A fan status monitoring method, system and computer equipment

Abstract

The present invention discloses a wind turbine status monitoring method, system and computer equipment, which relates to the technical field of wind turbine status monitoring, including selecting a target wind turbine in a wind farm, determining at least one adjacent wind turbine based on location information and real-time wind direction information; calculating the theoretical power generation power of the target wind turbine based on the real-time power generation power of the adjacent wind turbines using a preset power similarity function, calculating the power difference between the theoretical power generation power and the real-time power generation power of the target wind turbine, and finally comparing the difference with the preset difference threshold to determine the current operating state of the target wind turbine. The present invention only needs to measure the real-time power generation power of each wind turbine, and the hardware cost is low; using a similarity function to calculate the theoretical power generation power of the target wind turbine based on the real-time power generation power of the adjacent wind turbines, calculating the difference between the theoretical power generation power and the real-time power generation power of the target wind turbine and comparing the difference with the preset difference threshold to obtain the current operating state of the target wind turbine. The calculation method is simple and efficient, the computing resource consumption is small, the calculation result is accurate, and real-time monitoring of the wind turbine status is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine status monitoring, and more particularly, to a wind turbine status monitoring method, system and computer equipment. Background Art

[0002] With the widespread adoption of wind energy as a clean, renewable energy source, the number of wind turbines is rapidly increasing. Stable wind turbine operation is crucial for ensuring power supply and reducing maintenance costs. However, wind turbines are susceptible to various factors during long-term operation, such as wind and sand erosion, mechanical wear, and improper operation, all of which can lead to performance degradation or even failure.

[0003] Existing wind turbine condition monitoring technologies rely on sensors deployed throughout the wind turbine. By processing real-time sensor data, they determine the proper operating status of each component. However, analyzing and processing real-time data from multiple sensors requires significant computing and communication resources, placing extremely high demands on the performance of real-time acquisition, stable transmission, and massive storage systems. Complex real-time data processing algorithms also increase operational and maintenance difficulties. Therefore, a low-cost wind turbine monitoring method that consumes minimal computing resources is urgently needed. Summary of the Invention

[0004] One of the purposes of the present invention is to provide a fan status monitoring method to overcome the defects of the above-mentioned prior art in monitoring the fan status, such as high computing resource consumption and high hardware cost; the second purpose is to provide a fan status monitoring system; and the third purpose is to provide a computer device.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] The present invention provides a method for monitoring the status of a fan, comprising:

[0007] Obtain real-time power generation, location information, and wind direction information of all wind turbines in the wind farm;

[0008] Selecting a target wind turbine, and determining at least one adjacent wind turbine of the target wind turbine based on the location information and the real-time wind direction information;

[0009] Calculating the theoretical power generation of the target wind turbine using a preset power similarity function based on the real-time power generation of the adjacent wind turbines;

[0010] Calculating a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine;

[0011] The power difference is compared with a preset difference threshold to determine the current operating state of the target wind turbine.

[0012] In a wind farm, the models of wind turbines are basically the same, and adjacent wind turbines have the same or similar power generation and power generation change trends. Therefore, the adjacent wind turbines of the target wind turbine are found by using the location information and real-time wind direction information of all wind turbines in the wind farm. The theoretical power generation of the target wind turbine is then calculated using the real-time power generation of the adjacent wind turbines and the power similarity function. Finally, based on the power difference between the theoretical power generation and the real-time power generation, it is determined whether the current operating status of the target wind turbine is normal. In the present invention, only the real-time power generation of each wind turbine needs to be measured, and the hardware cost is low. The theoretical power generation of the target wind turbine is calculated using the similarity function in combination with the real-time power generation of the adjacent wind turbines. The calculation method is simple and efficient, the computing resource consumption is small, the calculation results are accurate, and real-time monitoring of the wind turbine status is achieved.

[0013] Preferably, the location information includes geographical coordinates and altitude data.

