Wind turbine generator early warning method and device based on IPC hardware platform

Abstract

The invention discloses a wind turbine generator early warning method and device based on an IPC hardware platform, and relates to the technical field of wind turbine generator early warning, and the method comprises the steps: collecting the state data of a wind turbine generator and the working interference parameters of the wind turbine generator based on a sensor network, and transmitting the state data of the wind turbine generator and the working interference parameters of the wind turbine generator to the IPC hardware platform, processing the wind turbine generator set state data and the set working interference parameters to obtain a wind turbine generator set state anomaly index; acquiring sensor communication data, performing comprehensive analysis according to the sensor communication data and the unit working interference parameter to obtain an early warning threshold fluctuation parameter, and performing processing according to the early warning threshold fluctuation parameter to obtain a wind turbine unit state abnormality index threshold; and comparing the wind turbine generator set state abnormity index with a wind turbine generator set state abnormity index threshold value, evaluating the operation state of the wind turbine generator set, and performing early warning feedback according to an evaluation result. A basis is provided for targeted operation and maintenance measures, and safe and stable operation of the wind turbine generator is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine warning, and specifically provides a wind turbine warning method and device based on an IPC hardware platform. Background Art

[0002] With the rapid development of the wind power industry in China, the service life of wind turbine generator sets is gradually increasing, and the failure rate is also increasing accordingly. These failures not only affect the availability and power generation of the wind turbines themselves, but also result in high maintenance costs and unnecessary economic losses. To avoid downtime and economic losses caused by wind turbine failures, it is necessary to conduct online centralized monitoring and warning of wind turbine generator sets.

[0003] For example, the invention patent with the publication number CN114215705B is a wind turbine fault warning method and system, which includes a wind turbine fault warning method. The method includes: obtaining the vibration data of the wind turbine and the meteorological data of the surrounding environment, establishing a corresponding relationship, and binding the time parameter to store it in the vibration state database; identifying the meteorological category of the current meteorological data, and matching the corresponding vibration data with the conditional data set of the same meteorological category; comparing the current vibration data with the historical vibration data of the conditional data set, calculating the conditional difference, and establishing a difference development trend graph; determining whether the conditional difference / difference development trend graph meets the preset abnormal conditions. If so, execute the fault warning determination logic based on the current vibration data.

[0004] For example, the invention patent with the publication number CN109723609B is a fault warning method and system for a pitch control system of a wind turbine, including: collecting historical data of the pitch control system during normal operation and when the pitch angle changes. The historical data includes the pitch angle of each blade in the pitch control system; performing filtering processing on the historical data, and determining the data deviation range according to the data deviation before and after the filtering processing; performing filtering processing on the data to be measured of the pitch control system. When the data deviation before and after the filtering processing exceeds the data deviation range, a fault warning is issued.

[0005] However, in the process of implementing the technical solutions of the present invention in the embodiments of the present application, it is found that the above technologies have at least the following technical problems: At present, the fault warning of wind turbine generator sets only stays in the monitoring of operation data and environmental data, and the warning dimension is relatively single, and the accuracy is not high. Summary of the Invention

[0006] In view of the deficiencies of the prior art, the present invention provides a wind turbine warning method and device based on an IPC hardware platform, which can effectively solve the problems involved in the above background art.

[0007] To achieve the above object, the present invention is realized by the following technical solutions: In the first aspect of the present invention, a wind turbine warning method based on an IPC hardware platform is provided, including: collecting wind turbine status data and unit working interference parameters based on a sensor network, transmitting the wind turbine status data and unit working interference parameters back to the IPC hardware platform, and processing the wind turbine status data and unit working interference parameters to obtain a wind turbine status anomaly index.

[0008] Obtain sensor communication data, comprehensively analyze to obtain a warning threshold fluctuation parameter according to the sensor communication data and unit working interference parameters, and process according to the warning threshold fluctuation parameter to obtain a wind turbine status anomaly index threshold.

[0009] Compare the wind turbine status anomaly index with the wind turbine status anomaly index threshold, evaluate the operation status of the wind turbine, and give a warning feedback according to the evaluation result.

[0010] As a further method, the wind turbine status data includes: hub working data and gearbox working data; the hub working data includes the hub rotation speed, hub tilt angle, and hub swing displacement at each monitoring time point; the gearbox working data includes the temperature, vibration acceleration amplitude, and oil particle size at each status monitoring point at each monitoring time point.

[0011] As a further method, the process of processing the wind turbine status data and unit working interference parameters to obtain a wind turbine status anomaly index is as follows: the unit working interference parameters include the wind speed and the cumulative working hours of the unit at each monitoring time point; process the hub working data to obtain a hub anomaly evaluation value; process the gearbox working data to obtain a gearbox anomaly evaluation value; comprehensively analyze according to the unit working interference parameters, hub anomaly evaluation value, and gearbox anomaly evaluation value to obtain a wind turbine status anomaly index.

[0012] As a further method, the process of processing the gearbox working data to obtain a gearbox anomaly evaluation value is as follows: obtain the reference working temperature, allowable deviation working temperature, critical vibration acceleration amplitude, and critical oil particle size from the wind turbine database; comprehensively analyze according to the gearbox working data to obtain a gearbox anomaly evaluation value.

