Vibration Monitoring Method, Device, Equipment and Medium for Wind Turbine Generator

Abstract

The present invention discloses a vibration monitoring method, device, equipment and medium for a wind turbine generator set. Among them, the vibration monitoring method for the wind turbine generator set includes: obtaining detection data of a target wind turbine generator set among a plurality of wind turbine generator sets within a preset time period, where the detection data includes unit vibration data and unit operation data; performing vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set; obtaining a plurality of preset parameter thresholds, where one preset parameter threshold corresponds to one vibration evaluation parameter; in the case that there is a first target parameter among the plurality of vibration evaluation parameters, sending a first type of early warning information to the target wind turbine generator set, where the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold. According to the embodiments of the present invention, it is possible to perform vibration monitoring on the wind turbine generator set in real time, so as to perform control protection and control optimization on the wind turbine generator set in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and particularly relates to a vibration monitoring method, device, equipment and medium for a wind turbine generator set. Background Art

[0002] A wind turbine generator set is a moving system that is in an aerodynamic and mechanical dynamic state for a long time. Therefore, the vibration of the unit is inevitable and occurs at all times. The vibration of the unit will affect the reliability and stability of the operation of the main components of the wind turbine generator set. Therefore, in order to enable the wind turbine generator set to operate safely, stably, in a long cycle and at full load, it is necessary to timely understand the vibration state of the wind turbine generator set so as to timely control the operation conditions of the wind turbine generator set with uncertain periods and continuously changing loads.

[0003] In the related art, generally, the vibration state of the wind turbine generator set is analyzed by using off-line vibration data, and thus the analysis result cannot be used to perform real-time control protection and control optimization on the wind turbine generator set. Summary of the Invention

[0004] The embodiments of the present invention provide a vibration monitoring method, device, equipment and medium for a wind turbine generator set, which can perform real-time vibration monitoring on the wind turbine generator set so as to perform real-time control protection and control optimization on the wind turbine generator set.

[0005] In a first aspect, the embodiments of the present invention provide a vibration monitoring method for a wind turbine generator set, including:

[0006] Obtaining detection data of a target wind turbine generator set among a plurality of wind turbine generator sets within a preset time period; wherein the detection data includes unit vibration data and unit operation data;

[0007] Performing vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set;

[0008] Obtaining a plurality of preset parameter thresholds; wherein one preset parameter threshold corresponds to one vibration evaluation parameter;

[0009] In the case that a first target parameter exists among the plurality of vibration evaluation parameters, sending a first type of early warning information to the target wind turbine generator set; wherein the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold.

[0010] In a second aspect, the embodiments of the present invention provide a vibration monitoring device for a wind turbine generator set, including:

[0011] A first obtaining module, configured to obtain detection data of a target wind turbine generator set among a plurality of wind turbine generator sets within a preset time period; wherein the detection data includes unit vibration data and unit operation data;

[0012] A first analysis module, configured to perform vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set;

[0013] A second acquisition module, configured to acquire a plurality of preset parameter thresholds; wherein, one preset parameter threshold corresponds to one vibration evaluation parameter;

[0014] A first sending module, configured to send a first type of warning information to the target wind turbine generator set when there is a first target parameter among the plurality of vibration evaluation parameters; wherein, the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold.

[0015] In a third aspect, an embodiment of the present invention provides a vibration monitoring device for a wind turbine generator set, including:

[0016] A processor;

[0017] A memory storing a computer program, which when executed by the processor, implements the vibration monitoring method for the wind turbine generator set as described in the first aspect.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by the processor, the vibration monitoring method for the wind turbine generator set as described in the first aspect is implemented.

[0019] The vibration monitoring method, device, equipment and medium for the wind turbine generator set according to the embodiments of the present invention can, during the operation of the target wind turbine generator set, acquire the detection data of the target wind turbine generator set within a preset time period at each preset time period, and perform vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set, thereby performing real-time vibration monitoring on the target wind turbine generator set. At the same time, when it is detected that there is a first target parameter among the plurality of vibration evaluation parameters that is greater than the corresponding preset parameter threshold, a first type of warning information can be sent to the target wind turbine generator set to perform control protection and control optimization on the wind turbine generator set in real time. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a schematic structural diagram of a vibration monitoring system for a wind turbine generator set provided by an embodiment of the present invention;

[0022] Figure 2 It is a schematic structural diagram of a vibration monitoring system for a wind turbine provided by another embodiment of the present invention;

[0023] Figure 3 It is a schematic flow diagram of a vibration monitoring method for a wind turbine provided by an embodiment of the present invention;

