Monitoring Method, System, Device and Medium for Abnormal Operating State of Wind Turbine

Abstract

The present application discloses a method, system, device and medium for monitoring the abnormal operation state of a wind turbine, mainly related to the technical field of wind turbine monitoring, and is used to solve the problem that the existing solutions cannot effectively identify the damage of the wind turbine when the damage degree of the wind turbine is not serious. It includes: fitting and generating a standard wind speed - pitch position curve within a preset time period according to the wind speed and pitch position in the standard second-level acquisition data; when the wind turbine is operating, obtaining effective second-level acquisition data from the real-time second-level acquisition data; storing the wind speed and pitch position in the effective second-level acquisition data into a preset edge computing system; when the number of wind speed and pitch position in the preset edge computing system reaches the preset fitting number, fitting and generating an actual wind speed - pitch position curve; comparing the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve, and when the deviation degree is greater than the preset deviation threshold, starting a preset deviation degree alarm program.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine monitoring, and particularly to a method, a system, a device and a medium for monitoring the abnormal operating state of a wind turbine. Background Art

[0002] Due to long-term operation in a complex environment, a wind turbine will inevitably have abnormal damages such as degradation of blade material properties, blade damage, and problems with the drive train. These problems may have a negative impact on the performance and reliability of the wind turbine. However, when the wind turbine operates with defects, its operating characteristics are not obvious and it is difficult to effectively identify them, which often leads to more serious accidents of the wind turbine. In order to identify the abnormal state of the wind turbine blades as early as possible and nip safety accidents in the bud, it is necessary to endow the wind turbine with the ability to autonomously and quickly identify abnormal states.

[0003] The existing means for monitoring the abnormal state of a wind turbine mainly include vibration monitoring, temperature monitoring, voltage and current monitoring, noise monitoring, etc. When faults such as degradation of blade material properties, minor blade damage, and minor damage to drive train components occur in a wind turbine, these means are often unable to effectively identify them due to the insignificant degree of damage. The operating state characteristics of an early-damaged unit are not obvious and are often easily overlooked. After the unit operates with defects for too long, the blade damage intensifies, which may cause serious accidents.

[0004] Therefore, there is an urgent need for a method, a system, a device and a medium for monitoring the abnormal operating state of a wind turbine to solve the problem that the existing solutions are unable to effectively identify the damage of a wind turbine when the degree of damage is not serious. Summary of the Invention

[0005] In view of the above deficiencies of the prior art, the present application provides a method, a system, a device and a medium for monitoring the abnormal operating state of a wind turbine to solve the problem that the existing solutions are unable to effectively identify the damage of a wind turbine when the degree of damage is not serious.

[0006] In a first aspect, the present application provides a method for monitoring the abnormal operating state of a wind turbine, the method comprising:

[0007] Export the second-level acquisition data related to the wind turbine within a preset time period from the supervisory control and data acquisition database; wherein, the second-level acquisition data at least includes: wind speed, pitch position, power, power setpoint, yaw error; based on the power, power setpoint, and yaw error, remove the second-level acquisition data in the limited power state and with a yaw error greater than the preset yaw threshold from all the second-level acquisition data to obtain the standard second-level acquisition data; according to the wind speed and pitch position in the standard second-level acquisition data, fit and generate the standard wind speed-pitch position curve within the preset time period; when the wind turbine is operating, obtain the second-level acquisition data of the wind turbine in real time, and based on the power, power setpoint, and yaw error, obtain the effective second-level acquisition data from the real-time second-level acquisition data; store the wind speed and pitch position in the effective second-level acquisition data into a preset edge computing system; when the number of wind speed and pitch position in the preset edge computing system reaches the preset fitting number, fit and generate the actual wind speed-pitch position curve; compare the deviation degree between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve, and when the deviation degree is greater than the preset deviation threshold, start the preset deviation degree alarm program.

[0008] The wind turbine abnormal operation state monitoring method provided by the embodiment of the present application obtains the wind turbine operation data from the supervisory control and data acquisition database, and screens and calculates the data; obtains the standard wind speed-pitch position curve; when the wind turbine is operating, extracts the wind turbine operation data in real time, and screens and calculates the data, and retains the wind speed and pitch position data under the normal power generation condition of the wind turbine; obtains the actual wind speed-pitch position curve; by comparing the deviation degree between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve, and setting an alarm threshold, it realizes the timely discovery of the abnormal operation condition of the wind turbine, can ensure the safe and stable operation of the unit, and reduce potential failures and losses. It solves the problem that the existing solution cannot effectively identify the damage of the wind turbine when the damage degree of the wind turbine is not serious.