[0013] As a further method, the process of comprehensively analyzing to obtain a warning threshold fluctuation parameter is as follows: the sensor communication data includes the signal strength, working voltage, and connection interruption times of each sensor node; obtain the critical signal strength, reference sensor working voltage, allowable deviation voltage, critical interruption times, critical wind speed, and unit service life from the wind turbine database; comprehensively analyze according to the sensor communication data and unit working interference parameters to obtain a warning threshold fluctuation parameter.

[0014] As a further method, the process of evaluating the operating state of the wind turbine is as follows: Compare the wind turbine state anomaly index with the wind turbine state anomaly index threshold. If the wind turbine state anomaly index is greater than or equal to the wind turbine state anomaly index threshold, the wind turbine state is evaluated as an abnormal state; if the wind turbine state anomaly index is less than the wind turbine state anomaly index threshold, the wind turbine state is evaluated as a normal state.

[0015] As a further method, the process of giving early warning feedback according to the evaluation result is as follows: For wind turbines in the normal state, no additional operations are performed; for wind turbines in the abnormal state, the IPC hardware platform performs self-regulation of the wind turbine according to the current wind speed, and evaluates the operating state of the wind turbine after self-regulation; if the operating state of the wind turbine remains abnormal after self-regulation, an early warning is given; if the operating state of the wind turbine changes from the abnormal state to the normal state, the operating state of the wind turbine is monitored within a preset monitoring period, and the self-regulation effect feedback is carried out.

[0016] As a further method, the process of giving the self-regulation effect feedback is as follows: If the operating state of the wind turbine remains normal within the preset monitoring period, no additional operations are performed; if the operating state of the wind turbine changes from the normal state to the abnormal state within the preset monitoring period, an early warning operation is carried out.

[0017] As a further method, the method for obtaining the wind turbine state anomaly index is as follows:

[0018]

[0019] In the formula, β represents the wind turbine state anomaly index, Lδ represents the hub anomaly evaluation value, Cδ represents the gearbox anomaly evaluation value, VF1 represents the wind speed of the wind turbine working environment, VF0 represents the critical wind speed, TM1 represents the cumulative working hours of the unit, TM0 represents the service life of the unit, τ1 represents the wind turbine state influence factor corresponding to the preset hub anomaly evaluation value, τ2 represents the wind turbine state influence factor corresponding to the preset gearbox anomaly evaluation value, τ3 represents the wind turbine state influence factor corresponding to the preset wind speed, and τ4 represents the wind turbine state influence factor corresponding to the preset cumulative working hours of the unit.

[0020] The second aspect of the present invention provides a wind turbine early warning device based on an IPC hardware platform, including: a sensor network for collecting wind turbine state data and unit working interference parameters, and transmitting the wind turbine state data and unit working interference parameters back to the IPC hardware platform.

[0021] The IPC hardware platform is used to process the status data of the wind turbine and the working interference parameters of the unit, obtain the sensor communication data, and comprehensively evaluate the operating status of the wind turbine.

[0022] The controller is used to obtain the evaluation result of the operating status of the wind turbine by the IPC hardware platform and give an early warning feedback.

[0023] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0024] (1) By providing a wind turbine early warning method and device based on the IPC hardware platform, the present invention integrates the unit status, working interference and communication data, accurately quantifies the operating status and the early warning threshold, realizes the accurate evaluation of the operating status of the wind turbine, and reduces the risk of misjudgment. At the same time, it automatically adjusts the abnormal wind turbine and continuously monitors the adjustment effect to form a closed-loop control, ensuring the long-term stable operation of the unit, laying a solid foundation for the operation and maintenance management of the wind farm, and overall improving the operation efficiency.

[0025] (2) By comprehensively analyzing the hub rotation speed, hub tilt angle and hub swing displacement, the present invention can accurately quantify and reflect the real-time abnormal degree of the hub, providing an intuitive and reliable decision-making basis for the operation and maintenance personnel of the wind turbine, and helping to take targeted operation and maintenance measures such as shutdown inspection, key monitoring, and fine-tuning repair in a timely manner, ensuring the safe, stable and efficient operation of the wind turbine.

[0026] (3) By self-adjusting the wind turbine according to the wind speed to dynamically match the blade pitch angle adjustment value, the present invention makes full use of the relationship between the wind speed and the blade pitch angle adjustment stored in the wind turbine database to achieve precise control, reduces the unstable operating conditions caused by wind speed fluctuations, and extends the service life of the equipment. At the same time, a preset monitoring period is set to continuously track the status of the adjusted wind turbine, which helps to continuously monitor the health status of the unit, ensure the long-term reliable operation of the wind turbine, and reduce the probability of fault recurrence and the complexity of operation and maintenance.

[0027] Of course, it is not necessary for any product implementing the present invention to achieve all the above advantages at the same time. Description of the Drawings

[0028] Figure 1 It is a schematic flowchart of the method of the present invention;

[0029] Figure 2 It is a schematic diagram of the functional relationship between the hub abnormal evaluation value and the wind turbine status abnormal index involved in the embodiment of the present invention. Detailed Embodiments

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0032] Referring to Figure 1 As shown, the first aspect of the present invention provides a wind turbine warning method based on an IPC hardware platform, including: collecting wind turbine status data and unit working interference parameters based on a sensor network, transmitting the wind turbine status data and unit working interference parameters back to the IPC hardware platform, and processing the wind turbine status data and unit working interference parameters to obtain a wind turbine status anomaly index.

