Fault diagnosis method and device for wind driven generator and wind turbine generator set

Abstract

The invention discloses a fault diagnosis method and device for a wind driven generator and a wind turbine generator set, and relates to the technical field of wind power generation. According to the embodiment of the invention, by calculating the current peak-scale ratio of the phase current of the generator and the acceleration peak-scale ratio of the vibration acceleration of the cabin, microsecond abnormal changes of the phase current of the generator and the vibration acceleration of the cabin can be found, so that grounding or electrical faults of the generator can be accurately identified. Moreover, the phase current of the generator and the vibration acceleration of the cabin can be obtained through a data device installed on the wind turbine generator, and other devices do not need to be additionally installed, so that the cost is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of wind power generation, and in particular, to a fault diagnosis method, device and wind turbine unit for a wind turbine generator. Background Art

[0002] With the continuous development of wind power generation technology, wind turbine generators are widely used in wind farms. However, in actual operation, due to various reasons, wind turbine generators may have grounding or electrical faults, etc., causing insulation failure, posing certain potential safety hazards and power losses.

[0003] For the currently adopted fault diagnosis schemes for wind turbine generators, some require additional devices, resulting in high costs, and some do not require additional devices, but cannot detect grounding or electrical faults of the generator. Summary of the Invention

[0004] Embodiments of the present application provide a fault diagnosis method, device and wind turbine unit for a wind turbine generator, which can accurately identify grounding or electrical faults of the generator without adding other devices.

[0005] In a first aspect, embodiments of the present application provide a fault diagnosis method for a wind turbine generator, including:

[0006] Obtaining the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine unit within N periods, where N is an integer greater than 1;

[0007] For each period, determining a target current peak ratio of the generator in the period according to the kurtosis and standard deviation of the phase current in the period, and determining a target acceleration peak ratio of the nacelle in the period according to the kurtosis and standard deviation of the vibration acceleration in the period;

[0008] In response to the wind turbine unit satisfying the start condition but not starting, performing fault diagnosis on the generator according to the target current peak ratio and target acceleration peak ratio in each period to obtain a fault diagnosis result.

[0009] In a second aspect, embodiments of the present application provide a fault diagnosis device for a wind turbine generator, including:

[0010] An obtaining module, configured to obtain the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine unit within N periods, where N is an integer greater than 1;

[0011] A determining module, configured to, for each period, determine a target current peak ratio of the generator in the period according to the kurtosis and standard deviation of the phase current in the period, and determine a target acceleration peak ratio of the nacelle in the period according to the kurtosis and standard deviation of the vibration acceleration in the period;

[0012] A diagnosis module, configured to, in response to the wind turbine generator set meeting the start-up conditions but not starting, perform fault diagnosis on the generator according to the target current peak ratio and the target acceleration peak ratio in each period, so as to obtain a fault diagnosis result.

[0013] In a third aspect, an embodiment of the present application provides a wind turbine generator set, including the fault diagnosis device of the wind turbine generator as described in the second aspect.

[0014] In a fourth aspect, an embodiment of the present application provides an electronic device, including:

[0015] A processor;

[0016] A memory, configured to store computer program instructions;

[0017] When the computer program instructions are executed by the processor, the method described in the first aspect is implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0019] In the embodiment of the present application, the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine generator set are obtained in N periods, where N is an integer greater than 1; for each period, according to the kurtosis and standard deviation of the phase current in the period, the target current peak ratio of the generator in the period is determined, and according to the kurtosis and standard deviation of the vibration acceleration in the period, the target acceleration peak ratio of the nacelle in the period is determined; in response to the wind turbine generator set meeting the start-up conditions but not starting, fault diagnosis is performed on the generator according to the target current peak ratio and the target acceleration peak ratio in each period, so as to obtain a fault diagnosis result. That is, in the embodiment of the present application, by calculating the current peak ratio of the generator phase current and the acceleration peak ratio of the nacelle vibration acceleration, microsecond abnormal changes in the generator phase current and the nacelle vibration acceleration can be found, so that faults such as grounding or electrical faults of the generator can be accurately identified. Moreover, the generator phase current and the nacelle vibration acceleration can generally be obtained through the data devices installed in the wind turbine generator set itself, without the need to install other additional devices, thus reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Next, the features, advantages, and technical effects of the exemplary embodiments of the present application will be described with reference to the drawings.

[0021] Figure 1 It is a flowchart of a fault diagnosis method for a wind turbine generator provided by an embodiment of the present application;

[0022] Figure 2Schematic diagram of the current peak-to-crest ratio of the generator phase current during normal operation of a wind turbine provided by an embodiment of the present application;

[0023] Figure 3 Schematic diagram of the acceleration peak-to-crest ratio of the nacelle vibration acceleration during normal operation of a wind turbine provided by an embodiment of the present application;

[0024] Figure 4 Schematic diagram of a target fitting curve obtained by linearly fitting the target acceleration peak-to-crest ratio calculated based on the maximum acceleration values at each time point provided by an embodiment of the present application;

[0025] Figure 5 Schematic diagram of a target fitting curve obtained by linearly fitting the maximum value of the acceleration peak-to-crest ratios in two directions at each time point provided by an embodiment of the present application;

[0026] Figure 6 Schematic diagram of a target curve obtained by linearly fitting the acceleration peak-to-crest ratios based on the first direction and the second direction respectively provided by an embodiment of the present application;

[0027] Figure 7 Structural diagram of a fault diagnosis device for a wind turbine provided by an embodiment of the present application;

[0028] Figure 8 Structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0029] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In the following detailed description, many specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application. In the drawings and the following description, at least some of the well-known structures and technologies are not shown in order to avoid unnecessarily obscuring the present application; and, for clarity, the dimensions of some structures may be exaggerated. In addition, the features, structures, or characteristics described below may be combined in any suitable manner in one or more embodiments.

[0030] The orientation terms used in the following description are all the directions shown in the figures, and do not limit the specific structure of the guyed tower and wind turbine generator set of the present application. In the description of the present application, it should also be noted that unless otherwise clearly specified and limited, the terms "installation" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0031] In a wind turbine generator set, due to various reasons, the wind turbine generator may have grounding or electrical faults, etc., resulting in insulation failure, posing certain potential safety hazards and power losses. Therefore, it is of great significance to diagnose the faults of the wind turbine generator.

[0032] For the currently adopted fault diagnosis schemes of wind turbine generators, some need to additionally add other devices. For example, for permanent magnet direct drive units, mainly an online insulation resistance monitoring device needs to be newly added, and corresponding technical transformation work for online insulation monitoring, line transformation, communication transformation, monitoring devices, etc. are required, with relatively high costs.