[0009] In an implementation manner of the present application, based on the power, power setpoint, and yaw error, removing the second-level acquisition data in the limited power state and with a yaw error greater than the preset yaw threshold from all the second-level acquisition data to obtain the standard second-level acquisition data specifically includes:

[0010] Calculate whether the difference between the power setpoint and the power is greater than the preset difference. When it is greater than the preset difference, it indicates the limited power state, and remove the second-level acquisition data in the limited power state; at the same time, remove the second-level acquisition data with a yaw error greater than the preset yaw threshold to obtain the standard second-level acquisition data.

[0011] In an implementation manner of the present application, according to the wind speed and pitch position in the standard second-level acquisition data, fitting and generating the standard wind speed-pitch position curve within the preset time period specifically includes:

[0012] Bin the wind speed data into intervals at a preset interval to obtain the wind speed intervals, the wind speed interval boundaries, and the pitch positions falling into different wind speed intervals; respectively calculate the average values of the pitch positions within different wind speed intervals, and use the wind speed interval boundaries as the abscissa and the average pitch position values as the ordinate to generate a standard wind speed - pitch position curve.

[0013] In an implementation manner of the present application, storing the wind speed and pitch position in the effective second-level acquisition data into a preset edge computing system specifically includes:

[0014] Create an empty wind speed array and a pitch position array with a fixed length of m through the preset edge computing system; the preset edge computing system sequentially fills the wind speed array and the pitch position array according to the wind speed and pitch position in the received effective second-level acquisition data until the wind speed array and the pitch position array are filled.

[0015] In an implementation manner of the present application, comparing the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve specifically includes:

[0016] Adopt the method of curve inflection points and differences to compare the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve.

[0017] In an implementation manner of the present application, when the deviation degree is greater than the preset deviation threshold, start the preset deviation degree alarm program, which specifically includes:

[0018] Display a preset alarm message on the preset human - machine display interface; at the same time, send a power limit instruction to the wind turbine so that the wind turbine operates according to the power setting value in the power limit instruction.

[0019] In an implementation manner of the present application, the real - time second - level acquisition data at least includes: wind speed, pitch position, power, power setting, yaw error; based on the power, power setting, and yaw error, obtain the effective second - level acquisition data from the real - time second - level acquisition data, which specifically includes: calculate whether the difference between the power setting and the power in the real - time second - level acquisition data is greater than the preset difference. When it is greater than the preset difference, it indicates a power limit state, and remove the real - time second - level acquisition data in the power limit state; at the same time, remove the real - time second - level acquisition data with a yaw error greater than the preset yaw threshold to obtain the effective second - level acquisition data.

[0020] In a second aspect, the present application provides a monitoring system for abnormal operating states of a wind turbine, and the system includes:

[0021] An export module for exporting the second-level acquisition data related to a wind turbine within a preset time period from a monitoring and data acquisition database; wherein the second-level acquisition data at least includes: wind speed, pitch position, power, power setting, and yaw error; a standard curve obtaining module for removing the second-level acquisition data in the limited power state and the second-level acquisition data with a yaw error greater than a preset yaw threshold from all the second-level acquisition data based on the power, power setting, and yaw error to obtain standard second-level acquisition data; fitting and generating a standard wind speed-pitch position curve within a preset time period according to the wind speed and pitch position in the standard second-level acquisition data; a real-time data storage module for, when the wind turbine is running, obtaining the second-level acquisition data of the wind turbine in real time, and obtaining effective second-level acquisition data from the real-time second-level acquisition data based on the power, power setting, and yaw error; storing the wind speed and pitch position in the effective second-level acquisition data into a preset edge computing system; a real-time curve obtaining module for, when the number of wind speed and pitch position in the preset edge computing system reaches a preset fitting number, fitting and generating an actual wind speed-pitch position curve; a comparison module for comparing the deviation degree between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve, and when the deviation degree is greater than a preset deviation threshold, starting a preset deviation degree alarm program.

[0022] In a third aspect, the present application provides a monitoring device for abnormal operating states of a wind turbine, and the device includes:

[0023] A processor; and a memory, on which executable code is stored, and when the executable code is executed, the processor is caused to execute a method for monitoring abnormal operating states of a wind turbine as described in any one of the above.

