A method, system, device, and readable storage medium for early warning of wind turbine faults.

By determining the wake influence relationship between wind turbine units and making dynamic corrections, the problem of low early warning accuracy caused by not considering the wake influence in the existing technology is solved, and more accurate fault early warning and improved operation and maintenance efficiency are achieved.

CN123109960APending Publication Date: 2026-11-17THREE GORGES HI TECH INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611189400.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-06
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing wind turbine fault early warning methods do not fully consider the impact of wake, resulting in low accuracy of early warnings.

Method used

By acquiring basic and real-time operating data of wind turbines, the wake influence relationship is determined, the wake influence factor is calculated, the initial health data is dynamically corrected, and the fault warning result is determined by combining real-time operating data.

Benefits of technology

It improved the accuracy of fault early warning, reduced the false alarm rate and missed alarm rate, and improved the operation and maintenance efficiency of wind farms and the reliability of unit operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123109960A_ABST
    Figure CN123109960A_ABST
Patent Text Reader

Abstract

This invention discloses a method, system, device, and readable storage medium for early warning of wind turbine faults, relating to the field of wind turbine fault warning technology. The method includes the following steps: S100: acquiring basic data, real-time operating data, and initial health data for each wind turbine; S200: determining the wake influence relationship between a target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines; S300: calculating the wake influence factor of the target wind turbine based on the wake influence relationship, and dynamically correcting the initial health data of the target wind turbine based on the wake influence factor to obtain corrected health data; S400: determining the fault warning result of the target wind turbine based on the real-time operating data and corrected health data of the target wind turbine. This invention improves the operation and maintenance efficiency of wind farms and the operational reliability of wind turbines.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of wind turbine fault early warning technology, and in particular to a wind turbine fault early warning method, system, device and readable storage medium. Background Technology

[0002] Health monitoring and fault early warning of wind turbines are crucial for ensuring the safe and efficient operation of wind farms. Current technologies typically rely on operational data from individual wind turbines, using fixed thresholds or historical statistical benchmarks as judgment criteria.

[0003] However, wind turbines are densely arranged in wind farms, and the operation of upstream wind turbines generates wake effects, causing downstream wind turbines to face complex operating conditions of wind speed loss and enhanced turbulence. Existing early warning methods do not fully consider the interference of wake effects on the operating indicators of wind turbines, resulting in low accuracy of fault early warning. Summary of the Invention

[0004] This invention provides a method, system, device, and readable storage medium for early warning of wind turbine faults, in order to solve the technical problem of low accuracy in existing early warning methods in related technologies.

[0005] Firstly, a method for early warning of wind turbine faults is provided, including the following steps: Acquire basic data, real-time operating data, and initial health data for each wind turbine. The basic data includes the wind turbine's spatial location and rotor radius. The real-time operating data includes current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed. The initial health data includes initial healthy power, initial healthy vibration value, initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle, and initial healthy rotational speed. Based on the basic data and real-time operating data of all wind turbine units, determine the wake influence relationship between the target wind turbine unit and the other wind turbine units. Based on the wake influence relationship, the wake influence factor of the target wind turbine is calculated, and the initial health data of the target wind turbine is dynamically corrected based on the wake influence factor to obtain the corrected health data. Based on the real-time operating data and corrected health data of the target wind turbine, the fault warning results of the target wind turbine are determined.

[0006] In some embodiments, the step of determining the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines includes the following steps: Based on the spatial location of the wind turbines in the basic data of all wind turbines and the current wind direction in the real-time operation data, calculate the distance projection of the remaining wind turbines relative to the target wind turbine in the wind direction and the lateral offset distance in the vertical wind direction. If the distance projection is greater than zero and the lateral offset distance is less than or equal to the wake coverage threshold, then it is determined that the target wind turbine is affected by the wake of the other corresponding wind turbines, and a wake influence relationship is established; wherein, the wake coverage threshold is determined based on the rotor radius of the other corresponding wind turbines, the rotor radius of the target wind turbine, the distance projection, and the preset wake expansion coefficient.