[0014] Preferably, determining at least one adjacent wind turbine of the target wind turbine based on the position information and the real-time wind direction information includes:

[0015] Calculating a first distance between each remaining wind turbine according to the geographic coordinates of the target wind turbine and the geographic coordinates of the remaining wind turbines;

[0016] Calculating a second distance of each remaining wind turbine according to the altitude data of the target wind turbine and the altitude data of the remaining wind turbines;

[0017] The remaining wind turbines whose first distance is less than the first preset distance threshold and whose second distance is less than the second preset distance threshold are selected as the wind turbines to be selected;

[0018] Among the wind turbines to be selected, the wind turbine located upwind of the target wind turbine and having the smallest first distance and / or located downwind of the target wind turbine and having the smallest first distance is selected as the adjacent wind turbine according to the real-time wind direction information.

[0019] The first distance and the second distance between the target wind turbine and each remaining wind turbine are calculated using the geographic coordinates and altitude data between the wind turbines, where the first distance is used to indicate the distance of the horizontal range, and the second distance is used to indicate the distance of the height difference; the first preset distance threshold and the second preset distance threshold are used to screen out the wind turbines to be selected from the remaining wind turbines, and then combined with the influence of the real-time wind direction, under the current wind direction, if the target wind turbine is in the first row of the wind farm, that is, there is no wind turbine to be selected at the upwind position, then the wind turbine to be selected that is located downwind of the target wind turbine and has the smallest first distance is selected as the adjacent wind turbine; if the target wind turbine is in the last row of the wind farm, that is, there is no wind turbine to be selected at the downwind position, then the wind turbine to be selected that is located upwind of the target wind turbine and has the smallest first distance is selected as the adjacent wind turbine; if the target wind turbine is in the middle position of the wind farm, that is, there are wind turbines to be selected both at the upwind position and the downwind position, then one wind turbine to be selected that has the smallest first distance is selected from each of the upwind and downwind positions of the target wind turbine as the adjacent wind turbine. The selection of adjacent wind turbines takes into account the location factors between the wind turbines and the real-time wind direction factors. The candidate wind turbine with the smallest first distance to the target wind turbine is selected as the adjacent wind turbine to ensure that the generated power and the change trend of the generated power are most similar, thereby ensuring the accuracy of the subsequent calculation of the theoretical generated power of the target wind turbine.

[0020] Preferably, the calculating of the theoretical power generation power of the target wind turbine using a preset power similarity function according to the real-time power generation power of the adjacent wind turbines includes:

[0021]

[0022] Where, P b Indicates the theoretical power generation of the target wind turbine, P a represents the real-time power generation of the adjacent wind turbine, k represents the wake effect coefficient, e represents the natural constant, d represents the distance between the adjacent wind turbine and the target wind turbine, and λ represents the wake attenuation length; c represents the wind direction correction factor. When the adjacent wind turbine is located upwind of the target wind turbine, c = +1; when the adjacent wind turbine is located downwind of the target wind turbine, c = -1.

[0023] The power similarity function takes into account the distance between wind turbines, the wake effect between wind turbines, and the wind direction. The wake effect coefficient reflects the degree of influence between wind turbines, which depends on the design of the wind turbines and the layout of the wind farm. The wake attenuation length reflects the rate at which the wake effect weakens with the distance between wind turbines. The wind direction correction factor reflects whether the wind direction has a positive or negative effect on the interaction between wind turbines. When it is +1, it means that the wind flows from the adjacent wind turbine in the upwind position to the target wind turbine. Under the current wind direction, it is beneficial to the target wind turbine. Otherwise, it is detrimental to the target wind turbine.

[0024] Preferably, at every preset time period, the historical power generation of several groups of target wind turbines and adjacent wind turbines within the preset time period is obtained, and input into a linear regression model, a polynomial regression model or a neural network model, and optimized using the least squares method or the gradient descent method to fit the wake effect coefficient and the wake attenuation length corresponding to the preset time period.