[0024] Figure 4 It is a schematic flow diagram of a frequency domain analysis process provided by an embodiment of the present invention;

[0025] Figure 5 It is a schematic flow diagram of a vibration monitoring control process provided by an embodiment of the present invention;

[0026] Figure 6 It is a schematic structural diagram of a vibration monitoring device for a wind turbine provided by an embodiment of the present invention;

[0027] Figure 7 It is a schematic structural diagram of a vibration monitoring device for a wind turbine provided by an embodiment of the present invention. Detailed implementation manners

[0028] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. To make the objectives, technical solutions and advantages of the present invention clearer, the present invention 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 configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without some of these specific details. The following description of the embodiments is only provided to provide a better understanding of the present invention by showing examples of the present invention.

[0029] 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 "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the said elements.

[0030] A wind turbine generator is a moving system that is in an aerodynamic and mechanical dynamic state for a long time. Therefore, the vibration of the unit is inevitable and occurs at all times. The vibration of the unit will affect the reliability and stability of the operation of the main components of the wind turbine generator. Therefore, in order to enable the wind turbine generator to operate safely, stably, in a long cycle, and at full load, it is necessary to timely understand the vibration state of the wind turbine generator to timely control the operating conditions of the wind turbine generator with indefinite cycles and continuously changing loads.

[0031] In the related art, limited by the operating resources such as the central processing unit (CPU), memory, and storage of the programmable logic controller (PLC) of the main controller of the wind turbine generator, it is difficult to perform high-frequency operations on a large amount of unit vibration data in real time. Therefore, the main controller of the wind turbine generator generally communicates with a cloud server, and an experienced expert analyzes the unit vibration data and analyzes the historical vibration trend of the wind turbine generator on the cloud server side.

[0032] Due to the consideration of wind farm network security, the unit vibration data generally needs to be collected manually at regular intervals after authorization. The cloud server can only analyze the vibration state of the wind turbine generator by using the offline vibration data collected manually. Therefore, there is a certain lag in the time analysis of the cloud server, which not only increases the labor cost of data collection and data analysis, but also cannot use the analysis results to perform control protection and control optimization on the wind turbine generator in real time.

[0033] At the same time, with the continuous expansion of the scale of the wind farm, the wind turbine generators in the wind farm can generate a large amount of unit vibration data. Limited by the transmission and storage costs, the cloud server is difficult to store the high-sampling data of the main controller of the wind turbine generator every 20 ms in large quantities. If methods such as regular collection or reduction of the sampling frequency are adopted, for the evaluation of unit vibration, some key vibration information may be lost. Although an experienced expert can judge certain vibration state changes and potential faults of the wind turbine generator from the changes in the unit vibration data with some key vibration information lost, there are also cases where the unit vibration data is incomplete due to the loss of some key vibration information, and the potential faults of the wind turbine generator cannot be found, resulting in low reliability of the vibration monitoring of the wind turbine generator.

[0034] To solve the above problems, the embodiment of the present invention provides a vibration monitoring system for a wind turbine generator, which can monitor the vibration of the wind turbine generator in real time, and perform control protection and control optimization on the wind turbine generator in real time, so as to provide a new way to improve the stability and power generation of the wind turbine generator, improve the data utilization level, and enhance the economic benefits.

[0035] Figure 1 The structural schematic diagram of the vibration monitoring system of a wind turbine provided by an embodiment of the present invention is shown.

[0036] As Figure 1 shown, the vibration monitoring system of the wind turbine includes at least the main controller 110 of one wind turbine, a wind farm controller (Wind Farm Controller, WFC) 120, and a supervisory control and data acquisition system (Supervisory Control And Data Acquisition, SCADA) 130.

[0037] Among them, the WFC 120 may include a database 121, a decision module (Decision Module, DM) 122, and a human machine interface (Human Machine Interface, HMI) 123.

[0038] Each main controller 110 communicates with the WFC 120 respectively through a pre-set network protocol, so as to send the corresponding unit vibration data and unit operation data of the wind turbine it obtains to the database 121 of the WFC 120 for storage.