[0007] In some embodiments, the step of calculating the wake influence factor of the target wind turbine based on the wake influence relationship includes the following steps: Based on the wake effect relationship, the total wind speed loss ratio, turbulence enhancement degree and overlap ratio of the blade sweep surfaces of the other wind turbines and the target wind turbine are calculated. The wake influence factor of the target wind turbine is calculated by weighting the total wind speed loss ratio, turbulence enhancement degree and overlap ratio.

[0008] In some embodiments, the step of dynamically correcting the initial health data of the target wind turbine based on the wake influence factor to obtain corrected health data includes the following steps: Based on the total wind speed loss ratio, the equivalent inflow wind speed is determined, and the corrected healthy power is obtained after correcting the initial healthy power. Based on the wake influence factor and the preset vibration threshold correction coefficient, the initial healthy vibration value is corrected to obtain the corrected healthy vibration value. Based on the wake influence factor and the corresponding preset correction coefficient, the initial healthy mean and initial healthy fluctuation range of the initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle and initial healthy speed are corrected to obtain the corrected healthy mean and corrected healthy fluctuation range.

[0009] In some embodiments, the step of determining the fault warning result of the target wind turbine based on the real-time operating data and corrected health data of the target wind turbine includes the following steps: Calculate the residual between the real-time operating data and the corrected health data, and determine the comprehensive fault anomaly score by combining the corresponding anomaly weights; The wake explanatory power is determined based on the initial healthy power, current power, and corrected healthy power of the target wind turbine. Calculate the individual deviation degree of the target wind turbine, which characterizes the deviation of the real-time operating data of the target wind turbine from the set of reference turbines with the same and similar wake conditions. The same and similar wake conditions are determined based on the similarity of wake influence factors. Based on the comprehensive fault anomaly score, individual deviation degree, and wake explanation degree, the comprehensive fault risk value is calculated; Based on the comprehensive fault risk value, the fault warning result of the target wind turbine is determined, wherein the fault warning result includes the warning level, the cause of the abnormality and the handling strategy.

[0010] In some embodiments, the step of calculating the individual deviation of the target wind turbine includes the following steps: A set of reference turbine units that are in similar wake conditions to the target wind turbine unit is determined, and the same and similar wake conditions are determined based on the similarity of wake influence factors; Calculate the power residual of the target wind turbine relative to the reference turbine set; The degree of deviation of the individual unit is obtained based on the power residual and the median absolute deviation of the power residual of the reference unit set.

[0011] In some embodiments, the step of determining the fault warning result of the target wind turbine further includes the following steps: Based on the relationship between the comprehensive fault risk value and the preset risk level threshold, the early warning level is divided; Based on the wake influence factor, wake explanatory power, individual deviation degree, and comprehensive fault anomaly score, the cause of the anomaly and the handling strategy are determined.

[0012] Secondly, a wind turbine fault early warning system is provided for executing the aforementioned wind turbine fault early warning method, the system comprising: The data acquisition module is used to acquire basic data and real-time operating data for each wind turbine. The basic data includes the spatial location of the wind turbine and the rotor radius, while the real-time operating data includes the current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed. The judgment module is used to determine the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines. The calculation module is used to calculate the wake influence factor of the target wind turbine when there is a wake influence, and to dynamically correct the health reference data of the target wind turbine based on the wake influence factor. The health reference data includes health reference power, health reference vibration value, health reference temperature, health reference pitch angle, health reference yaw angle and health reference speed. The early warning module is used to determine the fault warning result of the target wind turbine based on the real-time operating data and the corrected health benchmark data of the target wind turbine.

[0013] Thirdly, a computer device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, the at least one instruction being loaded and executed by the processor to implement the steps of the aforementioned wind turbine fault early warning method.

[0014] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the computer performs the steps of the aforementioned wind turbine fault early warning method.

