impact of different sub-systems is divided into local parameter and global parameter, the operating mode of wind-powered electricity generation unit is divided into some overall operating modes and subtense angle operating mode, by a plurality of parameters being given respectively different neuron weights and using two-layer self-organizing map neural network to determine the operating mode of wind-powered electricity generation unit.Thus, the present invention can improve the identification stability to the operating mode of wind-powered electricity generation unit, not can because of single parameter can several parameters extremely cause erroneous judgement, and multilayer identification of the present invention can with the further refinement of the operating mode of wind-powered electricity generation unit, improve the monitoring precision to the operation of wind-powered electricity generation unit.
Be described further below with reference to the technique effect of accompanying drawing to design of the present invention, concrete structure and generation, to understand fully purpose of the present invention, feature and effect.
Description of drawings
Fig. 1 is the structural representation of Intelligent wind power unit operating mode identification system of the present invention, has wherein shown data flow.
Fig. 2 is the work schematic diagram of the neural map neural network of two-layer self-organization that uses of Intelligent wind power unit operating mode identification system of the present invention and method thereof.
Fig. 3 is the flow chart of the neural map neural network of two-layer self-organization that uses of training Intelligent wind power unit operating mode identification system of the present invention and method thereof.
Fig. 4 be training Intelligent wind power unit operating mode identification system of the present invention and method thereof use the neural map neural network of two-layer self-organization the time, the flow chart of the work of the SOM module SOM1 in the neural map neural network of first layer self-organization.
Fig. 5 is the regular polygon of identification result of the operating mode of the demonstration wind-powered electricity generation unit that uses in one embodiment.
Embodiment
In Intelligent wind power unit operating mode identification system of the present invention and method thereof, the wind-powered electricity generation unit comprises a plurality of subtense angles of wheel hub subtense angle, drive subsystem, generator subtense angle, electrical control subtense angle and column foot subtense angle, and the operating mode of wind-powered electricity generation unit comprises a plurality of overall operating modes and a plurality of subtense angle operating mode.As shown in Figure 1, Intelligent wind power unit operating mode identification system of the present invention comprises data acquisition module 10, choice of parameters diversity module 20, characteristic extracting module 30 and operating mode recognition module 40.Data acquisition module 10 uses sensor to obtain a plurality of parameters 1 of wind-powered electricity generation unit, and parameter 1 comprises the enviromental parameter of wind-powered electricity generation unit and the unit parameter of wind-powered electricity generation unit, and these parameters are sent to choice of parameters diversity module 20.Choice of parameters diversity module 20 is to send to characteristic extracting module 30 after global parameter and local parameter with these parametric classifications.Characteristic extracting module 30 is extracted the eigenvalue of these parameters and the eigenvalue of these parameters is sent to operating mode recognition module 40.Operating mode recognition module 40 obtains the feature value vector of parameters according to the eigenvalue of parameters, and uses first layer self-organizing map neural network and second layer self-organizing map neural network to obtain the identification result of the operating mode of wind-powered electricity generation unit.
Particularly, Intelligent wind power unit operating mode discrimination method of the present invention comprises the following steps:
The first step uses sensor to obtain a plurality of parameters of wind-powered electricity generation unit.
Data acquisition module 10 uses sensor to obtain a plurality of parameters of wind-powered electricity generation unit, and these parameters comprise the enviromental parameter of wind-powered electricity generation unit and the unit parameter of wind-powered electricity generation unit, and these parameters are sent to choice of parameters diversity module 20.
Wherein, enviromental parameter comprises wind speed, wind direction, ambient temperature, atmospheric pressure, ambient humidity and the air density at place, wind-powered electricity generation unit place.unit parameter comprises the generator U phase voltage of wind-powered electricity generation unit, generator V phase voltage, generator W phase voltage, generator U phase current, generator V phase current, generator W phase current, mains frequency, motor power factor, output power, wind speed round, generator speed, generator-temperature detection, the controller temperature, the main bearing temperature, the gear box lubricating oil temperature, the Hydraulic System Oil temperature, the lubricant oil liquid level, the hydraulic oil liquid level, the cable torsion angle, blade angle, the position, cabin, generated energy, consumes power, program runtime, the wheel hub number of starts, yaw angle, driftage left-hand rotation number of times, driftage right-hand rotation number of times, driftage power, the angle of inclination, temperature in tower, braking state, bearing temperature, the gear temperature, the gear case oil pumping pressure, the wheel hub motor moment of torsion, become the slurry motor temperature, wattless power, voltage on line side, frequency-converter power, the pump start number of times, temperature difference, the coolant pump start-stop time, cooling water pressure and electric cabinet temperature and the brake number of starts.
