Anemometer fault warning method, device and electronic equipment

Abstract

The present invention discloses a method, device and electronic device for an anemometer fault warning. The method comprises the following steps: obtaining real-time data and historical operating data of a target anemometer; extracting impeller speed and wind speed data under stable working conditions from the historical operating data; calculating multiple levels of fault thresholds based on the impeller speed and wind speed data; performing deviation analysis on the real-time data to obtain data deviation; and comparing the data deviation with the fault threshold to obtain the fault level for early warning. The present invention analyzes the historical operating data of the anemometer and compares the real-time data with the historical situation to accurately determine whether the current operating state of the anemometer has a fault risk and the severity of the risk, thereby providing a timely early warning, facilitating timely maintenance by staff and reducing losses.

Description

Technical Field

[0001] The present invention relates to the technical field of fault warning, and in particular to an anemometer fault warning method, device and electronic equipment. Background Art

[0002] Anemometers are the sole wind-measuring device for wind turbines and serve as a crucial input for starting and stopping them. However, natural winds are constantly changing and uncontrollable. Sometimes, wind speeds are lower than the wind turbine's cut-in speed, making it difficult to start wind power generation. Other times, wind speeds exceed the wind turbine's maximum wind speed, damaging the turbine. Therefore, the anemometer's operating status is crucial to overall turbine control. Because anemometers must be constantly operating to monitor wind speed in real time, the likelihood of failure is high.

[0003] Currently, anemometer abnormalities are typically identified by comparing the wind speeds measured by two anemometers on the same turbine. If the difference is significant, an abnormal anemometer status is reported. However, this method cannot be used for identification, as earlier installed wind turbines only had a single anemometer. Furthermore, if both anemometers simultaneously exhibit problems, accurate identification is impossible. Consequently, existing fault identification methods are highly limited and inaccurate, hindering timely detection and maintenance before a fault occurs. This can easily lead to the control system inadvertently controlling the turbine based on erroneous anemometer data, impacting wind turbine efficiency and even causing downtime. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides an anemometer fault early warning method to solve the problems of large application limitations and low accuracy in fault risk identification in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] An embodiment of the present invention provides an anemometer fault early warning method, comprising:

[0007] Obtain real-time data and historical operating data of the target anemometer;

[0008] Extracting impeller speed and wind speed data under stable working conditions from the historical operating data;

[0009] Calculating multiple levels of fault thresholds based on the impeller speed and wind speed data;

[0010] Performing deviation analysis on the real-time data to obtain data deviation;

[0011] The data deviation is compared with the fault threshold to obtain the fault level for early warning.

[0012] Optionally, extracting the impeller speed and wind speed data under stable working conditions from the historical operating data includes:

[0013] extracting first rotation speed data and first wind speed data from the historical operation data;

[0014] Performing linear fitting on the first rotation speed data and the first wind speed data to obtain a first fitting straight line;

[0015] Analyze the steady-state data range according to the first rotational speed data and the distance between the first wind speed data and the first fitting straight line;

[0016] Data within the steady-state data range is extracted from the first rotational speed data and the first wind speed data to obtain impeller rotational speed and wind speed data under stable working conditions.

[0017] Optionally, analyzing the steady-state data range according to the first rotational speed data and the distance between the first wind speed data and the first fitting straight line includes:

[0018] Establishing a distance matrix based on the first rotation speed data and the distance between the first wind speed data and the fitting straight line;

[0019] Calculate the distance mean and distance standard deviation based on the distance matrix;

[0020] A steady-state data range is calculated based on the distance mean and the distance standard deviation.

[0021] Optionally, the calculation of multiple levels of fault thresholds based on the impeller speed and wind speed data includes:

[0022] Performing a linear fit on the impeller speed and the wind speed data to obtain a second fitting straight line;

[0023] Establishing a first residual matrix based on the residuals between the impeller speed data and the wind speed data and the second fitting straight line respectively;

[0024] Divide the residual data in the first residual matrix into quartiles to obtain the lower quartile, the middle quartile, and the upper quartile;

[0025] The interquartile range is calculated based on the upper quartile and the lower quartile;

[0026] The fault thresholds of different levels are calculated by using the lower quartile and the preset interquartile ranges corresponding to different levels.