[0015] The beneficial effects of the technical solution provided by this invention include: This invention provides a method, system, device, and readable storage medium for early warning of wind turbine faults. The method first acquires basic data, real-time operating data, and initial health data for each wind turbine. The basic data includes the wind turbine's spatial location and rotor radius. The real-time operating data includes current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed. The initial health data includes initial healthy power, initial healthy vibration value, initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle, and initial healthy rotational speed. Second, based on the basic data and real-time operating data of all wind turbines, the wake influence relationship between the target wind turbine and the other wind turbines is determined. Third, based on the wake influence relationship, the wake influence factor of the target wind turbine is calculated, and the initial health data of the target wind turbine is dynamically corrected based on the wake influence factor to obtain corrected health data. Finally, based on the real-time operating data and corrected health data of the target wind turbine, the fault warning result for the target wind turbine is determined. This invention, through determining the wake influence relationship between wind turbine units and dynamically correcting initial health data based on wake influence factors, enables fault warning standards to adapt to changes in wind speed deficit and turbulence enhancement under wake conditions. This distinguishes between normal operation fluctuations caused by wake effects and faults in the wind turbine unit itself. This method solves the problem of low fault warning accuracy in existing technologies due to insufficient consideration of wake interference, reducing false alarm and false negative rates, and improving wind farm operation and maintenance efficiency and unit operational reliability. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is the first flowchart of a wind turbine fault early warning method provided in an embodiment of the present invention; Figure 2 The second flowchart is provided for a wind turbine fault early warning method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a wind turbine fault early warning system provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention provides a method, system, device, and readable storage medium for early warning of wind turbine faults, which can solve the technical problem of low accuracy in existing early warning methods in related technologies.

[0020] See Figure 1 As shown in the figure, an embodiment of the present invention provides a wind turbine fault early warning method, the method comprising the following steps: Step S100: Obtain basic data, real-time operating data, and initial health data for each wind turbine; wherein, the basic data includes the spatial location of the wind turbine and the rotor radius, the real-time operating data includes the current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current speed, and the initial health data includes the initial healthy power, initial healthy vibration value, initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle, and initial healthy speed; Specifically, suppose there are n wind turbine units in the wind farm, and the spatial location of the i-th wind turbine unit is... for:

[0021] Real-time operating data of the i-th wind turbine at time t Represented as:

[0022] in: Indicates wind speed; Indicates the current wind direction; Indicates the current power; Indicates the current vibration characteristics; Indicates the current temperature; Indicates the current pitch angle; Indicates the current yaw angle; Indicates the current rotational speed; This indicates the current operating status code. By quantifying the spatial location and real-time operating data of the wind turbine, the problem of limited data dimensions in existing technologies is solved, providing information support for subsequent accurate calculations of wake impact relationships.

[0023] Step S200: Determine the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines; Specifically, it can dynamically identify upstream and downstream wake links within a wind farm, clarifying which wind turbines have interference relationships, thus avoiding the shortcomings of existing technologies that treat all wind turbines as independent individuals and ignore group interference.

[0024] Step S300: Based on the wake influence relationship, calculate the wake influence factor of the target wind turbine, and dynamically correct the initial health data of the target wind turbine based on the wake influence factor to obtain the corrected health data. Specifically, it achieves dynamic health benchmarks, ensuring that fluctuations in the normal operation of downstream wind turbines under wake conditions are not misjudged as faults, reducing false warnings caused by wake obstruction, and improving the environmental adaptability of the warning method.

[0025] Step S400: Determine the fault warning result of the target wind turbine based on the real-time operating data and corrected health data of the target wind turbine.

[0026] Specifically, it can accurately identify real anomalies that are beyond the range of wake interpretation, which avoids false alarms caused by wake influence and prevents missed alarms caused by wake noise masking real faults, thus improving the reliability of wind turbine fault early warning and operation and maintenance efficiency.

[0027] This invention provides a wind turbine fault early warning method. This method determines the wake influence relationship between wind turbines and dynamically corrects initial health data based on wake influence factors. This allows the fault early warning standard to adapt to changes in wind speed loss and turbulence enhancement under wake conditions, thereby distinguishing between normal operation fluctuations caused by wake effects and faults in the wind turbine itself. This method solves the problem of low fault early warning accuracy in existing technologies due to insufficient consideration of wake interference, reducing false alarm and false negative rates, and improving wind farm operation and maintenance efficiency and turbine operation reliability.

