Blade Fault Diagnosis Method, Device and Electronic Equipment for Wind Turbine Generator

Abstract

The present application discloses a method, device, and electronic device for diagnosing blade faults of a wind turbine, which can eliminate the interference caused by signal jumps in blade vibration signals to blade fault diagnosis. Among them, the method for diagnosing blade faults of a wind turbine includes: obtaining a blade vibration signal sequence collected by a vibration signal acquisition device; identifying whether there is a signal jump in the blade vibration signal sequence; and performing fault diagnosis on the blades of the wind turbine according to the blade vibration signal sequence when there is no signal jump in the blade vibration signal sequence.

Description

Technical Field

[0001] This application belongs to the technical field of wind power generation, and particularly relates to a method, device, and electronic device for diagnosing blade faults of a wind turbine generator set. Background Art

[0002] In order to monitor whether the blades of a wind turbine generator set are faulty, the vibration of the blades can be monitored, and the collected blade vibration signals can be analyzed to determine whether the blades are faulty.

[0003] However, the inventors found that due to interference such as incorrect parameter configuration of the blade vibration sensor or loose cables of the acquisition device, the collected blade vibration signals may be abnormal, resulting in signal jumps. Such abnormalities are not caused by blade faults but by abnormalities in the acquisition module. Therefore, if there are data quality problems caused by the above-mentioned interference during the acquisition process in the collected blade vibration signals, it may lead to misjudgment of blade fault diagnosis. Summary of the Invention

[0004] Embodiments of this application provide a method, device, and electronic device for diagnosing blade faults of a wind turbine generator set, which can eliminate the interference caused by signal jumps in blade vibration signals to blade fault diagnosis.

[0005] On the one hand, embodiments of this application provide a method for diagnosing blade faults of a wind turbine generator set. The method includes: obtaining a sequence of blade vibration signals collected by a vibration signal acquisition device; identifying whether there is a signal jump in the sequence of blade vibration signals; and when there is no signal jump in the sequence of blade vibration signals, diagnosing the faults of the blades of the wind turbine generator set according to the sequence of blade vibration signals.

[0006] Optionally, the sequence of blade vibration signals includes a first sequence of blade vibration signals in the flapping direction and a second sequence of blade vibration signals in the lead-lag direction. Identifying whether there is a signal jump in the sequence of blade vibration signals includes: respectively identifying whether there is a signal jump in the first sequence of blade vibration signals and the second sequence of blade vibration signals; and when there is no signal jump in the sequence of blade vibration signals, diagnosing the faults of the blades of the wind turbine generator set according to the sequence of blade vibration signals includes: when there is no signal jump in both the first sequence of blade vibration signals and the second sequence of blade vibration signals, diagnosing the faults of the blades of the wind turbine generator set according to the first sequence of blade vibration signals and the second sequence of blade vibration signals.

[0007] Optionally, identifying whether there is a signal jump in the blade vibration signal sequence includes: obtaining the sampling points with a signal intensity of zero in the blade vibration signal sequence to obtain target sampling points; calculating a first change rate between the signal intensity of a target sampling point and the signal intensity of the previous sampling point, and a second change rate between the signal intensity of the target sampling point and the signal intensity of the next sampling point; and determining whether there is a signal jump at the target sampling point based on the comparison result between the first change rate and a target threshold, and the comparison result between the second change rate and the target threshold.

[0008] Optionally, there are n target sampling points, where n is an integer greater than 1. Identifying whether there is a signal jump in the blade vibration signal sequence includes: sequentially determining whether there is a signal jump at the n target sampling points; determining that there is a signal jump in the blade vibration signal sequence if there is a signal jump at any one of the target sampling points; and stopping determining whether there is a signal jump at the remaining target sampling points.

[0009] Optionally, the blade vibration signal sequence includes a first blade vibration signal sequence in the flapping direction. Before determining whether there is a signal jump at the target sampling point based on the comparison result between the first change rate and a target threshold, and the comparison result between the second change rate and the target threshold, the method further includes: determining an average change rate of the first blade vibration signal sequence; and determining the target threshold according to the average change rate.

[0010] Optionally, the first blade vibration signal sequence is a trigonometric function. Determining the average change rate of the first blade vibration signal sequence includes: determining the peak-to-peak value A of the first blade vibration signal sequence, where the peak-to-peak value is the difference between the maximum value and the minimum value of the first blade vibration signal sequence; estimating the function period T of the first blade vibration signal sequence; and obtaining the average change rate of the first blade vibration signal sequence in the trigonometric function according to the peak-to-peak value A and the function period T.

[0011] Optionally, estimating the function period T of the first blade vibration signal sequence includes: estimating the number of function periods T of the first blade vibration signal sequence; determining the total sampling duration of the first blade vibration signal sequence according to the total number of sampling points and the sampling frequency of the first blade vibration signal sequence; and determining the function period T of the first blade vibration signal sequence according to the total sampling duration and the number of function periods.

[0012] Optionally, estimating the number of function periods of the first blade vibration signal sequence includes: removing the sampling points with a signal intensity of zero in the first blade vibration signal sequence to obtain a third blade vibration signal sequence; calculating the average signal intensity of the third blade vibration signal sequence; counting the number of sampling points in the third blade vibration signal sequence whose signal intensity is equal to the average signal intensity to obtain a first value; and determining the number of function periods of the first blade vibration signal sequence according to the first value.

[0013] Optionally, before identifying whether there is a signal jump in the blade vibration signal sequence, the method further includes: determining whether the signal intensities of the blade vibration signal sequence are all zero values; wherein, in the case of a signal sequence in which the signal intensities of the blade vibration signal sequence are not all zero values, identifying whether there is a signal jump in the blade vibration signal sequence.

[0014] On the other hand, an embodiment of the present application provides a blade fault diagnosis device for a wind turbine generator set, the device includes: an acquisition module, configured to acquire a blade vibration signal sequence acquired by a vibration signal acquisition device; an identification module, configured to identify whether there is a signal jump in the blade vibration signal sequence; a diagnosis module, configured to perform fault diagnosis on the blade of the wind turbine generator set according to the blade vibration signal sequence in the case where there is no signal jump in the blade vibration signal sequence.

[0015] Optionally, the blade vibration signal sequence includes a first blade vibration signal sequence in the flap direction and a second blade vibration signal sequence in the lead-lag direction, and the identification module includes: an identification unit, configured to respectively identify whether there is a signal jump in the first blade vibration signal sequence and the second blade vibration signal sequence; the diagnosis module includes: a diagnosis unit, configured to perform fault diagnosis on the blade of the wind turbine generator set according to the first blade vibration signal sequence and the second blade vibration signal sequence in the case where there is no signal jump in the first blade vibration signal sequence and the second blade vibration signal sequence.