[0039] The DM 122 of the WFC 120 may first obtain the unit vibration data and unit operation data of any wind turbine in the wind farm within a preset time period from the data stored in the database 121. Then, the DM 122 may perform vibration analysis on the unit vibration data and unit operation data to obtain a plurality of vibration evaluation parameters corresponding to the wind turbine. Next, the DM 122 may obtain the preset parameter thresholds corresponding to each vibration evaluation parameter from the database 121, and compare each vibration evaluation parameter with the corresponding preset parameter threshold respectively to obtain a comparison result. Finally, if the comparison result is that there is a vibration evaluation parameter greater than the corresponding preset parameter threshold among the plurality of vibration evaluation parameters corresponding to the wind turbine, it may be determined that the wind turbine has abnormal vibration, and a first type of early warning information is sent to the main controller 110 of the wind turbine.

[0040] At the same time, during the operation of the WFC 120, the management personnel may monitor the vibration monitoring process of the WFC 120 through the HMI 123 of the WFC 120, and the management personnel may also manually modify each parameter, threshold, etc. of the WFC 120 through the HMI 123.

[0041] In addition, the WFC 120 can also communicate with the SCADA 130, and send the vibration data and operation data of the wind turbine generator set, the vibration analysis results and warning information to the SCADA 130 for storage. Each wind turbine generator set can also communicate with the SCADA 130 respectively, and send its operation data and operation log to the SCADA 130 for storage.

[0042] Thus, Figure 1 For the system shown, real-time vibration monitoring of each wind turbine generator set in the wind farm can be achieved through the WFC 120. And when it is determined that a vibration anomaly occurs in the wind turbine generator set, a warning message is sent to the main controller 110 of the wind turbine generator set in real time, so that the main controller 110 of the wind turbine generator set can perform control and protection on the wind turbine generator set in real time.

[0043] Figure 2 The structural schematic diagram of the vibration monitoring system of the wind turbine generator set provided by another embodiment of the present invention is shown.

[0044] As Figure 2 shown, the vibration monitoring system of the wind turbine generator set includes at least the main controller 110 of one wind turbine generator set, the WFC 120, the SCADA 130 and the cloud server 140.

[0045] Among them, the main controller 110, the WFC 120 and the SCADA 130 have Figure 1 similar functions to those in the embodiment shown, which will not be elaborated here.

[0046] The database 121 of the WFC 120 can also receive and store the vibration characteristic data of the wind turbine generator sets with the same configuration as those in the wind farm within the wind farm from other wind farms sent by the cloud server 140. The DM 122 of the WFC120 can also obtain the vibration characteristic data corresponding to the wind turbine generator set being monitored from the database 121, and use the vibration data and operation data of the wind turbine generator set being monitored and the obtained vibration characteristic data to make a transportation decision to determine the predicted value of the vibration parameters of the wind turbine generator set, and use the predicted value of the vibration parameters as the vibration evaluation parameter. Then, the DM 122 can also obtain the preset parameter threshold corresponding to each vibration evaluation parameter from the database 121, and compare each vibration evaluation parameter with the corresponding preset parameter threshold respectively to obtain a comparison result. Finally, if the comparison result shows that there is a vibration evaluation parameter greater than the corresponding preset parameter threshold among the multiple vibration evaluation parameters corresponding to the wind turbine generator set, it can be determined that the wind turbine generator set has a vibration anomaly, and a first type of warning message is sent to the main controller 110 of the wind turbine generator set.

[0047] In addition, the WFC 120 can also send the vibration data, operation data of the wind turbine generator set, vibration analysis results and warning information to the cloud server 140 for storage. The SCADA 130 can also communicate with the cloud server 140 for data interaction.

[0048] Thus, Figure 2 For the system shown, the vibration diagnosis, warning and control of the wind turbine generator set can be carried out by the cooperation of the WFC 120 and the cloud server 140. It can not only judge the current vibration situation of the wind turbine generator set in real time, but also reliably predict the future vibration trend of the wind turbine generator set, so as to better prevent the occurrence of vibration faults in the wind turbine generator set.

[0049] Regarding Figure 1 and Figure 2 For the system shown, the embodiments of the present invention provide a vibration monitoring method, device, equipment and medium for a wind turbine generator set. First, the vibration monitoring method for a wind turbine generator set provided by the embodiments of the present invention will be introduced below.

[0050] Figure 3 The flowchart of the vibration monitoring method for a wind turbine generator set provided by an embodiment of the present invention is shown.

[0051] In some embodiments of the present invention, Figure 3 The method shown can be executed by the DM122 of the Figure 1 and Figure 2 shown in the WFC 120.

[0052] As Figure 3 shown, the vibration monitoring method for the wind turbine generator set may include the following steps.

[0053] S310. Obtain the detection data of the target wind turbine generator set among multiple wind turbine generator sets within a preset time period.

[0054] Among them, the detection data includes the vibration data and operation data of the unit.

