CN116398362A - Wind farm field device monitoring method, device and equipment - Google Patents
Wind farm field device monitoring method, device and equipment Download PDFInfo
- Publication number
- CN116398362A CN116398362A CN202310494497.6A CN202310494497A CN116398362A CN 116398362 A CN116398362 A CN 116398362A CN 202310494497 A CN202310494497 A CN 202310494497A CN 116398362 A CN116398362 A CN 116398362A
- Authority
- CN
- China
- Prior art keywords
- wind
- wind motor
- fault
- motor
- power generation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000010248 power generation Methods 0.000 claims description 98
- 238000012549 training Methods 0.000 claims description 30
- 238000012423 maintenance Methods 0.000 claims description 18
- 230000005611 electricity Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 239000000428 dust Substances 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000002203 pretreatment Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/047—Automatic control; Regulation by means of an electrical or electronic controller characterised by the controller architecture, e.g. multiple processors or data communications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/048—Automatic control; Regulation by means of an electrical or electronic controller controlling wind farms
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D9/00—Adaptations of wind motors for special use; Combinations of wind motors with apparatus driven thereby; Wind motors specially adapted for installation in particular locations
- F03D9/20—Wind motors characterised by the driven apparatus
- F03D9/25—Wind motors characterised by the driven apparatus the apparatus being an electrical generator
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Wind Motors (AREA)
Abstract
The application relates to the technical field of wind turbine detection, in particular to a method, a device and equipment for monitoring field equipment of a wind farm, wherein the method comprises the following steps: acquiring a plurality of pieces of continuous image information corresponding to each wind motor in a target area and temperature information corresponding to a plurality of internal components of each wind motor; determining whether an external component of the wind motor is failed based on the plurality of pieces of continuous image information, and determining whether an internal component of the wind motor is failed based on the plurality of internal components and respective corresponding temperature information; and determining the wind motor with the failure of the external component or the wind motor with the failure of the internal component as a failure wind motor. The technical effect that this application had is that the detection accuracy of trouble wind motor has been improved.
Description
Technical Field
The application relates to the technical field of wind turbine detection, in particular to a method, a device and equipment for monitoring field equipment of a wind farm.
Background
A wind power generator is an important power device that is provided in a wind farm and converts wind energy into electric energy. The wind power plant is a place for acquiring, converting wind energy into electric energy and sending the electric energy into a power grid through a power transmission line, a plurality of wind power generators are arranged in the wind power plant, and the electric energy generated by the wind power generators has important influence on the production and life of residents in a region of the wind power plant. When any wind driven generator fails, the total power generation capacity of the wind power plant can be influenced, so that the method has an important role in accurately positioning the failed wind driven generator in the wind power plant with large geographic span.
In the related art, vibration data of a wind turbine nacelle can be detected by using a vibration sensor, a wind turbine with the vibration data larger than a preset data threshold value is determined as a fault generator, and a fault signal is sent, however, when the wind turbine without faults is in bad weather, the wind turbine nacelle can also vibrate severely, and at the moment, the vibration sensor can send an error fault signal, so that the detection accuracy of the fault wind turbine in the related art is lower.
Disclosure of Invention
In order to improve detection accuracy, the application provides a method, a device and equipment for monitoring field equipment of a wind farm.
In a first aspect, the present application provides a method for monitoring a field device of a wind farm, which adopts the following technical scheme:
a method of monitoring a wind farm field device, comprising:
acquiring a plurality of pieces of continuous image information corresponding to each wind motor in a target area and temperature information corresponding to a plurality of internal components of each wind motor;
determining whether an external component of the wind motor is failed based on the plurality of pieces of continuous image information, and determining whether an internal component of the wind motor is failed based on the plurality of internal components and respective corresponding temperature information;
And determining the wind motor with the failure of the external component or the wind motor with the failure of the internal component as a failure wind motor.
Through adopting above-mentioned technical scheme, through the many pieces of continuous image information of every wind motor in the target area of acquireing to confirm whether wind motor external component breaks down, acquire the inside a plurality of subassemblies and the temperature information that correspond respectively of wind motor, so that confirm whether inside a plurality of subassemblies of wind motor break down, and through two judgments, will satisfy wind motor external component trouble, or the wind motor that inside a plurality of subassemblies of wind motor break down is confirmed as the trouble wind motor, has effectively improved the degree of accuracy that the trouble wind motor detected.
In one possible implementation, the wind turbine external component includes a wind turbine nacelle and a wind turbine blade, and the determining, based on the plurality of pieces of continuous image information, whether the wind turbine external component is faulty includes:
acquiring wind direction data and wind speed data;
determining position information corresponding to all key points of the wind turbine nacelle respectively based on the continuous image information and the key points of the wind turbine nacelle;
determining the position of the wind motor cabin based on the position information corresponding to all key points of the wind motor cabin;
Determining whether the wind turbine nacelle is in a normal yaw state based on the wind direction data and the prescribed position of the wind turbine nacelle;
determining the rotation speed of the wind motor blade based on the continuous image information, and determining whether the wind motor blade is in a normal running state based on the rotation speed and wind speed data of the wind motor blade;
and determining the wind turbine with the nacelle not in a normal yaw state or with the wind turbine blades not in a normal rotation state as a fault of an external component of the wind turbine.
By adopting the technical scheme, the wind direction data and the wind speed data are acquired, the position information corresponding to each key point is determined based on all the plurality of pieces of image information and the plurality of key points, the integral position of the wind turbine cabin is determined through all the position information, and whether the wind turbine cabin is in an optimal windward state or not can be determined according to the position of the wind turbine cabin; determining a rotational speed of the wind turbine blade based on the plurality of continuous image information to determine whether the rotational speed of the wind turbine blade varies with wind speed at the current wind speed; furthermore, when the engine room is not in a normal yaw state and/or the rotating speed of the wind turbine blade is not in a normal rotating speed, the wind turbine blade is determined to be a fault wind turbine blade, and the accuracy of judging the wind turbine blade fault is effectively improved based on the position of the engine room of the wind turbine and the rotating speed of the blade.
In one possible implementation, the determining, based on the plurality of internal components and the respective corresponding temperature information, whether a failure occurs in the plurality of internal components of the wind turbine includes:
acquiring the corresponding working data of all the internal components;
inputting the working data corresponding to all the internal components into a preset estimated working temperature model corresponding to each internal component to obtain an estimated working temperature corresponding to each component;
acquiring the actual working temperature of each component, and determining whether the internal components run abnormally or not based on all the internal components, the respective estimated working temperatures and the respective actual working temperatures;
and determining the internal fault component by the abnormally operated internal component.