Second step is global parameter and local parameter with a plurality of parametric classifications.
Choice of parameters diversity module 20 is to send to characteristic extracting module 30 after global parameter and local parameter with these parametric classifications.Wherein, global parameter is all relevant to a plurality of subtense angles of wind-powered electricity generation unit, and described local parameter is only relevant to a part in a plurality of subtense angles.Usually, the enviromental parameter of wind-powered electricity generation unit is all relevant to a plurality of subtense angles of wind-powered electricity generation unit, is categorized as global parameter; And the unit parameter of wind-powered electricity generation unit comprises the parameter that obtains from the subsystems of wind-powered electricity generation unit, some is all relevant to a plurality of subtense angles of wind-powered electricity generation unit for these parameters, be categorized as global parameter, other are relevant to one or subtense angle partly, are categorized as local parameter.
For example, above-mentioned wind speed, wind direction, ambient humidity and system operation time is categorized as global parameter.The local parameter that is categorized as of motor temperature is starched in wind speed round, blade angle, wheel hub motor moment of torsion and change, and it is relevant to the wheel hub subtense angle.The local parameter that is categorized as of braking state, bearing temperature, gear temperature, gear case oil pumping pressure, lubricating oil temperature, pump start number of times and the number of starts of braking, it is relevant to drive subsystem.Output power, reactive power generator, generator U phase voltage, generator V phase voltage, generator W phase voltage, generator U phase current, generator V phase current, generator W phase current, motor temperature, mains frequency, voltage on line side, frequency-converter power, consumed power and electric cabinet temperature be categorized as local parameter, it is relevant to the generator subtense angle.Yaw angle, driftage left-hand rotation number of times, driftage right-hand rotation number of times, driftage power, angle of inclination and Ta Nei temperature be categorized as local parameter, it is relevant to the column foot subtense angle.
The 3rd step, the eigenvalue of a plurality of parameters of extraction.
The 4th goes on foot, and obtains the feature value vector of parameters according to the eigenvalue of parameters, obtains the identification result of the operating mode of wind-powered electricity generation unit according to each feature value vector.
Operating mode recognition module 40 obtains the feature value vector of parameters according to the eigenvalue of parameters, and uses two-layer self-organizing map neural network to obtain the identification result of the operating mode of wind-powered electricity generation unit.
As shown in Figure 2, two-layer self-organizing map neural network comprises input layer 41, first layer self-organizing map neural network 42 and second layer self-organizing map neural network 43.the number of the node of input layer 41 equates with the number of feature value vector, is 64 in the present embodiment, is respectively wind speed, average ambient temperature, tower cylinder cabinet mean temperature, the average oil temperature in gear box oil ingress, the average oil temperature of gear tank, the box bearing mean temperature, the dynamo bearing mean temperature, winding maximum temperature mean value, active power mean value, the active power minimum value, the active power maximum value, wattless power mean value, the wattless power minimum value, the wattless power maximum value, generator voltage mean value, the generator voltage minimum value, the generator voltage maximum value, dynamo current mean value, the dynamo current minimum value, the dynamo current maximum value, generator voltage on line side mean value, generator voltage on line side minimum value, generator voltage on line side maximum value, generator power factor mean value, generator power factor minimum value, generator power factor maximum value, wheel hub motor moment of torsion effective value, blade angle mean value, the blade angle maximum value, driftage frequency variator mean temperature, the driftage power average value, driftage power maximum value, the cabin position mean, cabin cell voltage mean value, the main bearing mean temperature, the deflection of driving direction tower cylinder, 1 second wind data screening mean value, 1 second wind data screening minimum value, 1 second wind data screening maximum value, wheel speed mean value, the wheel speed maximum value, generator speed mean value, the generator speed minimum value, the generator speed maximum value, gear case oil electric pump pressure mean values, gear case oil mechanical pump pressure mean values, wind speed turbulent flow mean value, wind direction, generator cooling-water water in-out port temperature-averaging value, generated energy, consumes power, program runtime, the generator connecting in parallel with system number of times, the generator networking time, the wheel hub number of starts, wheel hub working time, the driftage left-hand rotation number of starts, the driftage left turn maneuver time, the pump start number of times, high speed fuel pump working time, the cooling fan number of starts, cooling fan working time, brake hydraulic working time, brake working time.The number of the node of first layer self-organizing map neural network 42 equates with the number of subtense angle operating mode, is 5 * 5 in the present embodiment, is respectively the operating mode (describing in detail hereinafter) of five grades of corresponding five sub-systems.The number of the node of second layer self-organizing map neural network 43 is relevant to the number of overall operating mode, is 6 * 6 in the present embodiment, and is relevant to six class overall situation operating modes (describing in detail hereinafter).As shown in Figure 2, the feature value vector of the parameters relevant to subtense angle 1 enters first layer self-organizing map neural network 42 from input layer 41 and obtains the output vector relevant with subtense angle 1, the feature value vector of the parameters relevant to subtense angle N enters first layer self-organizing map neural network 42 from input layer 41, obtains the output vector relevant to subtense angle N.