[0033] In this embodiment, the IPC (Industrial Personal Computer) hardware platform is a computer hardware system dedicated for industrial environments. The IPC hardware platform is connected to the sensors on the wind turbine through interfaces to collect the operation data of the wind turbine in real time. The IPC hardware platform can cooperate with other control devices, such as programmable logic controllers and frequency converters, to realize the start, stop, power adjustment and yaw control of the wind turbine, ensuring the stable and efficient operation of the wind turbine under different working conditions.

[0034] Obtain sensor communication data, comprehensively analyze according to the sensor communication data and unit working interference parameters to obtain a warning threshold fluctuation parameter, and process according to the warning threshold fluctuation parameter to obtain a wind turbine status anomaly index threshold.

[0035] Compare the wind turbine status anomaly index with the wind turbine status anomaly index threshold, evaluate the operation status of the wind turbine, and give a warning feedback according to the evaluation result.

[0036] Specifically, the wind turbine status data includes: hub working data and gearbox working data.

[0037] The hub working data includes the hub rotation speed, hub tilt angle, and hub swing displacement at each monitoring time point.

[0038] It should be understood that in this embodiment, the hub tilt angle refers to the tilt angle of the hub relative to the vertical axis direction of the normally operating hub, and the hub swing displacement refers to the linear distance that the center point of the hub swings during operation. The hub rotation speed and hub tilt angle can be monitored by a gyroscope, and the hub swing displacement can be collected by a displacement sensor.

[0039] The gearbox working data includes the temperature, vibration acceleration amplitude, and oil particle size at each state monitoring point.

[0040] It should be understood that in this embodiment, each state monitoring point is deployed inside the gearbox to monitor the gearbox working data. The oil particle size refers to the number of impurity particles per unit volume (such as per milliliter) of the gearbox lubricating oil. In this embodiment, the temperature is monitored by a temperature sensor, the vibration acceleration amplitude is monitored by an acceleration sensor, and the oil particle size can be collected by an optical occlusion particle counter.

[0041] Specifically, the wind turbine status data and the unit working interference parameters are processed to obtain the wind turbine status anomaly index. The specific analysis process is as follows: The unit working interference parameters include the wind speed and the cumulative working duration of the unit.

[0042] It should be understood that in this embodiment, the wind speed can be collected by an anemometer, and the cumulative working duration of the unit refers to the total duration since the wind turbine was put into use.

[0043] The hub working data is processed to obtain the hub anomaly evaluation value.

[0044] In a specific embodiment, the critical hub tilt angle and the critical hub swing displacement are extracted from the wind turbine database. The critical hub tilt angle refers to the maximum angle allowed for the hub to tilt, and the critical hub swing displacement refers to the maximum displacement allowed for the hub to swing. When the dynamic change of the hub exceeds the maximum limit, it indicates that there may be an anomaly in the hub operation.

[0045] The method for obtaining the hub anomaly evaluation value is as follows:

[0046]

[0047] In the formula, Lδ represents the hub anomaly evaluation value, e represents the natural constant, LV i represents the hub rotation speed at the i-th monitoring time point, LJ i represents the hub tilt angle at the i-th monitoring time point, LJ0 represents the critical hub tilt angle, LW iDenote the hub swing displacement at the $i$-th monitoring time point as $LW_i$, the critical hub swing displacement as $LW_0$, the hub anomaly impact factor corresponding to the preset hub rotation speed as $\varphi_1$, the hub anomaly impact factor corresponding to the preset hub tilt angle as $\varphi_2$, the hub anomaly impact factor corresponding to the preset hub swing displacement as $\varphi_3$, $i$ represents the number of each monitoring time point, $i = 1, 2, 3, \cdots, n$, and $n$ represents the total number of monitoring time points.

[0048] In this embodiment, the hub anomaly impact factors corresponding to the hub rotation speed, hub tilt angle, and hub swing displacement are preset in the wind turbine database. These impact factors are specific values obtained by quantifying the influence degrees of the hub rotation speed, hub tilt angle, and hub swing displacement on the hub anomaly evaluation value. In the actual application process, they can be directly retrieved from the wind turbine database.

[0049] For example, a mapping set can be constructed in the wind turbine database to correlate the rated power of the wind turbine with the hub anomaly impact factors corresponding to the preset hub rotation speed, hub tilt angle, and hub swing displacement. During operation, according to the input of the rated power of the wind turbine into the mapping set, the hub anomaly impact factors corresponding to the hub rotation speed, hub tilt angle, and hub swing displacement that match the rated power of the wind turbine can be output. In this embodiment, there is a one-to-one mapping relationship between the rated power of the wind turbine and the hub anomaly impact factors, and the values of all hub anomaly impact factors are limited within the range of 0 to 1.

[0050] It should be understood that the hub anomaly evaluation value is used to quantitatively evaluate the anomaly degree of the hub during the operation of the wind turbine. When the numerical fluctuations of the hub rotation speed, the hub tilt angle, and the hub swing displacement are larger, the corresponding hub anomaly evaluation value is larger, indicating a higher degree of hub anomaly and the existence of operation risks for the hub.

[0051] In the algorithm of this embodiment, the hub rotation speed, hub tilt angle, and hub swing displacement are closely related. The stability of the hub rotation speed is affected by the hub tilt angle and hub swing displacement. When the numerical value of the hub rotation speed fluctuates, such as a sudden increase or decrease in speed beyond the normal operation range, the hub is more likely to have problems such as an increase in the tilt angle and an intensification of the swing displacement, resulting in the entire hub deviating from the normal operation trajectory.