[0016] Optionally, the identification module includes: an acquisition unit, configured to acquire sampling points with zero signal intensity in the blade vibration signal sequence to obtain target sampling points; a first calculation unit, configured to calculate a first change rate between the signal intensity of a target sampling point and the signal intensity of the previous sampling point, and a second change rate between the signal intensity of the target sampling point and the signal intensity of the next sampling point; a judgment unit, configured to judge whether there is a signal jump at the target sampling point according to the comparison result between the first change rate and a target threshold, and the comparison result between the second change rate and the target threshold.

[0017] Optionally, there are n target sampling points, where n is an integer greater than 1, and the identification module further includes: a first execution unit, configured to sequentially judge whether there is a signal jump at the n target sampling points; a first determination unit, configured to determine that there is a signal jump in the blade vibration signal sequence in the case where there is a signal jump at any one of the target sampling points; a second execution unit, configured to stop judging whether there is a signal jump at the remaining target sampling points.

[0018] Optionally, the blade vibration signal sequence includes a first blade vibration signal sequence in the flap direction. The device further includes: a first determination module, configured to determine an average change rate of the first blade vibration signal sequence before determining whether there is a signal jump at a target sampling point according to a comparison result between a first change rate and a target threshold and a comparison result between a second change rate and the target threshold; a second determination module, configured to determine the target threshold according to the average change rate.

[0019] Optionally, the first blade vibration signal sequence is a trigonometric function. The first determination module includes: a first determination unit, configured to determine a peak-to-peak value A of the first blade vibration signal sequence, where the peak-to-peak value is the difference between the maximum value and the minimum value of the first blade vibration signal sequence; a first calculation unit, configured to estimate a function period T of the first blade vibration signal sequence; a second calculation unit, configured to obtain an average change rate of the first blade vibration signal sequence in the trigonometric function according to the peak-to-peak value A and the function period T.

[0020] Optionally, the first calculation unit includes: a third calculation unit, configured to estimate the number of function periods of the first blade vibration signal sequence; a first determination unit, configured to determine a total sampling duration of the first blade vibration signal sequence according to the total number of sampling points and the sampling frequency of the first blade vibration signal sequence; a second determination unit, configured to determine the function period T of the first blade vibration signal sequence according to the total sampling duration and the number of function periods.

[0021] Optionally, the third calculation unit includes: an execution unit, configured to remove sampling points with a signal strength of zero value from the first blade vibration signal sequence to obtain a third blade vibration signal sequence; a fourth calculation unit, configured to calculate an average signal strength of the third blade vibration signal sequence; a statistical unit, configured to count the number of sampling points in the third blade vibration signal sequence whose signal strength is equal to the average signal strength to obtain a first value; a third determination unit, configured to determine the number of function periods of the first blade vibration signal sequence according to the first value.

[0022] Optionally, the device further includes: a judgment module, configured to judge whether the signal strength of the blade vibration signal sequence is all zero values before identifying whether there is a signal jump in the blade vibration signal sequence; where, in the case of a signal sequence in which the signal strength of the blade vibration signal sequence is not all zero values, identify whether there is a signal jump in the blade vibration signal sequence.

[0023] In another aspect, an embodiment of the present application provides an electronic device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the blade fault diagnosis method of the wind turbine generator set as described in the embodiment of the present application is implemented.

[0024] In another aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method for diagnosing blade faults of a wind turbine generator set as described in the embodiments of the present application is implemented.

[0025] For the method, device, electronic device, and computer storage medium for diagnosing blade faults of a wind turbine generator set according to the embodiments of the present application, by identifying whether there is a signal jump in the blade vibration signal sequence, and in the case where there is no signal jump in the blade vibration signal sequence, fault diagnosis is performed on the blades of the wind turbine generator set according to the blade vibration signal sequence. In this way, a quality inspection can be performed on the blade vibration signal sequence to determine whether there is a signal jump, and fault diagnosis is performed according to the blade vibration signal sequence without signal jump, which can eliminate the interference of the signal jump of the blade vibration signal on blade fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0027] Figure 1 is a schematic flowchart of a method for diagnosing blade faults of a wind turbine generator set provided by an embodiment of the present application;

[0028] Figure 2 is an optional schematic diagram of a blade vibration signal sequence in the flapping direction in a normal state;

[0029] Figure 3 is an optional schematic diagram of a blade vibration signal sequence in the lead-lag direction in a normal state;

[0030] Figure 4 is an optional schematic diagram of a blade vibration signal sequence in the flapping direction when there is a signal jump;

[0031] Figure 5 is an optional schematic diagram of a blade vibration signal sequence in the lead-lag direction when there is a signal jump;

[0032] Figure 6 is a schematic flowchart of a method for diagnosing blade faults of a wind turbine generator set provided by another embodiment of the present application;

[0033] Figure 7 is a schematic flowchart of a method for diagnosing blade faults of a wind turbine generator set provided by another embodiment of the present application;

[0034] Figure 8It is a schematic flow chart of a blade fault diagnosis method for a wind turbine provided by another embodiment of the present application;

[0035] Figure 9 It is a schematic structural diagram of a blade fault diagnosis device for a wind turbine provided by another embodiment of the present application;

[0036] Figure 10 It is a schematic structural diagram of an electronic device provided by yet another embodiment of the present application;

[0037] Figure 11 It is a schematic diagram of an application scenario of a blade fault diagnosis device for a wind turbine provided by an embodiment of the present application. Detailed implementation manners

[0038] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented 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.

[0039] It should be noted that, in this document, 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 "comprises", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "comprising..." do not preclude the existence of additional identical elements in the process, method, article or device comprising the said elements.

[0040] First, an optional application scenario of the blade fault diagnosis method for a wind turbine provided by the embodiments of the present application will be introduced below.

[0041] The blade fault diagnosis method provided by the embodiments of the present application can be applied to an application environment for monitoring the blades of a wind turbine. Specifically, the components of the wind turbine include blades, and the vibration condition of the blades can reflect the overall health condition of the operation of the wind turbine, etc. Therefore, the vibration of the blades can be monitored to obtain the vibration monitoring signal of the blades. A vibration signal acquisition device can be installed on the wind turbine, and the vibration signal acquisition device can include a vibration sensor for sensing the vibration intensity, and the vibration sensor can be installed on the blade.