[0025] Affected by weather conditions, the wake effect coefficient and wake attenuation length need to be updated regularly or temporarily to adapt to actual weather conditions. If a fixed wake effect coefficient and wake attenuation length are used, the theoretical power generation calculated by the power similarity function will seriously deviate from the actual situation under different weather conditions or when the weather changes severely. Therefore, a preset time period is set, and the historical power generation of several groups of target wind turbines and adjacent wind turbines is obtained every preset time period. The existing linear regression model, polynomial regression or neural network model is used for optimization to fit the relationship between the historical power generation of the target wind turbine and the adjacent wind turbines in the time period, that is, the wake effect coefficient and wake attenuation length corresponding to the preset time period. Then, the values ​​are substituted into the power similarity function to calculate the theoretical power generation of the target wind turbine, which is more in line with the power generation situation under actual weather conditions.

[0026] Preferably, comparing the power difference with a preset difference threshold to determine the current operating state of the target wind turbine includes:

[0027] Comparing the power difference with a preset difference threshold;

[0028] If the power difference is not greater than the preset difference threshold, determining that the current operating state of the target wind turbine is normal;

[0029] If the power difference is greater than the preset difference threshold, it is determined that the current operating state of the target wind turbine is an abnormal state.

[0030] Preferably, the method further comprises:

[0031] When the current operating state of the target wind turbine is an abnormal state, an appearance image and a structure image of the target wind turbine are obtained, and the images are input into a trained wind turbine fault recognition model to obtain a fault type of the target wind turbine.

[0032] Preferably, after obtaining the real-time power generation of all wind turbines in the wind farm, the method further includes:

[0033] Data cleaning operations and time series synchronization operations are performed on the real-time power generation of all wind turbines in the wind farm; the data cleaning operations include one or more of removing outliers, removing noise, or removing missing values.

[0034] The present invention also provides a fan status monitoring system, based on the above-mentioned monitoring method, comprising:

[0035] Data acquisition module, used to obtain real-time power generation, location information and real-time wind direction information of all wind turbines in the wind farm;

[0036] A neighboring wind turbine determination module is used to select a target wind turbine and determine at least one neighboring wind turbine of the target wind turbine based on the location information and the real-time wind direction information;

[0037] a theoretical power generation calculation module, configured to calculate the theoretical power generation of the target wind turbine using a preset power similarity function according to the real-time power generation of the adjacent wind turbines;

[0038] A power difference calculation module, configured to calculate a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine;

[0039] The operating state determination module is used to compare the power difference with a preset difference threshold value to determine the current operating state of the target wind turbine.

[0040] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned wind turbine status monitoring method when executing the computer program.

[0041] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0042] The present invention uses the location information and real-time wind direction information of all wind turbines in a wind farm to locate neighboring wind turbines. It then uses the real-time generated power of the neighboring wind turbines and a power similarity function to calculate the theoretical generated power of the target wind turbine. Finally, based on the power difference between the theoretical and real-time generated power, it determines whether the target wind turbine's current operating status is normal. The present invention only requires measuring the real-time generated power of each wind turbine, resulting in low hardware costs. The theoretical generated power of the target wind turbine is calculated using a similarity function, combined with the real-time generated power of the neighboring wind turbines. This difference is then compared with a preset difference threshold to determine the target wind turbine's current operating status. The calculation method is simple and efficient, consumes little computing resources, and produces accurate results, enabling real-time monitoring of wind turbine status. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of a method for monitoring fan status according to Example 1;

[0044] Figure 2 This is a flow chart of a method for monitoring fan status according to Example 2;

[0045] Figure 3 This is a flow chart of determining adjacent wind turbines of a target wind turbine as described in Example 2;

[0046] Figure 4 This is a structural diagram of a fan status monitoring system according to Example 3;

[0047] Figure 5 This is a structural diagram of a computer device described in Example 3. DETAILED DESCRIPTION

[0048] The accompanying drawings are for illustrative purposes only and are not to be construed as limiting this patent;

[0049] In order to better illustrate this embodiment, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product size;

[0050] It is understandable to those skilled in the art that some well-known structures and descriptions thereof may be omitted in the drawings.