[0052] By comprehensively analyzing the hub rotation speed, hub tilt angle, and hub swing displacement, it is possible to accurately quantify and reflect the real-time anomaly degree of the hub, providing intuitive and reliable decision-making basis for the maintenance personnel of the wind turbine, and helping to take targeted maintenance measures such as shutdown inspection, key monitoring, and fine-tuning repair in a timely manner, ensuring the safe, stable, and efficient operation of the wind turbine.

[0053] The working data of the gearbox is processed to obtain the abnormal evaluation value of the gearbox. The specific process is as follows: Obtain the reference working temperature, allowable deviation working temperature, critical vibration acceleration amplitude, and critical oil particle size from the wind turbine database.

[0054] It should be understood that in this embodiment, the critical vibration acceleration amplitude refers to the maximum allowable vibration acceleration amplitude, and the critical oil particle size refers to the maximum allowable oil particle size. When the vibration acceleration amplitude or oil particle size of the gearbox exceeds the maximum limit value, there will be a greater risk of abnormality in the operation of the gearbox.

[0055] Based on the working data of the gearbox, the abnormal evaluation value of the gearbox is obtained through comprehensive analysis.

[0056] In a specific embodiment, the method for obtaining the abnormal evaluation value of the gearbox is as follows:

[0057]

[0058] In the formula, Cδ represents the abnormal evaluation value of the gearbox, CW j represents the temperature of the j-th condition monitoring point, CW0 represents the reference working temperature, ΔCW represents the allowable deviation working temperature, CZ j represents the vibration acceleration amplitude of the j-th condition monitoring point, CZ0 represents the critical vibration acceleration amplitude, CN j represents the oil particle size of the j-th condition monitoring point, CN0 represents the critical oil particle size, ω1 represents the gearbox abnormal influence factor corresponding to the preset temperature, ω2 represents the gearbox abnormal influence factor corresponding to the preset vibration acceleration amplitude, ω3 represents the gearbox abnormal influence factor corresponding to the preset oil particle size, j represents the number of each condition monitoring point, j = 1, 2, 3,..., m, m represents the total number of condition monitoring points, N 50μm represents the number of large particles in the gearbox lubricating oil, N max represents the maximum number of allowable large particles.

[0059] It should be understood that in this embodiment, impurity particles with a diameter greater than or equal to 50 microns are recorded as large particles. If the number of large particles in the gearbox lubricating oil is greater than or equal to the maximum number of allowable large particles, it indicates that the gearbox has a serious abnormality and an early warning operation needs to be carried out immediately.

[0060] In this embodiment, the wind turbine database has preset the gearbox abnormal influence factors corresponding to temperature, vibration acceleration amplitude, and oil particle size. These influence factors are specific values obtained by quantifying the influence degrees of temperature, vibration acceleration amplitude, and oil particle size on the abnormal evaluation value of the gearbox. In the actual application process, they can be directly retrieved from the wind turbine database.

[0061] For example, a mapping set can be constructed in the wind turbine database to correlate the rated power of the wind turbine with the abnormal influence factors of the gearbox corresponding to the preset temperature, vibration acceleration amplitude, and oil particle size. During operation, by inputting the rated power of the wind turbine into the mapping set, the abnormal influence factors of the gearbox corresponding to the temperature, vibration acceleration amplitude, and oil particle size that match the rated power of the wind turbine can be output. In this embodiment, there is a one-to-one mapping relationship between the rated power of the wind turbine and the abnormal influence factors of the gearbox, and the values of all abnormal influence factors of the gearbox are limited within the range of 0 to 1.

[0062] It should be understood that the abnormal evaluation value of the gearbox is used to quantitatively evaluate the abnormal degree of the gearbox during the operation of the wind turbine. When the working temperature of the gearbox deviates more from the reference value, or the vibration acceleration amplitude and oil particle size of the gearbox are larger, the corresponding abnormal evaluation value of the gearbox is larger, indicating a higher abnormal degree of the gearbox.

[0063] In the algorithm of this embodiment, there is a close and mutually influential relationship among the temperature, vibration acceleration amplitude, and oil particle size. When faults such as increased gear wear, tooth surface gluing, and bearing damage occur in the gearbox, the cooperation between components is abnormal and the impact force increases, resulting in increased vibration and a significant rise in the vibration acceleration amplitude. At the same time, the increase in the vibration acceleration amplitude and oil particle size will increase the internal friction of the gearbox, leading to a rapid rise in temperature. When the vibration acceleration amplitude increases due to component failures, it will cause strong mechanical shocks and oscillations, resulting in metal particles entering the oil, increasing the oil particle size. At the same time, the increase in the oil particle size will cause uneven stress, further exacerbating the vibration and causing the vibration acceleration amplitude to continue to rise.

[0064] By comprehensively considering and analyzing the temperature, vibration acceleration amplitude, and oil particle size, the abnormal degree of the gearbox during the entire operation of the wind turbine can be accurately quantified, providing reliable and accurate data support for the operation and maintenance of the wind turbine gearbox, ensuring the efficient and safe operation of the gearbox and even the entire wind turbine, and effectively reducing the fault losses and operation and maintenance costs.

[0065] According to the unit working interference parameters, the abnormal evaluation value of the hub, and the abnormal evaluation value of the gearbox, the abnormal state index of the wind turbine is comprehensively analyzed and obtained.