[0042] The vibration signal acquisition device can also include a signal processing module connected to the vibration sensor, etc. The signal processing module connected to the vibration sensor can be communicatively connected to the vibration sensor by means of wired cable communication or wireless communication. The signal processing module can be used to receive the signal obtained by the vibration sensor sensing the vibration intensity, convert the analog signal into a digital signal, and the signal of each sampling point is used to represent the magnitude of the vibration intensity collected at the corresponding sampling moment. Optionally, the signal processing module connected to the vibration sensor, etc. can be installed in parts such as the hub and nacelle of the wind turbine, and the embodiments of the present application do not make specific limitations thereto. The vibration sensor samples at a certain sampling frequency to obtain the signal of the blade during vibration. The collected vibration signal can include the vibration signal in the flap direction of the blade, or can also include the vibration signal in the lead-lag direction of the blade. In the case where the signal is normal and there is no jump, an optional example of the blade vibration signal sequence in the flap direction is as Figure 2 shown, and an optional example of the blade vibration signal sequence in the lead-lag direction is as Figure 3 shown. Figure 2 and Figure 3 In Figure 4 and Figure 5 , the horizontal axis is the sampling moment, and the vertical axis is the signal amount collected by the vibration sensor, which is used to represent the vibration intensity. In the case where the signal is abnormal and there is a jump, an optional example of the blade vibration signal sequence in the flap direction is as Figure 4 shown, and an optional example of the blade vibration signal sequence in the lead-lag direction is as Figure 5 shown. It can be seen from Figure 4 and Figure 5 that there is a situation where the signal suddenly jumps to zero, that is, there is a signal jump.

[0043] The blade vibration signals collected by the vibration signal acquisition device can be sent to the monitoring system, and the monitoring system analyzes the health status of each core component of the wind turbine generator set and the overall health status of the wind turbine generator set according to the blade vibration signals. The specific analysis method will not be elaborated here. The monitoring system can be a software program running on an electronic device with computing capabilities, and it performs fault diagnosis based on the received vibration signals. The above-mentioned electronic device can be an electronic device provided in an embodiment of the present application, and this electronic device may include: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the blade fault diagnosis method of the wind turbine generator set as described in the embodiment of the present application. The above-mentioned electronic device can be arranged inside components such as the nacelle and tower of the wind turbine generator set, or it can also be arranged in the monitoring room of the wind farm where the wind turbine generator set is located, etc. The embodiment of the present application does not make specific limitations on this.

[0044] Optionally, the monitoring system can be a commonly used condition monitoring system (Content Management System, abbreviated as CMS) in the wind power industry. CMS mainly monitors the components of the unit in real time by installing vibration sensors on components such as the blades or bearings of the wind turbine generator set, identifies the health status of each core component of the unit and the overall health status of the unit by analyzing the vibration data, and reasonably arranges the operation and maintenance plan according to the health status of the components. In practice, the blade vibration signal acquisition data obtained by CMS often has abnormal vibration data due to reasons such as sensor damage, incorrect sensor parameter configuration, loose sensor connection, abnormal network transmission, and electromagnetic interference caused by power supply. Abnormal vibration data will directly affect the vibration analysis result, causing CMS to misreport or miss reporting faults, bringing bad experiences and troubles to the operation and maintenance personnel. It can be seen that real-time detection of abnormal CMS data quality and timely giving a prompt for abnormal data quality can avoid misjudgment of the CMS diagnosis result by on-site operation and maintenance personnel due to data quality problems, which is of great practical significance for the actual application of CMS.

[0045] In order to eliminate the interference caused by signal jumps in the blade vibration signals to blade fault diagnosis, an embodiment of the present application provides a blade fault diagnosis method for a wind turbine generator set. Optionally, the method provided in the embodiment of the present application can be integrated into the above-mentioned CMS system.

[0046] Figure 1 The flowchart of the blade fault diagnosis method for a wind turbine generator set provided by an embodiment of the present application is shown. As Figure 1 shown, the method includes the following steps:

[0047] Step 101, obtain the blade vibration signal sequence collected by the vibration signal acquisition device.

[0048] The vibration signal acquisition device may include a vibration sensor for acquiring the vibration of the blade in the monitoring direction at a certain signal sampling frequency. The monitoring direction may be the flapping direction or the pitching direction, and the vibration intensity monitored in one direction is represented by the signal amplitude. The blade vibration signal sequence includes a sequence of multiple signals acquired at a preset sampling frequency within a period of time, which can also be referred to as multiple sampling points. The time interval between each sampling point is one sampling period, and the signal intensity of each sampling point is the vibration intensity in the monitoring direction at the corresponding sampling moment.

[0049] Step 102: Identify whether there is a signal jump in the blade vibration signal sequence.

[0050] A signal jump refers to the situation where the signal intensity suddenly becomes zero. Signal jumps are usually caused by signal reception problems such as cable connection problems or network transmission anomalies, or signal anomalies caused by sensor damage, power supply electromagnetic interference, etc.

[0051] Step 103: When there is no signal jump in the blade vibration signal sequence, perform a fault diagnosis on the blade of the wind turbine generator according to the blade vibration signal sequence.

[0052] When it is determined according to Step 102 that there is no signal jump in the blade vibration signal sequence, a fault diagnosis can be performed on the blade of the wind turbine generator according to the blade vibration signal sequence. An optional example is that the CMS system can analyze the operating health conditions of the main core components (including the blade) of the wind turbine generator according to the blade vibration signal sequence.

[0053] When there is a signal jump in the blade vibration signal sequence, this part of the blade vibration signal sequence collected can be discarded. Otherwise, if a fault diagnosis is performed according to the blade vibration signal sequence with signal jumps, it may lead to incorrect diagnosis situations such as false alarms or missed alarms. In addition, when there is a signal jump in the blade vibration signal sequence, a prompt alarm can be issued to prompt the operation and maintenance personnel to detect the signal acquisition path, including detecting the inside of the vibration signal acquisition device, such as whether the vibration sensor can work normally, whether the communication between the vibration sensor and the signal processing module of the vibration signal acquisition device is normal, and it can also include detecting whether the communication between the vibration signal acquisition device and the monitoring system is normal. After the repair is normal, the blade vibration signal sequence is collected again, and the method provided in the embodiment of the present application is executed. If there is no signal jump in the collected blade vibration signal sequence, a fault diagnosis can be performed on the blade of the wind turbine generator according to the blade vibration signal sequence.