[0055] In some embodiments, the vibration data of the unit may include the vibration acceleration in the X direction before and after the nacelle and the vibration acceleration in the Y direction left and right of the nacelle.

[0056] Optionally, the vibration data of the unit may further include the vibration acceleration in the X direction of the blade and the vibration acceleration in the Y direction of the blade.

[0057] In some other embodiments, the operating data of the wind turbine unit may include the rotational speed of the first generator, the rotational speed of the second generator, and the rotational speed of the impeller. Among them, the rotational speed of the first generator can be determined according to the generator voltage, and the rotational speed of the second generator can be determined according to the generator current. Specifically, the rotational speed of the first generator can be determined according to the corresponding relationship between the generator voltage and the rotational speed, and the rotational speed of the second generator can be determined according to the corresponding relationship between the generator current and the rotational speed.

[0058] Optionally, the operating data of the wind turbine unit may further include the operating state of the wind turbine unit, the wind alignment deviation of the wind turbine unit, the power of the wind turbine unit, and the pitch angle of the wind turbine unit.

[0059] Optionally, the operating data of the wind turbine unit may further include a hydraulic cylinder signal.

[0060] In some embodiments of the present invention, the multiple wind turbine units may be bindable wind turbine units in a wind farm, and the target wind turbine unit may be any bindable wind turbine unit. Among them, the bindable wind turbine unit is a wind turbine unit in the wind farm that is in normal communication with the DM and is in a normal operating state.

[0061] Optionally, before S310, the vibration monitoring method of the wind turbine unit may further include: First, obtain the number of bindable wind turbine units in the wind farm and the unit identifier of each bindable wind turbine unit. Then, establish bindable wind turbine unit index information according to the number of bindable wind turbine units and the unit identifier. Finally, sequentially use each bindable wind turbine unit as the target wind turbine unit according to the arrangement order of the bindable wind turbine unit index information.

[0062] Therefore, the DM can avoid analyzing and processing the detection data for wind turbine units in the wind farm that may not be suitable for vibration diagnosis due to factors such as communication loss and unit routine maintenance, reduce the data processing volume of the DM, and improve the data processing efficiency of the DM. In some embodiments of the present invention, the preset time period can be set as needed. For example, the preset time period can be 1 hour, 12 hours, 1 day, or 1 week, and no limitation is made here.

[0063] S320. Perform vibration analysis on the detection data to obtain multiple vibration evaluation parameters corresponding to the target wind turbine unit.

[0064] Specifically, the DM can perform vibration analysis and diagnosis on the obtained detection data. For example, perform time-domain analysis and frequency-domain analysis on the vibration under different operating states of the unit (such as standby state, maintenance state, start-up process state, shutdown process state, power generation state, etc.). For another example, perform correlation analysis on the vibration under different operating states of the unit, and then obtain multiple vibration evaluation parameters corresponding to the target wind turbine unit.

[0065] Among them, the vibration analysis of the detection data will be described in detail below.

[0066] In some embodiments of the present invention, after S310 and before S320, the vibration monitoring method of the wind turbine may further include: screening, grouping, and cleaning the detection data.

[0067] Specifically, the operating state of the unit within a preset time period can be screened, and then according to different operating states of the unit, the detection data within the preset time period can be grouped, and the inappropriate detection data can be cleaned. For example, when the operating state of the unit is the standby state, the detection data with too short time, too many missing time series, or abnormal values can be cleaned.

[0068] Thus, vibration analysis can be performed on the cleaned detection data to obtain multiple vibration evaluation parameters corresponding to the target wind turbine.

[0069] S330. Obtain multiple preset parameter thresholds.

[0070] Among them, one preset parameter threshold corresponds to one vibration evaluation parameter, that is, the preset parameter threshold and the vibration evaluation parameter are in a one-to-one correspondence relationship.

[0071] In the embodiments of the present invention, the multiple preset parameter thresholds can be pre-set fixed values, or can be dynamic values determined according to the historical detection data of multiple wind turbines in the wind farm to which the target wind turbine belongs, or can be dynamic values determined according to the historical detection data of multiple wind turbines in multiple wind farms, where the multiple wind farms include the wind farm to which the target wind turbine belongs and other wind farms outside this wind farm.

[0072] In some embodiments of the present invention, the vibration evaluation parameter may include at least one of a time-domain amplitude, a frequency-domain amplitude, and a vibration parameter prediction value. The vibration parameter prediction value can be, for example, a time-domain amplitude prediction value. Correspondingly, the preset parameter threshold may include at least one of a time-domain amplitude threshold corresponding to the time-domain amplitude, a frequency-domain amplitude threshold corresponding to the frequency-domain amplitude, and a vibration parameter prediction value threshold.