[0066] In a specific embodiment, the critical wind speed and the service life of the unit are extracted from the wind turbine database. The critical wind speed refers to the maximum wind speed that the wind turbine can withstand during normal operation. When the actual wind speed exceeds the maximum wind speed, the operation failure risk of the wind turbine will increase. The service life of the unit refers to the maximum allowable operation duration of the wind turbine, which can generally be obtained from the experimental data provided by the manufacturer.

[0067] The method for obtaining the abnormal state index of the wind turbine is as follows:

[0068]

[0069] In the formula, β represents the abnormal state index of the wind turbine, Lδ represents the abnormal evaluation value of the hub, Cδ represents the abnormal evaluation value of the gearbox, VF1 represents the wind speed of the working environment of the wind turbine, VF0 represents the critical wind speed, TM1 represents the cumulative working hours of the unit, TM0 represents the service life of the unit, τ1 represents the influence factor of the wind turbine state corresponding to the preset abnormal evaluation value of the hub, τ2 represents the influence factor of the wind turbine state corresponding to the preset abnormal evaluation value of the gearbox, τ3 represents the influence factor of the wind turbine state corresponding to the preset wind speed, and τ4 represents the influence factor of the wind turbine state corresponding to the preset cumulative working hours of the unit.

[0070] In this embodiment, the influence factors of the wind turbine state corresponding to the abnormal evaluation value of the hub, the abnormal evaluation value of the gearbox, the wind speed, and the cumulative working hours of the unit are preset in the wind turbine database. These influence factors are specific values obtained by quantifying the influence degree of the abnormal evaluation value of the hub, the abnormal evaluation value of the gearbox, the wind speed, and the cumulative working hours of the unit on the abnormal state index of the wind turbine. In the actual application process, they can be directly retrieved from the wind turbine database.

[0071] For example, a mapping set can be constructed in the wind turbine database to correlate the rated power of the wind turbine with the influence factors of the wind turbine state corresponding to the preset abnormal evaluation value of the hub, the abnormal evaluation value of the gearbox, the wind speed, and the cumulative working hours of the unit. During operation, according to the rated power of the wind turbine input into the mapping set, the influence factors of the wind turbine state corresponding to the abnormal evaluation value of the hub, the abnormal evaluation value of the gearbox, the wind speed, and the cumulative working hours of the unit that match the rated power of the wind turbine can be output. In this embodiment, there is a one-to-one mapping relationship between the rated power of the wind turbine and the influence factors of the wind turbine state, and the values of all the influence factors of the wind turbine state are limited within the range of 0 to 1.

[0072] It should be understood that the abnormal state index of the wind turbine is used to quantitatively evaluate the abnormal degree of the operation state of the wind turbine. When the environmental wind speed, the service life of the unit, the abnormal evaluation value of the hub, and the abnormal evaluation value of the gearbox are larger, the corresponding abnormal state index of the wind turbine is larger, indicating that the operation state of the wind turbine is more abnormal. In a specific embodiment, as Figure 2 shown

[0073] τ1 = τ2 = 0.3, τ3 = τ4 = 0.2, VF1 = 10 m / s, VF0 = 25 m / s, TM1 = 10 years

[0074] TM0 = 20 years. When Cδ = 0.5, the functional relationship between the abnormal evaluation value of the hub and the abnormal index of the wind turbine unit state is shown as curve a; when Cδ = 1, the functional relationship between the abnormal evaluation value of the hub and the abnormal index of the wind turbine unit state is shown as curve b; when Cδ = 1.5, the functional relationship between the abnormal evaluation value of the hub and the abnormal index of the wind turbine unit state is shown as curve c.

[0075] In this embodiment, the abnormal evaluation value of the hub, the abnormal evaluation value of the gearbox, the wind speed, and the cumulative working hours of the unit are interrelated. Both the hub and the gearbox are key components of the wind turbine unit, and their operating states will affect each other. The wind speed is an external driving factor for the operation of the wind turbine unit. When the wind speed exceeds the rated wind speed, the aerodynamic force on the wind wheel increases sharply, and the load borne by the hub far exceeds the normal working conditions, which may lead to out-of-control hub speed, rapid increase in tilt angle and swing displacement, resulting in a rapid increase in the abnormal evaluation value of the hub. The interference of the wind speed can be transmitted to the gearbox through the transmission system, causing components such as gears and bearings in the gearbox to bear greater impact and load, thereby increasing the abnormal evaluation value of the gearbox. At the same time, as the cumulative working hours of the unit increase, wear and aging phenomena will occur in each component, further amplifying the mutual influence between the hub and the gearbox, making the change trends of their abnormal evaluation values interrelated and rising synchronously.

[0076] By comprehensively considering the abnormal evaluation value of the hub, the abnormal evaluation value of the gearbox, the wind speed, and the cumulative working hours of the unit, it is possible to accurately quantify the degree of abnormal operation of the wind turbine unit under different working conditions and different operation stages, making the evaluation result more scientific and accurate. Based on the accurately quantified abnormal index of the wind turbine unit state, the operation and maintenance personnel can clearly judge the health level of the unit and then formulate reasonable operation and maintenance strategies.

[0077] Specifically, the early warning threshold fluctuation parameter is obtained through comprehensive analysis. The specific analysis process is as follows: The sensor communication data includes the signal strength, working voltage, and connection interruption times of each sensor node.