[0054] Optionally, the vibration sensor of the vibration signal acquisition device can be a multi-axis sensor, which can respectively collect the vibration amplitude of the blade in the flapping direction and the vibration amplitude in the lead-lag direction, and obtain the first blade vibration signal sequence in the flapping direction and the second blade vibration signal sequence in the lead-lag direction.

[0055] Correspondingly, in step 102, when identifying whether there is a signal jump in the blade vibration signal sequence, it is possible to separately identify whether there is a signal jump in the first blade vibration signal sequence and the second blade vibration signal sequence.

[0056] When there is no signal jump in both the first blade vibration signal sequence and the second blade vibration signal sequence, the blade of the wind turbine generator can be fault diagnosed based on the first blade vibration signal sequence and the second blade vibration signal sequence.

[0057] However, when there is a signal jump in the first blade vibration signal sequence or the second blade vibration signal sequence, it indicates that the monitored vibration signal may have abnormal data quality. The collected signal can be discarded, and an alarm prompt can be issued to prompt the staff to repair the vibration signal acquisition device.

[0058] Optionally, the steps for identifying whether there is a signal jump in the first blade vibration signal sequence and the second blade vibration signal sequence can be respectively executed by different software modules. The first software module is used to identify whether there is a signal jump in the first blade vibration signal sequence, and the second software module is used to identify whether there is a signal jump in the second blade vibration signal sequence.

[0059] Optionally, step 102 for identifying whether there is a signal jump in the blade vibration signal sequence may include the following steps:

[0060] Step 201, obtain the sampling points with a signal intensity of zero in the blade vibration signal sequence to obtain the target sampling points;

[0061] Step 202, calculate the first change rate between the signal intensity of the target sampling point and the signal intensity of the previous sampling point, and the second change rate between the signal intensity of the target sampling point and the signal intensity of the next sampling point;

[0062] Step 203, based on the comparison result between the first change rate and the target threshold, and the comparison result between the second change rate and the target threshold, determine whether there is a signal jump at the target sampling point.

[0063] Sampling points with zero signal strength are target sampling points. There may be signal jumps at target sampling points, or there may not be signal jumps. For further judgment, after obtaining the target sampling points, compare the signal strengths of the target sampling points with the previous and next sampling points. If the change rate is relatively high and higher than the target threshold, it indicates that a mutation has occurred at the target sampling point, jumping from near a non-zero value to zero value, and there is a signal jump. The target threshold can be a preset value.

[0064] When there are n target sampling points (n is an integer greater than 1), step 102 of identifying whether there is a signal jump in the blade vibration signal sequence may include the following steps:

[0065] Step 301, sequentially judge whether there is a signal jump for each of the n target sampling points;

[0066] Step 302, when there is a signal jump at any one of the target sampling points, determine that there is a signal jump in the blade vibration signal sequence;

[0067] Step 303, stop judging whether there is a signal jump in the remaining target sampling points.

[0068] That is, when identifying whether there is a signal jump in the blade vibration signal sequence, after obtaining the target sampling points in step 201, sequentially execute step 202 and step 203 for each target sampling point respectively, judge whether there is a signal jump at one target sampling point. If not, continue to judge whether there is a signal jump at the next target sampling point. If there is a signal jump, it means that there is a signal jump in the blade vibration signal sequence, and the judgment of the remaining target sampling points can be stopped. As can be seen from the above, the steps of separately judging whether there is a signal jump for multiple target sampling points are processed serially, and the order of identifying whether there is a signal jump for multiple target sampling points can be a preset order. For example, judge the n target sampling points sequentially in ascending order of sampling time.

[0069] For the blade vibration signal sequence in the flapping direction, since the blade vibration signal sequence is a relatively smooth signal under normal circumstances (as Figure 2 shown), therefore, the change rate is relatively stable. Then, the average change rate of the sampling points other than the target sampling points with zero signal can be calculated, and the thresholds of the first change rate and the second change rate (that is, the target threshold) can be determined according to the average change rate.

[0070] Among them, the average change rate means that for a function, there is an increment Δx at x_0, then y will also have a corresponding increment Δy. Then we call the ratio Δy / Δx of the increment of Δy to the increment of Δx the average change rate of the function f(x) with an increment of Δx at x_0.

[0071] The target threshold can be determined according to the average rate of change. It can be directly taking the average rate of change as the target threshold, or alternatively, the average rate of change can be processed by a preset algorithm, such as multiplying by a preset coefficient and other processing methods, to obtain the target threshold.

[0072] For the blade vibration signal sequence in the flapping direction, since the signal is relatively rough and not smooth, therefore, the target threshold of the rate of change can be preset according to experience.

[0073] As can be seen from the above analysis, for the first blade vibration signal sequence in the lead-lag direction, the average rate of change of the first blade vibration signal sequence can be estimated, and the target threshold can be determined according to the average rate of change.

[0074] The first blade vibration signal sequence can be regarded as a trigonometric function. Therefore, an optional implementation manner for determining the average rate of change of the first blade vibration signal sequence is:

[0075] First, determine the peak-to-peak value A of the first blade vibration signal sequence.

[0076] Among them, the peak-to-peak value A is the difference between the maximum value and the minimum value of the first blade vibration signal sequence, and can be calculated by obtaining the maximum value max(xx(t)) and the minimum value min(xx(t)) of the first blade vibration signal sequence xx(t), A=(max(xx(t)) - min(xx(t))).

[0077] Secondly, estimate the function period T of the first blade vibration signal sequence.

[0078] Finally, according to the peak-to-peak value A and the function period T, obtain the average rate of change of the first blade vibration signal sequence in the trigonometric function

[0079] Since in a period T of the trigonometric function, the sign of the rate of change will change direction three times, respectively at the three positions of nT+T / 4, nT+T / 2, and nT+3T / 4 (as Figure 2 shown), a period T of the trigonometric function is divided into four intervals by the above three positions, and the time length of each interval is T / 4. Therefore, in any T / 4 interval where the sign of the rate of change remains unchanged, according to the ratio of the increment of the dependent variable to the increment of the independent variable, the mean value of the magnitude of the rate of change can be calculated.

[0080] For a trigonometric function with a period of T, taking the calculation of the average rate of change in any T / 4 interval where the sign of the rate of change remains unchanged as an example, the increment of the dependent variable is A / 2, and the increment of the independent variable is T / 4. The average rate of change rate tmp of the signal xx(t) is calculated as shown in Formula 1:

[0081]

[0082] Optionally, the function period T of the first blade vibration signal sequence can be estimated by the following steps:

[0083] Step 401, estimate the number of function periods T of the first blade vibration signal sequence.