Wherein, in the process of the feature value vector that obtains parameters according to the eigenvalue of parameters, the eigenvalue of 40 pairs of parameters of operating mode recognition module is weighted calculating, and the neuron weights that use in weighted calculation obtain by training first layer self-organizing map neural network 42 and second layer self-organizing map neural network 43.Concrete steps following (referring to Fig. 3,4):
As shown in Figure 3, first layer self-organizing map neural network 42 comprise k SOM module: SOM1, SOM2 ..., SOMk, they process respectively with subtense angle 1, subtense angle 2 ..., parameter that subtense angle k is relevant.Correspondingly, each SOM module is carried out initialization: the peripheral sensory neuron weights of its use are set and impose a condition.
Wherein, the method for the eigenvalue of extracting parameter is the same with the method for description in aforesaid the 3rd step.The peripheral sensory neuron weights that each SOM module is used are to be all weight matrix, as the formula (1), for subtense angle i, SOM module SOMi can obtain the feature value vector (referred to as the feature value vector relevant with subtense angle i) of a plurality of parameters relevant with subtense angle i with weight matrix and the dot product of each eigenvalue.In formula, eigenvalue x (i)
1, x (i)
2..., x (i)
nBe n the parameter relevant to subtense angle i.
SOM1, SOM2 ..., SOMk obtain in calculation procedure 102 respectively with subtense angle 1, subtense angle 2 ..., feature value vector R that subtense angle k is relevant
1, R
2..., R
kWith mapping layer L2 norm.
Wherein, the formula of calculating mixed vector P is:
P=θ
1Y
1+θ
2Y
2+…+θ
kY
k (2)
In formula, θ
1, θ
2..., θ
kBe the first weights of nervus opticus.
Step 203 according to the result of calculation in step 202, is revised correction value that nervus opticus unit weights obtain correction value and use this nervus opticus unit weights according to each output vector Y
1, Y
2..., Y
kCalculate mixed vector P.Identical in the method for calculating mixed vector P herein and step 202.
Step 204 judges whether to satisfy imposing a condition in step 201, if the judgment is Yes, enters step 205; If the judgment is No, enter step 202.
Thus, each feature value vector passes through first layer self-organizing map neural network 42 from input layer 41, each SOM module SOM1, SOM2 in first layer self-organizing map neural network 42 ..., SOMk processes respectively with subtense angle 1, subtense angle 2 ..., parameter that subtense angle k is relevant eigenvalue, by use the peripheral sensory neuron weights to the eigenvalue of parameters be weighted calculate obtain with subtense angle 1, subtense angle 2 ..., feature value vector that subtense angle k is relevant.Each SOM module SOM1, SOM2 ..., SOMk exports respectively with subtense angle 1, subtense angle 2 ..., output vector that subtense angle k is relevant.Second layer self-organizing map neural network 43 by use nervus opticus unit weights to each and subtense angle 1, subtense angle 2 ..., output vector that subtense angle k is relevant is weighted the identification result that calculates the operating mode that obtains the wind-powered electricity generation unit.
Intelligent wind power unit operating mode identification system of the present invention and method thereof use regular polygon to show the identification result of the operating mode of wind-powered electricity generation unit.This regular polygon is by the overall operating mode zone that comprises the overall operating mode of a plurality of correspondences, and each overall operating mode zone all is divided into the subtense angle operating mode zone of a plurality of corresponding subtense angle operating modes and the stepped zone of the severe degree of a plurality of corresponding operating mode.Particularly, it is regional that the line on the center of regular polygon and each summit of regular polygon is divided into a plurality of leg-of-mutton overall operating modes with regular polygon, and overall operating mode zone is corresponding one by one with overall operating mode.Each overall operating mode zone all is divided into a plurality of subtense angle operating modes zones from the center of regular polygon to the line on the leg-of-mutton base in overall operating mode zone; In each overall operating mode zone, subtense angle operating mode zone is corresponding one by one with the subtense angle operating mode.The line that each overall operating mode zone all is parallel to the leg-of-mutton base in overall operating mode zone is divided into a plurality of stepped zones, and stepped zone and the operating mode grade severe degree of operating mode that the center of respective distances regular polygon stepped zone far away is corresponding one by one is higher.