[0078] It should be understood that in this embodiment, the sensor node is a small device with sensing and communication capabilities and is also the basic unit of the wireless sensor network. The signal strength refers to the wireless signal strength received by the sensor node, the working voltage refers to the actual working voltage of the sensor node, and the connection interruption times refer to the number of interruptions in the connection between the sensor node and the IPC hardware platform. Among them, the signal strength can be collected by a spectrum analyzer, the working voltage can be monitored by a voltage sensor, and the connection interruption times can be recorded and obtained by using a network management tool.

[0079] Obtain the critical signal strength, reference sensor working voltage, allowable deviation voltage, critical interruption times, critical wind speed, and service life of the unit from the wind turbine unit database.

[0080] It should be understood that in this embodiment, the critical signal strength refers to the minimum allowable signal strength, and the critical interruption times refer to the maximum allowable interruption times.

[0081] Based on the sensor communication data and the unit working interference parameters, the early warning threshold fluctuation parameter is comprehensively analyzed and obtained.

[0082] In a specific embodiment, the acquisition method of the early warning threshold fluctuation parameter is as follows:

[0083]

[0084] In the formula, represents the early warning threshold fluctuation parameter, e represents the natural constant, DU r represents the working voltage of the rth sensor node, DU0 represents the reference sensor working voltage, ΔDU represents the allowable deviation voltage, DX r represents the signal strength of the rth sensor node, DX0 represents the critical signal strength, DZ r represents the connection interruption times of the rth sensor node, DZ0 represents the critical interruption times, VF1 represents the wind speed of the wind turbine working environment, VF0 represents the critical wind speed, TM1 represents the cumulative working duration of the unit, TM0 represents the service life of the unit, σ1 represents the early warning threshold fluctuation influence factor corresponding to the preset working voltage, σ2 represents the early warning threshold fluctuation influence factor corresponding to the preset signal strength, σ3 represents the early warning threshold fluctuation influence factor corresponding to the preset connection interruption times, σ4 represents the early warning threshold fluctuation influence factor corresponding to the preset wind speed, σ5 represents the early warning threshold fluctuation influence factor corresponding to the preset cumulative working duration of the unit, r represents the number of each sensor node, r = 1, 2, 3,..., h, and h represents the total number of sensor nodes.

[0085] In this embodiment, the early warning threshold fluctuation influence factors corresponding to the working voltage, signal strength, connection interruption times, wind speed, and cumulative working duration of the unit are preset in the wind turbine database. These influence factors are specific values obtained by quantifying the influence degrees of the hub abnormality evaluation value, gearbox abnormality evaluation value, wind speed, and cumulative working duration of the unit on the early warning threshold fluctuation parameter. In the actual application process, they can be directly retrieved from the wind turbine database.

[0086] For example, a mapping set can be constructed in the wind turbine database to correlate the rated power of the wind turbine with the warning threshold fluctuation impact factors corresponding to the preset working voltage, signal strength, connection interruption times, wind speed, and cumulative working hours of the unit. During operation, when the rated power of the wind turbine is input into the mapping set, the warning threshold fluctuation impact factors corresponding to the working voltage, signal strength, connection interruption times, wind speed, and cumulative working hours of the unit that match the rated power of the wind turbine can be output. In this embodiment, there is a one-to-one mapping relationship between the rated power of the wind turbine and the warning threshold fluctuation impact factors, and the values of all warning threshold fluctuation impact factors are limited within the range of 0 to 1.

[0087] It should be understood that the warning threshold fluctuation parameter is used to quantitatively evaluate the influence degree of external factors on the acquisition of wind turbine status data. In this embodiment, the smaller the signal strength of the sensor node, or the more the working voltage of the sensor node deviates from the reference voltage, or the larger the wind speed, cumulative working hours of the unit, and connection interruption times of the sensor node, the larger the corresponding warning threshold fluctuation parameter, indicating that the acquisition of wind turbine status data is more affected by external factors.

[0088] In this embodiment, the working voltage, signal strength, connection interruption times, wind speed, and cumulative working hours of the unit are interrelated. The working voltage of the sensor node provides energy guarantee for the normal operation of the sensor node. When the working voltage deviates from the reference voltage, it may cause the communication module of the sensor node to fail to work normally at the rated power state, resulting in a weakening of the signal strength sent out, and at the same time, the ability to receive signals sent by other devices also decreases, resulting in a decrease in the actually detected signal strength. At the same time, the lower the signal strength, the worse the quality of the communication link of the sensor node, and it is easily affected by external interference, resulting in an increase in the connection interruption times. As the cumulative working hours of the unit increase, the hardware of the sensor node will gradually age, further amplifying the mutual influence between these parameters, and acting together with external factors such as wind speed to affect the data acquisition process.

[0089] By comprehensively considering the working voltage, signal strength, connection interruption times, wind speed, and cumulative working hours of the sensor node, the influence degree of external factors on the acquisition of wind turbine status data can be accurately quantified, making the evaluation result more scientific and accurate, providing a basis for optimizing data acquisition and warning strategies, avoiding false warnings or missed warnings caused by inaccurate data acquisition, and ensuring the effectiveness of wind turbine status monitoring and warning work.

[0090] The abnormal index threshold of the wind turbine is obtained by processing the warning threshold fluctuation parameter. The specific process is as follows: Match the warning threshold fluctuation parameter with the threshold correction parameter corresponding to each preset warning threshold fluctuation parameter interval in the wind turbine database to obtain the threshold correction parameter of the abnormal index of the wind turbine state. Then extract the initial abnormal index threshold of the wind turbine from the wind turbine database, and subtract the threshold correction parameter of the abnormal index of the wind turbine state from the initial abnormal index threshold of the wind turbine to obtain the abnormal index threshold of the wind turbine state.