[0084] Since the first blade vibration signal sequence is a trigonometric function in the form of as shown in Figure 2 , the number of function periods can be estimated based on the number of signals where the signal volume (signal intensity) of the first blade vibration signal sequence is equal to the average signal volume.

[0085] First, the average value mean of the signal volume of the first blade vibration signal sequence xx(t) can be calculated, that is, the average signal intensity; then, the number count of sampling points in the signal xx(t) that are equal to the signal mean (if adjacent points are the same, only the first one is retained) is counted, that is, the first value. Thus, the number of function periods of the signal xx(t) is: round((count - 1) / 2).

[0086] Among them, in order to avoid the influence of possible jump signals on the average value, the sampling points with a signal intensity of zero in the first blade vibration signal sequence can be removed to obtain the third blade vibration signal sequence; the average signal intensity of the third blade vibration signal sequence is calculated.

[0087] Step 402, determine the total sampling duration of the first blade vibration signal sequence according to the total number of sampling points and the sampling frequency of the first blade vibration signal sequence;

[0088] According to the sampling frequency fs of the first blade vibration signal sequence, the sampling period 1 / fs of the first blade vibration signal sequence can be determined, that is, how often a signal is sampled.

[0089] Furthermore, according to the product of the total number of sampling points len(x(t)) of the first blade vibration signal sequence x(t) and the sampling period, the total duration consumed for collecting the first blade vibration signal sequence can be obtained: len(x(t)) / fs.

[0090] Step 403, determine the function period T of the first blade vibration signal sequence according to the total sampling duration and the number of function periods.

[0091] Dividing the total duration consumed by the first blade vibration signal sequence by the number of function periods can estimate the period (duration) T of the function of the first blade vibration signal sequence:

[0092]

[0093] Optionally, the target threshold rate can be directly set to the average rate of change, or can be set to a preset multiple of the average rate of change, that is, multiplied by a preset coefficient.

[0094] When the target threshold is directly set to the average rate of change, the target threshold rate can be calculated by the following formula:

[0095]

[0096] That is, the target threshold can be determined according to the peak-to-peak value and the function period, and the rate threshold more suitable for determining whether it is a jump signal can be obtained through Formula 3.

[0097] The above is an example of estimating the target threshold rate for the first blade vibration signal sequence in the form of a trigonometric function

[0098] Optionally, after obtaining the blade vibration signal sequence, before performing step 102 to identify whether there is a signal jump in the blade vibration signal sequence, it can also be determined whether the signal intensity of the blade vibration signal sequence is all zero. If it is all zero, then the blade vibration signal sequence is abnormal, and the determination of whether there is a signal jump in the blade vibration signal sequence can be directly abandoned. Otherwise, if the signal intensity of the blade vibration signal sequence is not all zero, then step 102 is executed to identify whether there is a signal jump in the blade vibration signal sequence.

[0099] The following combines Figures 6 to 8 A specific optional implementation manner of the blade fault diagnosis method for a wind turbine provided by the embodiments of the present application is described in detail as follows:

[0100] In this example, the vibration signal acquisition device includes a vibration sensor, a signal processing module, and a demodulator. The vibration sensor is installed on the blade. After the collected vibration signal data is converted into a frame value based on the Controller Area Network (CAN) bus protocol by the signal processing module, it is sent from the demodulator to the monitoring system, and the monitoring system determines the collected signal quantity according to the data of the CAN frame value sent by the vibration signal acquisition device.

[0101] As Figure 6 shown, first, the monitoring system obtains the CAN frame value collected by the vibration signal acquisition device to obtain the blade vibration signal sequence.

[0102] ​To avoid misjudgment of faults in the monitoring system caused by problems with the quality of the collected signal data, after obtaining the blade vibration signal sequence and before performing fault detection based on the blade vibration signal sequence, the blade vibration signal sequence is detected for data anomalies to determine whether there are signal jumps.

[0103] As Figure 6 shown, data anomaly detection can be performed separately by Software Module 1 and Software Module 2. Software Module 1 is used to determine whether there is a signal jump in the blade vibration signal sequence in the flapping direction, and Software Module 2 is used to determine whether there is a signal jump in the blade vibration signal sequence in the lead-lag direction.

[0104] Furthermore, as Figure 6 shown, based on the judgment results of Software Module 1 and Software Module 2, it is determined whether the blade vibration signal sequence is normal. Among them, if there are no signal jumps in both the flapping direction and the lead-lag direction, the signal data is normal, and the temperature influence processing can be further performed on the blade vibration signal sequence, converted into engineering quantities, and fault detection can be performed based on the engineering quantities. Among them, before detecting whether the blade vibration signal sequence has signal data anomalies, no processing is performed on the blade vibration signal sequence, otherwise it may cause abnormal blade vibration signal sequences to be processed as normal signal sequences, resulting in inaccurate judgment results; if a signal jump is detected in any one of the flapping direction and the lead-lag direction, or the blade vibration signal sequence in any one direction is a signal with all zero values, it is determined that the signal data is abnormal, the collected blade vibration signal is discarded, and no further fault detection is performed based on the collected blade vibration signal sequence, and it can be prompted that there are anomalies in the collected blade vibration signal.

[0105] Regarding the above-mentioned Software Module 1, that is, whether there is a signal jump in the lead-lag direction, an optional flowchart is as Figure 7 shown, including the following steps:

[0106] Step 1: All-zero signal judgment.

[0107] Calculate the total number of signals N in the blade vibration signal sequence x(t), and the number of signals equal to 0 is denoted as k. If N = k, the signal is an all-zero signal, and no further operation is performed, and the blade vibration signal sequence x(t) is discarded. Otherwise, the next calculation and judgment are performed.

[0108] Step 2: Screen out non-zero signals and calculate the peak-to-peak value.

[0109] The peak-to-peak value refers to the difference between the highest value and the lowest value of a signal within one period, that is, the range between the maximum and the minimum. It describes the size of the change range of the signal value.

[0110] Filter out all signals where the blade vibration signal sequence x(t) in the flapping direction is not equal to 0, denoted as xx(t), as shown in Equation 4.

[0111] xx(t) = x(t)[x j != 0] (Equation 4)

[0112] Here j = 1, 2..len(x(t)). Additionally, the signals equal to 0 are denoted as x i(t) , where i = 1, 2, k.

[0113] The signal xx(t) is a trigonometric function in the form of , where the vibration frequency is denoted as f. The vibration period of the signal function is T = 1 / f. The calculation of half of the peak-to-peak value A of the signal xx(t) is shown in Equation 5.