[0027] Optionally, performing deviation analysis on the real-time data to obtain data deviation includes:

[0028] extracting real-time rotation speed and real-time wind speed from the real-time data;

[0029] Establishing a second residual matrix based on the residuals between the real-time rotation speed and the real-time wind speed and the second fitting straight line respectively;

[0030] Perform mean calculation on the data in the second residual matrix to obtain data deviation.

[0031] Optionally, the method further includes:

[0032] Obtain historical maintenance data and historical ambient temperature averages;

[0033] Determine whether the historical ambient temperature average is less than a preset temperature threshold;

[0034] Determining whether the target anemometer has been overhauled based on the historical overhaul data;

[0035] The temperature judgment results and maintenance judgment results are analyzed to obtain the cause of the early warning.

[0036] Optionally, analyzing the temperature judgment result and the maintenance judgment result to obtain the warning cause includes:

[0037] If the historical ambient temperature average is not less than the preset temperature threshold and the target anemometer has been repaired, the warning reason is an abnormal anemometer coefficient;

[0038] If the historical ambient temperature average is not less than the preset temperature threshold but the target anemometer has not been repaired, the warning reason is that the anemometer is stuck or the wind speed acquisition circuit is faulty;

[0039] If the historical ambient temperature average is less than the preset temperature threshold and the target anemometer has been repaired, the warning reason is an abnormal anemometer coefficient or anemometer icing;

[0040] If the historical ambient temperature average is less than a preset temperature threshold but the target anemometer has not been repaired, the warning reason is that the anemometer is frozen.

[0041] The embodiment of the present invention further provides an anemometer failure warning device, comprising:

[0042] Acquisition module, used to obtain real-time data and historical operation data of the target anemometer;

[0043] An extraction module, configured to extract impeller speed and wind speed data under stable operating conditions from the historical operating data;

[0044] A calculation module, configured to calculate multiple levels of fault thresholds based on the impeller speed and wind speed data;

[0045] An analysis module, configured to perform deviation analysis on the real-time data to obtain data deviation;

[0046] The early warning module is used to compare the data deviation with the fault threshold to obtain the fault level for early warning.

[0047] An embodiment of the present invention further provides an electronic device, including:

[0048] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the anemometer fault warning method provided by an embodiment of the present invention by executing the computer instructions.

[0049] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the anemometer fault early warning method provided by the embodiment of the present invention.

[0050] The technical solution of the present invention has the following advantages:

[0051] The present invention provides a method for early warning of anemometer failures, which comprises obtaining real-time data and historical operating data of a target anemometer; extracting impeller speed and wind speed data under stable working conditions from the historical operating data; calculating multiple levels of fault thresholds based on the impeller speed and wind speed data; performing deviation analysis on the real-time data to obtain data deviation; and comparing the data deviation with the fault threshold to obtain the fault level for early warning. The present invention analyzes the historical operating data of the anemometer and compares the real-time data with the historical situation to accurately determine whether the current operating state of the anemometer has a fault risk and the severity of the risk, thereby providing a timely early warning, facilitating timely maintenance by staff and reducing losses. At the same time, since the comparison is made with the data state during normal and stable operation of the anemometer itself, it is not limited by the number of anemometers in the unit and can be used for anemometer failure early warnings in various types of units. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 Flowchart of an anemometer fault warning method in an embodiment of the present invention;

[0054] Figure 2Flowchart of extracting impeller speed and wind speed data under stable working conditions according to an embodiment of the present invention;

[0055] Figure 3 Flowchart for analyzing steady-state data range according to an embodiment of the present invention;

[0056] Figure 4 A flowchart of calculating multiple levels of fault thresholds according to an embodiment of the present invention;

[0057] Figure 5 Flowchart of performing deviation analysis on real-time data to obtain data deviation according to an embodiment of the present invention;

[0058] Figure 6 Flowchart for analyzing the cause of an early warning based on historical maintenance data and historical ambient temperature according to an embodiment of the present invention;

[0059] Figure 7 Flowchart of analyzing and obtaining warning causes according to an embodiment of the present invention;

[0060] Figure 8 Schematic diagram of the structure of an anemometer failure warning device in an embodiment of the present invention;