[0051] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0052] Example 1

[0053] This embodiment provides a method for monitoring the status of a fan. Figure 1 As shown, including:

[0054] S1: Obtain the real-time power generation, location information and wind direction information of all wind turbines in the wind farm;

[0055] S2: Select a target wind turbine and determine at least one adjacent wind turbine of the target wind turbine based on the location information and the real-time wind direction information;

[0056] S3: Calculating the theoretical power generation power of the target wind turbine using a preset power similarity function according to the real-time power generation power of the adjacent wind turbines;

[0057] S4: Calculating a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine;

[0058] S5: Compare the power difference with a preset difference threshold to determine the current operating state of the target wind turbine.

[0059] In the specific implementation process, in the same wind farm, the models of wind turbines are basically the same, and the adjacent wind turbines have the same or similar power generation and power generation change trends; therefore, the adjacent wind turbines of the target wind turbine are found through the position information and real-time wind direction information of all wind turbines in the wind farm; the theoretical power generation of the target wind turbine is calculated using the real-time power generation of the adjacent wind turbines and the power similarity function, and finally, based on the power difference between the theoretical power generation and the real-time power generation, it is judged whether the current operating status of the target wind turbine is normal. In the present invention, only the real-time power generation of each wind turbine needs to be measured, and the hardware cost is low; the theoretical power generation of the target wind turbine is calculated by the similarity function in combination with the real-time power generation of the adjacent wind turbines, and the theoretical power generation of the target wind turbine is subtracted from the real-time power generation of the target wind turbine and compared with the preset difference threshold to obtain the current operating status of the target wind turbine. The calculation method is simple and efficient, the computing resource consumption is small, the calculation result is accurate, and the real-time monitoring of the wind turbine status is realized.

[0060] Example 2

[0061] This embodiment provides a method for monitoring the status of a fan. Figure 2 As shown, including:

[0062] S1: Obtain the real-time power generation, location information and wind direction information of all wind turbines in the wind farm;

[0063] It's important to note that after obtaining the real-time power generation data for all wind turbines in a wind farm, data cleaning and time-series synchronization are required. Data cleaning involves removing one or more of outliers, noise, or missing values. Data cleaning ensures data accuracy and reliability, while time-series synchronization ensures that all data is synchronized, facilitating subsequent analysis and comparison.

[0064] In this embodiment, the location information includes geographic coordinates and altitude data.

[0065] S2: Select a target wind turbine and determine at least one adjacent wind turbine of the target wind turbine based on the location information and the real-time wind direction information;

[0066] like Figure 3 As shown, including:

[0067] S21: Calculating a first distance of each remaining wind turbine according to the geographic coordinates of the target wind turbine and the geographic coordinates of the remaining wind turbines;

[0068] S22: Calculating a second distance of each remaining wind turbine based on the altitude data of the target wind turbine and the altitude data of the remaining wind turbines;

[0069] S23: Select the remaining wind turbines whose first distance is less than the first preset distance threshold and whose second distance is less than the second preset distance threshold as wind turbines to be selected;

[0070] S24: Among the wind turbines to be selected, according to the real-time wind direction information, a wind turbine located upwind of the target wind turbine and having the smallest first distance and / or located downwind of the target wind turbine and having the smallest first distance is selected as an adjacent wind turbine.

[0071] It can be understood that this embodiment calculates the first distance and the second distance between the target wind turbine and each remaining wind turbine through the geographical coordinates and altitude data between the wind turbines, where the first distance is used to indicate the distance of the horizontal range, and the second distance is used to indicate the distance of the height difference; the first preset distance threshold and the second preset distance threshold are used to screen out the wind turbines to be selected from the remaining wind turbines, and then combined with the influence of the real-time wind direction, under the current wind direction, if the target wind turbine is in the first row of the wind farm, that is, there is no wind turbine to be selected at the upwind position, then the wind turbine to be selected that is located downwind of the target wind turbine and has the smallest first distance is selected as the adjacent wind turbine; if the target wind turbine is in the last row of the wind farm, that is, there is no wind turbine to be selected at the downwind position, then the wind turbine to be selected that is located upwind of the target wind turbine and has the smallest first distance is selected as the adjacent wind turbine; if the target wind turbine is in the middle position of the wind farm, that is, there are wind turbines to be selected both at the upwind position and the downwind position, then one wind turbine to be selected that has the smallest first distance is selected from each of the upwind position and the downwind position of the target wind turbine as the adjacent wind turbine. The selection of adjacent wind turbines takes into account the location factors between the wind turbines and the real-time wind direction factors. The candidate wind turbine with the smallest first distance to the target wind turbine is selected as the adjacent wind turbine. The environmental conditions are closest, ensuring that the generated power and the change trend of the generated power are most similar, thereby ensuring the accuracy of the subsequent calculation of the theoretical generated power of the target wind turbine.