[0033] Some, although they do not need to additionally add other devices, by checking the conventional generator operating temperature, motor current, etc., often the changes in data cannot be seen in terms of time series, thus the grounding or electrical faults of the generator cannot be detected.

[0034] Therefore, the embodiments of the present application provide a fault diagnosis method, device and wind turbine generator set for a wind turbine generator, which can accurately identify the grounding or electrical faults of the generator without adding other devices.

[0035] The following will specifically describe in detail the fault diagnosis method, device and wind turbine generator set provided by the embodiments of the present application in combination with specific embodiments.

[0036] Figure 1 It is a flowchart of a fault diagnosis method for a wind turbine generator provided by an embodiment of the present application. The embodiment of the present application takes the GW1500 permanent magnet direct drive full converter wind turbine generator set as an example to illustrate the fault diagnosis method of the generator. Of course, it can also be applied to other models of wind turbine generator sets, and only corresponding parameters need to be adjusted adaptively.

[0037] As Figure 1 shown, the fault diagnosis method of the wind turbine generator may include the following steps:

[0038] S110. Obtain the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine generator set within N cycles.

[0039] S120. For each period, determine the target current peak ratio of the generator within the period according to the current kurtosis and current standard deviation of the phase current within the period, and determine the target acceleration peak ratio of the nacelle within the period according to the acceleration kurtosis and acceleration standard deviation of the vibration acceleration within the period.

[0040] S130. In response to the wind turbine generator set satisfying the start-up condition but not starting, perform a fault diagnosis on the generator according to the target current peak ratio and target acceleration peak ratio within each period, and obtain a fault diagnosis result.

[0041] In the embodiment of the present application, by calculating the current peak ratio of the generator phase current and the acceleration peak ratio of the nacelle vibration acceleration, it is possible to discover the microsecond abnormal changes in the generator phase current and the nacelle vibration acceleration, so that the grounding or electrical faults of the generator can be accurately identified. Moreover, the generator phase current and the nacelle vibration acceleration can generally be obtained through the data devices installed on the wind turbine generator set itself without the need to install other additional devices, thus reducing the cost.

[0042] The above steps are described in detail below, as shown specifically as follows:

[0043] In S110, the phase current of the generator may include the phase current on the grid side or the machine side of the generator. Exemplarily, it may include one or more phase currents in the three-phase current. The phase current of the generator can be obtained through a current detection device.

[0044] The vibration acceleration of the nacelle may include the vibration acceleration of the nacelle in the X direction and / or the Y direction. The vibration acceleration of the nacelle can be measured by an acceleration sensor. For example, the vibration acceleration of the nacelle in the X direction can be measured by an acceleration sensor in the X direction, and the vibration acceleration of the nacelle in the Y direction can be measured by an acceleration sensor in the Y direction.

[0045] Both the current detection device and the acceleration sensor are existing devices of the wind turbine generator set, that is, the existing devices of the wind turbine generator set can be used to collect the phase current of the generator and the vibration acceleration of the nacelle without the need to add other additional devices, so the cost can be reduced.

[0046] Exemplarily, the phase current of the generator and the vibration acceleration of the nacelle within multiple periods can be obtained. The size of the period can be set according to actual needs. For example, one hour can be used as one period. Each period may include multiple sampling time points, and each sampling time point corresponds to a phase current and a vibration acceleration.

[0047] Exemplarily, a sampling time point can be set every p seconds, and the size of p can be set according to actual needs.

[0048] In S120, kurtosis is one of the statistics that describe the steepness of the data distribution pattern, and is usually used to measure the sharpness or flatness of the data distribution curve relative to the normal distribution. For example, a kurtosis greater than zero indicates that the data distribution is sharper than the normal distribution; a kurtosis less than zero indicates that the data distribution is flatter than the normal distribution; a kurtosis equal to zero indicates that the data distribution is similar to the normal distribution.

[0049] Exemplarily, the current kurtosis of the phase current within each period can be determined according to the number of phase currents and the magnitudes of the phase currents within that period.

[0050] Exemplarily, where Kurtosisc is the current kurtosis of a certain phase's phase current, n is the number of that phase's phase currents within each period, n is an integer greater than 3, x i is the i-th phase current within each period, is the mean of the phase currents within each period, and S tdevc is the current standard deviation of the phase currents within each period.

[0051] Exemplarily,

[0052] Exemplarily, when the phase current includes multiple phases, the calculation process for the current kurtosis of each phase's phase current is similar.

[0053] The calculation process for the acceleration kurtosis of the vibration acceleration is similar to the calculation process for the current kurtosis of the phase current. Exemplarily, where Kurtosisa is the acceleration kurtosis of the vibration acceleration, n is the number of that phase's phase currents within each period, n is an integer greater than 3, y i is the i-th vibration acceleration within each period, is the mean of the vibration accelerations within each period, and S tdeva is the acceleration standard deviation of the vibration accelerations within each period.

[0054] Exemplarily,

[0055] The target current peak ratio is the ratio of the current kurtosis to the current standard deviation, and the target acceleration peak ratio is the ratio of the acceleration kurtosis to the acceleration standard deviation.

[0056] Exemplarily, psr_current = Kurtosisc / S tdevc , psr_acc = Kurtosisa / S tdeva , where psr_current is the target current peak ratio and psr_acc is the target acceleration peak ratio.

[0057] It can be understood that when faults such as generator winding grounding, short - circuit, or abnormal insulation occur in the unit, it is often accompanied by asymmetry of the three - phase magnetic field. The resulting electromotive force will trigger short - circuit electromotive force and conduct to mechanical components. The vibration acceleration sensor will thus receive a huge instantaneous impact force. This kind of vibration has a short duration, and the abnormal signal is easily directly covered in the second - level data, or this precise data cannot be collected. Through the peak - to - marker ratio, the microsecond - level abnormal changes in the phase current and vibration of the wind turbine can be found, so that the faults of the generator can be accurately identified and potential safety hazards can be reduced.

[0058] In S130, the wind turbine meeting the start - up conditions can be, for example, that the wind turbine has not triggered a fault, or the fault has been eliminated through reset or other means after the fault is triggered.

[0059] Exemplarily, during the operation of the wind turbine, the operation data of the wind turbine can be marked by means of cursor positioning.

[0060] For example, for the operation data of the converter, when a converter fault is triggered, the start index and end index of the fault occurrence can be marked, so that the time point when the wind turbine has an abnormality can be determined. Table 1 exemplarily lists some faults of the converter, and the start index and end index of the occurrence of each fault are marked.

[0061] Table 1 Some faults of the wind turbine

[0062]

[0063]

[0064] Among them, fault_code is the fault code. "0" indicates no fault; "95" indicates that the pitch safety chain relay is not energized; "455" indicates that the converter is not ready, for example, when the converter has not started and the main control issues a signal allowing the converter to start, and after 20 s, the converter does not feedback a signal of being ready to start; "458" indicates that the converter is in emergency stop.