[0028] As an optional implementation, in one embodiment of the invention, the step of determining the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines includes the following steps: calculating the distance projection of the other wind turbines relative to the target wind turbine in the wind direction and the lateral offset distance in the vertical wind direction based on the spatial position of the wind turbines in the basic data of all wind turbines and the current wind direction in the real-time operating data; if the distance projection is greater than zero and the lateral offset distance is less than or equal to the wake coverage range threshold, then it is determined that the target wind turbine is affected by the wake of the corresponding other wind turbines, and a wake influence relationship is established; wherein, the wake coverage range threshold is determined based on the rotor radius of the corresponding other wind turbines, the rotor radius of the target wind turbine, the distance projection, and a preset wake expansion coefficient.

[0029] Specifically, let the current wind direction at time t be... The projected distance in the wind direction from the i-th wind turbine to the j-th wind turbine. and the lateral offset distance in the vertical wind direction They are respectively: = =∣-( sin + cosθ(t)∣ The i-th wind turbine is determined to be upstream of the j-th wind turbine and to have a wake effect on the j-th wind turbine when the following conditions are met: >0 ≤ +k +

[0030] in: This represents the radius of the rotor of the i-th wind turbine unit; denoted by , where represents the rotor radius of the j-th wind turbine; and denoted by k, representing the preset wake expansion coefficient. This method can accurately quantify the spatial geometric relationship and wake diffusion effect between wind turbines, clarifying not only the upstream and downstream orientations but also considering the dynamic changes of the wake cone. This allows for the accurate identification of wind turbine pairs experiencing actual interference, avoiding the neglect or misjudgment of wake due to positional errors, and providing a reliable basis for the dynamic correction of subsequent health benchmarks.

[0031] Additionally, define a wake effect indicator variable. :

[0032] when When =1, it indicates that the i-th wind turbine has a wake influence relationship with the j-th wind turbine at time t.

[0033] As an optional implementation, in one embodiment of the invention, referring to Figure *, the step of calculating the wake influence factor of the target wind turbine based on the wake influence relationship includes the following steps: based on the wake influence relationship, calculating the total wind speed loss ratio, turbulence enhancement degree, and overlap ratio of the swept surfaces of the blades of the target wind turbine caused by the other wind turbines to the target wind turbine; and calculating the wake influence factor of the target wind turbine by weighted calculation based on the total wind speed loss ratio, turbulence enhancement degree, and overlap ratio.

[0034] Specifically, the target wind turbine unit is the first Wake effect factors on typhoon turbines for:

[0035] in, , , Here, ε represents the corresponding weighting coefficient, and ε is a minimal constant to prevent the denominator from being zero. This represents the percentage of total wind speed loss. To the degree of turbulence enhancement, The calculation formula is:

[0036] Among them, the overlap ratio of the swept surfaces of the rotors of the other wind turbine units and the target wind turbine unit is... for:

[0037] in: This represents the area of ​​overlap between the wake section and the swept surface of the downstream wind turbine rotor; ,when =0 indicates no overlap, when =1 indicates complete coverage.

[0038] The proportion of wind speed loss caused by the i-th wind turbine to the j-th wind turbine The calculation method is as follows:

[0039] in: This represents the correction factor for the operating status of the upstream wind turbine. If the upstream wind turbine is operating normally, then... The capacity is relatively large; if the machine is shut down or operates with limited power, then... Smaller; This represents the thrust coefficient of the i-th wind turbine.

[0040] When multiple upstream wind turbines simultaneously generate wake effects on the j-th wind turbine, the total wind speed loss ratio is calculated using a sum-of-squares method. :

[0041] The degree of turbulence enhancement caused by the wake for:

[0042] in: Indicates the intensity of free-flow turbulence. This represents the turbulence enhancement correction coefficient. This embodiment comprehensively quantifies wake intensity from three dimensions: total wind speed deficit ratio, turbulence enhancement degree, and overlap ratio. This avoids the one-sidedness of single-index evaluation, ensuring that the calculated wake impact factor accurately reflects the complex wake conditions actually faced by downstream wind turbines. This provides a precise quantitative basis for subsequent dynamic correction of health data based on the wake impact factor, thereby distinguishing wake interference from equipment failure and improving the accuracy of fault warnings.