[0114]

[0115] Step 3: Calculate the target threshold rate according to Equations 1 - 3.

[0116] Step 4: Calculate the change rate at the target signal (target sampling point) where the signal value is 0.

[0117] The change rate calculation includes the first change rate of the target signal and the previous signal and the second change rate of the target signal and the next signal:

[0118] Use the following Equations 6 and 7 to calculate the first change rate rate ibefore and the second change rate rate i :

[0119]

[0120]

[0121] Among them, the next signal of the target signal x i (t) is x next (t), and the previous signal of the target signal x i (t) is x_before(t).

[0122] Step 5: Identify whether there is a signal jump.

[0123] For each target signal x i (t), perform the following judgment:

[0124] The first judgment step: Whether abs(rate i) > co * A * rate, where co is a preset coefficient. Optionally, a typical value can be 10. If the judgment result is yes, it indicates that the target signal is a jump signal.

[0125] The second judgment step: whether abs(rate ibefore ) > co * A * rate. If the judgment result is yes, it indicates that the target signal is a jump signal.

[0126] If, according to the above first judgment step and second judgment step, the judgment results are both no, then the target signal is not a jump signal. Increment i by 1 and return to execute step four until i = k or a jump signal is determined for any target signal, and then jump out of the loop. If, according to the above first judgment step and second judgment step, any one of the judgment results is yes, it indicates that the target signal is a jump signal, and the judgment of other target signals can be stopped. Optionally, the first judgment step and the second judgment step can be parallel or serial. When the result of any one of the judgment steps is determined to be yes, stop executing step five and determine that the target signal is a jump signal, that is, there is a signal anomaly in the blade vibration signal sequence in the flapping direction.

[0127] Among them, the change rate threshold in the above software module one is determined based on the peak-to-peak value and the average change rate of the 1 / 4 period of the sine function. In fact, other methods can also be used to determine the threshold, such as the expert-specified threshold, which are all within the protection scope of this application.

[0128] Regarding the above software module two, that is, whether there is a signal jump in the flapping direction, an optional flowchart is as Figure 8 shown, including the following steps:

[0129] Step one: All-zero signal judgment.

[0130] Calculate the total number of signals N of the blade vibration signal sequence x(t). If N = k, then the signal is an all-zero signal and no further operation is performed. Otherwise, proceed to the next calculation and judgment.

[0131] Step two: Signal screening.

[0132] Screen out all signals where the flapping direction signal x(t) is equal to 0, denoted as x i(t) , i = 1, 2, k, as shown in formula 8.

[0133] x i(t) = x(t)[x j == 0] (formula 8)

[0134] Step three: Calculate the change rate at the target signal (target sampling point).

[0135] The calculation of the rate of change includes the first rate of change of the target signal and the previous signal, and the second rate of change of the target signal and the next signal:

[0136] Using the following formulas 9 and 10, calculate the first rate of change rate ibefore and the second rate of change rate i :

[0137]

[0138]

[0139] where x next (t) is the next signal of the target signal x i (t) in the signal sequence x(t), fs is the sampling frequency, and the previous signal of the signal x i (t) is x before (t).

[0140] Step Four: Identify whether there is a signal jump.

[0141] For each target signal x i (t), perform the following judgment:

[0142] The first judgment step: Whether abs(rate i ) > b, where b is a preset value (target threshold), and a typical value of b can be 10 4 . If the judgment result is yes, it means that the target signal is a jump signal.

[0143] The second judgment step: Whether abs(rate ibefore ) > b. If the judgment result is yes, it means that the target signal is a jump signal.

[0144] If according to the above first judgment step and second judgment step, the judgment results are both no, then the target signal is not a jump signal, increment i by 1, and return to execute step four until i = k or a jump signal is judged for any target signal, and then jump out of the loop. If according to the above first judgment step and second judgment step, any one of the judgment results is yes, it means that the target signal is a jump signal, and the judgment of other target signals can be stopped. Optionally, the first judgment step and the second judgment step can be parallel or serial. When it is determined that the result of any one of the judgment steps is yes, stop executing step five and determine that the target signal is a jump signal, that is, there is a signal anomaly in the blade vibration signal sequence in the waving direction.

[0145] Among them, Software Module 2 detects jump signals by comparing whether the change rate at the 0 signal with the previous signal and the next signal is greater than the target threshold. In practical applications, the range of the change rate can also be segmented to determine whether the change rate is within a relatively high interval, and so on. That is, according to the comparison result between the first change rate and the target threshold, and the comparison result between the second change rate and the target threshold, to determine whether there is a signal jump at the target sampling point, different comparison methods can be adopted. The above is only an exemplary illustration and does not constitute a limitation to the embodiments of the present application.

[0146] The embodiments of the present application also provide a blade fault diagnosis device for a wind turbine generator, which can be used to execute the blade fault diagnosis method for a wind turbine generator provided by the embodiments of the present application. For the parts not detailed in the blade fault diagnosis device for a wind turbine generator provided by the embodiments of the present application, reference can be made to the description in the blade fault diagnosis method for a wind turbine generator provided by the embodiments of the present application, and details will not be described here again.

[0147] As Figure 9 shown, the blade fault diagnosis device for a wind turbine generator provided by the embodiments of the present application includes an acquisition module 11, an identification module 12, and a diagnosis module 13.

[0148] Among them, the acquisition module 11 is used to acquire the blade vibration signal sequence collected by the vibration signal acquisition device; the identification module 12 is used to identify whether there is a signal jump in the blade vibration signal sequence; the diagnosis module 13 is used to perform a fault diagnosis on the blades of the wind turbine generator according to the blade vibration signal sequence when there is no signal jump in the blade vibration signal sequence.

[0149] Figure 11 is a schematic diagram of the application scenario of the blade fault diagnosis device for a wind turbine generator provided by an embodiment of the present application. As Figure 11 shown, the blade fault diagnosis device 731 for a wind turbine generator provided by the embodiments of the present application can be integrated into the wind turbine main controller 73. The wind turbine main controller 73 can be arranged in the nacelle 712 and / or the tower barrel 713 of the wind turbine generator 71. The embodiments of the present application do not limit the specific installation position of the wind turbine main controller 73. The acquisition module 11 of the blade fault diagnosis device 731 for a wind turbine generator can acquire the vibration signals collected by the vibration signal acquisition device 72.