[0072] S3: Calculating the theoretical power generation power of the target wind turbine using a preset power similarity function according to the real-time power generation power of the adjacent wind turbines;

[0073] The preset power similarity function is:

[0074]

[0075] Where, P b Indicates the theoretical power generation of the target wind turbine, P a represents the real-time power generation of the adjacent wind turbine, k represents the wake effect coefficient, e represents the natural constant, d represents the distance between the adjacent wind turbine and the target wind turbine, and λ represents the wake attenuation length; c represents the wind direction correction factor. When the adjacent wind turbine is located upwind of the target wind turbine, c = +1; when the adjacent wind turbine is located downwind of the target wind turbine, c = -1.

[0076] It can be understood that the power similarity function set in this embodiment takes into account the distance factors between wind turbines, the wake effect between wind turbines and the wind direction factors; the wake effect coefficient reflects the degree of influence between wind turbines, which depends on the design of the wind turbines and the layout of the wind farm. The wake attenuation length reflects the rate at which the wake effect weakens with the distance between wind turbines; the wind direction correction factor reflects whether the wind direction has a positive promoting effect or a negative impact on the interaction between wind turbines. When it is +1, it means that the wind flows from the adjacent wind turbine at the upwind position to the target wind turbine. Under the current wind direction, it is beneficial to the target wind turbine, otherwise it is detrimental to the target wind turbine.

[0077] It should be noted that, at every preset time period, the historical power generation of several groups of target wind turbines and adjacent wind turbines within the preset time period is obtained and input into a linear regression model, polynomial regression model or neural network model. The least squares method or gradient descent method is used for optimization, and the wake effect coefficient and wake attenuation length corresponding to the preset time period are fitted.

[0078] Affected by weather conditions, the wake effect coefficient and wake attenuation length need to be updated regularly or temporarily to adapt to actual weather conditions. If a fixed wake effect coefficient and wake attenuation length are used, the theoretical power generation calculated by the power similarity function will seriously deviate from the actual situation under different weather conditions or when the weather changes severely. Therefore, a preset time period is set, and the historical power generation of several groups of target wind turbines and adjacent wind turbines is obtained every preset time period. The existing linear regression model, polynomial regression or neural network model is used for optimization to fit the relationship between the historical power generation of the target wind turbine and the adjacent wind turbines in the time period, that is, the wake effect coefficient and wake attenuation length corresponding to the preset time period. Then, the values ​​are substituted into the power similarity function to calculate the theoretical power generation of the target wind turbine, which is more in line with the power generation situation under actual weather conditions.

[0079] It should be noted that if only one adjacent wind turbine is determined in step S2, only the real-time power generation power of this adjacent wind turbine is used to calculate the theoretical power generation power of the target wind turbine; that is, when the target wind turbine is in the first row or the last row of the wind farm, only one theoretical power generation power can be calculated based on the power similarity function; if two adjacent wind turbines are determined, two theoretical power generation powers of the target wind turbine are calculated using the real-time power generation power of the two adjacent wind turbines; that is, when the target wind turbine is in the middle position of the wind farm, two theoretical power generation powers are calculated based on the power similarity function.

[0080] S4: Calculating a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine;

[0081] It should be noted that all theoretical generated powers obtained in step S3 are respectively subtracted from the real-time generated powers of the target wind turbines, and the absolute values ​​are taken as the power differences.

[0082] S5: comparing the power difference with a preset difference threshold to determine the current operating state of the target wind turbine, including:

[0083] Comparing the power difference with a preset difference threshold;

[0084] If the power difference is not greater than the preset difference threshold, determining that the current operating state of the target wind turbine is normal;

[0085] If the power difference is greater than the preset difference threshold, it is determined that the current operating state of the target wind turbine is an abnormal state.