By adopting the technical scheme, the working data corresponding to each of the plurality of components in each wind turbine are acquired, and the working data corresponding to each of the plurality of components are input into the corresponding estimated working temperature model so as to obtain the actual working temperature of each of the internal components in the current working state; and acquiring the actual working temperature of each internal component, and determining whether a plurality of components in the wind motor have the problem of abnormal operation due to overhigh temperature according to the actual working temperature and the estimated working temperature of each internal component, wherein the wind motor cannot normally generate electricity when the components in the wind motor abnormally operate, so that the abnormally operated internal components are determined to be internal fault components, and further, the accuracy of judging whether the components are faulty is effectively improved.
In one possible implementation manner, after the wind motor with the failed external component or the wind motor with the failed internal component is determined as the failed wind motor, the method further includes:
obtaining model information and fault information of each fault wind motor, wherein the fault information represents a plurality of fault parts of the wind motor with faults; generating a fault alarm signal based on the model information and the fault information of each fault wind motor, wherein the fault alarm signal is used for reminding maintenance personnel to maintain the fault wind motor.
Through adopting above-mentioned technical scheme, through obtaining wind turbine model information and trouble information to generate corresponding trouble alarm signal, in order to in time maintain trouble wind motor through reminding, and then reduce the influence to the wind farm generated energy.
In one possible implementation manner, after generating the fault alarm signal based on the model information and the fault information, the method further includes:
aiming at a target area, acquiring all fault alarm signals corresponding to each fault wind motor in a preset time period;
determining respective failure frequencies of all components of each failure wind motor based on all failure alarm signals corresponding to each failure wind motor, wherein all components of the wind motor represent external components of the wind motor and internal multiple components of the wind motor;
And determining the fault grade of the wind motor in the target area based on the fault frequency corresponding to each component of each wind motor in the target area, and determining maintenance personnel based on the fault grade.
By adopting the technical scheme, all fault alarm signals of each fault wind motor in a preset time period are obtained, so that the fault frequency of each component of each wind motor is determined based on all fault alarm signals, further the fault grade of the wind motor in a target area can be determined, and maintenance personnel are determined according to the fault grade so as to reduce the fault frequency of the wind motor in the target area by adjusting the maintenance personnel.
In one possible implementation, before determining whether the wind motor blade is faulty based on the plurality of pieces of continuous image information, the method further includes:
preprocessing the pieces of continuous image information; the pretreatment method comprises the following steps: resizing and/or de-averaging; correspondingly, the determining whether the wind turbine blade is faulty based on the plurality of pieces of continuous image information comprises:
and determining whether the wind turbine blade fails or not based on the plurality of preprocessed continuous image information.
By adopting the technical scheme, the continuous image information is preprocessed, and the pictures are more in accordance with the processing standard through size adjustment; the pretreated pictures are processed by removing the mean value to more highlight the blades of the wind turbine, so that the picture analysis efficiency can be effectively improved.
In one possible implementation manner, before the acquiring the pieces of continuous image information corresponding to each wind turbine and the temperature information corresponding to each of the internal components of each wind turbine in the target area, the method further includes:
obtaining a predicted power generation amount of a current period and an actual power generation amount of the current period in a target area, wherein the predicted power generation amount is obtained based on a plurality of weather influence data and a power generation amount prediction model;
determining whether all wind turbines in the current period of time in a target area generate electricity normally or not based on the actual generated electricity and the predicted generated electricity;
correspondingly, the acquiring the continuous image information corresponding to each wind turbine and the temperature information corresponding to each internal component of each wind turbine in the target area includes:
if not, acquiring a plurality of pieces of continuous image information corresponding to each wind motor and temperature information corresponding to a plurality of internal components of each wind motor in a target area of the wind motor with abnormal power generation.
By adopting the technical scheme, the predicted power generation amount of the current period and the actual power generation amount of the current period in the target area are obtained, whether the actual power generation amount is the same as the predicted power generation amount or not is judged, so that whether a wind turbine incapable of normally generating power exists in the current period in the target area is determined, if not, the wind turbine incapable of normally generating power exists in the current period in the target area, and if not, the wind turbine capable of normally generating power in the current period in the target area is indicated.
In one possible implementation manner, the training process of the power generation amount prediction model includes:
acquiring a training set, wherein the training set comprises a plurality of weather-influencing data acquisition time periods and actual power generation data of a next time period of the respective corresponding acquisition time periods, and the weather-influencing data comprises illumination intensity data, humidity data, dust content data and wind speed data;
inputting the multiple weather-influencing data into a power generation amount prediction model to be trained so as to obtain predicted power generation amounts corresponding to the multiple weather-influencing data;
determining a loss value based on the predicted power generation amount corresponding to each of the plurality of weather-influencing data and the actual power generation amount of the next period of the acquisition period corresponding to each of the plurality of weather-influencing data;
and carrying out iterative training on the power generation quantity prediction model to be trained according to the loss value and the plurality of meteorological influence data until the loss value reaches a preset loss threshold value, and determining the power generation quantity prediction model to be trained which reaches the preset loss threshold value as the power generation quantity prediction model.
By adopting the technical scheme, iterative training is carried out on the power generation quantity prediction model to be trained according to the loss value, the power generation quantity prediction model after training is finally obtained, the loss value can be continuously reduced by carrying out iterative training on the power generation quantity prediction model to be trained, the loss value gradually approaches to a preset loss threshold value, the power generation quantity is predicted according to the power generation quantity prediction model reaching the preset loss threshold value, and the accuracy of power generation quantity prediction can be effectively improved.
In a second aspect, the present application provides a wind farm field device monitoring apparatus, which adopts the following technical scheme:
a wind farm field device monitoring apparatus comprising:
the acquisition module is used for acquiring a plurality of pieces of continuous image information corresponding to each wind motor in the target area and temperature information corresponding to a plurality of internal components of each wind motor;
the determining module is used for determining whether the external components of the wind motor are faulty or not based on the continuous image information, and determining whether the internal components of the wind motor are faulty or not based on the internal components and the corresponding temperature information; and the fault wind motor determining module is used for determining the wind motor with the fault of the external component or the wind motor with the fault of the internal component as the fault wind motor.