[0043] As an optional implementation, in one embodiment of the invention, the step of dynamically correcting the initial health data of the target wind turbine based on the wake influence factor to obtain corrected health data includes the following steps: Based on the total wind speed loss ratio Determine the equivalent inflow velocity The corrected health power is obtained by correcting the initial health power. Specifically, calculate the equivalent inflow wind speed of the j-th wind turbine. :

[0044] in: This represents the equivalent inflow velocity after taking into account the wake effect; The reference wind speed can be obtained from the wind speed of the wind tower, the wind speed of the lidar, the average free-flow wind speed of the power plant, or the estimated wind speed of the upstream unit that is not affected by the wake.

[0045] Let the initial healthy power of the j-th wind turbine be when it is not affected by the wake. for:

[0046] in: The power reference model can be a manufacturer's power curve, a historical fitted power curve, or a machine learning power prediction model; ρ(t) represents air density.

[0047] After considering the wake effect, the equivalent inflow velocity is adopted. Calculate corrected health power :

[0048] Power residual for:

[0049] in: Indicates the current power; This indicates the rated power.

[0050] when If the power level remains above the set threshold, it indicates that the current power is below the power level that the wake can explain, and there may be an abnormality in the device itself.

[0051] Based on the wake influence factor and the preset vibration threshold correction coefficient, the initial healthy vibration value is corrected to obtain the corrected healthy vibration value. Wake waves can increase turbulence in downstream wind turbines, leading to increased vibration fluctuations. To avoid misjudging wake disturbances as mechanical faults, this invention corrects the initial healthy vibration value based on the wake influence factor.

[0052] Assume the initial healthy vibration value without considering the wake is The corrected healthy vibration value after wake correction for:

[0053] in: This represents the preset vibration threshold correction coefficient.

[0054] Vibration abnormality for:

[0055] when Furthermore, if the duration exceeds the set time threshold, it is determined that there is a risk of abnormal vibration.

[0056] Based on the wake influence factor and the corresponding preset correction coefficient, the initial healthy mean and initial healthy fluctuation range of the initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle and initial healthy speed are corrected to obtain the corrected healthy mean and corrected healthy fluctuation range.

[0057] For the initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle, and initial healthy speed, the initial healthy mean values ​​and initial healthy fluctuation ranges are all used, with a uniform wake correction method employed:

[0058] in: This indicates a certain type of monitoring indicator, including temperature, pitch angle, yaw angle, and engine speed; This represents the initial health mean without considering the wake effect; This indicates the initial health fluctuation range without considering the wake effect; This represents the corrected healthy mean after wake correction; This indicates the corrected health fluctuation range after wake correction; This represents the wake correction coefficient for the corresponding indicator.

[0059] Residual of corresponding indicators for:

[0060] when If the value is consistently greater than the set threshold, the indicator is considered abnormal.

[0061] The embodiments of the present invention enable the health benchmark to be dynamically and adaptively adjusted according to the wake conditions, avoiding misjudging the wind speed loss and turbulence enhancement caused by the wake as equipment failure, reducing the false alarm rate, and preventing the real fault from being masked by the wake interference, thereby improving the accuracy and reliability of fault warning.

[0062] As an optional implementation, in one embodiment of the invention, see [link to relevant documentation]. Figure 2 As shown, the step of determining the fault warning result of the target wind turbine based on the real-time operating data and corrected health data of the target wind turbine includes the following steps: Step S410: Calculate the residual between the real-time operating data and the corrected health data, and determine the comprehensive fault anomaly score by combining the corresponding anomaly weights; Specifically, as mentioned above, calculate the power residual. The residuals of the corresponding indicators The comprehensive fault anomaly score of the j-th wind turbine at time t. for:

[0063] in:

[0064] This indicates the overall fault and anomaly score; Indicates the power anomaly weight; This represents the outlier weight of the m-th type of indicator; This represents the abnormal threshold for the m-th type of indicator; This indicates the number of indicators involved in the judgment.

[0065] Step S420: Based on the initial healthy power of the target wind turbine Current power and corrected health power Determine the wake explanatory power ; Specifically, to determine whether an anomaly can be explained by the wake, the wake explanatory power is defined. :

[0066] in:

[0067]

[0068] This represents the observed power loss; This represents the power loss explained by the wake.

[0069] when The closer to 1, the more the power drop can be explained by the wake; when If the preset value is not reached, it indicates that the power reduction cannot be fully explained by the wake, and there may be an abnormality in the equipment itself.