as shown in Figure 5, in the present embodiment, the number of the overall operating mode of wind-powered electricity generation unit is 6, correspondingly use regular hexagon to show the identification result of the operating mode of this wind-powered electricity generation unit, this regular hexagon is by the overall operating mode zone that comprises six overall operating modes of correspondence: overall operating mode zone 300, overall situation operating mode zone 400, overall situation operating mode zone 500, overall situation operating mode zone 600, overall situation operating mode zone 700 and overall operating mode zone 800, their respectively corresponding first kind overall situation operating modes, Equations of The Second Kind overall situation operating mode, the 3rd class overall situation operating mode, the 4th class overall situation operating mode, the 5th class overall situation operating mode and the 6th class overall situation operating mode.
Take overall operating mode zone 400 as example, in the present embodiment, the overall operating mode of overall operating mode zone 400 correspondences comprises 5 sub-systems operating modes.Correspondingly, overall situation operating mode zone 400 is divided into five sub-systems operating modes zones by the line from orthohexagonal center to its base: subtense angle operating mode zone 410, subtense angle operating mode zone 420, subtense angle operating mode zone 430, subtense angle operating mode zone 440 and subtense angle operating mode zone 450, they are corresponding wheel hub subtense angle operating mode, drive subsystem operating mode, generator subtense angle operating mode, electrical control subtense angle operating mode and column foot subtense angle operating mode respectively.In addition, take overall operating mode zone 400 as example, in the present embodiment, the severe degree of operating mode is divided into 5 grades.Correspondingly, the line that overall situation operating mode zone 400 is parallel to its base is divided into five stepped zones: stepped zone 401, stepped zone 402, stepped zone 403, stepped zone 404 and stepped zone 405, they are corresponding first order operating mode, second level operating mode, third level operating mode, fourth stage operating mode and level V operating mode respectively.The severe degree of operating mode that the stepped zone far away apart from the center of regular polygon is corresponding is higher, the severe degree of operating mode of second level operating mode that namely is in stepped zone 402 higher than the first order operating mode that is in stepped zone 401, be in the severe degree of operating mode of third level operating mode of stepped zone 403 higher than the second level operating mode that is in stepped zone 402,, by that analogy.
Each node mapping of second layer self-organizing map neural network 43 is to the overall operating mode zone of these six overall operating modes of correspondence, the overall operating mode of every six node mappings to a zone wherein is presented at the identification result of the operating mode of wind-powered electricity generation unit on regular polygon as shown in Figure 5 thus.Identification result according to the operating mode of wind-powered electricity generation unit, stepped zone in the overall operating mode zone of choosing represents that the operating mode of wind-powered electricity generation unit is the overall operating mode that is in the corresponding severe degree of operating mode, stepped zone in the subtense angle operating mode zone of choosing represents that the operating mode of wind-powered electricity generation unit is the subtense angle operating mode that is in the corresponding severe degree of operating mode, and the color in the zone of wherein choosing is different from the color in not selected zone.The hue preserving in not selected zone constant (being the background colour of figure, for example white) in the present embodiment, the color in the zone of choosing will be changed (for example black).And, for the purpose of image, use the different colors of choosing to represent each stepped zone in the present embodiment, and select darker color (for example from stepped zone 401 to stepped zone 405, that selects chooses color from the light gray to black) along with the aggravation of the severe degree of operating mode corresponding to stepped zone.The identification result of the operating mode of the wind-powered electricity generation unit that shows as Fig. 5 therefore as can be known, is: in Equations of The Second Kind overall situation operating mode, the wheel hub subtense angle is in fourth stage operating mode; The Transmitted chains subtense angle is in third level operating mode; The generator subtense angle is in fourth stage operating mode; The electrical control subtense angle is in second level operating mode; The column foot subtense angle is in fourth stage operating mode.
More than describe preferred embodiment of the present invention in detail.Should be appreciated that those of ordinary skill in the art need not creative work and just can design according to the present invention make many modifications and variations.Therefore, all those skilled in the art all should be in the determined protection domain by claims under this invention's idea on the basis of existing technology by the available technological scheme of logical analysis, reasoning, or a limited experiment.