[0086] It should be noted that when two adjacent wind turbines are determined in step S2, two theoretical power generation powers and two power differences are obtained. At this time, if the power differences are not greater than the preset difference threshold, the current operating status of the target wind turbine is judged to be normal; otherwise, the current operating status of the target wind turbine is judged to be abnormal.

[0087] It is understandable that the preset difference threshold is a specific value or interval value that is dynamically adjusted according to weather conditions, age of the wind turbine, and operating time of the wind turbine, and is not limited here.

[0088] S6: When the current operating state of the target wind turbine is an abnormal state, an appearance image and a structure image of the target wind turbine are obtained, and the images are input into a trained wind turbine fault recognition model to obtain a fault type of the target wind turbine.

[0089] It should be noted that the trained wind turbine fault recognition model is obtained by training a convolutional neural network or a recurrent neural network using a large amount of labeled wind turbine appearance fault image data and wind turbine structural fault images. The wind turbine appearance fault image data covers various common mechanical and electrical faults, such as bearing damage, blade cracks, tower corrosion, insulation damage, and traces of line short circuits. The wind turbine structural fault images reflect the integrity and structural characteristics of the internal materials of the wind turbine, such as poor bearing assembly and aging and wear of seals. The appearance fault image data provides external status information, and the structural fault images reveal subtle damage to the internal structure. The combination of the two can provide a more comprehensive diagnostic perspective. The trained wind turbine fault recognition model can accurately identify the fault type of the target wind turbine.

[0090] When the target wind turbine's current operating status is abnormal, a drone is deployed based on a pre-set flight path and the target wind turbine's location information to reach the target wind turbine. The drone is equipped with a high-definition camera and an ultrasonic detection device. The HD camera captures 360-degree exterior images, while the ultrasonic detection device acquires internal structural images of the wind turbine. These images are then fed into a trained wind turbine fault recognition model to determine the target wind turbine's fault type. Combined with image processing algorithms, the fault location is determined within the exterior image or image itself, and quantitative parameters such as the area and length of the fault area are obtained. This allows maintenance personnel to assess the severity of the fault, set maintenance priorities and strategies, and begin maintenance work.

[0091] Example 3

[0092] The present invention provides a fan status monitoring system, based on the monitoring method described in embodiment 1 or 2, such as Figure 4 Shown, including:

[0093] Data acquisition module, used to obtain real-time power generation, location information and real-time wind direction information of all wind turbines in the wind farm;

[0094] A neighboring wind turbine determination module is used to select a target wind turbine and determine at least one neighboring wind turbine of the target wind turbine based on the location information and the real-time wind direction information;

[0095] a theoretical power generation calculation module, configured to calculate the theoretical power generation of the target wind turbine using a preset power similarity function according to the real-time power generation of the adjacent wind turbines;

[0096] A power difference calculation module, configured to calculate a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine;

[0097] The operating state determination module is used to compare the power difference with a preset difference threshold value to determine the current operating state of the target wind turbine.

[0098] Since the embodiments of the system part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the system part, which will not be repeated here. The beneficial effects are the same as those of the above-mentioned method part, please refer to the method part for details.

[0099] This embodiment also provides a computer device, such as Figure 5 As shown, at least one processor 01 , at least one communication interface 02 , at least one memory 03 and at least one communication bus 04 .

[0100] In the embodiment of the present application, the number of the processor 01 , the communication interface 02 , the memory 03 , and the communication bus 04 is at least one, and the processor 01 , the communication interface 02 , and the memory 03 communicate with each other through the communication bus 04 .

[0101] Processor 01 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. Processor 01 may be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). Processor 01 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, processor 01 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, processor 01 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0102] The memory 03 may include one or more computer-readable storage media, which may be non-transitory, and may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices.

[0103] The memory 03 stores a program, and the processor 01 can call the program stored in the memory 03 , and the program is used to execute the steps of a wind turbine status monitoring method described in Example 1 or 2.