[0070] Step S430: Calculate the individual deviation degree of the target wind turbine, wherein the individual deviation degree characterizes the deviation of the real-time operating data of the target wind turbine from the set of reference turbines with the same and similar wake conditions, wherein the same and similar wake conditions are determined based on the similarity of wake influence factors. Step S440: Based on the comprehensive fault anomaly score Individual deviation degree and wake explanatory power Calculate the comprehensive failure risk value ; Specifically, comprehensive failure risk value for:

[0071] in: a, b, and c are weighting coefficients.

[0072] Step S450: Based on the comprehensive fault risk value, determine the fault warning result of the target wind turbine, wherein the fault warning result includes a warning level, abnormal cause and handling strategy.

[0073] As an optional implementation, in one embodiment of the invention, the step of calculating the individual deviation of the target wind turbine j includes the following steps: A set of reference turbine units that are in similar wake conditions to the target wind turbine unit is determined, and the same and similar wake conditions are determined based on the similarity of wake influence factors; Specifically, to avoid misjudgment of a single unit, a correlation analysis was further conducted on multiple wind turbines on the same wake link.

[0074] Let there be a set of reference turbines that operate under the same or similar wake conditions as the j-th wind turbine. for: Same or similar model, in normal condition. in, This indicates the preset similarity threshold for wake influence factors.

[0075] As mentioned above, calculate the power residual of the target wind turbine relative to the reference turbine set. ; The degree of deviation of the individual unit is obtained based on the power residual and the median absolute deviation of the power residual of the reference unit set.

[0076] Specifically, the individual deviation degree of the j-th wind turbine is defined. :

[0077] Among them: median( ) represents the median; MAD( () indicates the absolute deviation of the median; The larger the value, the more significant the deviation of the j-th wind turbine compared to other wind turbines under the same wake conditions.

[0078] If multiple downstream units experience power reduction simultaneously, and the degree of power reduction is related to the wake influence factor... If there is a positive correlation, it is determined to be due to the wake effect of the wind turbine; if only a single wind turbine deviates for a long period of time under the same wake conditions, it is determined to be an individual equipment malfunction.

[0079] The following correlation indicators are introduced:

[0080] when When the value exceeds the set threshold, it indicates that the power residual within the wind turbine is consistent with the wake effect, making it more likely to be judged as a group operational fluctuation caused by the wake; when a certain wind turbine unit When the value is significantly higher than normal, it is more likely to be judged as a single-unit failure. This embodiment of the invention introduces station-level correlation analysis and uses statistically robust median and median absolute deviation algorithms to eliminate the interference of individual outliers on the benchmark judgment, avoid single-unit misjudgment, and improve the accuracy of fault early warning.

[0081] As an optional implementation, in one embodiment of the invention, the step of determining the fault warning result of the target wind turbine further includes the following steps: Based on the relationship between the comprehensive fault risk value and the preset risk level threshold, the early warning level is divided; Specifically, the warning level It can be divided according to the following rules:

[0082] in, These are different preset risk level thresholds.

[0083] According to the wake influence factor Wake Explanation Individual deviation degree and comprehensive fault anomaly score Determine the cause of the anomaly and the corresponding handling strategy.

[0084] Specifically, the judgment logic is as follows: when Reaching the corresponding preset value Reaching the corresponding preset value and If the corresponding preset value is not reached, the abnormality is determined to be mainly caused by the wake effect. No equipment failure work order is generated, and only a wake effect prompt is output.

[0085] when The corresponding preset value was not reached. The corresponding preset value was not reached and When the corresponding preset value is reached, the abnormality is determined to be unexplainable by the wake, and a device fault warning is generated.

[0086] when Reaching the corresponding preset value and When the corresponding preset value is reached, it indicates that the unit deviates significantly from other units under the same wake conditions. It is judged as a potential equipment abnormality under wake conditions, and an early warning work order is generated to prompt key checks on blades, yaw, pitch or drive train components.