Claims (9)
1. an Intelligent wind power unit operating mode discrimination method, is characterized in that, the wind-powered electricity generation unit comprises a plurality of subtense angles, and described discrimination method comprises step:
Use sensor to obtain a plurality of parameters of described wind-powered electricity generation unit, described parameter comprises the enviromental parameter of described wind-powered electricity generation unit and the unit parameter of described wind-powered electricity generation unit;
Be global parameter and local parameter with described a plurality of parametric classifications, described global parameter is all relevant to described a plurality of subtense angles, and described local parameter is only relevant to a part in described a plurality of subtense angles;
Extract the eigenvalue of described a plurality of parameters, described eigenvalue comprise the statistics eigenvalue and the time, the frequency domain character value;
Obtain the feature value vector of each described parameter according to the eigenvalue of each described parameter;
The feature value vector input first layer self-organizing map neural network of described a plurality of parameters that will be relevant to same described subtense angle obtains the output vector relevant with described subtense angle; Will to described a plurality of subtense angles respectively relevant each described output vector as mixed vector and described mixed vector input second layer self-organizing map neural network is obtained the identification result of the operating mode of described wind-powered electricity generation unit.
2. Intelligent wind power unit operating mode discrimination method as claimed in claim 1, wherein said subtense angle comprises wheel hub subtense angle, drive subsystem, generator subtense angle, electrical control subtense angle and column foot subtense angle.
3. Intelligent wind power unit operating mode discrimination method as claimed in claim 1 or 2, wherein said operating mode comprises a plurality of overall operating modes and a plurality of subtense angle operating mode; Described overall operating mode represents the overall operation state of described wind-powered electricity generation unit; Described subtense angle operating mode represents the running state of described subsystems.
4. Intelligent wind power unit operating mode discrimination method as claimed in claim 3, wherein use regular polygon to show the identification result of described operating mode;
It is regional that the line on the center of described regular polygon and each summit of described regular polygon is divided into a plurality of leg-of-mutton overall operating modes with described regular polygon, and described overall operating mode zone is corresponding one by one with described overall operating mode;
Each described overall operating mode zone all is divided into a plurality of subtense angle operating modes zones from the center of described regular polygon to the line on the leg-of-mutton base in described overall operating mode zone; In each described overall operating mode zone, described subtense angle operating mode zone is corresponding one by one with described subtense angle operating mode;
The line that each described overall operating mode zone all is parallel to the leg-of-mutton base in described overall operating mode zone is divided into a plurality of stepped zones, and the severe degree of operating mode that the center of the described regular polygon of distance described stepped zone far away is corresponding is higher;
The identification result of the described operating mode that shows when needs is when being in an overall operating mode of a severe degree of operating mode, and is selected to the stepped zone to should the severe degree of operating mode in overall operating mode zone that should overall operating mode in described regular polygon; The identification result of the described operating mode that shows when needs is when being in a sub-systems operating mode of a severe degree of operating mode, and is selected to the stepped zone to should the severe degree of operating mode in subtense angle operating mode zone that should the subtense angle operating mode in described regular polygon.
5. Intelligent wind power unit operating mode discrimination method as claimed in claim 4, wherein in described regular polygon, the color in the described zone of choosing is different from the color in not selected zone.
6. as claim 1,2,4 or 5 described Intelligent wind power unit operating mode discrimination methods, wherein said enviromental parameter comprises wind speed, wind direction and the ambient temperature at place, described wind-powered electricity generation unit place, described unit parameter comprises the generator U phase voltage of described wind-powered electricity generation unit, generator V phase voltage, generator W phase voltage, generator U phase current, generator V phase current, generator W phase current, mains frequency, motor power factor, output power, wind speed round, generator speed, generator-temperature detection, the controller temperature, the main bearing temperature, the gear box lubricating oil temperature, the Hydraulic System Oil temperature, the lubricant oil liquid level, the hydraulic oil liquid level, the cable torsion angle, blade angle, the position, cabin, generated energy, consumes power, program runtime, the wheel hub number of starts, yaw angle, driftage left-hand rotation number of times, driftage right-hand rotation number of times, driftage power, angle of inclination and Ta Nei temperature.
7. Intelligent wind power unit operating mode discrimination method as claimed in claim 6, wherein said wind speed, described wind direction and described ambient temperature described are categorized as described global parameter; Described wind speed round and described blade angle described is categorized as described local parameter, and it is relevant to described wheel hub subtense angle; Described gear box lubricating oil temperature described is categorized as described local parameter, and it is relevant to described drive subsystem; Described output power, described generator U phase voltage, described generator V phase voltage, described generator W phase voltage, described generator U phase current, described generator V phase current, described generator W phase current, described generator-temperature detection, described mains frequency and described consumes power described is categorized as described local parameter, and it is relevant to described generator subtense angle; Temperature described is categorized as described local parameter in described yaw angle, described driftage left-hand rotation number of times, described driftage right-hand rotation number of times, described driftage power, described angle of inclination and described tower, and it is relevant to described column foot subtense angle.