[0091] It should be understood that in this embodiment, a mapping set of the warning threshold fluctuation parameter interval and the threshold correction parameter of the abnormal index of the wind turbine state is stored in the wind turbine database, and there is a one-to-one correspondence between the warning threshold fluctuation parameter interval and the threshold correction parameter of the abnormal index of the wind turbine state.

[0092] Specifically, to evaluate the operating state of the wind turbine, the specific process is as follows: Compare the abnormal index of the wind turbine state with the abnormal index threshold of the wind turbine state. If the abnormal index of the wind turbine state is greater than or equal to the abnormal index threshold of the wind turbine state, the state of the wind turbine is evaluated as an abnormal state; if the abnormal index of the wind turbine state is less than the abnormal index threshold of the wind turbine state, the state of the wind turbine is evaluated as a normal state.

[0093] Specifically, warning feedback is performed according to the evaluation result. The specific process is as follows: For the wind turbine in the normal state, no additional operation is performed; for the wind turbine in the abnormal state, the IPC hardware platform performs self-regulation of the wind turbine according to the current wind speed, and evaluates the operating state of the wind turbine after self-regulation.

[0094] In a specific embodiment, the self-regulation of the wind turbine according to the current wind speed is as follows: Match the blade pitch angle adjustment value of the wind turbine from the wind turbine database according to the current wind speed, and adjust the blade pitch angle of the current wind turbine according to the blade pitch angle adjustment value.

[0095] It should be understood that in this embodiment, a mapping set between each wind speed interval and the blade pitch angle adjustment value is stored in the wind turbine database, and there is a one-to-one correspondence between the wind speed interval and the blade pitch angle adjustment value.

[0096] If the operating state of the wind turbine remains abnormal after self-regulation, a warning operation is performed.

[0097] In a specific embodiment, the IPC hardware platform issues an alarm through the locally connected sound and light alarm device, records the abnormal wind turbine number and the wind turbine warning time, and generates a wind turbine abnormal report. The IPC hardware platform pushes the wind turbine abnormal report to the intelligent terminal of the operation and maintenance personnel through the wireless transmission module to complete the warning operation.

[0098] If the operating state of the wind turbine changes from an abnormal state to a normal state, the operating state of the wind turbine is monitored within a preset monitoring period, and the feedback of the self-regulation effect is carried out.

[0099] Specifically, the process of carrying out the feedback of the self-regulation effect is as follows: if the operating state of the wind turbine remains normal within the preset monitoring period, no additional operation is performed; if the operating state of the wind turbine changes from a normal state to an abnormal state within the preset monitoring period, a warning operation is performed.

[0100] It should be understood that in this embodiment, the self-regulation of the wind turbine is carried out by dynamically matching the blade pitch angle adjustment value according to the wind speed for the abnormal state unit, making full use of the relationship between the wind speed and the blade pitch angle adjustment stored in the wind turbine database to achieve precise control, reducing the unstable operating conditions caused by wind speed fluctuations, and extending the service life of the equipment. At the same time, a preset monitoring period is set to continuously track the state of the wind turbine after adjustment, forming a complete closed-loop management. If the unit returns to normal after self-regulation and operates stably during the monitoring period, it proves that the adjustment is effective and no additional operation is required, avoiding excessive intervention; if an abnormality occurs again, a timely warning prompts the operation and maintenance to intervene. This method verifies the effectiveness of the self-regulation measures, consolidates the stability of the normal operation of the unit, helps to continuously monitor the health status of the unit, ensures the long-term reliable operation of the wind turbine, and reduces the probability of fault recurrence and the complexity of operation and maintenance.

[0101] The second aspect of the present invention provides a wind turbine warning device based on an IPC hardware platform, including: a sensor network for collecting wind turbine state data and unit working interference parameters, and transmitting the wind turbine state data and unit working interference parameters back to the IPC hardware platform.

[0102] The IPC hardware platform is used for processing the wind turbine state data and unit working interference parameters, obtaining sensor communication data, and comprehensively evaluating the operating state of the wind turbine.

[0103] The controller is used for obtaining the evaluation result of the operating state of the wind turbine by the IPC hardware platform and performing warning feedback.

[0104] The wind turbine database is used for storing data related to the operating state of the wind turbine, including indicators such as the reference working temperature, allowable deviation working temperature, critical vibration acceleration amplitude, and critical oil particle size. The data in the wind turbine database can be obtained through sensor monitoring and equipment self-checking, or from the database provided by the wind turbine manufacturer.

[0105] In a specific embodiment, the present invention provides a warning method and device for a wind turbine based on an IPC hardware platform, integrating the unit status, working interference, and communication data, accurately quantifying the operating status and warning thresholds, achieving an accurate assessment of the operating status of the wind turbine, and reducing the risk of misjudgment. At the same time, automatic adjustment is performed on abnormal wind turbines, and the adjustment effect is continuously monitored to form a closed-loop control, ensuring the long-term stable operation of the unit, laying a solid foundation for the operation and maintenance management of the wind farm, and overall improving the operation efficiency.

[0106] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. As long as it does not deviate from the structure of the present invention or exceed the scope defined by the present invention, it should fall within the protection scope of the present invention.