Third, the application provides an electronic equipment, adopts following technical scheme:
at least one processor;
a memory;
at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: a method of wind farm field device monitoring according to any of the first aspect is performed.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of monitoring a wind farm field device according to any of the first aspects.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the method has the advantages that whether the external components of the wind motors are faulty or not is determined by acquiring the continuous image information of each wind motor in the target area, the internal multiple components of the wind motors and the corresponding temperature information are acquired, whether the internal multiple components of the wind motors are faulty or not is determined, and the wind motors meeting the faults of the external components of the wind motors or the faults of the internal multiple components of the wind motors are determined as faulty wind motors through two-time judgment, so that the detection accuracy of the faulty wind motors is effectively improved.
2. And carrying out iterative training on the power generation quantity prediction model to be trained according to the loss value to finally obtain a power generation quantity prediction model after training, and carrying out iterative training on the power generation quantity prediction model to be trained to continuously reduce the loss value so that the loss value gradually approaches a preset loss threshold value, and predicting the power generation quantity according to the power generation quantity prediction model reaching the preset loss threshold value, thereby effectively improving the accuracy of power generation quantity prediction.
Drawings
Fig. 1 is a schematic flow chart of a method for monitoring field devices of a wind farm according to an embodiment of the present application.
Fig. 2 is a schematic diagram of a normal yaw state of a wind turbine according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a wind farm field device monitoring apparatus according to an embodiment of the present application.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application is described in further detail below in conjunction with fig. 1-4.
The present embodiment is merely illustrative of the present application and is not intended to be limiting, and those skilled in the art, after having read the present specification, may make modifications to the present embodiment without creative contribution as required, but is protected by patent laws within the scope of the present application.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
Embodiments of the present application are described in further detail below with reference to the drawings attached hereto.
The embodiment of the application provides a method for monitoring field equipment of a wind farm, which is executed by electronic equipment, wherein the electronic equipment can be a server or terminal equipment, and the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server for providing cloud computing service. The terminal device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto, and the terminal device and the server may be directly or indirectly connected through a wired or wireless communication manner, which is not limited herein.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for monitoring a field device of a wind farm, where the method includes steps S101, S102 and S103, where:
Step S101, acquiring a plurality of pieces of continuous image information corresponding to each wind motor in a target area, and a plurality of internal components and respective corresponding temperature information of each wind motor.
Specifically, the plurality of pieces of continuous image information corresponding to each wind turbine can be obtained through shooting by a technician, and also can be obtained through unmanned aerial vehicle aerial shooting, wherein in the embodiment of the application, in order to better determine whether the wind turbine is faulty based on the images, preferably, the plurality of pieces of continuous images can be obtained through shooting from different angles. Each wind turbine has a plurality of internal components, and in this embodiment, preferably, the plurality of internal components may include: the temperature information corresponding to each component is obtained by monitoring a corresponding temperature sensor.
Step S102, determining whether an external component of the wind motor is faulty or not based on the plurality of pieces of continuous image information, and determining whether the internal plurality of components of the wind motor are faulty or not based on the internal plurality of components and the respective corresponding temperature information.
Specifically, the wind turbine external component comprises a wind turbine cabin and wind turbine blades, and whether the wind turbine external component fails or not can be accurately determined through a plurality of continuous images; based on the internal components and the temperature information corresponding to the internal components, namely when the temperature of any internal component is abnormal, the faults of the internal components of the wind turbine can be determined, and whether the internal components of the wind turbine are abnormal or not can be accurately determined based on the temperature.
And step S103, determining the wind motor with the failure of the external component or the wind motor with the failure of the internal component as a failure wind motor.
Specifically, when detecting that the external component of the wind motor fails, or at least one failed component exists in the wind motor, determining that the wind motor fails.
Based on the above embodiment, by acquiring a plurality of pieces of continuous image information of each wind motor in the target area so as to determine whether the external component of the wind motor is faulty, acquiring a plurality of internal components of the wind motor and respective corresponding temperature information so as to determine whether the internal components of the wind motor are faulty, and by two determinations, determining the wind motor meeting the fault of the external component of the wind motor or the fault of the internal components of the wind motor as a faulty wind motor, the accuracy of detecting the faulty wind motor is effectively improved.
Further, in the embodiment of the present application, the wind turbine external component includes a wind turbine nacelle and a wind turbine blade, and determining whether the wind turbine external component is faulty based on a plurality of pieces of continuous image information includes steps SA1 to SA6 (not shown in the drawings), wherein:
and step SA1, acquiring wind direction data and wind speed data.
Specifically, wind direction data and wind speed data in the current period of the target area can be called from the meteorological data query system.
And step SA2, determining position information corresponding to all key points of the wind turbine cabin based on the continuous image information and the key points of the wind turbine cabin.
Specifically, be provided with preset quantity's key point on each wind turbine cabin, the key point sets up at wind turbine cabin edge side, and then can form the cabin profile through connecting a plurality of key points, in this application embodiment, do not prescribe a limit to preset quantity, the user can set up by oneself. The method for determining the position information of each of all key points of the wind turbine nacelle by establishing a space three-dimensional coordinate system specifically comprises the following steps: the method comprises the steps of inputting a plurality of pieces of continuous image information into three-dimensional live-action modeling software to establish a space three-dimensional model, and establishing a space three-dimensional coordinate system based on the space three-dimensional model. Further, the three-dimensional position of each key point in the space three-dimensional coordinate system can be obtained based on the space three-dimensional coordinate system.
It should be noted that the wind turbine nacelle may rotate with the wind direction.
And step SA3, determining the position of the wind motor cabin based on the position information corresponding to all key points of the wind motor cabin.
Specifically, the position of the wind turbine nacelle may be determined through a position range of the wind turbine nacelle, which may specifically include: all key points of the wind turbine nacelle are connected in three-dimensional positions in a space three-dimensional coordinate system to draw the outline of the wind turbine nacelle, further, the tail end and the starting end of the wind turbine can be determined according to the outline of the wind turbine nacelle, and the trend of a straight line formed by connecting the starting end and the tail end is the azimuth of the wind turbine nacelle.
Step SA4, determining whether the wind turbine nacelle is in a normal yaw state based on wind direction data and the prescribed position of the wind turbine nacelle.
Specifically, the actual angle of the wind turbine nacelle in the target area can be determined based on the position of the wind turbine nacelle, and then the angle of the wind direction in the space three-dimensional coordinate system is determined according to the wind direction data; when the azimuth of the wind motor cabin is opposite to the wind direction angle, the wind motor cabin can be determined to be in a windward state, and the wind motor is indicated to be in a normal yaw state; if the wind turbine nacelle is not in a windward state, the wind turbine nacelle is indicated to not yaw normally. Referring specifically to fig. 2, as shown in fig. 2, when the wind turbine nacelle is in a normal yaw state, the wind turbine nacelle is oriented in a windward direction.