[0150] Among them, the vibration signal acquisition device 72 may include a vibration sensor 721 and a signal processing module 722. The vibration sensor 721 may be disposed on the blade 711 of the wind turbine generator 71 for acquiring the vibration signal of the blade 711. Optionally, the vibration sensor 721 may be a multi-axis sensor capable of sensing the vibration of the blade 711 in the flapping direction and the pitching direction. The signal processing module 722 may process the analog vibration signal sensed by the vibration sensor 721 to generate a digital blade vibration signal sequence.

[0151] Optionally, the blade fault diagnosis device 731 of the wind turbine generator may communicate with a server 74 disposed in the wind farm control room. Each wind turbine generator in the wind farm may be equipped with a corresponding wind turbine main controller, and the central control room server 74 may communicate with all the wind turbine main controllers in the wind farm. In the embodiment of the present application, the central control room server 74 may, according to the blade fault diagnosis result of the blade fault diagnosis device 731 integrated in the wind turbine main controller 73.

[0152] The blade fault diagnosis device 731 of the wind turbine generator may send the judgment result of the recognition module 12 to the central control room server 74 to display an alarm prompt on the front-end interface of the central control room server 74, prompting the staff that there is a signal jump in the vibration signal acquired by the vibration signal acquisition device 72, and reminding the staff to immediately check the working state of the vibration signal acquisition device 72.

[0153] The blade fault diagnosis device 731 of the wind turbine generator may also send the blade fault diagnosis result of the diagnosis module 13 to the central control room server 74 to display an alarm prompt on the front-end interface of the central control room server 74, prompting the staff that a fault exists in the blade according to the blade vibration signal sequence, and reminding the staff to immediately check the blade.

[0154] Optionally, the blade vibration signal sequence includes a first blade vibration signal sequence in the flapping direction and a second blade vibration signal sequence in the pitching direction. The recognition module 12 includes: a recognition unit for respectively recognizing whether there is a signal jump in the first blade vibration signal sequence and the second blade vibration signal sequence; the diagnosis module 13 includes: a diagnosis unit for, when there is no signal jump in both the first blade vibration signal sequence and the second blade vibration signal sequence, performing a fault diagnosis on the blade of the wind turbine generator according to the first blade vibration signal sequence and the second blade vibration signal sequence.

[0155] Optionally, the recognition module 12 includes: an acquisition unit configured to acquire a sampling point with a signal intensity of zero in the blade vibration signal sequence to obtain a target sampling point; a first calculation unit configured to calculate a first change rate between the signal intensity of the target sampling point and the signal intensity of the previous sampling point, and a second change rate between the signal intensity of the target sampling point and the signal intensity of the next sampling point; and a determination unit configured to determine whether there is a signal jump at the target sampling point according to a comparison result between the first change rate and a target threshold, and a comparison result between the second change rate and the target threshold.

[0156] Optionally, there are n target sampling points, where n is an integer greater than 1. The recognition module 12 further includes: a first execution unit configured to sequentially determine whether there is a signal jump at the n target sampling points; a first determination unit configured to determine that there is a signal jump in the blade vibration signal sequence when there is a signal jump at any one of the target sampling points; and a second execution unit configured to stop determining whether there is a signal jump at the remaining target sampling points.

[0157] Optionally, the blade vibration signal sequence includes a first blade vibration signal sequence in the flapping direction. The device further includes: a first determination module configured to determine an average change rate of the first blade vibration signal sequence before determining whether there is a signal jump at the target sampling point according to a comparison result between the first change rate and a target threshold, and a comparison result between the second change rate and the target threshold; and a second determination module configured to determine the target threshold according to the average change rate.

[0158] Optionally, the first blade vibration signal sequence is a trigonometric function. The first determination module includes: a first determination unit configured to determine a peak-to-peak value A of the first blade vibration signal sequence, where the peak-to-peak value is the difference between the maximum value and the minimum value of the first blade vibration signal sequence; a first calculation unit configured to estimate a function period T of the first blade vibration signal sequence; and a second calculation unit configured to obtain an average change rate of the first blade vibration signal sequence in the trigonometric function according to the peak-to-peak value A and the function period T.

[0159] Optionally, the first calculation unit includes: a third calculation unit configured to estimate the number of function periods of the first blade vibration signal sequence; a first determination unit configured to determine a total sampling duration of the first blade vibration signal sequence according to the total number of sampling points and the sampling frequency of the first blade vibration signal sequence; and a second determination unit configured to determine the function period T of the first blade vibration signal sequence according to the total sampling duration and the number of function periods.

[0160] Optionally, the third calculation unit is configured to include: an execution unit, configured to remove the sampling points with a signal intensity of zero in the first blade vibration signal sequence to obtain a third blade vibration signal sequence; a fourth calculation unit, configured to calculate the average signal intensity of the third blade vibration signal sequence; a statistics unit, configured to count the number of sampling points in the third blade vibration signal sequence whose signal intensity is equal to the average signal intensity to obtain a first value; a third determination unit, configured to determine the number of function periods of the first blade vibration signal sequence according to the first value.

[0161] Optionally, the device further includes: a judgment module, configured to judge whether the signal intensity of the blade vibration signal sequence is all zero before identifying whether there is a signal jump in the blade vibration signal sequence; wherein, in the case of a signal sequence in which the signal intensity of the blade vibration signal sequence is not all zero, it is identified whether there is a signal jump in the blade vibration signal sequence.

[0162] The blade fault diagnosis device of the wind turbine generator set in the embodiment of the present application identifies whether there is a signal jump in the blade vibration signal sequence, and in the case where there is no signal jump in the blade vibration signal sequence, performs fault diagnosis on the blade of the wind turbine generator set according to the blade vibration signal sequence. In this way, a quality inspection can be performed on the blade vibration signal sequence to judge whether there is a signal jump, and fault diagnosis is performed according to the blade vibration signal sequence without signal jump, which can eliminate the interference of the signal jump of the blade vibration signal on the blade fault diagnosis.

[0163] Figure 10 The hardware structure diagram of the electronic device provided by the embodiment of the present application is shown.

[0164] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

[0165] Specifically, the above-mentioned processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0166] The memory 602 may include a mass storage for data or instructions. By way of example and not limitation, the memory 602 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. Where appropriate, the memory 602 may include removable or non-removable (or fixed) media. Where appropriate, the memory 602 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, the memory 602 is a non-volatile solid state memory.

[0167] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present application.

[0168] The processor 601 reads and executes the computer program instructions stored in the memory 602 to implement the blade fault diagnosis method of any one of the above embodiments for a wind turbine generator.