Claims

1. A wind turbine warning method based on an IPC hardware platform, characterized in that: Including: Collecting the state data of the wind turbine and the unit working interference parameters based on the sensor network, transmitting the state data of the wind turbine and the unit working interference parameters back to the IPC hardware platform, and processing the state data of the wind turbine and the unit working interference parameters to obtain the wind turbine state anomaly index; Obtaining the sensor communication data, comprehensively analyzing according to the sensor communication data and the unit working interference parameters to obtain the warning threshold fluctuation parameter, and processing according to the warning threshold fluctuation parameter to obtain the wind turbine state anomaly index threshold; Comparing the wind turbine state anomaly index with the wind turbine state anomaly index threshold, evaluating the operation state of the wind turbine, and giving a warning feedback according to the evaluation result.

2. The wind turbine early warning method based on the IPC hardware platform according to claim 1, characterized in that: The state data of the wind turbine includes: hub working data and gearbox working data; The hub working data includes the hub rotation speed, hub tilt angle, and hub swing displacement at each monitoring time point; The gearbox working data includes the temperature, vibration acceleration amplitude, and oil particle size at each state monitoring point at each monitoring time point.

3. The wind turbine warning method based on the IPC hardware platform according to claim 2, characterized in that: The processing of the state data of the wind turbine and the unit working interference parameters to obtain the wind turbine state anomaly index, the specific analysis process is: The unit working interference parameters include the wind speed and the cumulative working duration of the unit at each monitoring time point; Processing the hub working data to obtain the hub anomaly evaluation value; Processing the gearbox working data to obtain the gearbox anomaly evaluation value; Comprehensively analyzing according to the unit working interference parameters, hub anomaly evaluation value, and gearbox anomaly evaluation value to obtain the wind turbine state anomaly index.

4. The wind turbine warning method based on the IPC hardware platform according to claim 2, characterized in that: The process of processing the gearbox working data to obtain the gearbox anomaly evaluation value is specifically: Obtaining the reference working temperature, allowable deviation working temperature, critical vibration acceleration amplitude, and critical oil particle size from the wind turbine database; Comprehensively analyzing according to the gearbox working data to obtain the gearbox anomaly evaluation value.

5. The wind turbine warning method based on the IPC hardware platform according to claim 1, wherein: The comprehensive analysis to obtain the warning threshold fluctuation parameter, the specific analysis process is: The sensor communication data includes the signal strength, working voltage, and connection interruption times of each sensor node; Obtaining the critical signal strength, reference sensor working voltage, allowable deviation voltage, critical interruption times, critical wind speed, and unit service life from the wind turbine database; Comprehensively analyzing according to the sensor communication data and the unit working interference parameters to obtain the warning threshold fluctuation parameter.

6. The wind turbine warning method based on the IPC hardware platform according to claim 1, characterized in that: The process of evaluating the operation state of the wind turbine is specifically: Comparing the wind turbine state anomaly index with the wind turbine state anomaly index threshold. If the wind turbine state anomaly index is greater than or equal to the wind turbine state anomaly index threshold, the wind turbine state is evaluated as an abnormal state. If the wind turbine state anomaly index is less than the wind turbine state anomaly index threshold, the wind turbine state is evaluated as a normal state.

7. The wind turbine warning method based on the IPC hardware platform according to claim 6, characterized in that: The process of giving a warning feedback according to the evaluation result is specifically: For the wind turbine in the normal state, no additional operation is performed; For the wind turbine in the abnormal state, the IPC hardware platform performs self-regulation of the wind turbine according to the current wind speed, and evaluates the operation state of the wind turbine after self-regulation; If the operation state of the wind turbine remains abnormal after self-regulation, a warning is given. If the operating state of the wind turbine changes from an abnormal state to a normal state, the operating state of the wind turbine is monitored within a preset monitoring period, and the feedback of the self-regulation effect is carried out.

8. The wind turbine early warning method based on the IPC hardware platform according to claim 7, wherein: The specific process of the feedback of the self-regulation effect is as follows: If the operating state of the wind turbine remains normal within the preset monitoring period, no additional operations are performed; If the operating state of the wind turbine changes from a normal state to an abnormal state within the preset monitoring period, a warning operation is performed.

9. The wind turbine warning method based on the IPC hardware platform according to claim 1, characterized in that: The method for obtaining the abnormal index of the wind turbine state is as follows: In the formula, β represents the abnormal index of the wind turbine state, Lδ represents the abnormal evaluation value of the hub, Cδ represents the abnormal evaluation value of the gearbox, VF1 represents the wind speed of the working environment of the wind turbine, VF0 represents the critical wind speed, TM1 represents the cumulative working hours of the unit, TM0 represents the service life of the unit, τ1 represents the influence factor of the wind turbine state corresponding to the preset abnormal evaluation value of the hub, τ2 represents the influence factor of the wind turbine state corresponding to the preset abnormal evaluation value of the gearbox, τ3 represents the influence factor of the wind turbine state corresponding to the preset wind speed, and τ4 represents the influence factor of the wind turbine state corresponding to the preset cumulative working hours of the unit.

10. An apparatus applying the wind turbine warning method based on an IPC hardware platform according to any one of claims 1-9, characterized in that: It includes: A sensor network for collecting wind turbine state data and unit working interference parameters and transmitting the wind turbine state data and unit working interference parameters back to the IPC hardware platform; The IPC hardware platform for processing the wind turbine state data and unit working interference parameters, obtaining sensor communication data, and comprehensively evaluating the operating state of the wind turbine; A controller for obtaining the evaluation result of the operating state of the wind turbine by the IPC hardware platform and performing warning feedback.

Images