[0061] Figure 9 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0063] According to an embodiment of the present invention, an embodiment of an anemometer fault warning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0064] In this embodiment, a method for early warning of anemometer failure is provided, which can be used for the above-mentioned terminal equipment, such as a computer, etc. Figure 1 As shown, the anemometer failure early warning method includes the following steps:

[0065] Step S1: Acquire the real-time data and historical operating data of the target anemometer. Specifically, the historical operating data includes: the operating status of the wind turbine, wind speed data, impeller speed, three pitch angles and active power; wherein the wind speed data and impeller speed are acquired by filtering out the operating data of the wind turbine during normal power generation according to the operating status (whether it is operating normally to generate electricity), and filtering out the wind speed data and impeller speed of the impeller speed climbing section of the wind turbine according to the active power and three pitch angles from the operating data, for example: the impeller speed when the active power is greater than 0 and the three pitch angles are less than 3 degrees at the same time. and wind speed

[0066] Step S2: Extracting the impeller speed and wind speed data under stable operating conditions from the historical operating data. Specifically, by extracting the impeller speed and wind speed data under stable operating conditions, relatively accurate data from the anemometer during normal operation can be obtained. This data can be used to analyze the real-time data and determine whether there are any anomalies in the real-time data, effectively improving the accuracy of fault warnings.

[0067] Step S3: Calculate multiple levels of fault thresholds based on the impeller speed and wind speed data. Specifically, by calculating the warning thresholds, it is convenient to issue different levels of warnings for abnormal situations, reflecting the severity of the fault and providing convenience for maintenance personnel.

[0068] Step S4: Perform deviation analysis on the real-time data to obtain data deviation. Specifically, the data deviation can be used to determine the difference between the current anemometer operating state and the normal stable operation state, which is convenient for subsequent judgment of the warning level.

[0069] Step S5: Compare the data deviation with the fault threshold to determine the fault level and issue a warning. Specifically, the data deviation is compared with the fault threshold. For example, when μ2 is less than or equal to l1, a level 1 warning is issued; when μ2 is greater than l1 and less than or equal to l2, a level 2 warning is issued; when μ2 is greater than l2 and less than or equal to l3, a level 3 warning is issued; and when μ2 is greater than l3, the unit is normal and no warning is required. Depending on the warning level, maintenance personnel can accurately understand the severity of the fault, allowing them to conduct timely and effective maintenance and reduce losses caused by the fault.

[0070] Through the above steps S1 to S5, the anemometer fault warning method provided by the embodiment of the present invention analyzes the historical operating data of the anemometer and compares the real-time data with the historical situation to accurately determine whether there is a failure risk and the severity of the risk in the current operating state of the anemometer, thereby providing a timely warning, facilitating timely maintenance by staff and reducing losses; at the same time, since it is compared with the data state during normal and stable operation of the anemometer itself, it is not limited by the number of anemometers in the unit and can be used for anemometer failure warning of various types of wind turbines.

[0071] Specifically, in one embodiment, the above step S2, such as Figure 2 As shown, the specific steps include:

[0072] Step S21: extracting first rotational speed data and first wind speed data from the historical operation data. Specifically, the first rotational speed data and first wind speed data are all rotational speed data and wind speed data in the historical operation data.

[0073] Step S22: Linearly fit the first rotation speed data and the first wind speed data to obtain a first fitting line. Specifically, the linear fitting can be performed using, for example, the optimize module in Python, and the formula of the obtained first fitting line L1 is: ax+by+c=0.

[0074] Step S23: Analyze the steady-state data range based on the distance between the first rotational speed data and the first wind speed data and the first fitting line. Specifically, by determining the steady-state data range, abnormal data in the unit's unstable state can be screened out during subsequent data screening, ensuring data stability and reliability.

[0075] Step S24: Extract the data within the steady-state data range from the first speed data and the first wind speed data to obtain the impeller speed and wind speed data under stable working conditions. Specifically, filter out the impeller speed corresponding to the distance within the range of [min1, max1]. and wind speed data By analyzing the steady-state data range and extracting the impeller speed and wind speed data under stable working conditions, more accurate data of the anemometer during normal operation can be obtained, which facilitates subsequent analysis of real-time data based on this data and determines whether there are any abnormalities in the real-time data, which can effectively improve the accuracy of fault warning.