[0087] This invention first classifies warning levels based on a comprehensive fault risk value and a preset risk level threshold. Then, it combines the wake influence factor, the wake explanatory power, the individual deviation degree, and the comprehensive fault anomaly score to determine the cause of the anomaly. This not only provides a quantitative risk level but also clarifies the root cause of the anomaly through multi-dimensional logical judgment, providing targeted handling strategies. This avoids ineffective troubleshooting of wake interference by operation and maintenance personnel, while ensuring that potential faults are not overlooked, thus improving the accuracy and efficiency of wind farm operation and maintenance.

[0088] This invention also provides a wind turbine fault early warning system, see [link to relevant documentation]. Figure 3 As shown, the system includes a data acquisition module, a judgment module, a calculation module, and an early warning module. The data acquisition module acquires basic data and real-time operating data for each wind turbine. The basic data includes the wind turbine's spatial location and rotor radius, while the real-time operating data includes current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed. The judgment module determines the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines. The calculation module calculates the wake influence factor of the target wind turbine when wake influence exists and dynamically corrects the health baseline data of the target wind turbine based on the wake influence factor. The health baseline data includes health baseline power, health baseline vibration value, health baseline temperature, health baseline pitch angle, health baseline yaw angle, and health baseline rotational speed. The early warning module determines the fault early warning result of the target wind turbine based on the real-time operating data and the corrected health baseline data.

[0089] This invention also provides a computer device, see [link to documentation]. Figure 4 As shown, the computer device includes a memory and a processor. The memory stores at least one instruction, which is loaded and executed by the processor to implement the aforementioned wind turbine fault early warning method. The processor can be a CPU, or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, etc. The general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of the computer device, connecting various parts of the entire computer device through various interfaces and lines.

[0090] Memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for at least one function (such as video playback, image playback, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as video data, image data, etc.). In addition, memory can include high-speed mobile access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital cards (SD cards), flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0091] In one embodiment of the invention, the processor is used to run a computer program stored in a memory to perform the following steps: Step S100: Acquire basic data, real-time operating data, and initial health data for each wind turbine; wherein, the basic data includes the spatial location of the wind turbine and the rotor radius, the real-time operating data includes the current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed, and the initial health data includes the initial health power, initial health vibration value, initial health temperature, initial health pitch angle, initial health yaw angle, and initial health rotational speed; Step S200: Determine the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines; Step S300: Calculate the wake influence factor of the target wind turbine based on the wake influence relationship, and dynamically correct the initial health data of the target wind turbine based on the wake influence factor to obtain corrected health data; Step S400: Determine the fault warning result of the target wind turbine based on the real-time operating data and corrected health data of the target wind turbine.

[0092] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements all or part of the steps of the aforementioned wind turbine fault early warning method.

[0093] The embodiments of the present invention can implement all or part of the aforementioned processes, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0094] In the description of this invention, it should be noted that the terms "upper," "lower," etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication between two elements. For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances.

[0095] It should be noted that in this invention, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0096] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for early warning of wind turbine faults, characterized in that, Includes the following steps: Acquire basic data, real-time operating data, and initial health data for each wind turbine. The basic data includes the wind turbine's spatial location and rotor radius. The real-time operating data includes current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed. The initial health data includes initial healthy power, initial healthy vibration value, initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle, and initial healthy rotational speed. Based on the basic data and real-time operating data of all wind turbine units, determine the wake influence relationship between the target wind turbine unit and the other wind turbine units. Based on the wake influence relationship, the wake influence factor of the target wind turbine is calculated, and the initial health data of the target wind turbine is dynamically corrected based on the wake influence factor to obtain the corrected health data. Based on the real-time operating data and corrected health data of the target wind turbine, the fault warning results of the target wind turbine are determined.

2. The wind turbine fault early warning method according to claim 1, characterized in that, The step of determining the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines includes the following steps: Based on the spatial location of the wind turbines in the basic data of all wind turbines and the current wind direction in the real-time operation data, calculate the distance projection of the remaining wind turbines relative to the target wind turbine in the wind direction and the lateral offset distance in the vertical wind direction. If the distance projection is greater than zero and the lateral offset distance is less than or equal to the wake coverage threshold, then it is determined that the target wind turbine is affected by the wake of the other corresponding wind turbines, and a wake influence relationship is established; wherein, the wake coverage threshold is determined based on the rotor radius of the other corresponding wind turbines, the rotor radius of the target wind turbine, the distance projection, and the preset wake expansion coefficient.