And step SA5, determining the rotation speed of the wind motor blade based on the plurality of pieces of continuous image information, and determining whether the wind motor blade is in a normal running state or not based on the rotation speed and wind speed data of the wind motor blade.
Specifically, the rotational speed of the wind motor blade can be determined through position information of key points of the wind motor blade or a rotational speed identification model.
Wherein, position information based on wind turbine blade key pointsThe method for determining the rotating speed of the wind motor blade comprises the following steps: any two pieces of image information are selected, the position of a key point in each piece of image information and the interval time between the two pieces of images are determined, the rotation angle of the wind turbine blade corresponding to the key point is obtained based on the position and angle calculation formula of the key point, and it can be understood that the two-dimensional position of the key point is selected so as to facilitate calculation. Wherein, the angle calculation formula:wherein x is 1 And y 1 Characterizing location information, x, of key points in a first image 2 And y 1 And representing the position information of the key points in the second image, wherein theta represents the rotation angle of the wind turbine blade, and the rotation angle of the wind turbine blade can be obtained based on the rotation angle of the key points, so that the rotation speed of the wind turbine blade can be determined.
The rotation speed recognition model determines the rotation speed of the wind turbine blade, and specifically may include inputting a plurality of continuous images into the rotation speed recognition model, where the rotation speed recognition model may determine the rotation speed of the wind turbine blade by recognizing the plurality of images.
Further, the rotation speed of the wind turbine blade can be calculated according to a calculation formula of the rotation speed and the wind speed of the wind turbine blade, and the calculation formula of the rotation speed of the wind turbine blade is as follows:l=f×v, where L represents the air volume, D 2 Characterization of the Length, Q, of a wind turbine blade 1 Characterization of flow coefficient, μ 2 The rotating speed of the wind turbine blade is represented, F represents the cross-sectional area of wind speed, and V represents the wind speed.
And step SA6, determining the wind turbine with the nacelle not in a normal yaw state or with the wind turbine blades not in a normal rotation state as a fault of an external component of the wind turbine.
Specifically, when the wind turbine nacelle is not in a normal yaw state or the wind turbine blades are not in a normal running state, it can be determined that the external components of the wind turbine have faults, and then normal power generation cannot be performed.
Based on the embodiment, wind direction data and wind speed data are obtained, position information corresponding to each key point is determined based on all the plurality of pieces of image information and the plurality of key points, so that the overall position of the wind turbine cabin is determined through all the position information, and whether the wind turbine cabin is in an optimal windward state or not can be determined according to the position of the wind turbine cabin; determining a rotational speed of the wind turbine blade based on the plurality of continuous image information to determine whether the rotational speed of the wind turbine blade varies with wind speed at the current wind speed; furthermore, when the engine room is not in a normal yaw state and/or the rotating speed of the wind turbine blade is not in a normal rotating speed, the wind turbine blade is determined to be a fault wind turbine blade, and the accuracy of judging the wind turbine blade fault is effectively improved based on the position of the engine room of the wind turbine and the rotating speed of the blade.
Further, in the embodiment of the present application, based on the internal plurality of components and the respective corresponding temperature information, it is determined whether the internal plurality of components of the wind turbine are malfunctioning, including steps SB1-SB4 (not shown in the drawings), wherein:
step SB1, obtaining the working data corresponding to all the internal components of the wind turbine.
Specifically, the working data characterizes the working frequency of the internal component, where in this embodiment, to improve accuracy, preferably, the working data of the gearbox may be an output rotation speed of the gearbox, the working data of the high-speed shaft may be power of the high-speed shaft, and the working data of the generator may be output power of the generator.
Step SB2, inputting the working data corresponding to each internal component into a preset estimated working temperature model corresponding to each internal component to obtain the estimated working temperature corresponding to each internal component.
Specifically, each internal component corresponds to a unique estimated working temperature model, and each internal component is input into the corresponding estimated working temperature model, so that the estimated working temperature of the component under the current working data can be obtained. For example, the estimated operating temperature model corresponding to the gear box is an estimated operating temperature model of the gear box, the estimated operating temperature model corresponding to the high-speed shaft is an estimated operating temperature model of the high-speed shaft, and the estimated operating temperature model corresponding to the generator is an estimated operating temperature model of the generator. The electronic equipment inputs the temperatures corresponding to the acquired components into corresponding estimated working temperature models so as to obtain the estimated working temperature corresponding to each internal component.
Step SB3, obtaining the actual working temperature of each component, and determining whether an abnormally operated internal component exists or not based on all components, the respective estimated working temperatures and the respective actual working temperatures.
And step SB4, determining the internal component fault of the abnormally operated internal component.
Specifically, whether the difference value between the estimated working temperature and the actual working temperature of each internal component is within the preset temperature difference value range is judged, the preset temperature difference value range can be set according to the actual requirement, if not, the corresponding internal component can be determined to have abnormality, wherein it can be understood that the internal component temperature is increased when the internal component is abnormal. An abnormally operated internal component is determined as an internal failure component.
Based on the embodiment, the working data corresponding to the environmental temperature of each wind motor and the working data of the internal multiple components are obtained, and the environmental temperature and the working data of the components are input into the corresponding estimated working temperature model so as to obtain the actual working temperature of each component in the current environmental temperature and working state; and acquiring the actual temperature of each component, and determining whether a plurality of components in the wind motor have the problem of abnormal operation due to overhigh temperature according to the actual temperature and the working temperature of each component, wherein the wind motor cannot normally generate electricity when the components in the wind motor abnormally operate, so that the abnormally operated internal components are determined to be internal fault components, and further, the accuracy of judging whether the components are faulty is effectively improved.
Further, in the embodiment of the present application, after determining whether the external component of the wind turbine fails based on the plurality of pieces of continuous image information and determining whether the internal plurality of components of the wind turbine fails based on the internal plurality of components and the respective corresponding temperature information, the method further includes:
obtaining model information and fault information of each fault wind motor, wherein the fault information represents a plurality of fault parts of the wind motor with faults; based on the model information and the fault information of each fault wind motor, generating a fault alarm signal, wherein the fault alarm signal is used for reminding maintenance personnel to maintain the fault wind motor.