[0065] Through cursor positioning and Table 1, it can be monitored whether the wind turbine is in normal operation. If the wind turbine triggers a fault, the fault_code is generally in a non - zero state, and then the important state time interval of the unit and the time point when the unit has an abnormality can be determined.

[0066] It should be noted that the faults related to the converter listed in Table 1 are not the causes of the unit faults, but just the manifestations of the faults. At this time, it is necessary to further judge whether there is an abnormality in the generator.

[0067] When the wind turbine meets the start-up conditions but still has not started, fault diagnosis can be performed on the generator based on the target current peak ratio and the target acceleration peak ratio calculated in each period to determine whether there is a fault in the generator.

[0068] Exemplarily, the maximum current peak ratio can be determined according to the target current peak ratio in each period, and the maximum acceleration peak ratio can be determined according to the target acceleration peak ratio in each period;

[0069] In response to the wind turbine meeting the start-up conditions but not starting, the maximum current peak ratio being greater than the first threshold, and the maximum acceleration peak ratio being greater than the second threshold, it is determined that there is a fault in the generator.

[0070] The maximum current peak ratio psr_curmax is the maximum target current peak ratio in each period. Similarly, the maximum acceleration peak ratio psr_accmax is the maximum target acceleration peak ratio in each period.

[0071] The current peak ratio and the acceleration peak ratio of a normal unit can be referred to Figures 2 - 3 , that is, the current peak ratio of a normal unit in each period is less than the first threshold, and the acceleration peak ratio is less than the second threshold.

[0072] In some embodiments, when the wind turbine meets the start-up conditions but has not started, if psr_curmax is greater than the first threshold and psr_accmax is greater than the second threshold, it can be determined that there is a fault.

[0073] Among them, the magnitudes of the first threshold and the second threshold can be set according to actual needs. For example, the first threshold can be set to 1, and the second threshold can be set to 15.

[0074] Exemplarily, when the maximum current peak ratio is greater than the first threshold and the maximum acceleration peak ratio is greater than the second threshold, the maximum current peak ratio and the maximum acceleration peak ratio can also be recorded, as well as the positions and time tags of the phase current and the vibration acceleration corresponding to the maximum current peak ratio and the maximum acceleration peak ratio, so as to facilitate subsequent maintenance personnel to search.

[0075] Through the maximum current peak ratio and the maximum acceleration peak ratio in each period in the embodiments of the present application, microsecond abnormal changes in the phase current of the generator and the vibration acceleration of the nacelle can be discovered, so that faults such as grounding or electrical faults of the generator can be accurately identified.

[0076] When it is determined that there is a fault in the generator, the environmental parameters and the blade angle of the wind turbine can also be combined to further determine whether there is a grounding fault or an insulation failure fault in the generator. Based on this, in some embodiments, the fault diagnosis method of the wind turbine may further include the following steps:

[0077] Obtain the environmental parameters and blade angles of the wind turbine generator set;

[0078] In response to the wind turbine generator set satisfying the start-up condition but not starting, the maximum current peak ratio being greater than a first threshold, and the maximum acceleration peak ratio being greater than a second threshold, determine that there is a fault in the generator, including:

[0079] In response to the wind turbine generator set satisfying the start-up condition but not starting, the environmental parameters and blade angles satisfying the power generation conditions of the generator but the generator not entering the power generation state, the maximum current peak ratio being greater than a first threshold, and the maximum acceleration peak ratio being greater than a second threshold, determine that there is a ground fault or insulation failure in the generator.

[0080] Exemplarily, the environmental parameters of the wind turbine generator set may be parameters that affect the power generation state of the generator, such as, but not limited to, wind speed, ambient temperature, etc.

[0081] Exemplarily, when the wind turbine generator set satisfies the start-up condition but not starting, the environmental parameters and blade angles satisfy the power generation conditions of the generator but the generator does not enter the power generation state, and the maximum current peak ratio is greater than a first threshold and the maximum acceleration peak ratio is greater than a second threshold, it can be determined that there is a ground fault or insulation failure in the generator.

[0082] By collecting the environmental parameters, blade angles, phase currents of the generator, and vibration acceleration of the nacelle of the wind turbine generator set in real time in the embodiments of the present application, the state of the generator can be monitored in real time, so that the ground fault or insulation failure fault of the generator can be discovered in time, improving the reliability and safety of the wind turbine generator set.

[0083] In some embodiments, when there are more cycles, it is also possible to determine whether there is an increasing trend in the target acceleration peak ratio of the nacelle. Therefore, on the basis of the above embodiments, it is also possible to further combine the trend parameter of the target acceleration peak ratio to determine whether there is a fault in the generator.

[0084] Exemplarily, the above S130 may include the following steps:

[0085] Determine the maximum current peak ratio according to the target current peak ratios in each cycle, and determine the maximum acceleration peak ratio according to the target acceleration peak ratios in each cycle;

[0086] Determine the trend parameter of the target acceleration peak ratio according to the target acceleration peak ratios in each cycle;

[0087] In response to the wind turbine generator set satisfying the start-up condition but not starting, the maximum current peak ratio being greater than a first threshold, the maximum acceleration peak ratio being greater than a second threshold, and the trend parameter being greater than a third threshold, determine that there is a fault in the generator.

[0088] The trend parameter is used to characterize the change trend of the target acceleration peak ratio in each period. Exemplarily, a linear fit can be performed on the target acceleration peak ratio in each period to obtain the slope of the linear curve, and the slope of this linear curve is the trend parameter of the target acceleration peak ratio in each period.

[0089] Of course, other methods can also be used to determine the change trend of the target acceleration peak ratio in each period, and the embodiments of the present application do not limit this.

[0090] Exemplarily, when the wind turbine meets the start-up conditions but has not started, psr_curmax is greater than the first threshold, psr_accmax is greater than the second threshold, and psr_slope is greater than the third threshold, it can be determined that there is a fault in the generator. Wherein, psr_slope is the trend parameter.

[0091] For example, when the wind turbine meets the start-up conditions but has not started, psr_curmax > 1, psr_accmax > 15, and psr_slope > 0.15, it can be determined that there is a fault in the generator.

[0092] Based on the maximum acceleration peak ratio in each period and combined with the trend parameter of the maximum acceleration peak ratio in each period, the embodiments of the present application can more accurately detect the microsecond abnormal changes in the vibration acceleration of the nacelle, so as to accurately identify faults such as grounding or electrical problems of the generator.