3. The wind turbine fault early warning method according to claim 1, characterized in that, The step of calculating the wake influence factor of the target wind turbine based on the wake influence relationship includes the following steps: Based on the wake effect relationship, the total wind speed loss ratio, turbulence enhancement degree and overlap ratio of the blade sweep surfaces of the other wind turbines and the target wind turbine are calculated. The wake influence factor of the target wind turbine is calculated by weighting the total wind speed loss ratio, turbulence enhancement degree and overlap ratio.

4. The wind turbine fault early warning method according to claim 3, characterized in that, The step of dynamically correcting the initial health data of the target wind turbine based on the wake influence factor to obtain corrected health data includes the following steps: Based on the total wind speed loss ratio, the equivalent inflow wind speed is determined, and the corrected healthy power is obtained after correcting the initial healthy power. Based on the wake influence factor and the preset vibration threshold correction coefficient, the initial healthy vibration value is corrected to obtain the corrected healthy vibration value. Based on the wake influence factor and the corresponding preset correction coefficient, the initial healthy mean and initial healthy fluctuation range of the initial healthy temperature, initial healthy pitch angle, initial healthy yaw angle and initial healthy speed are corrected to obtain the corrected healthy mean and corrected healthy fluctuation range.

5. The wind turbine fault early warning method according to claim 1, characterized in that, The step of determining the fault warning result of the target wind turbine based on the real-time operating data and corrected health data of the target wind turbine includes the following steps: Calculate the residual between the real-time operating data and the corrected health data, and determine the comprehensive fault anomaly score by combining the corresponding anomaly weights; The wake explanatory power is determined based on the initial healthy power, current power, and corrected healthy power of the target wind turbine. Calculate the individual deviation degree of the target wind turbine, which characterizes the deviation of the real-time operating data of the target wind turbine from the set of reference turbines with the same and similar wake conditions. The same and similar wake conditions are determined based on the similarity of wake influence factors. Based on the comprehensive fault anomaly score, individual deviation degree, and wake explanation degree, the comprehensive fault risk value is calculated; Based on the comprehensive fault risk value, the fault warning result of the target wind turbine is determined, wherein the fault warning result includes the warning level, the cause of the abnormality and the handling strategy.

6. The wind turbine fault early warning method according to claim 5, characterized in that, The step of calculating the individual deviation of the target wind turbine includes the following steps: A set of reference turbine units that are in similar wake conditions to the target wind turbine unit is determined, and the same and similar wake conditions are determined based on the similarity of wake influence factors; Calculate the power residual of the target wind turbine relative to the reference turbine set; The degree of deviation of the individual unit is obtained based on the power residual and the median absolute deviation of the power residual of the reference unit set.

7. The wind turbine fault early warning method according to claim 5, characterized in that, The step of determining the fault warning result of the target wind turbine unit further includes the following steps: Based on the relationship between the comprehensive fault risk value and the preset risk level threshold, the early warning level is divided; Based on the wake influence factor, wake explanatory power, individual deviation degree, and comprehensive fault anomaly score, the cause of the anomaly and the handling strategy are determined.

8. A wind turbine fault early warning system, characterized in that, include: The data acquisition module is used to acquire basic data and real-time operating data for each wind turbine. The basic data includes the spatial location of the wind turbine and the rotor radius, while the real-time operating data includes the current wind direction, current power, current vibration characteristics, current temperature, current pitch angle, current yaw angle, and current rotational speed. The judgment module is used to determine the wake influence relationship between the target wind turbine and the other wind turbines based on the basic data and real-time operating data of all wind turbines. The calculation module is used to calculate the wake influence factor of the target wind turbine when there is a wake influence, and to dynamically correct the health reference data of the target wind turbine based on the wake influence factor. The health reference data includes health reference power, health reference vibration value, health reference temperature, health reference pitch angle, health reference yaw angle and health reference speed. The early warning module is used to determine the fault warning result of the target wind turbine based on the real-time operating data and the corrected health benchmark data of the target wind turbine.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is used to implement the wind turbine fault early warning method as described in claim 1 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the wind turbine fault early warning method as described in claim 1.