Specifically, the types of the wind motors in the target area may be different or the same, and the type of each wind motor is stored in the electronic device in advance. When the electronic equipment determines that the wind motor fails, the position information of the failed wind motor is obtained from a plurality of pieces of continuous image information, and model information of the wind motor is further determined according to the model and the position information database of the wind motor. The failure information of the wind motor is the failure part of the wind motor, namely an external failure component of the wind motor or an internal failure component of the wind motor. For example, when the electronic device determines that the internal gear box of the wind turbine is faulty, that is, the internal component of the wind turbine is faulty, a corresponding fault alarm signal is generated based on the information of the wind turbine type and the fault of the gear box, wherein the fault alarm signal can be transmitted to the mobile device of a technician in a wireless transmission mode or to a fault alarm center.
Based on the embodiment, the wind turbine model information and the fault information are obtained, and the corresponding fault alarm signal is generated, so that the fault wind turbine can be maintained in time by reminding, and further the influence on the generated energy of the wind power plant is reduced.
Further, in the embodiment of the present application, after generating the fault alarm signal based on the model information and the fault information, steps SC1 to SC3 (not shown in the drawings) are further included, where:
and step SC1, acquiring all fault alarm signals of each fault wind motor in a preset time period aiming at a target area.
Specifically, after the electronic device generates the fault alarm signals, the fault alarm signals are automatically recorded, and a fault alarm information base can be generated by recording all the fault alarm signals, wherein the fault alarm information base comprises each wind motor and all the corresponding fault alarm signals. The preset duration is not limited, and the preset duration can be three months or six months, so that the user can set the preset duration by himself.
And step SC2, determining the respective corresponding fault frequency of all components of each fault wind motor based on all fault alarm signals corresponding to each fault wind motor, wherein all components of the wind motor represent the external components of the wind motor and the internal multiple components of the wind motor.
Specifically, the time unit of the failure frequency may be days or months. For example, if the gear box of the wind motor generates three fault alarm signals and the engine of the wind motor generates six fault alarm signals within 3 months, the fault frequency of the gear box of the wind motor can be determined to be one time/month, and the fault frequency of the engine is determined to be two times/month.
And step SC3, determining the fault grade of the wind motor in the target area based on the fault frequency corresponding to all components of each wind motor in the target area, and determining maintenance personnel based on the fault grade.
Specifically, the failure level of the wind turbine in the target area may be determined based on the sum of the failure frequencies, or any component failure frequency threshold. In the embodiment of the present application, it is preferable that the failure level of the wind motor in the target area is classified into a safety level and a risk level.
The determining the fault level of the wind motor in the target area based on the sum of the fault frequencies specifically may include adding the fault frequencies corresponding to all components to obtain the sum of the fault frequencies; judging whether the sum of the fault frequencies is not smaller than the minimum threshold value of the sum of the preset fault frequencies, if yes, indicating that the fault level of the wind turbine in the target area is a dangerous level, and if not, indicating that the wind turbine in the target area is a safe level.
Determining a failure level of a wind turbine in a target area based on any component failure frequency threshold may specifically include: judging whether the fault frequency of each component is not smaller than a preset fault frequency threshold value, and if any component fault frequency is not smaller than the preset fault frequency threshold value, indicating that the fault level of the wind turbine in the target area is a dangerous level.
Further, when the fault level is a safety level, the number of maintenance personnel is increased, and the number of corresponding maintenance personnel is increased for the components of the wind motor with higher fault rate; when the fault level is a dangerous level, replacing maintenance personnel corresponding to the components of the wind motor with higher fault rate, and replacing the maintenance personnel with higher fault repair rate based on historical maintenance data.
Based on the embodiment, all fault alarm signals of each fault wind motor in a preset time period are obtained, so that the fault frequency of each component of each wind motor is determined based on all fault alarm signals, further the fault grade of the wind motor in a target area can be determined, and the adjustment strategy of maintenance personnel is customized in a targeted manner according to the fault grade, so that the fault frequency of the wind motor in the target area is reduced by the maintenance personnel.
Further, in an embodiment of the present application, before determining whether the wind motor blade is faulty based on the plurality of pieces of continuous image information, the method further includes:
preprocessing a plurality of pieces of continuous image information; the pretreatment method comprises the following steps: resizing and/or de-averaging;
correspondingly, based on the plurality of pieces of continuous image information, determining whether the wind turbine blade is faulty includes:
and determining whether the wind turbine blade fails or not based on the plurality of preprocessed continuous image information.
Specifically, the size of the multi-length continuous image information is adjusted, the embodiment of the application does not limit the specific size of adjustment, a user can set the multi-length continuous image information by himself, the average value of the multi-length continuous image information is removed, the shadow part in the image information is removed, and the edge characteristics of the wind turbine blade are highlighted.
Based on the above embodiment, preprocessing is performed on a plurality of pieces of continuous image information, and the pictures are more in accordance with the processing standard through size adjustment; the pretreated pictures are processed by removing the mean value to more highlight the blades of the wind turbine, so that the picture analysis efficiency can be effectively improved.
Further, in this embodiment of the present application, before acquiring the pieces of continuous image information corresponding to each wind turbine and the temperature information corresponding to each of the plurality of internal components of each wind turbine in the target area, the method further includes:
And obtaining a predicted power generation amount of the current period and an actual power generation amount of the current period in the target area, wherein the predicted power generation amount is obtained based on a plurality of weather influence data and a power generation amount prediction model.
Specifically, the weather-influencing data are obtained from a weather statistical system, and the actual power generation amount is obtained from power generation amount statistical equipment.
Determining whether all wind turbines in the current period of time in the target area generate electricity normally or not based on the actual generated electricity and the predicted generated electricity;
correspondingly, acquiring a plurality of pieces of continuous image information corresponding to each wind motor and temperature information corresponding to a plurality of internal components of each wind motor in a target area, including:
if not, acquiring a plurality of pieces of continuous image information corresponding to each wind motor and temperature information corresponding to a plurality of internal components of each wind motor in a target area of the wind motor with abnormal power generation.
Specifically, the electronic device determines whether the obtained difference value between the actual generated energy and the predicted generated energy is within a preset difference value range, if yes, it indicates that all wind turbines in the current period of the target area are in a normal working state, otherwise, step S101 is executed, and it indicates that there is no normal power generation of the wind turbines in the current period of the target area, that is, the wind turbines are in a fault state, and the preset difference value range can be set according to actual requirements.
Based on the embodiment, the predicted power generation amount of the current period and the actual power generation amount of the current period in the target area are obtained, whether the actual power generation amount is the same as the predicted power generation amount or not is judged, so that whether a wind turbine incapable of normally generating power exists in the current period in the target area is determined, if not, the wind turbine incapable of normally generating power exists in the current period in the target area, and if not, the wind turbine capable of normally generating power in the current period in the target area is indicated.