[0076] Specifically, in one embodiment, the above step S23, as Figure 3 As shown, the specific steps include:

[0077] Step S231: Establish a distance matrix based on the distances between the first rotational speed data and the first wind speed data and the fitting line. Specifically, calculate the distances d between the first rotational speed data and the first wind speed data and the straight line L1. i , the distance matrix composed of them is recorded as list1;

[0078]

[0079] Step S232: Calculate the distance mean and distance standard deviation based on the distance matrix. Specifically, the distance mean μ1 and distance standard deviation σ1 are:

[0080]

[0081]

[0082] Step S233: Calculate the range of steady-state data based on the distance mean and distance standard deviation. Specifically, the maximum and minimum values ​​used to filter the steady-state data are denoted as max1 and min1. The formula is as follows:

[0083] max1=μ1+3σ1;

[0084] min1=μ1-3σ1.

[0085] Specifically, when calculating the steady-state data range, the coefficients in the formula can be modified to suit the specific equipment. By determining the steady-state data range, abnormal data from the unit's unstable state can be screened out during subsequent data screening, ensuring data stability and reliability.

[0086] Specifically, in one embodiment, the above step S3, such as Figure 4 As shown, the specific steps include:

[0087] Step S31: linearly fit the impeller speed and wind speed data to obtain a second fitting line. Specifically, the linear fitting here can use the optimize module in Python to fit the impeller speed to the wind speed data. and wind speed data Perform linear fitting to obtain the formula of the second fitting line L2: y=Ax+B.

[0088] Step S32: Establish a first residual matrix based on the residuals between the impeller speed and wind speed data and the second fitting straight line. Specifically, calculate the residual H between the impeller speed and wind speed data and the straight line L2. j , and the row matrix it consists of is recorded as list2.

[0089]

[0090] Step S33: Divide the residual data in the first residual matrix into quartiles to obtain the lower quartile, middle quartile, and upper quartile. Specifically, the percentile function in Python can be used to calculate the lower quartile Q1, middle quartile Q2, and upper quartile Q3 of list2;

[0091] Step S34: Calculate the interquartile range based on the upper quartile and the lower quartile. Specifically, the interquartile range is denoted as IQR: IQR = Q3 - Q1.

[0092] Step S35: Calculate the fault thresholds of different levels by using the lower quartile and the preset interquartile ranges corresponding to different levels. Specifically, the first-level warning threshold l1, the second-level warning threshold l2, and the third-level warning threshold l3:

[0093] l1=Q1-4IQR

[0094] l2=Q1-3IQR

[0095] l3=Q1-2IQR

[0096] Specifically, quantiles are the variable values ​​at each equal point after all the data in the population are arranged in order of size. The first quartile (Q1), also known as the "lower quartile" or "lower quartile", is equal to the 25th percentile of all the values ​​in the sample arranged from small to large. The second quartile (Q2), also known as the "median", is equal to the 50th percentile of all the values ​​in the sample arranged from small to large. The third quartile (Q3), also known as the "upper quartile" or "larger quartile", is equal to the 75th percentile of all the values ​​in the sample arranged from small to large. The difference between the third quartile and the first quartile is also called the interquartile range (IQR). Under stable operation, the closer to the first-level warning threshold, the greater the risk of possible failure. When it is close to the third-level warning threshold or greater than the third-level warning threshold, it means that the operation is in good condition and the risk of failure is low. The quartile method is used to more scientifically calculate and divide the warning thresholds, which facilitates the subsequent warning of different levels for abnormal situations, reflecting the severity of the failure risk, providing convenience for maintenance personnel to carry out maintenance in advance, and avoiding unit shutdown due to failure, which causes huge losses.

[0097] Specifically, in one embodiment, the above step S4, such as Figure 5 As shown, the specific steps include:

[0098] Step S41: Extracting real-time rotational speed and wind speed from the real-time data. Specifically, before extracting these data, the current turbine state must be analyzed. The real-time rotational speed and wind speed are extracted when the turbine is operating normally, with active power greater than 0 and all three pitch angles less than 3 degrees. If the turbine state is unstable, data extraction and analysis is performed after the state stabilizes.

[0099] Step S42: Establish a second residual matrix based on the residuals between the real-time rotation speed and the real-time wind speed and the second fitting straight line. Specifically, calculate the screened impeller rotation speed and wind speed The residual h from the data to the second fitting line L2 i , recorded as list3.