[0169] In one example, the xx device may further include a communication interface 603 and a bus 610. Among them, as Figure 3 shown, the processor 601, the memory 602, and the communication interface 603 are connected through the bus 610 and complete communication with each other.

[0170] The communication interface 603 is mainly used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present application.

[0171] The bus 610 includes hardware, software, or both, and couples the components of the online data flow metering device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel 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 buses, or a combination of two or more of these. Where appropriate, the bus 610 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0172] 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.

[0173] It should also be noted that the functional blocks shown in the above-described structural block diagrams 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 function card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform 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 capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, 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.

[0174] 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.

[0175] As described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems) and computer program products according to embodiments of the present application. It should be understood that each block in the flowchart and / or block diagram, and the combination of blocks in the flowchart and / or block diagram, 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 flowchart and / or block diagram. 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 should also be understood that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware performing the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0176] As described above, the above is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present application, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A method for diagnosing blade faults of a wind turbine generator, characterized in that, Including: Obtaining a blade vibration signal sequence collected by a vibration signal acquisition device; Identifying whether there is a signal jump in the blade vibration signal sequence; When there is no such signal jump in the blade vibration signal sequence, performing a fault diagnosis on the blade of the wind turbine according to the blade vibration signal sequence; The identifying whether there is a signal jump in the blade vibration signal sequence includes: Obtaining sampling points with a signal intensity of zero in the blade vibration signal sequence to obtain target sampling points; Calculating a first change rate between the signal intensity of the target sampling point and the signal intensity of the previous sampling point, and a second change rate between the signal intensity of the target sampling point and the signal intensity of the next sampling point; Judging whether there is a signal jump at the target sampling point according to the comparison result between the first change rate and a target threshold, and the comparison result between the second change rate and the target threshold.

2. The blade fault diagnosis method of a wind turbine according to claim 1, characterized in that The blade vibration signal sequence includes a first blade vibration signal sequence in the flapping direction and a second blade vibration signal sequence in the lead-lag direction, The identifying whether there is a signal jump in the blade vibration signal sequence includes: respectively identifying whether there is such a signal jump in the first blade vibration signal sequence and the second blade vibration signal sequence; When there is no such signal jump in the blade vibration signal sequence, performing a fault diagnosis on the blade of the wind turbine according to the blade vibration signal sequence includes: when there is no such signal jump in both the first blade vibration signal sequence and the second blade vibration signal sequence, performing a fault diagnosis on the blade of the wind turbine according to the first blade vibration signal sequence and the second blade vibration signal sequence.

3. The blade fault diagnosis method for a wind turbine according to claim 1, wherein There are n target sampling points, where n is an integer greater than 1, and the identifying whether there is a signal jump in the blade vibration signal sequence includes: Sequentially judging whether there is a signal jump at the n target sampling points; When there is such a signal jump at any one of the target sampling points, determining that there is a signal jump in the blade vibration signal sequence; Stopping judging whether there is a signal jump at the remaining target sampling points.

4. The blade fault diagnosis method for a wind turbine according to claim 1, characterized in that The blade vibration signal sequence includes a first blade vibration signal sequence in the lead-lag direction. Before judging whether there is a signal jump at the target sampling point according to the comparison result between the first change rate and the target threshold, and the comparison result between the second change rate and the target threshold, the method further includes: Determining an average change rate of the first blade vibration signal sequence; Determining the target threshold according to the average change rate.

5. The blade fault diagnosis method for a wind turbine according to claim 4, characterized in that, The first blade vibration signal sequence is a trigonometric function, and the determining the average change rate of the first blade vibration signal sequence includes: Determining a peak-to-peak value A of the first blade vibration signal sequence, where the peak-to-peak value is the difference between the maximum value and the minimum value of the first blade vibration signal sequence; Estimating a function period T of the first blade vibration signal sequence; Based on the peak-to-peak value A and the function period T, obtain the average change rate of the first blade vibration signal sequence in the trigonometric function 6. The blade fault diagnosis method of a wind turbine according to claim 5, characterized in that, The estimating the function period T of the first blade vibration signal sequence includes: Estimating the number of function periods of the first blade vibration signal sequence; Determine the total sampling duration of the first blade vibration signal sequence according to the total number of sampling points and the sampling frequency of the first blade vibration signal sequence; Determine the function period T of the first blade vibration signal sequence according to the total sampling duration and the number of function periods.

7. The blade fault diagnosis method for a wind turbine according to claim 6, wherein The estimating the number of function periods of the first blade vibration signal sequence includes: Remove the sampling points with a signal intensity of zero value from the first blade vibration signal sequence to obtain a third blade vibration signal sequence; Calculate the average signal intensity of the third blade vibration signal sequence; Count the number of sampling points in the third blade vibration signal sequence whose signal intensity is equal to the average signal intensity to obtain a first value; Determine the number of function periods of the first blade vibration signal sequence according to the first value.

8. The blade fault diagnosis method for a wind turbine according to any one of claims 1 to 7, characterized in that, Before identifying whether there is a signal jump in the blade vibration signal sequence, the method further includes: Judge whether the signal intensity of the blade vibration signal sequence is all zero value; Wherein, in the case of a signal sequence where the signal intensity of the blade vibration signal sequence is not all zero value, identify whether there is a signal jump in the blade vibration signal sequence.

9. A blade fault diagnosis device for a wind turbine generator, characterized in that, The device includes: An acquisition module, configured to acquire a blade vibration signal sequence acquired by a vibration signal acquisition device; An identification module, configured to identify whether there is a signal jump in the blade vibration signal sequence; A diagnosis module, configured to perform a fault diagnosis on the blade of the wind turbine according to the blade vibration signal sequence when there is no signal jump in the blade vibration signal sequence; The identification module includes: An acquisition unit, configured to acquire sampling points with a signal intensity of zero value in the blade vibration signal sequence to obtain target sampling points; A first calculation unit, configured to calculate a first change rate between the signal intensity of the target sampling point and the signal intensity of the previous sampling point, and a second change rate between the signal intensity of the target sampling point and the signal intensity of the next sampling point; A judgment unit, configured to judge whether there is a signal jump at the target sampling point according to the comparison result between the first change rate and a target threshold, and the comparison result between the second change rate and the target threshold.

10. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for fault diagnosis of the blade of the wind turbine as described in any one of claims 1-8 is implemented.

11. A computer storage medium, characterized in that, Computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by the processor, the method for fault diagnosis of the blade of the wind turbine as described in any one of claims 1-8 is implemented.

Images