Further, in the embodiment of the present application, the training process of the power generation amount prediction model includes steps SD1 to SD4 (not shown in the drawings), in which:
and step SD1, acquiring a training set, wherein the training set comprises a plurality of weather-influencing data acquisition time periods and actual power generation data of the next time period of the respective corresponding acquisition time periods, and the weather-influencing data comprises illumination intensity data, humidity data, dust content data and wind speed data.
Specifically, the illumination intensity data is detected by an optical radiation sensor, the humidity data is detected by a humidity sensor, the dust content data is obtained in a system based on meteorological data statistics, and the actual power generation data is obtained in a system based on power generation statistics.
And step SD2, inputting the plurality of weather-influencing data into a power generation amount prediction model to be trained so as to obtain predicted power generation amounts corresponding to the plurality of weather-influencing data.
Specifically, the temperature data and the illumination intensity data are input into a power generation amount prediction model to be trained, so that the predicted power generation amount corresponding to the temperature data and the illumination intensity data can be obtained.
And step SD3, determining a loss value based on the predicted power generation amount corresponding to each of the plurality of weather-influencing data and the actual power generation amount of the next period of the sample acquisition period corresponding to each of the plurality of weather-influencing data.
Specifically, according to the predicted power generation amount and the actual power generation amount corresponding to each meteorological influence data, loss values are determined based on preset loss functions, and the smaller the loss values are, the smaller the difference between the predicted power generation amount and the actual power generation amount is, and the higher the data accuracy of the predicted power generation amount is. The embodiment of the application does not limit the preset loss function, and a user can set the loss function by combining with actual requirements.
And step SD4, performing iterative training on the power generation quantity prediction model to be trained according to the loss value and the plurality of meteorological influence data until the loss value reaches a preset loss threshold value, and determining the power generation quantity prediction model to be trained which reaches the preset loss threshold value as a power generation quantity prediction model.
Specifically, the preset loss threshold is preset by a user, and the embodiment of the application does not limit the preset loss threshold, and performs iterative training on the power generation quantity prediction model to be trained. The iterative training is to perform the activity of repeating the feedback process by using a slope unique preset model, and repeat the operation steps, so that the accuracy of the model can be effectively improved by performing iterative training on the power generation quantity prediction model to be trained. Calculating according to the generated energy at the moment of acquiring the training meteorological data and the actual generated energy at the moment of agreeing corresponding to the moment of acquiring the meteorological influence data by using a preset loss function to obtain a loss value, and determining that the generated energy prediction model training is completed when the loss value is not smaller than a preset loss threshold value.
Based on the embodiment, iterative training is performed on the power generation amount prediction model to be trained according to the loss value, the power generation amount prediction model after training is finally obtained, the loss value can be continuously reduced through iterative training on the power generation amount prediction model to be trained, the loss value gradually approaches to a preset loss threshold value, the power generation amount is predicted according to the power generation amount prediction model reaching the preset loss threshold value, and the accuracy of power generation amount prediction can be effectively improved.
The above embodiments describe a wind farm field device monitoring method from the aspect of a method flow, and the following embodiments describe a wind farm field device monitoring apparatus from the aspect of a virtual module or a virtual unit, specifically the following embodiments.
The embodiment of the application provides a wind farm field device monitoring device, as shown in fig. 3, the wind farm field device monitoring device may specifically include:
an obtaining module 210, configured to obtain a plurality of pieces of continuous image information corresponding to each wind turbine in the target area and temperature information corresponding to each of a plurality of internal components of each wind turbine;
a determining module 220, configured to determine, based on the plurality of pieces of continuous image information, whether an external component of the wind turbine is faulty, and determine, based on the plurality of internal components and respective corresponding temperature information, whether an internal component of the plurality of internal components of the wind turbine is faulty;
the failure wind motor determining module 230 is configured to determine a wind motor with a failure of an external component or a wind motor with a failure of an internal component as a failure wind motor.
In one possible implementation manner of the embodiments of the present application, the determining module 220 is configured, when executing determining whether an external component of the wind turbine is faulty based on the multiple pieces of continuous image information, to:
Acquiring wind direction data and wind speed data;
determining position information corresponding to all key points of the wind turbine nacelle based on the continuous image information and the key points of the wind turbine nacelle;
determining the position of the wind motor cabin based on the position information corresponding to all key points of the wind motor cabin;
determining whether the wind turbine nacelle is in a normal yaw state based on the wind direction data and the prescribed position of the wind turbine nacelle;
determining the rotation speed of the wind motor blade based on the continuous image information, and determining whether the wind motor blade is in a normal running state based on the rotation speed and wind speed data of the wind motor blade;
and determining the wind turbine with the nacelle not in a normal yaw state or with the wind turbine blades not in a normal rotation state as a fault of an external component of the wind turbine.
In one possible implementation manner of the embodiment of the present application, when determining whether a failure occurs in a plurality of internal components of a wind turbine based on the plurality of internal components and respective corresponding temperature information, the determining module 220 is configured to:
acquiring the corresponding working data of all the internal components;
inputting the working data corresponding to all the internal components into a preset estimated working temperature model corresponding to each internal component to obtain an estimated working temperature corresponding to each component;
Acquiring the actual working temperature of each component, and determining whether the internal components run abnormally or not based on all the internal components, the respective estimated working temperatures and the respective actual working temperatures;
and determining the internal fault component by the abnormally operated internal component.
One possible implementation manner in the embodiments of the present application, a wind farm field device monitoring apparatus further includes:
the fault alarm module is used for:
obtaining model information and fault information of each fault wind motor, wherein the fault information represents a plurality of fault parts of the wind motor with faults; based on the model information and the fault information of each fault wind motor, generating a fault alarm signal, wherein the fault alarm signal is used for reminding maintenance personnel to maintain the fault wind motor.
One possible implementation manner in the embodiments of the present application, a wind farm field device monitoring apparatus further includes:
the maintenance personnel determining module is used for:
aiming at a target area, acquiring all fault alarm signals corresponding to each fault wind motor in a preset time period;
determining respective failure frequencies of all components of each failure wind motor based on all failure alarm signals corresponding to each failure wind motor, wherein all components of the wind motor represent external components of the wind motor and internal multiple components of the wind motor;
And determining the fault grade of the wind motor in the target area based on the fault frequency corresponding to each component of each wind motor in the target area, and determining maintenance personnel based on the fault grade.