[0073] It should be noted that in order to improve the accuracy of vibration monitoring, since the detection data under different operating states of the unit may vary greatly, therefore, in some embodiments of the present invention, the same vibration evaluation parameter under different operating states of the unit can correspond to different preset parameter thresholds. That is, in some embodiments of the present invention, one preset parameter threshold can correspond to one vibration evaluation parameter under one operating state of the unit.

[0074] S340. When there is a first target parameter among multiple vibration evaluation parameters, send a first type of warning message to the target wind turbine generator; wherein, the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold.

[0075] In the embodiments of the present invention, each vibration evaluation parameter can be compared with the corresponding preset parameter threshold respectively to determine whether there is a first target parameter greater than the corresponding preset parameter threshold among the vibration evaluation parameters. If there is, it indicates that the target wind turbine generator has abnormal vibration, and a first type of warning message should be generated and sent to the main controller of the target wind turbine generator so that the target wind turbine generator can perform unit protection control according to the first type of warning message; if not, it indicates that the target wind turbine generator has no abnormal vibration and there is no need to generate a first type of warning message.

[0076] Among them, the first type of warning message can be used to indicate that the target wind turbine generator is diagnosed as having abnormal vibration during the single-unit vibration diagnosis process.

[0077] In some embodiments of the present invention, after S340, the vibration monitoring method of the wind turbine generator can further include: storing the first type of warning message in the database of the WFC to record the warning message; displaying the first type of warning message on the HMI interface of the WFC so that the management personnel can monitor the vibration monitoring process; and pushing the first type of warning message to the SCADA for storage to record the warning message.

[0078] In other embodiments of the present invention, when the WFC communicates with the cloud server, after S340, the vibration monitoring method of the wind turbine generator can further include: pushing the detection data and the first type of warning message of the target wind turbine generator to the cloud server for storage to record the detection data and warning message of the target wind turbine generator, and then it can be applied to the vibration monitoring of other wind turbine generators.

[0079] In summary, in the embodiments of the present invention, the DM of the WFC can obtain the detection data of the target wind turbine generator within each preset time period during the operation of the target wind turbine generator, perform vibration analysis on the detection data to obtain multiple vibration evaluation parameters corresponding to the target wind turbine generator, and then monitor the vibration of the target wind turbine generator in real time. At the same time, when it is detected that there is a first target parameter greater than the corresponding preset parameter threshold among the multiple vibration evaluation parameters, it can send a first type of warning message to the target wind turbine generator to perform control protection and control optimization on the wind turbine generator in real time.

[0080] In some embodiments of the present invention, S320 may specifically include at least one of the following:

[0081] Perform time-domain analysis on the vibration data of the unit to obtain the time-domain amplitude of the target wind turbine generator set, and use the time-domain amplitude as the vibration evaluation parameter;

[0082] Perform frequency-domain analysis on the vibration data of the unit according to the unit operation data to obtain the frequency-domain amplitude of the target wind turbine generator set, and use the frequency-domain amplitude as the vibration evaluation parameter;

[0083] Perform correlation analysis on the vibration data of the unit to obtain the principal components of the generalized eigenvalues of the target wind turbine generator set, and use the principal components of the generalized eigenvalues as the vibration evaluation parameter.

[0084] In these embodiments, optionally, the vibration data of the unit may include the vibration acceleration in the X direction before and after the nacelle and the vibration acceleration in the Y direction left and right of the nacelle, and the unit operation data may include the first generator speed, the second generator speed, and the impeller speed.

[0085] In these embodiments, optionally, the time-domain amplitude may include the time-domain amplitude in the X direction and the time-domain amplitude in the Y direction, and the frequency-domain amplitude may include the frequency-domain amplitude in the X direction and the frequency-domain amplitude in the Y direction. Correspondingly, the preset parameter thresholds may include the time-domain amplitude threshold in the X direction corresponding to the time-domain amplitude in the X direction, the time-domain amplitude threshold in the Y direction corresponding to the time-domain amplitude in the Y direction, the frequency-domain amplitude threshold in the X direction corresponding to the frequency-domain amplitude in the X direction, and the frequency-domain amplitude threshold in the Y direction corresponding to the frequency-domain amplitude in the Y direction.