[0100]

[0101] Step S43: Calculate the mean of the data in the second residual matrix to obtain the data deviation. Specifically, calculate the mean of list3 and record it as μ2.

[0102]

[0103] Specifically, by calculating the data deviation between the real-time data and the second fitting straight line, the difference between the current operating state of the anemometer and the normal stable operation can be obtained, which facilitates subsequent analysis of whether to issue a fault warning and the warning level.

[0104] Specifically, in one embodiment, the anemometer failure warning method is as follows: Figure 6 As shown, the specific steps also include the following:

[0105] Step S61: Obtain historical maintenance data and historical ambient temperature averages. Specifically, the historical ambient temperature average is obtained by obtaining temperature data within a preset time period before the current time and performing average calculation on the temperature data.

[0106] Step S62: Determine whether the historical ambient temperature average is less than a preset temperature threshold.

[0107] Step S63: Determine whether the target anemometer has been repaired based on the historical maintenance data.

[0108] Step S64: Analyze the temperature judgment result and the maintenance judgment result to obtain the cause of the early warning.

[0109] Specifically, by judging the ambient temperature and historical maintenance conditions, the cause of the fault is analyzed to determine whether it is caused by the temperature conditions or the target anemometer itself, providing a reference for staff to repair.

[0110] Specifically, in one embodiment, the above step S64 is as follows: Figure 7 As shown, the specific steps include:

[0111] Step S641: If the historical ambient temperature average is not less than the preset temperature threshold and the target anemometer has been repaired, the warning reason is that the anemometer coefficient is abnormal.

[0112] Step S642: If the historical ambient temperature average is not less than the preset temperature threshold but the target anemometer has not been repaired, the warning reason is that the anemometer is stuck or the wind speed collection circuit is faulty.

[0113] Step S643: If the historical ambient temperature average is less than the preset temperature threshold and the target anemometer has been repaired, the warning reason is that the anemometer coefficient is abnormal or the anemometer is frozen.

[0114] Step S644: If the historical ambient temperature average is less than the preset temperature threshold but the target anemometer has not been repaired, the warning reason is that the anemometer is frozen.

[0115] Specifically, for example, when the ambient temperature is below 5°C, data anomalies may easily occur due to ice formation. After eliminating the temperature factor, if the data is still abnormal, it is due to a fault in the anemometer itself. This fault cause analysis can provide a reference for maintenance personnel to improve maintenance efficiency.

[0116] This embodiment also provides an anemometer fault warning device, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0117] This embodiment provides a device for early warning of anemometer failure. Figure 8 Shown, including:

[0118] The acquisition module 101 is used to acquire the real-time data and historical operation data of the target anemometer. For details, please refer to the relevant description of step S1 in the above method embodiment, which will not be repeated here.

[0119] The extraction module 102 is used to extract the impeller speed and wind speed data under stable working conditions from the historical operation data. For details, please refer to the relevant description of step S2 in the above method embodiment, which will not be repeated here.

[0120] The calculation module 103 is used to calculate multiple levels of fault thresholds based on the impeller speed and wind speed data. For details, please refer to the relevant description of step S3 in the above method embodiment, which will not be repeated here.

[0121] The analysis module 104 is used to perform deviation analysis on the real-time data to obtain data deviation. For details, please refer to the relevant description of step S4 in the above method embodiment, which will not be repeated here.

[0122] The early warning module 105 is used to compare the data deviation with the fault threshold to obtain the fault level and issue an early warning. For details, please refer to the relevant description of step S5 in the above method embodiment, which will not be repeated here.

[0123] The anemometer fault warning device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0124] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0125] According to an embodiment of the present invention, there is also provided an electronic device, such as Figure 9 As shown, the electronic device may include a processor 901 and a memory 902, wherein the processor 901 and the memory 902 may be connected via a bus or other means. Figure 9 The bus connection is taken as an example.

[0126] The processor 901 may be a central processing unit (CPU). The processor 901 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0127] Memory 902, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the program instructions / modules corresponding to the methods in the method embodiments of the present invention. Processor 901 executes the non-transitory software programs, instructions, and modules stored in memory 902 to perform various processor functions and data processing, thereby implementing the methods in the above-mentioned method embodiments.