[0093] In some embodiments, the maximum acceleration peak ratio in each period, that is, the trend parameter of the target acceleration peak ratio, can be determined in the following manner:

[0094] Perform a linear fit on the m-th power of the target acceleration peak ratio and the corresponding period in chronological order to obtain the target fitting curve, where m is an integer greater than 1;

[0095] Determine the slope of the target fitting curve as the trend parameter of the target acceleration peak ratio.

[0096] To accurately identify the abnormal vibration of the nacelle, the target acceleration peak ratio can be enhanced to enhance the abnormal vibration acceleration.

[0097] Exemplarily, a linear fit can be performed on the m-th power of the target acceleration peak ratio and the corresponding period in chronological order to obtain the target fitting curve. The slope of the target fitting curve is the trend parameter of the target acceleration peak ratio.

[0098] Taking m = 2 as an example, exemplarily, the maximum acceleration values of the vibration accelerations in two directions can be taken at each time point, and then the target acceleration peak-to-peak ratio of the cabin in each period can be calculated based on the maximum acceleration values at each time point. For each period, the square value of the target acceleration peak-to-peak ratio is calculated, and a linear fit is performed on the square values of the target acceleration peak-to-peak ratios in each period, and then the slope of the target fitting curve can be obtained, that is, the trend parameter of the target acceleration peak-to-peak ratio.

[0099] Figure 4 It is a schematic diagram of the target fitting curve obtained by calculating the target acceleration peak-to-peak ratio based on the maximum acceleration values at each time point and performing a linear fit. The trend parameter obtained in this way is 0.2414.

[0100] Exemplarily, the first acceleration peak-to-peak ratio and the second acceleration peak-to-peak ratio can also be calculated respectively based on the kurtosis and standard deviation of acceleration in the first direction and the second direction, and the maximum value is determined from the first acceleration peak-to-peak ratio and the second acceleration peak-to-peak ratio to obtain the target acceleration peak-to-peak ratio, and a linear fit is performed based on the square of the target acceleration peak-to-peak ratio in each period, and then the slope of the target fitting curve can be obtained, that is, the trend parameter of the target acceleration peak-to-peak ratio.

[0101] Figure 5 It is a schematic diagram of the target fitting curve obtained by performing a linear fit on the maximum value of the acceleration peak-to-peak ratios in two directions at each time point. The trend parameter obtained in this way is 0.2953.

[0102] Exemplarily, a linear fit can also be performed on the acceleration peak-to-peak ratios in different directions respectively to obtain the target fitting curve.

[0103] For example, a linear fit can be performed on the square values of the first acceleration peak-to-peak ratios in the first direction in each period to obtain the first target fitting curve, and a linear fit can be performed on the square values of the second acceleration peak-to-peak ratios in the second direction in each period to obtain the second target fitting curve.

[0104] Exemplarily, the trend parameter of the target acceleration peak value can be the maximum value of the slopes of the first target fitting curve and the second target fitting curve.

[0105] Figure 6 It is a schematic diagram of the target curves obtained by performing a linear fit respectively based on the acceleration peak-to-peak ratios in the first direction and the second direction. Among them, PSR_X is a schematic diagram of the first target fitting curve obtained by performing a linear fit based on the acceleration peak-to-peak ratio in the first direction, and PSR_Y is a schematic diagram of the second target fitting curve obtained by performing a linear fit based on the acceleration peak-to-peak ratio in the second direction. The slope of the first target fitting curve is 0.0996, and the slope of the second target fitting curve is 0.2372.

[0106] In actual application, any of the above methods can be used to calculate the trend parameter of the target acceleration peak ratio, that is, the slope of any of the above target fitting curves can be used as the trend parameter.

[0107] In the embodiment of the present application, the square value of the target acceleration peak ratio is linearly fitted according to time sequence, which realizes the amplification of abnormal vibration acceleration and obtains the change trend of the target acceleration peak ratio, so that the faults existing in the generator can be identified more accurately.

[0108] In some embodiments, the fault diagnosis of the wind turbine may further include the following steps:

[0109] In response to determining that the generator has a fault, generate a fault warning message and output it.

[0110] Exemplarily, when it is determined that the generator has a fault, a fault warning message can be generated and output, so that the operation and maintenance personnel can discover the fault problem of the generator early, and can handle the fault of the generator in the first time to ensure the safety of the wind turbine unit.

[0111] Exemplarily, the fault warning message may include but is not limited to the following contents: the number of the wind turbine unit, wind speed, ambient temperature, blade angle, maximum target current peak ratio, maximum acceleration peak ratio, and fault type, etc.

[0112] The output modes of the fault warning message may include at least one of the following: text message, phone call, buzzer, indicator light, email.

[0113] When it is determined that the generator has a fault, generating a fault warning message and outputting it can enable the operation and maintenance personnel to discover the fault problem early and take corresponding solutions in time, ensuring the reliability and safety of the wind turbine unit.

[0114] Taking the phase current including the three-phase currents on the grid side or machine side of the generator as the A-phase current, B-phase current, and C-phase current respectively as an example, exemplarily, the target current peak ratio of the generator in each cycle can be determined in the following manner:

[0115] Perform numerical differential processing on each phase current in the cycle to obtain a difference array corresponding to each phase current;

[0116] For each phase current, according to each differential data in the corresponding difference array, determine the kurtosis and standard deviation of the phase current, and determine the ratio of the kurtosis and standard deviation of the phase current as the first current peak ratio of the phase current;

[0117] Determine the maximum value among the first current peak ratios of each phase current in the cycle as the target current peak ratio of the generator in the cycle.

[0118] Taking the phase A current as an example, exemplarily, for each period, the phase A current within the period can be numerically differentiated to obtain a difference array of the phase A current.

[0119] For example, assuming that the period contains n sampling time points, that is, each sampling time point corresponds to a phase A current. At this time, the difference between the phase currents of two adjacent sampling time points can be calculated to obtain a difference array of the phase A current.

[0120] Exemplarily, A1 = [a2 - a1, a3 - a2, a4 - a3, …, an - a(n - 1)], where a1, a2, …, an are the phase A currents corresponding to n sampling time points respectively.

[0121] Similarly, a difference array B1 = [b2 - b1, b3 - b2, b4 - b3, …, bn - b(n - 1)] corresponding to the phase B current and a difference array C1 = [c2 - c1, c3 - c2, c4 - c3, …, cn - c(n - 1)] corresponding to the phase C current can be obtained, where b1, b2, …, bn are the phase B currents corresponding to n sampling time points respectively, and c1, c2, …, cn are the phase C currents corresponding to n sampling time points respectively.

[0122] Exemplarily, a difference matrix can also be generated based on the difference arrays of each phase current, where each row of the difference matrix corresponds to a phase current.