[0086] Since before S320, DM has screened, grouped, and cleaned the detection data, DM can determine the unit operation status that needs to be analyzed next based on the effective grouped data after cleaning, and analyze the vibration evaluation parameters under different unit operation statuses of the target wind turbine generator set.

[0087] Next, the above-mentioned various vibration analysis methods will be described.

[0088] In some embodiments, DM can perform time-domain analysis on the vibration data of the unit to obtain the time-domain amplitude of the target wind turbine generator set. The time-domain amplitude may be the maximum value of the time-domain amplitude, that is, DM can obtain the maximum value of the time-domain amplitude in the X direction and the maximum value of the time-domain amplitude in the Y direction, and use the maximum value of the time-domain amplitude in the X direction and the maximum value of the time-domain amplitude in the Y direction as the vibration evaluation parameters respectively.

[0089] In some other embodiments, DM can perform statistical classification on the effective grouped data to obtain vibration state characteristics, and then perform eigen-decomposition on the vibration state characteristics through a machine learning algorithm to obtain generalized eigenvalues, and further determine the principal components of the generalized eigenvalues among the generalized eigenvalues.

[0090] In some other embodiments, the DM can also perform frequency-domain analysis on the valid packet data. Next, reference will be made to Figure 4 for a detailed description.

[0091] Figure 4 Fig. shows a schematic flowchart of the frequency-domain analysis process provided by an embodiment of the present invention.

[0092] S401. Perform spectrum analysis on the detection data respectively.

[0093] Considering that the cabin vibration signal generally comes from the accelerometer, and there will be a phenomenon of modal frequency information being submerged when the unit operates in some states. Therefore, in addition to the cabin vibration signals such as the cabin vibration acceleration in the X direction and the cabin vibration acceleration in the Y direction, other unit signals with different measurement principles but also containing the unit modal frequency information can be introduced for auxiliary frequency identification and synthesis, such as the first generator speed, the second generator speed, and the impeller speed.

[0094] Thus, spectrum analysis can be performed on the cabin vibration acceleration in the X direction, the cabin vibration acceleration in the Y direction, the first generator speed, the second generator speed, and the impeller speed respectively.

[0095] In some embodiments of the present invention, the impeller speed can be obtained by a mechanical sensor, a proximity switch, or an encoder.

[0096] S402. Compare the above analysis results with the main simulation modal frequencies of the unit respectively to identify the actual modal frequencies with obvious on-site characteristics reflected in the cabin vibration signal, and obtain the maximum X-direction frequency-domain amplitude value and the maximum Y-direction frequency-domain amplitude value at the actual modal frequency. Furthermore, the maximum X-direction frequency-domain amplitude value and the maximum Y-direction frequency-domain amplitude value at the actual modal frequency are respectively used as the vibration evaluation parameters at the actual modal frequency. Among them, the modal frequencies can include: the first-order frequency of the tower, the second-order frequency of the tower, the first-order in-plane frequency of the blade, the second-order in-plane frequency of the blade, the third-order in-plane frequency of the blade, the unit rotation frequency 1P, the unit rotation frequency 3P, the unit rotation frequency 6P, the fundamental frequency of the generator, the second harmonic of the generator fundamental frequency, the stator frequency of the generator, and the rotor vibration mode frequency of the generator, etc.

[0097] It should be noted that in order to improve the accuracy of vibration monitoring, since the detection data at different modal frequencies may vary greatly, in some embodiments of the present invention, different actual modal frequencies may correspond to different preset parameter thresholds.

[0098] In the embodiments of the present invention, optionally, the unit vibration data may further include the blade vibration acceleration in the X direction and the blade vibration acceleration in the Y direction, and the unit operation data may further include the hydraulic cylinder signal.

[0099] Therefore, when performing spectral analysis on the detection data respectively, spectral analysis can also be performed on the vibration acceleration in the X direction of the blade, the vibration acceleration in the Y direction of the blade, and the hydraulic cylinder signal to increase the reference mode.

[0100] In some embodiments of the present invention, the vibration source type of the target wind turbine generator can be directly determined, and the first type of warning information can be generated according to the vibration source type, so that the main controller of the target wind turbine generator can independently determine the unit protection control strategy according to the first type of warning information.

[0101] In some other embodiments of the present invention, in order to enable the main controller of the wind turbine generator to better control and protect the wind turbine generator, the first type of warning information can also carry control information for the main controller to perform unit protection control. Optionally, before S340, the vibration monitoring method of the wind turbine generator may further include:

[0102] Determine the vibration source type of the target wind turbine generator according to the first target parameter;

[0103] Generate target control information according to the vibration source type;

[0104] Generate the first type of warning information according to the target control information.