One possible implementation manner in the embodiments of the present application, a wind farm field device monitoring apparatus further includes:
an image preprocessing module for:
preprocessing a plurality of pieces of continuous image information; the pretreatment method comprises the following steps: resizing and/or de-averaging;
accordingly, the determining module 220, when executing determining whether a wind turbine blade is faulty based on the plurality of pieces of continuous image information, is configured to: and determining whether the wind turbine blade fails or not based on the plurality of preprocessed continuous image information.
One possible implementation manner in the embodiments of the present application, a wind farm field device monitoring apparatus further includes:
the wind motor power generation module is used for:
obtaining a predicted power generation amount of a current period and an actual power generation amount of the current period in a target area, wherein the predicted power generation amount is obtained based on a plurality of weather influence data and a power generation amount prediction model;
determining whether all wind turbines in the current period of time in the target area generate electricity normally or not based on the actual generated electricity and the predicted generated electricity;
Accordingly, the acquiring module 210 is configured to, when executing the acquisition of the plurality of pieces of continuous image information corresponding to each wind turbine and the temperature information corresponding to each of the plurality of internal components of each wind turbine in the target area:
if not, acquiring a plurality of pieces of continuous image information corresponding to each wind motor and temperature information corresponding to a plurality of internal components of each wind motor in a target area of the wind motor with abnormal power generation.
One possible implementation manner in the embodiments of the present application, a wind farm field device monitoring apparatus further includes:
the generating capacity prediction training module is used for:
acquiring a training set, wherein the training set comprises a plurality of weather-influencing data acquisition time periods and actual power generation data of a next time period of the respective corresponding acquisition time periods, and the weather-influencing data comprises illumination intensity data, humidity data, dust content data and wind speed data;
inputting the multiple weather-influencing data into a power generation amount prediction model to be trained so as to obtain predicted power generation amounts corresponding to the multiple weather-influencing data;
determining a loss value based on the predicted power generation amount corresponding to each of the plurality of weather-influencing data and the actual power generation amount of the next period of the acquisition period corresponding to each of the plurality of weather-influencing data;
And carrying out iterative training on the power generation quantity prediction model to be trained according to the loss value and the plurality of meteorological influence data until the loss value reaches a preset loss threshold value, and determining the power generation quantity prediction model to be trained which reaches the preset loss threshold value as the power generation quantity prediction model.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, a specific working process of the wind farm field device monitoring apparatus described above may refer to a corresponding process in the foregoing method embodiment, which is not described herein again.
The following describes an electronic device provided in an embodiment of the present application, where the electronic device described below and the method for monitoring a field device of a wind farm described above may be referred to correspondingly to each other
An embodiment of the present application provides an electronic device, as shown in fig. 4, fig. 4 is a schematic structural diagram of the electronic device provided in the embodiment of the present application, and an electronic device 300 shown in fig. 4 includes: a processor 301 and a memory 303. Wherein the processor 301 is coupled to the memory 303, such as via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that, in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 is not limited to the embodiment of the present application.
The processor 301 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with the disclosure of embodiments of the present application. Processor 301 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
The Memory 303 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 303 is used for storing application program codes for executing embodiments of the present application, and is controlled to be executed by the processor 301. The processor 301 is configured to execute the application code stored in the memory 303 to implement what is shown in the foregoing method embodiments.
Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments herein.
A computer readable storage medium provided in the embodiments of the present application will be described below, where a computer program is stored on the computer readable storage medium, and when the computer program runs on a computer, the computer program makes the computer execute the corresponding content in the foregoing method embodiments. Compared with the related art, by acquiring a plurality of pieces of continuous image information of each wind motor in the target area so as to determine whether the external components of the wind motor are faulty or not, acquiring a plurality of internal components of the wind motor and temperature information corresponding to the internal components of the wind motor so as to determine whether the internal components of the wind motor are faulty or not, and determining the wind motor meeting the faults of the external components of the wind motor or the faults of the internal components of the wind motor as a faulty wind motor through two-time judgment, the accuracy of detecting the faulty wind motor is effectively improved.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A method of monitoring field devices of a wind farm, comprising:
acquiring a plurality of pieces of continuous image information corresponding to each wind motor in a target area and temperature information corresponding to a plurality of internal components of each wind motor;
determining whether an external component of the wind motor is failed based on the plurality of pieces of continuous image information, and determining whether an internal component of the wind motor is failed based on the plurality of internal components and respective corresponding temperature information;
and determining the wind motor with the failure of the external component or the wind motor with the failure of the internal component as a failure wind motor.
2. The method of monitoring a wind farm field device according to claim 1, wherein the wind turbine external component comprises: a wind motor nacelle and wind motor blades,
the determining whether the wind motor external component is faulty based on the plurality of pieces of continuous image information includes:
Acquiring wind direction data and wind speed data;
determining position information corresponding to all key points of the wind turbine nacelle respectively based on the continuous image information and the key points of the wind turbine nacelle;
determining the position of the wind motor cabin based on the position information corresponding to all key points of the wind motor cabin;
determining whether the wind turbine nacelle is in a normal yaw state based on the wind direction data and the prescribed position of the wind turbine nacelle;
determining the rotation speed of the wind motor blade based on the continuous image information, and determining whether the wind motor blade is in a normal running state based on the rotation speed and wind speed data of the wind motor blade;
and determining the wind turbine with the nacelle not in a normal yaw state or with the wind turbine blades not in a normal rotation state as a fault of an external component of the wind turbine.
3. The method of monitoring field devices of a wind farm according to claim 1, wherein the determining whether a failure is occurring in the plurality of internal components of the wind turbine based on the plurality of internal components and the respective corresponding temperature information comprises:
acquiring the corresponding working data of all the internal components;
inputting the working data corresponding to all the internal components into a preset estimated working temperature model corresponding to each internal component to obtain an estimated working temperature corresponding to each component;
Acquiring the actual working temperature of each component, and determining whether the internal components run abnormally or not based on all the internal components, the respective estimated working temperatures and the respective actual working temperatures;
and determining the internal fault component by the abnormally operated internal component.
4. The method of monitoring a field device of a wind farm according to claim 1, wherein after determining a wind motor with a failure of an external component or a wind motor with a failure of an internal component as a failed wind motor, further comprising:
obtaining model information and fault information of each fault wind motor, wherein the fault information represents a plurality of fault parts of the wind motor with faults; generating a fault alarm signal based on the model information and the fault information of each fault wind motor, wherein the fault alarm signal is used for reminding maintenance personnel to maintain the fault wind motor.