[0123] Exemplarily, for the convenience of identifying abnormal data points, time tags can be added to each difference array. Taking the phase A current as an example, the time tag of the phase current a2, that is, the sampling time point of the phase current a2, can be added to the first element a2 - a1.

[0124] For each difference array, the kurtosis and standard deviation of each phase current within the period can be calculated according to the calculation formulas of current kurtosis and current standard deviation recorded in the above embodiments, and then the current kurtosis ratio of each phase current within the period, that is, the first current kurtosis ratio, can be obtained.

[0125] Table 2 exemplarily lists the first current kurtosis ratios of each phase current within some periods. In actual applications, more periods can be included. Table 2 takes one hour as a period as an example. In actual applications, a period with a duration less than one hour or greater than one hour can also be used. Among them, A1, B1, and C1 are the first current kurtosis ratios of the phase A, phase B, and phase C currents respectively.

[0126] Table 2 First current kurtosis ratios of each phase current within some periods

[0127] Number Hour A1 B1 C1 1 06-30 00:00:00 0.0010769 0.0012044 0.0014072 2 06-30 01:00:00 0.0049605 0.0048414 0.0061493 3 06-30 02:00:00 0.0101429 0.0117110 0.0213262

[0128] After the first current peak ratio of each phase current in each period is determined, the maximum value can be determined from the first current peak ratios of each phase current, and this maximum value is determined as the target current peak ratio of the generator in this period.

[0129] For example, for the period numbered 1, A1 = 0.0010769 < B1 = 0.0012044 < C1 = 0.0014072. Therefore, it can be determined that the target current peak ratio of the generator in this period is C1 = 0.0014072.

[0130] In the embodiment of the present application, for each phase current, based on the current kurtosis and current standard deviation of this phase current in each period, the current peak ratio of this phase current in each period can be determined. Through this current peak ratio, abnormal changes in the grid-side or machine-side current of the generator can be identified without additionally adding other devices, reducing costs.

[0131] Taking the vibration acceleration of the nacelle including the first vibration acceleration of the nacelle in the first direction and the second vibration acceleration of the nacelle in the second direction, where the first direction and the second direction are perpendicular as an example, exemplarily, the target acceleration peak ratio of the nacelle in each period can be determined in the following manner:

[0132] Take the absolute value of the first vibration acceleration and the second vibration acceleration in the period respectively to obtain the first vibration acceleration array and the second vibration acceleration array;

[0133] According to the absolute values of the first vibration accelerations in the first vibration acceleration array, determine the first acceleration kurtosis and the first acceleration standard deviation of the first vibration acceleration, and according to the absolute values of the second vibration accelerations in the second vibration acceleration array, determine the second acceleration kurtosis and the second acceleration standard deviation of the second vibration acceleration;

[0134] Determine the first acceleration peak ratio of the first vibration acceleration as the first ratio of the first acceleration kurtosis and the first acceleration standard deviation, and determine the second acceleration peak ratio of the second vibration acceleration as the second ratio of the second acceleration kurtosis and the second acceleration standard deviation;

[0135] Determine the maximum value of the first acceleration peak ratio and the second acceleration peak ratio as the target acceleration peak ratio of the nacelle in the period.

[0136] Exemplarily, the first direction can be the X direction, and the second direction can be the Y direction. To avoid the influence of the direction on the diagnosis result, exemplarily, the absolute value processing can be performed on the vibration accelerations of the nacelle in the first direction and the second direction respectively, that is, only consider the numerical value of the vibration acceleration, regardless of positive or negative.

[0137] For example, for the vibration acceleration of the cabin in the first direction, that is, the first vibration acceleration, the absolute value of each first vibration acceleration can be taken, and the first vibration acceleration array X1=[|accx1|,|accx2|,…,|accxn|] can be generated based on each absolute value. Similarly, for the vibration acceleration of the cabin in the second direction, that is, the second vibration acceleration, the second vibration acceleration array Y1=[|accy1|,|accy2|,…,|accyn|] can be obtained, wherein accx1, accx2,…, accxn are respectively the first vibration accelerations of the cabin at each sampling time point in each cycle, accy1, accy2,…, accyn are respectively the second vibration accelerations of the cabin at each sampling time point in each cycle, and || indicates taking the absolute value.

[0138] Taking the first vibration acceleration array as an example, illustratively, the first vibration acceleration kurtosis and the first vibration acceleration standard deviation in the cycle can be calculated based on each element in the first vibration acceleration array according to the calculation formula of the acceleration kurtosis and the acceleration standard deviation recorded in the above embodiment, and then the acceleration peak-to-standard ratio of the first vibration acceleration in the cycle, that is, the first vibration acceleration peak-to-standard ratio, can be obtained. Similarly, the acceleration peak-to-standard ratio of the second vibration acceleration in the cycle, that is, the first vibration acceleration peak-to-standard ratio, can be obtained.

[0139] Table 3 exemplarily lists the first vibration acceleration peak-to-standard ratio and the second vibration acceleration peak-to-standard ratio in some cycles. In actual application, there may be more cycles. Among them, accx_psr is the first vibration acceleration peak-to-standard ratio, and accy_psr is the second vibration acceleration peak-to-standard ratio.

[0140] Table 3 Peak-to-standard ratio of the first vibration acceleration and peak-to-standard ratio of the second vibration acceleration in a partial cycle

[0141] Number Hour accx_psr accy_psr 1 06-30 00:00:00 2.2430536 1.1278229 2 06-30 01:00:00 2.1230805 1.3095118 3 06-30 02:00:00 3.1506719 2.2500815

[0142] Exemplarily, for each cycle, the first acceleration peak-to-standard ratio and the second acceleration peak-to-standard ratio in the cycle may be compared, and the maximum value of the first acceleration peak-to-standard ratio and the second acceleration peak-to-standard ratio may be determined as the target acceleration peak-to-standard ratio of the cabin in the cycle.

[0143] For example, for the cycle numbered 1, accx_psr=2.<2430536>accy_psr=1.1278229 in the cycle, so the target acceleration peak-to-standard ratio of the cabin in the cycle can be determined to be accx_psr=2.2430536.

[0144] In the embodiments of the present application, for the vibration accelerations of the engine nacelle in different directions, the peak-to-peak ratios of the accelerations of the engine nacelle in different periods are calculated respectively, so that abnormal changes in the vibration of the engine nacelle can be identified without additionally adding other devices, thereby reducing the cost.