[0024] In a fourth aspect, the present application provides a non-volatile computer storage medium, on which computer instructions are stored, and when the computer instructions are executed, a method for monitoring abnormal operating states of a wind turbine as described in any one of the above is implemented.

[0025] Those skilled in the art can understand that the present application has at least the following beneficial effects:

[0026] An embodiment of the present application provides a method, system, device and medium for monitoring the abnormal operation state of a wind turbine. The method includes obtaining the operation data of the wind turbine from a monitoring and data acquisition database, screening and calculating the data; obtaining a standard wind speed - pitch position curve; when the wind turbine is operating, extracting the operation data of the wind turbine in real time, screening and calculating the data, and retaining the wind speed and pitch position data under the normal power generation condition of the wind turbine; obtaining an actual wind speed - pitch position curve; by comparing the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve, and setting an alarm threshold, the abnormal operation condition of the wind turbine can be discovered in time, ensuring the safe and stable operation of the unit, and reducing potential failures and losses. It solves the problem that the existing solutions cannot effectively identify the damage of the wind turbine when the damage degree of the wind turbine is not serious. Description of the Drawings

[0027] The following describes some embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0028] Figure 1 is a flowchart of a method for monitoring the abnormal operation state of a wind turbine provided by an embodiment of the present application.

[0029] Figure 2 is a schematic internal structure diagram of a system for monitoring the abnormal operation state of a wind turbine provided by an embodiment of the present application.

[0030] Figure 3 is a schematic internal structure diagram of a device for monitoring the abnormal operation state of a wind turbine provided by an embodiment of the present application. Detailed Embodiments

[0031] Those skilled in the art should understand that the embodiments described below are only the preferred embodiments of the present disclosure, which does not mean that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are only used to explain the technical principles of the present disclosure and are not used to limit the protection scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should still fall within the protection scope of the present disclosure.

[0032] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover a non - exclusive inclusion, such that a process, method, commodity or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitations, an element defined by the phrase "including one..." does not exclude the existence of additional identical elements in the process, method, commodity or device including the element.

[0033] The technical solutions proposed in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0034] An embodiment provides a method for monitoring the abnormal operation state of a wind turbine. As Figure 1 shown, the method provided in the embodiments of the present application mainly includes the following steps:

[0035] Step 110: Export the second-level acquisition data related to the wind turbine within a preset time period from the monitoring and data acquisition database.

[0036] It should be noted that the second-level acquisition data at least includes: wind speed, pitch position, power, power setting, and yaw error.

[0037] The monitoring and data acquisition database can be a database involved in the SCADA (Supervisory Control And Data Acquisition) system.

[0038] Step 120: Based on power, power setting, and yaw error, remove the second-level acquisition data in the limited power state and the second-level acquisition data with a yaw error greater than the preset yaw threshold from all the second-level acquisition data to obtain the standard second-level acquisition data.

[0039] This step can be specifically:

[0040] Calculate whether the difference between the power setting and the power is greater than the preset difference. When it is greater than the preset difference, it indicates the limited power state, and remove the second-level acquisition data in the limited power state; for example, ; where represents the power setting, represents the power, and the preset difference can be .

[0041] At the same time, remove the second-level acquisition data with a yaw error greater than the preset yaw threshold to obtain the standard second-level acquisition data.

[0042] For example, the acquisition method of the yaw error can be: ; where is the measured wind direction, is the nacelle position, and the preset yaw threshold can be .

[0043] Step 130: According to the wind speed and pitch position in the standard second-level acquisition data, fit and generate a standard wind speed - pitch position curve within a preset time period.

[0044] This step can be specifically:

[0045] Bin the wind speed data with a preset interval as the interval to obtain the wind speed interval, the wind speed interval boundary, and the pitch positions falling into different wind speed intervals;

[0046] Calculate the average value of the pitch position in different wind speed intervals respectively. Using the wind speed interval boundary as the abscissa and the average value of the pitch position as the ordinate, generate the standard wind speed - pitch position curve.

[0047] As an example,

[0048] Bin the wind speed data in intervals of 0.2 m / s. The corresponding pitch positions fall into different intervals. Calculate the average value of the pitch position in different intervals respectively. Using the wind speed interval boundary as the abscissa and the average value of the pitch position as the ordinate, draw a fitted standard wind speed - pitch position curve.