5. The method for monitoring field devices of a wind farm according to claim 4, wherein after generating a fault alarm signal based on the model information and fault information, further comprising:
aiming at a target area, acquiring all fault alarm signals corresponding to each fault wind motor in a preset time period;
Determining respective failure frequencies of all components of each failure wind motor based on all failure alarm signals corresponding to each failure wind motor, wherein all components of the wind motor represent external components of the wind motor and internal multiple components of the wind motor;
and determining the fault grade of the wind motor in the target area based on the fault frequency corresponding to each component of each wind motor in the target area, and determining maintenance personnel based on the fault grade.
6. The method of monitoring a wind farm field device according to claim 1, wherein the determining whether a wind motor blade is malfunctioning based on the plurality of consecutive image information further comprises:
preprocessing the pieces of continuous image information; the pretreatment method comprises the following steps: resizing and/or de-averaging;
correspondingly, the determining whether the wind turbine blade is faulty based on the plurality of pieces of continuous image information comprises:
and determining whether the wind turbine blade fails or not based on the plurality of preprocessed continuous image information.
7. The method for monitoring a field device of a wind farm according to claim 1, further comprising, before the step of obtaining the continuous image information corresponding to each wind turbine and the temperature information corresponding to each of the internal components of each wind turbine in the target area:
Obtaining a predicted power generation amount of a current period and an actual power generation amount of the current period in a target area, wherein the predicted power generation amount is obtained based on a plurality of weather influence data and a power generation amount prediction model;
determining whether all wind turbines in the current period of time in a target area generate electricity normally or not based on the actual generated electricity and the predicted generated electricity;
correspondingly, the acquiring the continuous image information corresponding to each wind turbine and the temperature information corresponding to each internal component of each wind turbine in the target area includes:
if not, acquiring a plurality of pieces of continuous image information corresponding to each wind motor and temperature information corresponding to a plurality of internal components of each wind motor in a target area of the wind motor with abnormal power generation.
8. The method of monitoring a wind farm field device according to claim 7, wherein the training process of the power generation capacity prediction model comprises:
acquiring a training set, wherein the training set comprises a plurality of weather-influencing data acquisition time periods and actual power generation data of a next time period of the respective corresponding acquisition time periods, and the weather-influencing data comprises illumination intensity data, humidity data, dust content data and wind speed data;
Inputting the multiple weather-influencing data into a power generation amount prediction model to be trained so as to obtain predicted power generation amounts corresponding to the multiple weather-influencing data;
determining a loss value based on the predicted power generation amount corresponding to each of the plurality of weather-influencing data and the actual power generation amount of the next period of the acquisition period corresponding to each of the plurality of weather-influencing data;
and carrying out iterative training on the power generation quantity prediction model to be trained according to the loss value and the plurality of meteorological influence data until the loss value reaches a preset loss threshold value, and determining the power generation quantity prediction model to be trained which reaches the preset loss threshold value as the power generation quantity prediction model.
9. A wind farm field device monitoring apparatus, comprising:
the acquisition module is used for acquiring a plurality of pieces of continuous image information corresponding to each wind motor in the target area and temperature information corresponding to a plurality of internal components of each wind motor;
the determining module is used for determining whether the external components of the wind motor are faulty or not based on the continuous image information, and determining whether the internal components of the wind motor are faulty or not based on the internal components and the corresponding temperature information;
and the fault wind motor determining module is used for determining the wind motor with the fault of the external component or the wind motor with the fault of the internal component as the fault wind motor.
10. An electronic device, comprising:
at least one processor;
a memory;
at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: a method of performing the wind farm field device monitoring of any of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310494497.6A CN116398362A (en) | 2023-05-05 | 2023-05-05 | Wind farm field device monitoring method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310494497.6A CN116398362A (en) | 2023-05-05 | 2023-05-05 | Wind farm field device monitoring method, device and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116398362A true CN116398362A (en) | 2023-07-07 |
Family
ID=87014307
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310494497.6A Pending CN116398362A (en) | 2023-05-05 | 2023-05-05 | Wind farm field device monitoring method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116398362A (en) |
-
2023
- 2023-05-05 CN CN202310494497.6A patent/CN116398362A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110985309B (en) | Yaw wind anomaly detection method, device, equipment and storage medium | |
US11746753B2 (en) | Method and apparatus for detecting fault, method and apparatus for training model, and device and storage medium | |
Zhang et al. | A survey of condition monitoring and fault diagnosis toward integrated O&M for wind turbines | |
EP3731158A1 (en) | Wind farm noise prediction method, apparatus and system | |
CN110009736B (en) | Method, device, equipment and storage medium for establishing three-dimensional wake model | |
CN110348654A (en) | Wind generating set evaluation and operation data correction method, device and terminal | |
Skrimpas et al. | Employment of kernel methods on wind turbine power performance assessment | |
CN117077064A (en) | Fault detection method, device and equipment for wind power equipment and storage medium | |
CN112855460B (en) | Method, system, medium and equipment for predicting real-time fatigue life of shafting of wind turbine generator | |
He et al. | A non-intrusive approach for fault detection and diagnosis of water distribution systems based on image sensors, audio sensors and an inspection robot | |
CN112211794B (en) | Cabin temperature abnormity early warning method, device, equipment and medium of wind turbine generator | |
CN116398362A (en) | Wind farm field device monitoring method, device and equipment | |
Zhang et al. | Robust fault‐detection based on residual K–L divergence for wind turbines | |
CN115434870B (en) | Method, device, equipment and storage medium for processing vibration data of wind power generation set | |
CN113565699B (en) | Method, device and system for detecting pitch angle of wind generating set | |
CN115842408A (en) | Wind power plant operation state detection system and method based on SCADA | |
CN116047499A (en) | High-precision real-time protection system and method for power transmission line of target construction vehicle | |
Zhang et al. | Probability warning for wind turbine gearbox incipient faults based on SCADA data | |
CN112699598A (en) | Intelligent diagnosis method and device for abnormal oil temperature of gear box | |
CN117212074B (en) | Wind power generation system, temperature rise early warning method of variable pitch motor of wind power generation system and storage medium | |
CN116502543B (en) | Wind turbine generator set wind deviation recognition method and device, electronic equipment and storage medium | |
Fazli et al. | Wind turbine fault detection and isolation robust against data imbalance using KNN | |
CN111310959A (en) | Wind generating set damage prediction analysis method, device, equipment and storage medium | |
Lydia et al. | Condition monitoring in wind turbines: a review | |
CN113268937B (en) | Wind turbine generator system large part damage analysis system based on data fusion |
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 |