[0145] In some embodiments, the target peak-to-peak ratio of the acceleration of the engine nacelle in each period can also be determined in the following manner:

[0146] The absolute value processing is respectively performed on the first vibration acceleration and the second vibration acceleration in the period to obtain a third vibration acceleration array, and each element of the third vibration acceleration array is composed of the processed first vibration acceleration and the second vibration acceleration;

[0147] For each element in the third vibration acceleration array, the maximum value of the processed first vibration acceleration and the second vibration acceleration is determined as the maximum vibration acceleration corresponding to the element;

[0148] According to the maximum vibration accelerations corresponding to the elements in the third vibration acceleration array, the third kurtosis of the acceleration and the third standard deviation of the acceleration are determined;

[0149] The third ratio of the third kurtosis of the acceleration and the third standard deviation of the acceleration is determined as the target peak-to-peak ratio of the acceleration of the engine nacelle in the period.

[0150] Exemplarily, the absolute value processing can be performed on the first vibration acceleration and the second vibration acceleration obtained at each sampling time point, and a binary array is formed, that is, each element of the binary array is composed of the processed first vibration acceleration and the second vibration acceleration. Here, the binary array is also the third vibration acceleration array.

[0151] Exemplarily, the third vibration acceleration array XY = [(|accx1|, |accy1|), (|accx2|, |accy2|),..., (|accxn|, |accyn|)].

[0152] For each element in the third vibration acceleration array, the absolute value of the first vibration acceleration and the absolute value of the second vibration acceleration can be compared to obtain the maximum vibration acceleration, that is, each sampling time point can be normalized to a maximum vibration acceleration. For the maximum vibration accelerations at each sampling time point in the period, the third kurtosis of the acceleration and the third standard deviation of the acceleration in the period can be calculated, and then the target peak-to-peak ratio of the acceleration of the engine nacelle in the period can be obtained.

[0153] In the embodiment of the present application, the vibration accelerations in two directions are normalized into one vibration acceleration, and then the third acceleration kurtosis and the third acceleration standard deviation are calculated based on the normalized vibration acceleration, so as to obtain the target acceleration peak-to-standard ratio of the nacelle in each period, which can identify abnormal changes in the nacelle vibration without adding other devices additionally, reducing the cost.

[0154] In the embodiment of the present application, the existing acceleration sensors of the unit are used to collect the vibration accelerations of the nacelle in different directions, and the current acquisition device is used to collect the phase currents on the grid side or the machine side of the generator, without adding other devices additionally, reducing the cost. At the same time, based on the acceleration kurtosis and the acceleration standard deviation, the acceleration peak-to-standard ratio is calculated, and based on the current kurtosis and the current standard deviation of the phase current, the current peak-to-standard ratio is calculated. Through the acceleration peak-to-standard ratio and the current peak-to-standard ratio, the phase current of the generator and the vibration acceleration of the nacelle can be monitored in real time, and the microsecond abnormal changes of the phase current and the vibration acceleration can be detected in time, improving the reliability and safety of the wind turbine.

[0155] Based on the same inventive concept, the embodiment of the present application also provides a fault diagnosis device for a wind turbine, which will be described in detail below through Figure 7 a detailed description of the fault diagnosis device for a wind turbine provided by the embodiment of the present application.

[0156] Figure 7 It is a structural diagram of a fault diagnosis device for a wind turbine provided by the embodiment of the present application.

[0157] As Figure 7 shown, the fault diagnosis device for the wind turbine may include:

[0158] An acquisition module 701, configured to acquire the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine within N periods, where N is an integer greater than 1;

[0159] A determination module 702, configured to, for each period, determine the target current peak-to-standard ratio of the generator in the period according to the current kurtosis and the current standard deviation of the phase current in the period, and determine the target acceleration peak-to-standard ratio of the nacelle in the period according to the acceleration kurtosis and the acceleration standard deviation of the vibration acceleration in the period;

[0160] A diagnosis module 703, configured to, in response to the wind turbine satisfying the start condition but not starting, perform a fault diagnosis on the generator according to the target current peak-to-standard ratio and the target acceleration peak-to-standard ratio in each period, and obtain a fault diagnosis result.

[0161] The embodiments of the present application obtain the phase current of the generator and the vibration acceleration of the nacelle within N periods, where N is an integer greater than 1; for each period, according to the kurtosis and standard deviation of the phase current within the period, determine the target current peak ratio of the generator within the period, and according to the kurtosis and standard deviation of the vibration acceleration within the period, determine the target acceleration peak ratio of the nacelle within the period; in response to the wind turbine generator set satisfying the start condition but not starting, perform fault diagnosis on the generator according to the target current peak ratio and target acceleration peak ratio within each period to obtain a fault diagnosis result. That is, the embodiments of the present application can discover the microsecond abnormal changes in the phase current of the generator and the vibration acceleration of the nacelle by calculating the current peak ratio of the generator phase current and the acceleration peak ratio of the nacelle vibration acceleration, so as to accurately identify faults such as grounding or electrical faults of the generator. Moreover, the phase current of the generator and the vibration acceleration of the nacelle can generally be obtained through the data devices installed in the wind turbine generator set itself without installing other additional devices, thus reducing costs.

[0162] In some embodiments, the phase current includes the three-phase currents on the grid side or the machine side of the generator; the determining module 702 is specifically configured to:

[0163] Perform numerical differential processing on each phase current within the period to obtain a difference array corresponding to each phase current;

[0164] For each phase current, determine the kurtosis and standard deviation of the phase current according to each differential data in the corresponding difference array, and determine the ratio of the kurtosis and standard deviation of the phase current as the first current peak ratio of the phase current;

[0165] Determine the maximum value among the first current peak ratios of each phase current within the period as the target current peak ratio of the generator within the period.

[0166] In some embodiments, the vibration acceleration of the nacelle includes a first vibration acceleration of the nacelle in a first direction and a second vibration acceleration of the nacelle in a second direction, and the first direction and the second direction are perpendicular;

[0167] The determining module 702 is specifically configured to:

[0168] Perform absolute value processing on the first vibration acceleration and the second vibration acceleration within the period respectively to obtain a first vibration acceleration array and a second vibration acceleration array;

[0169] According to the absolute values of the first vibration accelerations in the first vibration acceleration array, determine the first kurtosis and the first standard deviation of the first vibration acceleration, and according to the absolute values of the second vibration accelerations in the second vibration acceleration array, determine the second kurtosis and the second standard deviation of the second vibration acceleration;

[0170] Determine the first acceleration peak-to-standard deviation ratio of the first acceleration kurtosis and the first acceleration standard deviation as the first acceleration peak-to-standard deviation ratio of the first vibration acceleration, and determine the second acceleration peak-to-standard deviation ratio of the second acceleration kurtosis and the second acceleration standard deviation as the second acceleration peak-to-standard deviation ratio of the second vibration acceleration;

[0171] Determine the maximum value of the first acceleration peak-to-standard deviation ratio and the second acceleration peak-to-standard deviation ratio as the target acceleration peak-to-standard deviation ratio of the nacelle within the period.