[0105] In some embodiments of the present invention, taking the first target parameter as the frequency domain amplitude as an example, in the case where the first target parameter is the frequency domain amplitude, since the DM has determined the actual modal frequency with obvious on-site characteristics reflected in the nacelle vibration signal, that is, the vibration source type corresponding to the actual modal frequency can be used as the vibration source type of the target wind turbine generator. For example, if the actual modal frequency is the first-order frequency of the tower or the second-order frequency of the tower, the vibration source type can be the tower. For another example, if the actual modal frequency is the first-order in-plane frequency of the blade, the second-order in-plane frequency of the blade, or the third-order in-plane frequency of the blade, the vibration source type can be the blade. For another example, if the actual modal frequency is the unit rotation frequency 1P, the unit rotation frequency 3P, or the unit rotation frequency 6P, the vibration source type can be the rotation frequency. For another example, if the actual modal frequency is the fundamental frequency of the generator, the second harmonic of the generator fundamental frequency, the stator frequency of the generator, or the rotor vibration mode frequency of the generator, the vibration source type can be the generator.

[0106] In some embodiments of the present invention, the DM can determine the specific vibration source of the target wind turbine according to the type of vibration source, and use the specific vibration source to determine the vibration type to which the target wind turbine belongs. Specifically, according to different specific vibration sources, the vibration types of the target wind turbine can be divided into four categories: input type, design type, control type, and subsystem type. For example, if the vibration source type is the generator, and the specific vibration source determined by the DM is the generator stall caused by wind conditions, wind direction, and icing, the vibration type can be the input type. For another example, if the vibration source type is the tower or the blade, and the specific vibration sources determined by the DM are the first-order frequency of the tower, the second-order frequency of the tower, the first in-plane of the blade, the second in-plane of the blade, or the third in-plane of the blade, the vibration type can be the design type. For yet another example, if the vibration source type is the rotational frequency or the generator, and the specific vibration source determined by the DM is the rotational frequency or the generator operation error caused by logical errors, parameter errors, or function block activation errors, etc., the vibration type can be the control type. For yet another example, if the vibration source type is the tower or the blade, and the specific vibration sources determined by the DM are the damage, cracking, or imbalance of the tower or the blade, the vibration type can be the subsystem type.

[0107] In some embodiments of the present invention, the DM can determine a specific unit protection strategy according to the vibration type to which the target wind turbine belongs, and generate target control information corresponding to this vibration type to suppress or eliminate the related abnormal vibration of the target wind turbine. For example, if the vibration type is the input type, the DM can generate target control information such as power limit, speed limit, pitch angle limit, shutdown command, etc. For another example, if the vibration type is the control type, the DM can generate target control information carrying preset control parameters, where the preset control parameters can include proportional-integral (PI) parameters, cut-in speed, rated speed, and filter parameters. The preset control parameters can also be used to turn off the control function that causes abnormal vibration, adjust the overspeed range that causes abnormal vibration, and trigger parameters, etc.

[0108] In still some other embodiments of the present invention, in order to enable the main controller of the wind turbine to better control and protect the wind turbine, control information can also be generated according to different vibration warning levels. Optionally, before S340, the vibration monitoring method of this wind turbine can further include:

[0109] Determine the vibration source type and vibration warning level of the target wind turbine according to the first target parameter;

[0110] Generate target control information according to the vibration source type and vibration warning level;

[0111] Generate the first type of warning information according to the target control information.

[0112] In some embodiments of the present invention, the DM may determine the vibration warning level of the target wind turbine according to the degree to which the first target parameter exceeds the corresponding preset parameter threshold. The higher the degree to which the first target parameter exceeds the corresponding preset parameter threshold, the higher the vibration warning level of the target wind turbine. Different vibration warning levels are combined with control strategies corresponding to different vibration source types to generate different target control information.

[0113] Taking the vibration type as the input class as an example, from low to high vibration warning levels, target control information for power limitation, speed limitation, pitch angle limitation, and shutdown commands can be generated respectively. For example, if the vibration warning level is level one, the target control information can be generated according to the power limit value. For another example, if the vibration warning level is level two, the target control information can be generated according to the speed limit value. For yet another example, if the vibration warning level is level three, the target control information can be generated according to the pitch angle limit value. For still another example, if the vibration warning level is level four, the target control information can be generated according to the shutdown command.