8. Intelligent wind power unit operating mode discrimination method as claimed in claim 7 wherein comprises that according to the process that the eigenvalue of each described parameter obtains the feature value vector of each described parameter the eigenvalue to each described parameter is weighted calculating; The neuron weights that use in described weighted calculation obtain by the described first layer self-organizing map neural network of training and described second layer self-organizing map neural network.
9. an Intelligent wind power unit operating mode identification system, use Intelligent wind power unit operating mode discrimination method as claimed in claim 1, it is characterized in that, comprises data acquisition module, choice of parameters diversity module, characteristic extracting module and operating mode recognition module; Described data acquisition module uses sensor to obtain described a plurality of parameters of described wind-powered electricity generation unit; Described choice of parameters diversity module is described global parameter and described local parameter with described a plurality of parametric classifications; Described characteristic extracting module is extracted the eigenvalue of described a plurality of parameters; Described operating mode recognition module obtains the feature value vector of each described parameter according to the eigenvalue of each described parameter, and uses described first layer self-organizing map neural network and described second layer self-organizing map neural network to obtain the identification result of the operating mode of described wind-powered electricity generation unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310056495.5A CN103161668B (en) | 2013-02-21 | 2013-02-21 | Intelligent wind turbine generator working condition identification system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310056495.5A CN103161668B (en) | 2013-02-21 | 2013-02-21 | Intelligent wind turbine generator working condition identification system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103161668A true CN103161668A (en) | 2013-06-19 |
CN103161668B CN103161668B (en) | 2015-07-15 |
Family
ID=48585099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310056495.5A Expired - Fee Related CN103161668B (en) | 2013-02-21 | 2013-02-21 | Intelligent wind turbine generator working condition identification system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103161668B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103675355A (en) * | 2013-11-19 | 2014-03-26 | 中国大唐集团科学技术研究院有限公司 | Anemometer monitoring method and system |
CN103711645A (en) * | 2013-11-25 | 2014-04-09 | 北京能高自动化技术股份有限公司 | Wind generating set state evaluation method based on modeling parameter feature analysis |
CN103912448A (en) * | 2014-04-25 | 2014-07-09 | 江苏龙源风力发电有限公司 | Method for monitoring power characteristics of units of regional wind farms |
CN104200001A (en) * | 2014-07-23 | 2014-12-10 | 清华大学 | Selection method of marker post fan |
CN104201686A (en) * | 2014-07-24 | 2014-12-10 | 清华大学 | Wind power plant reactive power control method by taking mountain earth wind resource characteristics into account |
CN104377815A (en) * | 2014-01-08 | 2015-02-25 | 国家电网公司 | Relaying protection equipment on-line monitoring method |
CN105673333A (en) * | 2015-11-17 | 2016-06-15 | 北京恒泰实达科技股份有限公司 | Method for displaying operating state of wind driven generator |
CN105787584A (en) * | 2016-01-28 | 2016-07-20 | 华北电力大学(保定) | Wind turbine malfunction early warning method based on cloud platform |
CN107110119A (en) * | 2014-11-24 | 2017-08-29 | 维斯塔斯风力系统集团公司 | The rated value operating of crossing of wind turbine generator is controlled |
CN108051211A (en) * | 2017-12-29 | 2018-05-18 | 湖南优利泰克自动化系统有限公司 | A kind of wind generator set main shaft holds temperature pre-warning diagnostic method |
CN108131247A (en) * | 2017-12-20 | 2018-06-08 | 北京金风科创风电设备有限公司 | Data processing method and device for wind generating set |
CN108241840A (en) * | 2016-12-26 | 2018-07-03 | 河南农业大学 | A kind of piercing and sucking current potential collection of illustrative plates(EPG)Waveform Auto-specification method |
CN108663600A (en) * | 2018-05-09 | 2018-10-16 | 广东工业大学 | A kind of method for diagnosing faults, device and storage medium based on power transmission network |
CN109026530A (en) * | 2018-07-20 | 2018-12-18 | 国网冀北电力有限公司迁西县供电分公司 | A kind of wind power generating set intelligence learning method |
CN109116102A (en) * | 2018-08-08 | 2019-01-01 | 贵州电网有限责任公司 | A kind of electric railway power factor metering method based on operating mode's switch |