[0172] In some embodiments, the vibration acceleration of the nacelle includes the first vibration acceleration of the nacelle in the first direction and the second vibration acceleration of the nacelle in the second direction, and the first direction and the second direction are perpendicular;

[0173] The determining module 702 is specifically configured to:

[0174] Perform absolute value processing on the first vibration acceleration and the second vibration acceleration within the period respectively to obtain a third vibration acceleration array, and each element of the third vibration acceleration array is composed of the processed first vibration acceleration and the second vibration acceleration;

[0175] For each element in the third vibration acceleration array, determine the maximum value of the processed first vibration acceleration and the second vibration acceleration as the maximum vibration acceleration corresponding to the element;

[0176] Determine the third acceleration kurtosis and the third acceleration standard deviation according to the maximum vibration acceleration corresponding to each element in the third vibration acceleration array;

[0177] Determine the third ratio of the third acceleration kurtosis and the third acceleration standard deviation as the target acceleration peak-to-standard deviation ratio of the nacelle within the period.

[0178] In some embodiments, the determining module 702 is further configured to determine the maximum current peak-to-standard deviation ratio according to the target current peak-to-standard deviation ratio within each period, and determine the maximum acceleration peak-to-standard deviation ratio according to the target acceleration peak-to-standard deviation ratio within each period;

[0179] The diagnosing module 703 is specifically configured to:

[0180] In response to the wind turbine meeting the start-up conditions but not starting, the maximum current peak-to-standard deviation ratio being greater than the first threshold, and the maximum acceleration peak-to-standard deviation ratio being greater than the second threshold, determine that there is a fault in the generator.

[0181] In some embodiments, the obtaining module 701 is further configured to obtain the environmental parameters and the blade angle of the wind turbine;

[0182] The diagnosing module 703 is specifically configured to:

[0183] Determine that the generator has a ground fault or insulation failure in response to the wind turbine meeting the start-up conditions but not starting, the environmental parameters and blade angles meeting the power generation conditions of the generator but the generator not entering the power generation state, the maximum current crest ratio being greater than a first threshold, and the maximum acceleration crest ratio being greater than a second threshold.

[0184] In some embodiments, the determination module 702 is further configured to determine the maximum current crest ratio according to the target current crest ratio in each period, and determine the maximum acceleration crest ratio according to the target acceleration crest ratio in each period;

[0185] Determine the trend parameter of the target acceleration crest ratio according to the target acceleration crest ratio in each period;

[0186] The diagnosis module 703 is specifically configured to:

[0187] Determine that the generator has a fault in response to the wind turbine meeting the start-up conditions but not starting, the maximum current crest ratio being greater than a first threshold, the maximum acceleration crest ratio being greater than a second threshold, and the trend parameter being greater than a third threshold.

[0188] In some embodiments, the determination module 702 is specifically configured to:

[0189] Perform a linear fit on the m-th power of the target acceleration crest ratio and the corresponding period in chronological order to obtain a target fitting curve, where m is an integer greater than 1;

[0190] Determine the slope of the target fitting curve as the trend parameter of the target acceleration crest ratio.

[0191] In some embodiments, the fault diagnosis device of the wind turbine may further include:

[0192] A generation module, configured to generate and output a fault warning message in response to determining that the generator has a fault.

[0193] The fault diagnosis device of the wind turbine provided by the embodiments of the present application can implement Figure 1 Each process in the fault diagnosis method embodiment of the wind turbine shown, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0194] Based on the same inventive concept, the embodiments of the present application also provide an electronic device, which may be, for example, a tablet computer, a notebook computer, a handheld computer, etc. The following combines Figure 8 To describe the electronic device provided by the embodiments of the present application in detail.

[0195] As Figure 8 Shown, the electronic device may include a processor 801 and a memory 802 for storing computer program instructions.

[0196] The processor 801 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be an integrated circuit configured to implement one or more embodiments of the present application.

[0197] The memory 802 may include a mass storage for data or instructions. By way of example and not limitation, the memory 802 may include a Hard Disk Drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In one example, the memory 802 may include removable or non-removable (or fixed) media, or the memory 802 is a non-volatile solid-state memory. In one example, the memory 802 may be a Read Only Memory (ROM). In one example, the ROM may be a mask-programmed ROM, a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), an Electrically Rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0198] The processor 801 reads and executes computer program instructions stored in the memory 802 to implement Figure 1 the method in the illustrated embodiment and achieve Figure 1 the corresponding technical effects achieved by the illustrated embodiment when executing its method. For the sake of brevity of description, details are not repeated herein.

[0199] In one example, the electronic device may further include a communication interface 803 and a bus 804. Among them, as Figure 8 shown, the processor 801, the memory 802, and the communication interface 803 are connected through the bus 804 to complete communication with each other.

[0200] The communication interface 803 is mainly used to implement communication between various modules, devices, and / or apparatuses in the embodiments of the present application.

[0201] Bus 804 includes hardware, software, or both, and couples the various components of the electronic device to each other. By way of example and not limitation, bus 804 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable bus or a combination of two or more of these. Where appropriate, bus 804 may include one or more buses. Although embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0202] After acquiring the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine within N cycles, the electronic device can execute the fault diagnosis method of the wind turbine in the embodiments of the present application, so as to implement the combination Figure 1 of the described fault diagnosis method of the wind turbine and Figure 7 the described fault diagnosis device of the wind turbine.

[0203] In addition, in combination with the fault diagnosis method of the wind turbine in the above embodiments, the embodiments of the present application can provide a computer storage medium to implement. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the fault diagnosis methods of the wind turbine in the above embodiments is implemented.

[0204] It should be clear that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0205] The functional blocks shown in the above structural block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted via a data signal carried in a carrier wave over a transmission medium or a communication link. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0206] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0207] Aspects of the embodiments of the present application have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each block in the block diagrams and / or flowcharts, and the combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0208] Although the present application has been described with reference to the preferred embodiments, various modifications can be made thereto and components thereof can be replaced with equivalents without departing from the scope of the present application. In particular, as long as there is no structural conflict, the technical features mentioned in each embodiment can be combined in any manner. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A fault diagnosis method for a wind turbine, characterized in that, Including: Obtaining the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine within N periods, where N is an integer greater than 1; For each period, determining the target current peak ratio of the generator in the period according to the current kurtosis and current standard deviation of the phase current in the period, and determining the target acceleration peak ratio of the nacelle in the period according to the acceleration kurtosis and acceleration standard deviation of the vibration acceleration in the period; In response to the wind turbine satisfying the start condition but not starting, performing a fault diagnosis on the generator according to the target current peak ratio and target acceleration peak ratio in each period to obtain a fault diagnosis result.