[0049] Step 140: When the wind turbine is operating, obtain the second - level acquisition data of the wind turbine in real time, and based on power, power setting, and yaw error, obtain the effective second - level acquisition data from the real - time second - level acquisition data; store the wind speed and pitch position in the effective second - level acquisition data into a preset edge computing system.

[0050] It should be noted that the real - time second - level acquisition data at least includes: wind speed, pitch position, power, power setting, and yaw error; based on power, power setting, and yaw error.

[0051] Based on power, power setting, and yaw error, the specific scheme for obtaining the effective second - level acquisition data from the real - time second - level acquisition data is similar to step 120. Specifically, it can be:

[0052] Calculate whether the difference between the power setting and the power in the real - time second - level acquisition data is greater than a preset difference. When it is greater than the preset difference (the preset difference can be ), it indicates a power - limited state. Remove the real - time second - level acquisition data in the power - limited state; at the same time, remove the real - time second - level acquisition data with a yaw error greater than a preset yaw threshold (the preset yaw threshold can be ), and obtain the effective second - level acquisition data.

[0053] In step 140, storing the wind speed and pitch position in the effective second - level acquisition data into a preset edge computing system can be specifically:

[0054] Create an empty wind speed array and a pitch position array with a fixed length of m through the preset edge computing system; the preset edge computing system fills the wind speed array and the pitch position array in sequence according to the wind speed and pitch position in the received effective second - level acquisition data until the wind speed array and the pitch position array are filled.

[0055] For example, the preset edge computing system sets the wind speed array and the pitch position array. First, create an empty array with a fixed length of m 、 , when the main control system transmits data, each time data is stored , , until the array is filled.

[0056] The update method of the wind speed array is as follows:

[0057] ;

[0058] ;

[0059] ;

[0060] …….

[0061] The update method of the pitch position array is as follows:

[0062] ;

[0063] ;

[0064] ;

[0065] …….

[0066] Step 150: When the number of wind speeds and pitch positions in the preset edge computing system reaches the preset fitting quantity, fit and generate the actual wind speed - pitch position curve.

[0067] It should be noted that the specific scheme for fitting and generating the actual wind speed - pitch position curve is the same as that in Step 130, and this application will not elaborate here.

[0068] Step 160: Compare the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve. When the deviation degree is greater than the preset deviation threshold, start the preset deviation warning program.

[0069] In this step, comparing the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve can be specifically:

[0070] Adopt the method of curve inflection points and differences to compare the deviation degree between the actual wind speed - pitch position curve and the standard wind speed - pitch position curve.

[0071] As an example, the deviation includes a first deviation threshold and a second deviation threshold. Using a mathematical method or a graphical method, numerically compare the wind speed inflection point corresponding to the pitch position from 0 to the pitch closing on the actual wind speed - pitch position curve with the wind speed inflection point of the standard wind speed - pitch position curve. When the difference is greater than the preset first deviation threshold, start the preset deviation warning program and display it on the human - machine interaction interface, and issue a power limit instruction to make the wind turbine enter the safety control mode; at the same time, calculate the pitch positions corresponding to each wind speed interval in the actual wind speed - pitch position curve of the wind speed - pitch position, and numerically compare them with the pitch positions corresponding to the same wind speed interval in the standard wind speed - pitch position curve. When the difference is greater than the preset second deviation threshold, start the preset deviation warning program and display it on the human - machine interaction interface, and issue a power limit instruction to make the wind turbine enter the safety control mode.

[0072] Among them, when the deviation is greater than the preset deviation threshold, starting the preset deviation warning program can specifically be:

[0073] Display the preset warning information on the preset human - machine display interface; at the same time, issue a power limit instruction to the wind turbine so that the wind turbine operates according to the power setting value in the power limit instruction.

[0074] In addition, this application Figure 2 is a wind turbine abnormal operation state monitoring system provided by an embodiment of this application. As Figure 2 shown, the system provided by the embodiment of this application mainly includes:

[0075] An export module 210, configured to export the second - level acquisition data related to the wind turbine within a preset time period from the monitoring and data acquisition database.

[0076] Among them, the second - level acquisition data at least includes: wind speed, pitch position, power, power setting, and yaw error.

[0077] A standard curve obtaining module 220, configured to remove the second - level acquisition data in the limited - power state and with a yaw error greater than the preset yaw threshold from all the second - level acquisition data based on power, power setting, and yaw error, to obtain standard second - level acquisition data; and fit and generate a standard wind speed - pitch position curve within a preset time period according to the wind speed and pitch position in the standard second - level acquisition data.