[0128] The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created by the processor 901, etc. In addition, the memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 902 may optionally include a memory remotely located relative to the processor 901, and these remote memories may be connected to the processor 901 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0129] One or more modules are stored in the memory 902 and, when executed by the processor 901 , perform the method in the above method embodiment.

[0130] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the above method embodiments, and will not be repeated here.

[0131] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0132] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for early warning of anemometer failure, characterized in that: include: Obtain real-time data and historical operating data of the target anemometer; Extracting impeller speed and wind speed data under stable working conditions from the historical operating data, including: extracting first speed data and first wind speed data from the historical operating data; performing linear fitting on the first speed data and the first wind speed data to obtain a first fitting straight line; analyzing a steady-state data range based on the distance between the first speed data and the first wind speed data and the first fitting straight line, including: establishing a distance matrix based on the distance between the first speed data and the first wind speed data and the fitting straight line, calculating a distance mean and a distance standard deviation based on the distance matrix, and calculating a steady-state data range based on the distance mean and the distance standard deviation; extracting data within the steady-state data range from the first speed data and the first wind speed data to obtain impeller speed and wind speed data under stable working conditions; Calculating multiple levels of fault thresholds based on the impeller speed and wind speed data, including: performing linear fitting on the impeller speed and the wind speed data to obtain a second fitting straight line; establishing a first residual matrix based on the residuals between the impeller speed and the wind speed data and the second fitting straight line respectively; dividing the residual data in the first residual matrix into quartiles to obtain a lower quartile, a middle quartile, and an upper quartile; calculating an interquartile range based on the upper quartile and the lower quartile; and calculating different levels of fault thresholds based on the lower quartile and the interquartile ranges corresponding to preset different levels; Performing deviation analysis on the real-time data to obtain data deviation includes: extracting real-time rotation speed and real-time wind speed from the real-time data; establishing a second residual matrix based on residuals between the real-time rotation speed and real-time wind speed and the second fitting straight line respectively; and performing mean calculation on data in the second residual matrix to obtain data deviation; The data deviation is compared with the fault threshold to obtain the fault level for early warning.

2. The anemometer failure early warning method according to claim 1, characterized in that: The method further comprises: Obtain historical maintenance data and historical ambient temperature averages; Determine whether the historical ambient temperature average is less than a preset temperature threshold; Determining whether the target anemometer has been overhauled based on the historical overhaul data; The temperature judgment results and maintenance judgment results are analyzed to obtain the cause of the early warning.

3. The anemometer failure early warning method according to claim 2, characterized in that: The analysis of the temperature judgment result and the maintenance judgment result to obtain the warning cause includes: If the historical ambient temperature average is not less than the preset temperature threshold and the target anemometer has been repaired, the warning reason is an abnormal anemometer coefficient; If the historical ambient temperature average is not less than the preset temperature threshold but the target anemometer has not been repaired, the warning reason is that the anemometer is stuck or the wind speed collection circuit is faulty; If the historical ambient temperature average is less than the preset temperature threshold and the target anemometer has been repaired, the warning reason is an abnormal anemometer coefficient or anemometer icing; If the historical ambient temperature average is less than a preset temperature threshold but the target anemometer has not been repaired, the warning reason is that the anemometer is frozen.

4. A anemometer fault warning device, characterized in that: The device is used to execute the anemometer failure early warning method according to any one of claims 1 to 3, comprising: Acquisition module, used to obtain real-time data and historical operation data of the target anemometer; an extraction module, configured to extract impeller speed and wind speed data under stable operating conditions from the historical operating data, comprising: extracting first speed data and first wind speed data from the historical operating data; performing linear fitting on the first speed data and the first wind speed data to obtain a first fitting straight line; analyzing a steady-state data range based on the distance between the first speed data and the first wind speed data and the first fitting straight line; and extracting data within the steady-state data range from the first speed data and the first wind speed data to obtain impeller speed and wind speed data under stable operating conditions; A calculation module, configured to calculate multiple levels of fault thresholds based on the impeller speed and wind speed data; An analysis module, configured to perform deviation analysis on the real-time data to obtain data deviation; The early warning module is used to compare the data deviation with the fault threshold to obtain the fault level for early warning.

5. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the anemometer fault warning method according to any one of claims 1 to 3 by executing the computer instructions.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the anemometer failure early warning method according to any one of claims 1 to 3.

Images