[0104] The same or similar reference numerals correspond to the same or similar components;

[0105] The terms used in the drawings to describe positional relationships are for illustrative purposes only and should not be construed as limiting this patent;

[0106] Obviously, the above embodiments of the present invention are merely examples for the purpose of clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring the status of a fan, characterized in that: include: Obtain real-time power generation, location information, and wind direction information of all wind turbines in the wind farm; The location information includes geographic coordinates and altitude data; Selecting a target wind turbine and determining at least one adjacent wind turbine of the target wind turbine based on the location information and the real-time wind direction information includes: Calculating a first distance between each remaining wind turbine according to the geographic coordinates of the target wind turbine and the geographic coordinates of the remaining wind turbines; Calculating a second distance of each remaining wind turbine according to the altitude data of the target wind turbine and the altitude data of the remaining wind turbines; The remaining wind turbines whose first distance is less than the first preset distance threshold and whose second distance is less than the second preset distance threshold are selected as the wind turbines to be selected; Among the wind turbines to be selected, according to the real-time wind direction information, a wind turbine located upwind of the target wind turbine and having the smallest first distance and / or a wind turbine located downwind of the target wind turbine and having the smallest first distance is selected as an adjacent wind turbine; Calculating the theoretical power generation of the target wind turbine using a preset power similarity function according to the real-time power generation of the adjacent wind turbines includes: Where, represents the theoretical power generation of the target wind turbine, Indicates the real-time power generation of the nearby wind turbines. represents the wake effect coefficient, represents a natural constant, Indicates the distance between the adjacent wind turbine and the target wind turbine. represents the wake attenuation length; Indicates the wind direction correction factor. When the adjacent wind turbine is located upwind of the target wind turbine, , when the adjacent wind turbine is located downwind of the target wind turbine, ; Calculating a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine; The power difference is compared with a preset difference threshold to determine the current operating state of the target wind turbine.

2. The method for monitoring the status of a fan according to claim 1, wherein: At every preset time period, the historical power generation of several groups of target wind turbines and adjacent wind turbines within the preset time period is obtained and input into a linear regression model, polynomial regression model or neural network model. The model is optimized using the least squares method or gradient descent method to fit the wake effect coefficient and wake attenuation length corresponding to the preset time period.

3. The method for monitoring the status of a fan according to claim 1, wherein: The comparing the power difference with a preset difference threshold to determine the current operating state of the target wind turbine includes: Comparing the power difference with a preset difference threshold; If the power difference is not greater than the preset difference threshold, determining that the current operating state of the target wind turbine is normal; If the power difference is greater than the preset difference threshold, it is determined that the current operating state of the target wind turbine is an abnormal state.

4. The method for monitoring the status of a fan according to claim 3, wherein: The method further comprises: When the current operating state of the target wind turbine is an abnormal state, an appearance image and a structure image of the target wind turbine are obtained, and the images are input into a trained wind turbine fault recognition model to obtain a fault type of the target wind turbine.

5. The method for monitoring the status of a fan according to claim 1, wherein: After obtaining the real-time power generation of all wind turbines in the wind farm, the method further includes: Data cleaning operations and time series synchronization operations are performed on the real-time power generation of all wind turbines in the wind farm; the data cleaning operations include one or more of removing outliers, removing noise, or removing missing values.

6. A wind turbine status monitoring system, based on the monitoring method according to any one of claims 1 to 5, characterized in that: include: Data acquisition module, used to obtain real-time power generation, location information and real-time wind direction information of all wind turbines in the wind farm; A neighboring wind turbine determination module is used to select a target wind turbine and determine at least one neighboring wind turbine of the target wind turbine based on the location information and the real-time wind direction information; a theoretical power generation calculation module, configured to calculate the theoretical power generation of the target wind turbine using a preset power similarity function according to the real-time power generation of the adjacent wind turbines; A power difference calculation module, configured to calculate a power difference based on the theoretical power generation power and the real-time power generation power of the target wind turbine; The operating state determination module is used to compare the power difference with a preset difference threshold value to determine the current operating state of the target wind turbine.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the monitoring method according to any one of claims 1 to 5 are implemented.

Images