[0078] A real - time data storage module 230, configured to, when the wind turbine is operating, obtain the second - level acquisition data of the wind turbine in real time, and obtain valid second - level acquisition data from the real - time second - level acquisition data based on power, power setting, and yaw error; store the wind speed and pitch position in the valid second - level acquisition data into a preset edge computing system.

[0079] A real-time curve acquisition module 240, configured to fit and generate an actual wind speed-pitch position curve when the number of wind speed and pitch positions in a preset edge computing system reaches a preset fitting number.

[0080] A comparison module 250, configured to compare the deviation degree between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve, and start a preset deviation degree warning program when the deviation degree is greater than a preset deviation threshold.

[0081] The above is the method embodiment in this application. Based on the same inventive concept, the embodiment of this application also provides a monitoring device for abnormal operating states of a wind turbine. As Figure 3 shown, the device includes: a processor; and a memory storing executable code thereon, which when executed, causes the processor to execute a method for monitoring abnormal operating states of a wind turbine as in the above embodiment.

[0082] Specifically, the server side exports the second-level acquisition data related to the wind turbine within a preset time period from the monitoring and data acquisition database; wherein, the second-level acquisition data at least includes: wind speed, pitch position, power, power setting, yaw error; based on the power, power setting, and yaw error, remove the second-level acquisition data in the limited power state and with a yaw error greater than a preset yaw threshold from all the second-level acquisition data to obtain standard second-level acquisition data; according to the wind speed and pitch position in the standard second-level acquisition data, fit and generate a standard wind speed-pitch position curve within the preset time period; when the wind turbine is operating, obtain the second-level acquisition data of the wind turbine in real time, and based on the power, power setting, and yaw error, obtain valid second-level acquisition data from the real-time second-level acquisition data; store the wind speed and pitch position in the valid second-level acquisition data into a preset edge computing system; when the number of wind speed and pitch positions in the preset edge computing system reaches a preset fitting number, fit and generate an actual wind speed-pitch position curve; compare the deviation degree between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve, and start a preset deviation degree warning program when the deviation degree is greater than a preset deviation threshold.

[0083] In addition, the embodiment of this application also provides a non-volatile computer storage medium storing executable instructions, which when executed, implement a method for monitoring abnormal operating states of a wind turbine as described above.

[0084] So far, the technical solutions of the present disclosure have been described in combination with multiple embodiments in the foregoing text. However, those skilled in the art can easily understand that the protection scope of the present disclosure is not limited to these specific embodiments. Without departing from the technical principle of the present disclosure, those skilled in the art can split and combine the technical solutions in the above-mentioned various embodiments, and can also make equivalent changes or substitutions to the relevant technical features. Any changes, equivalent substitutions, improvements, etc. made within the technical concept and / or technical principle of the present disclosure will fall within the protection scope of the present disclosure.

Claims

1. A method for monitoring abnormal operation status of a wind turbine generator set, characterized in that: The method comprises: Exporting the second-level collected data related to the wind turbine in a preset time period from the monitoring and data acquisition database; wherein the second-level collected data at least includes: wind speed, pitch position, power, power setting, and yaw error; Based on power, power setting, and yaw error, the second-level collected data in the power-limited state and with yaw errors greater than a preset yaw threshold are removed from all the second-level collected data to obtain standard second-level collected data; According to the wind speed and pitch position in the standard second-level collected data, a standard wind speed-pitch position curve within a preset time period is generated by fitting; specifically, it includes: The wind speed data is binned according to preset intervals to obtain wind speed intervals, wind speed interval boundaries, and pitch positions falling into different wind speed intervals; the average values ​​of pitch positions in different wind speed intervals are obtained respectively, and the wind speed interval boundaries are used as the horizontal coordinates and the average value of pitch positions is used as the vertical coordinates to generate a standard wind speed-pitch position curve; When the wind turbine is running, the wind turbine's second-level data is acquired in real time, and effective second-level data is acquired from the real-time second-level data based on power, power setting, and yaw error; the wind speed and pitch position in the effective second-level data are stored in the preset edge computing system; When the number of wind speeds and pitch positions in the preset edge computing system reaches the preset fitting number, an actual wind speed-pitch position curve is generated by fitting; The deviation between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve is compared. When the deviation is greater than a preset deviation threshold, a preset deviation alarm program is started.