CN110832192A (en) * | 2017-07-06 | 2020-02-21 | 乌本产权有限公司 | Wind power plant controller and method for providing data as well as wind power plant and method for receiving data |
CN112180157A (en) * | 2020-09-28 | 2021-01-05 | 国电联合动力技术有限公司 | Wind turbine generator generating capacity metering method and intelligent analysis method and system based on wind turbine generator generating capacity metering method |
CN113915078A (en) * | 2021-11-26 | 2022-01-11 | 龙源(北京)风电工程技术有限公司 | Intelligent identification method and system for working conditions of blades of fiber grating type wind turbine generator |
CN114687928A (en) * | 2020-12-25 | 2022-07-01 | 新疆金风科技股份有限公司 | Wind-waiting starting control method and device for wind generating set, controller and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101603502A (en) * | 2008-06-11 | 2009-12-16 | 武汉事达电气股份有限公司 | A kind of wind energy control method based on artificial-intelligent |
CN101737257A (en) * | 2008-11-26 | 2010-06-16 | 西门子公司 | Estimating an achievable power production of a wind turbine by means of a neural network |
WO2012000505A2 (en) * | 2010-06-29 | 2012-01-05 | Vestas Wind Systems A/S | Callibration of wind turbine sensor |
WO2012149984A1 (en) * | 2011-05-04 | 2012-11-08 | Siemens Aktiengesellschaft | System and method for operating a wind turbine using an adaptive speed reference |
-
2013
- 2013-02-21 CN CN201310056495.5A patent/CN103161668B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101603502A (en) * | 2008-06-11 | 2009-12-16 | 武汉事达电气股份有限公司 | A kind of wind energy control method based on artificial-intelligent |
CN101737257A (en) * | 2008-11-26 | 2010-06-16 | 西门子公司 | Estimating an achievable power production of a wind turbine by means of a neural network |
WO2012000505A2 (en) * | 2010-06-29 | 2012-01-05 | Vestas Wind Systems A/S | Callibration of wind turbine sensor |
WO2012149984A1 (en) * | 2011-05-04 | 2012-11-08 | Siemens Aktiengesellschaft | System and method for operating a wind turbine using an adaptive speed reference |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103675355B (en) * | 2013-11-19 | 2016-06-08 | 中国大唐集团科学技术研究院有限公司 | Anemoscope monitoring method and system |
CN103675355A (en) * | 2013-11-19 | 2014-03-26 | 中国大唐集团科学技术研究院有限公司 | Anemometer monitoring method and system |
CN103711645A (en) * | 2013-11-25 | 2014-04-09 | 北京能高自动化技术股份有限公司 | Wind generating set state evaluation method based on modeling parameter feature analysis |
CN103711645B (en) * | 2013-11-25 | 2016-03-30 | 北京能高自动化技术股份有限公司 | Based on the wind power generating set state evaluating method of modeling parameters signature analysis |
CN104377815A (en) * | 2014-01-08 | 2015-02-25 | 国家电网公司 | Relaying protection equipment on-line monitoring method |
CN103912448A (en) * | 2014-04-25 | 2014-07-09 | 江苏龙源风力发电有限公司 | Method for monitoring power characteristics of units of regional wind farms |
CN103912448B (en) * | 2014-04-25 | 2016-01-20 | 江苏龙源风力发电有限公司 | A kind of regional wind power power of the assembling unit characteristic monitoring method |
CN104200001B (en) * | 2014-07-23 | 2017-09-22 | 清华大学 | The choosing method of mark post blower fan |
CN104200001A (en) * | 2014-07-23 | 2014-12-10 | 清华大学 | Selection method of marker post fan |
CN104201686A (en) * | 2014-07-24 | 2014-12-10 | 清华大学 | Wind power plant reactive power control method by taking mountain earth wind resource characteristics into account |
US10544779B2 (en) | 2014-11-24 | 2020-01-28 | Vestas Wind Systems A/S | Over-rating control of a wind turbine generator |
CN107110119A (en) * | 2014-11-24 | 2017-08-29 | 维斯塔斯风力系统集团公司 | The rated value operating of crossing of wind turbine generator is controlled |
CN105673333A (en) * | 2015-11-17 | 2016-06-15 | 北京恒泰实达科技股份有限公司 | Method for displaying operating state of wind driven generator |
CN105673333B (en) * | 2015-11-17 | 2018-06-15 | 北京恒泰实达科技股份有限公司 | Running status of wind generator methods of exhibiting |
CN105787584A (en) * | 2016-01-28 | 2016-07-20 | 华北电力大学(保定) | Wind turbine malfunction early warning method based on cloud platform |
CN105787584B (en) * | 2016-01-28 | 2020-03-10 | 华北电力大学(保定) | Wind turbine group fault early warning method based on cloud platform |
CN108241840A (en) * | 2016-12-26 | 2018-07-03 | 河南农业大学 | A kind of piercing and sucking current potential collection of illustrative plates(EPG)Waveform Auto-specification method |
CN110832192A (en) * | 2017-07-06 | 2020-02-21 | 乌本产权有限公司 | Wind power plant controller and method for providing data as well as wind power plant and method for receiving data |
CN108131247B (en) * | 2017-12-20 | 2020-09-29 | 北京金风科创风电设备有限公司 | Data processing method and device for wind generating set |