2. The fault diagnosis method according to claim 1, wherein The phase current includes the three-phase currents on the grid side or machine side of the generator, and the determining the target current peak ratio of the generator in the period according to the current kurtosis and current standard deviation of the phase current in the period includes: Performing numerical differential processing on each phase current in the period to obtain a difference array corresponding to each phase current; For each phase current, determining the current kurtosis and current standard deviation of the phase current according to the differential data in the corresponding difference array, and determining the ratio of the current kurtosis and current standard deviation of the phase current as the first current peak ratio of the phase current; Determining the maximum value among the first current peak ratios of each phase current in the period as the target current peak ratio of the generator in the period.

3. The fault diagnosis method according to claim 1, wherein The vibration acceleration of the nacelle includes a first vibration acceleration of the nacelle in a first direction and a second vibration acceleration of the nacelle in a second direction, and the first direction and the second direction are perpendicular; The determining the target acceleration peak ratio of the nacelle in the period according to the acceleration kurtosis and acceleration standard deviation of the vibration acceleration in the period includes: Performing absolute value processing on the first vibration acceleration and the second vibration acceleration in the period to obtain a first vibration acceleration array and a second vibration acceleration array; Determining the first acceleration kurtosis and first acceleration standard deviation of the first vibration acceleration according to the absolute values of the first vibration accelerations in the first vibration acceleration array, and determining the second acceleration kurtosis and second acceleration standard deviation of the second vibration acceleration according to the absolute values of the second vibration accelerations in the second vibration acceleration array; Determining the first ratio of the first acceleration kurtosis and the first acceleration standard deviation as the first acceleration peak ratio of the first vibration acceleration, and determining the second ratio of the second acceleration kurtosis and the second acceleration standard deviation as the second acceleration peak ratio of the second vibration acceleration; Determining the maximum value between the first acceleration peak ratio and the second acceleration peak ratio as the target acceleration peak ratio of the nacelle in the period.

4. The fault diagnosis method according to claim 1, wherein The vibration acceleration of the nacelle includes a first vibration acceleration of the nacelle in a first direction and a second vibration acceleration of the nacelle in a second direction, and the first direction and the second direction are perpendicular; Determining the target acceleration peak-to-peak ratio of the nacelle during the period according to the kurtosis and standard deviation of the vibration acceleration during the period includes: Performing absolute value processing on the first vibration acceleration and the second vibration acceleration during the period to obtain a third vibration acceleration array, and each element of the third vibration acceleration array consists of the processed first vibration acceleration and the second vibration acceleration; For each element in the third vibration acceleration array, determining the maximum value of the processed first vibration acceleration and the second vibration acceleration as the maximum vibration acceleration corresponding to the element; Determining the third kurtosis and the third standard deviation of the acceleration according to the maximum vibration accelerations corresponding to the elements in the third vibration acceleration array; Determining the third ratio of the third kurtosis of the acceleration and the third standard deviation of the acceleration as the target acceleration peak-to-peak ratio of the nacelle during the period.

5. The fault diagnosis method according to any one of claims 1-4, characterized in that, Responding to the wind turbine generator set satisfying the start-up condition but not starting, and performing fault diagnosis on the generator according to the target current peak-to-peak ratio and the target acceleration peak-to-peak ratio during each period to obtain a fault diagnosis result, including: Determining the maximum current peak-to-peak ratio according to the target current peak-to-peak ratio during each period, and determining the maximum acceleration peak-to-peak ratio according to the target acceleration peak-to-peak ratio during each period; Responding to the wind turbine generator set satisfying the start-up condition but not starting, the maximum current peak-to-peak ratio being greater than the first threshold, and the maximum acceleration peak-to-peak ratio being greater than the second threshold, and determining that the generator has a fault.

6. The fault diagnosis method according to claim 5, characterized in that, The method further includes: Obtaining the environmental parameters and the blade angle of the wind turbine generator set; The responding to the wind turbine generator set satisfying the start-up condition but not starting, the maximum current peak-to-peak ratio being greater than the first threshold, and the maximum acceleration peak-to-peak ratio being greater than the second threshold, and determining that the generator has a fault includes: Responding to the wind turbine generator set satisfying the start-up condition but not starting, the environmental parameters and the blade angle satisfying the power generation condition of the generator but the generator not entering the power generation state, the maximum current peak-to-peak ratio being greater than the first threshold, and the maximum acceleration peak-to-peak ratio being greater than the second threshold, and determining that the generator has a ground fault or insulation failure.

7. The fault diagnosis method according to any one of claims 1-4, characterized in that, Responding to the wind turbine generator set satisfying the start-up condition but not starting, and performing fault diagnosis on the generator according to the target current peak-to-peak ratio and the target acceleration peak-to-peak ratio during each period to obtain a fault diagnosis result, including: Determining the maximum current peak-to-peak ratio according to the target current peak-to-peak ratio during each period, and determining the maximum acceleration peak-to-peak ratio according to the target acceleration peak-to-peak ratio during each period; Determining the trend parameter of the target acceleration peak-to-peak ratio according to the target acceleration peak-to-peak ratio during each period; Responding to the wind turbine generator set satisfying the start-up condition but not starting, the maximum current peak-to-peak ratio being greater than the first threshold, the maximum acceleration peak-to-peak ratio being greater than the second threshold, and the trend parameter being greater than the third threshold, and determining that the generator has a fault.

8. The fault diagnosis method according to claim 7, wherein The determining the trend parameter of the target acceleration peak-to-peak ratio according to the target acceleration peak-to-peak ratio during each period includes: Perform a linear fit on the m-th power of the target acceleration peak-to-peak ratio and the corresponding period in chronological order to obtain a target fitting curve, where m is an integer greater than 1; Determine the slope of the target fitting curve as the trend parameter of the target acceleration peak-to-peak ratio.

9. The fault diagnosis method according to any one of claims 1-4, characterized in that The method further includes: In response to determining that the generator has a fault, generate a fault warning message and output it.

10. A fault diagnosis device for a wind turbine, characterized in that, Including: An acquisition module for acquiring the phase current of the generator and the vibration acceleration of the nacelle in the wind turbine within N periods, where N is an integer greater than 1; A determination module for, for each period, determining the target current peak-to-peak ratio of the generator in the period according to the kurtosis and standard deviation of the phase current in the period, and determining the target acceleration peak-to-peak ratio of the nacelle in the period according to the kurtosis and standard deviation of the vibration acceleration in the period; A diagnosis module for, in response to the wind turbine satisfying the start condition but not starting, performing a fault diagnosis on the generator according to the target current peak-to-peak ratio and the target acceleration peak-to-peak ratio in each period to obtain a fault diagnosis result.

11. A wind turbine unit, characterized in that, Including the fault diagnosis device of the wind turbine as described in claim 10.

Images