2. The method for monitoring abnormal operation status of a wind turbine according to claim 1, characterized in that: Based on power, power setting, and yaw error, the second-level collected data in the power-limited state and with yaw error greater than the preset yaw threshold are removed from all the second-level collected data to obtain standard second-level collected data, including: Calculate whether the difference between the power setting and the power reduction is greater than a preset difference. If it is greater than the preset difference, it indicates a power limit state, and remove the second-level collected data of the power limit state; At the same time, the second-level acquisition data with a yaw error greater than a preset yaw threshold is removed to obtain standard second-level acquisition data.

3. The method for monitoring abnormal operation status of a wind turbine according to claim 1, characterized in that: The wind speed and pitch position in the effective second-level collected data are stored in the preset edge computing system, including: Create an empty array wind speed array and a pitch position array with a fixed length of m through a preset edge computing system; The preset edge computing system fills the wind speed array and the pitch position array in sequence according to the wind speed and pitch position in the received valid second-level collected data until the wind speed array and the pitch position array are filled.

4. The method for monitoring abnormal operation status of a wind turbine according to claim 1, characterized in that: Compare the deviation between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve, including: The deviation between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve is compared by using the curve inflection point and difference method.

5. The method for monitoring abnormal operation status of a wind turbine according to claim 1, characterized in that: When the deviation is greater than the preset deviation threshold, the preset deviation alarm procedure is initiated, including: Display preset alarm information on the preset human-machine display interface; At the same time, a power limit instruction is issued to the wind turbine generator set so that the wind turbine generator set operates according to the power setting value in the power limit instruction.

6. The method for monitoring abnormal operation status of a wind turbine generator set according to claim 1, characterized in that: Real-time, second-level data collection includes at least: wind speed, pitch position, power, power setting, and yaw error; Based on power, power setting, and yaw error, obtain effective second-level collection data from real-time second-level collection data, including: Calculate whether the difference between the power setting and the power reduction in the real-time second-level collected data is greater than a preset difference. If it is greater than the preset difference, it indicates a power-limited state, and remove the real-time second-level collected data in the power-limited state. At the same time, the real-time second-level collected data with yaw errors greater than the preset yaw threshold is removed to obtain effective second-level collected data.

7. A wind turbine abnormal operation status monitoring system, characterized in that: The system comprises: An export module is used to export the second-level collected data related to the wind turbine in a preset time period from the monitoring and data acquisition database; wherein the second-level collected data at least includes: wind speed, pitch position, power, power setting, and yaw error; The standard curve acquisition module is used to remove the second-level acquisition data in the power-limited state and the second-level acquisition data with a yaw error greater than a preset yaw threshold from all the second-level acquisition data based on power, power setting, and yaw error, and obtain standard second-level acquisition data; according to the wind speed and pitch position in the standard second-level acquisition data, a standard wind speed-pitch position curve within a preset time period is fitted and generated; specifically includes: The wind speed data is binned according to preset intervals to obtain wind speed intervals, wind speed interval boundaries, and pitch positions falling into different wind speed intervals; the average values ​​of pitch positions in different wind speed intervals are obtained respectively, and the wind speed interval boundaries are used as the horizontal coordinates and the average value of pitch positions is used as the vertical coordinates to generate a standard wind speed-pitch position curve; The real-time data storage module is used to obtain the second-level collected data of the wind turbine in real time when the wind turbine is running, and obtain the effective second-level collected data from the real-time second-level collected data based on power, power setting, and yaw error; and store the wind speed and pitch position in the effective second-level collected data in the preset edge computing system; A real-time curve acquisition module is used to fit and generate an actual wind speed-pitch position curve when the number of wind speeds and pitch positions in the preset edge computing system reaches a preset fitting number; The comparison module is used to compare the deviation between the actual wind speed-pitch position curve and the standard wind speed-pitch position curve. When the deviation is greater than a preset deviation threshold, a preset deviation alarm program is started.

8. A wind turbine abnormal operation status monitoring device, characterized in that: The device comprises: processor; and a memory storing executable codes thereon, wherein when the executable codes are executed, the processor executes a method for monitoring abnormal operation status of a wind turbine set as claimed in any one of claims 1 to 6.

9. A non-volatile computer storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, a method for monitoring abnormal operation status of a wind turbine set as described in any one of claims 1 to 6 is implemented.

Images