CN108131247A (en) * | 2017-12-20 | 2018-06-08 | 北京金风科创风电设备有限公司 | Data processing method and device for wind generating set |
CN108051211A (en) * | 2017-12-29 | 2018-05-18 | 湖南优利泰克自动化系统有限公司 | A kind of wind generator set main shaft holds temperature pre-warning diagnostic method |
CN108663600A (en) * | 2018-05-09 | 2018-10-16 | 广东工业大学 | A kind of method for diagnosing faults, device and storage medium based on power transmission network |
CN109026530B (en) * | 2018-07-20 | 2019-10-11 | 国网冀北电力有限公司迁西县供电分公司 | A kind of wind power generating set intelligence learning method |
CN109026530A (en) * | 2018-07-20 | 2018-12-18 | 国网冀北电力有限公司迁西县供电分公司 | A kind of wind power generating set intelligence learning method |
CN109116102A (en) * | 2018-08-08 | 2019-01-01 | 贵州电网有限责任公司 | A kind of electric railway power factor metering method based on operating mode's switch |
CN109116102B (en) * | 2018-08-08 | 2020-12-01 | 贵州电网有限责任公司 | Electrified railway power factor metering method based on working condition identification |
CN112180157A (en) * | 2020-09-28 | 2021-01-05 | 国电联合动力技术有限公司 | Wind turbine generator generating capacity metering method and intelligent analysis method and system based on wind turbine generator generating capacity metering method |
CN112180157B (en) * | 2020-09-28 | 2022-07-29 | 国电联合动力技术有限公司 | Wind turbine generator generating capacity metering method and intelligent analysis method and system based on wind turbine generator generating capacity metering method |
CN114687928A (en) * | 2020-12-25 | 2022-07-01 | 新疆金风科技股份有限公司 | Wind-waiting starting control method and device for wind generating set, controller and medium |
CN113915078A (en) * | 2021-11-26 | 2022-01-11 | 龙源(北京)风电工程技术有限公司 | Intelligent identification method and system for working conditions of blades of fiber grating type wind turbine generator |
CN113915078B (en) * | 2021-11-26 | 2023-06-06 | 龙源(北京)风电工程技术有限公司 | Intelligent recognition method and system for working conditions of blades of fiber bragg grating type wind turbine generator |
Also Published As
Publication number | Publication date |
---|---|
CN103161668B (en) | 2015-07-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103161668B (en) | Intelligent wind turbine generator working condition identification system and method | |
US8912674B2 (en) | System and method of selecting wind turbine generators in a wind park for change of output power | |
US8860237B2 (en) | System and method of selecting wind turbine generators in a wind park for curtailment of output power to provide a wind reserve | |
CN108680358A (en) | A kind of Wind turbines failure prediction method based on bearing temperature model | |
Pao et al. | A tutorial on the dynamics and control of wind turbines and wind farms | |
EP3317520B1 (en) | Control method and system for protection of wind turbines | |
CN103080540B (en) | The control of wind turbine in wind energy turbine set | |
CN107820540A (en) | Wind turbine control based on prediction | |
US9018787B2 (en) | System and method of wind turbine control using a torque setpoint | |
EP2644888A2 (en) | Control system and method for avoiding overspeed of a wind turbine | |
CN107110121A (en) | Determination to wind turbine configuration | |
CN105134510A (en) | State monitoring and failure diagnosis method for wind generating set variable pitch system | |
CN107709761A (en) | Extreme loads control | |
CN106194582B (en) | Wind power system MPPT control device and methods based on measuring wind speed and estimation | |
CN104632521A (en) | Wind generator power optimization system and method based on drift correction | |
CA2755154A1 (en) | Method and system for adjusting a power parameter of a wind turbine | |
CN108708824A (en) | The Yaw control method and device of wind power generating set | |
CN107810323A (en) | The method and system arranged for generating wind turbine control | |
CN107850048A (en) | The method and system arranged for generating wind turbine control | |
CN114033617B (en) | Controllable wind power generation method and system with control parameters adjusted in self-adaptive mode | |
EP3608538A1 (en) | Model-based repowering solutions for wind turbines | |
CN108988381B (en) | Low voltage ride through control method, device and system for wind generating set | |
Ali et al. | Comparison of wind farm aggregate models for transient stability studies | |
CN105649896A (en) | Intelligent monitoring operation control system for wind turbine unit and control method thereof | |
Gao et al. | Real-time monitoring, fault prediction and health management for offshore wind turbine systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150715 |
|
CF01 | Termination of patent right due to non-payment of annual fee |