[0114] In some other embodiments of the present invention, the DM may also generate a first type of warning information according to the target control information and the vibration warning level, so that the first type of warning information carries the target control information and the vibration warning level, which is not limited here.

[0115] In another implementation manner of the present invention, if it is determined that the target wind turbine is not diagnosed as having abnormal vibration during the single-machine vibration diagnosis, but it can still be further determined whether the target wind turbine has abnormal vibration relative to other wind turbines in the wind farm to improve the power generation reliability of the wind farm. Therefore, after S330, the vibration monitoring method of the wind turbine may further include:

[0116] In the case where the first target parameter does not exist among multiple vibration evaluation parameters, determine the upper limits of the multiple vibration evaluation parameters corresponding to multiple wind turbines; wherein, one upper limit of a vibration evaluation parameter corresponds to one vibration evaluation parameter.

[0117] In the case where a second target parameter exists among multiple vibration evaluation parameters, send a second type of warning information to the target wind turbine; wherein, the second target parameter is a vibration evaluation parameter greater than the corresponding upper limit of the vibration evaluation parameter.

[0118] Specifically, if the DM determines that there is no first target parameter among multiple vibration evaluation parameters, it can be determined that the target wind turbine generator set is not diagnosed as having abnormal vibration during the single-unit vibration diagnosis. Furthermore, the DM can determine the upper limit of each vibration evaluation parameter with respect to the vibration evaluation parameters of multiple wind turbine generator sets. Then, the DM compares each vibration evaluation parameter with the corresponding upper limit of the vibration evaluation parameter to determine whether there is a second target parameter in the vibration evaluation parameters that is greater than the corresponding upper limit of the vibration evaluation parameter. If there is, it indicates that the target wind turbine generator set has abnormal vibration relative to other wind turbine generator sets, and a second type of warning information should be generated and sent to the main controller of the target wind turbine generator set so that the target wind turbine generator set can perform unit protection control based on the second type of warning information. If not, it indicates that the target wind turbine generator set has no abnormal vibration relative to other wind turbine generator sets, and there is no need to generate the second type of warning information.

[0119] In some embodiments of the present invention, the same vibration evaluation parameter under different unit operating states can correspond to different upper limits of the vibration evaluation parameter. That is, in some embodiments of the present invention, an upper limit of a vibration evaluation parameter can correspond to a vibration evaluation parameter under a unit operating state.

[0120] In other embodiments of the present invention, different actual modal frequencies can correspond to different upper limits of the vibration evaluation parameter.

[0121] In some embodiments of the present invention, the upper limits of the vibration evaluation parameters corresponding to multiple wind turbine generator sets can be respectively preset fixed values.

[0122] In other embodiments of the present invention, the upper limits of the vibration evaluation parameters corresponding to multiple wind turbine generator sets can also be dynamic values determined based on the vibration evaluation parameters of multiple wind turbine generator sets in the wind farm. For example, the upper limit value of the time-domain amplitude and the dynamic value of the upper limit value of the frequency-domain amplitude determined according to the time-domain amplitude and the frequency-domain amplitude of the vibration of the bindable wind turbine generator sets in the wind farm.

[0123] In some embodiments, the vibration evaluation parameter limit can be determined according to the quartile method. Therefore, the quartile method can calculate the maximum estimated value (i.e., the upper limit value) among the multiple vibration evaluation parameters corresponding to multiple wind turbine generator sets, and thus the vibration evaluation parameters outside the range of the maximum estimated value may be outliers.

[0124] Taking the calculation of the upper limit value of the X-direction time-domain amplitude in the time-domain amplitude of vibration as an example, first, after removing the zero drift from the collected X-direction time-domain amplitude, the X-direction time-domain amplitude fluctuates up and down around 0. Then, take the absolute value of each X-direction time-domain amplitude, and calculate the lower quartile (the latter 25%) Q1 and the upper quartile (the former 25%) Q3. And set the upper limit value U_upper of the X-direction time-domain amplitude as U_upper = Q3 + k(Q3 - Q1). Thus, the upper limit value U_upper of the X-direction time-domain amplitude can be calculated.

[0125] Among them, k is an adjustment parameter. Different k values can correspond to different vibration anomaly levels. If k = 1, and there is a second target parameter in the vibration evaluation parameter that is greater than the upper limit of the corresponding vibration evaluation parameter, it indicates that the target wind turbine has a mild vibration anomaly relative to other wind turbines. If k = 1.5, and there is a second target parameter in the vibration evaluation parameter that is greater than the upper limit of the corresponding vibration evaluation parameter, it indicates that the target wind turbine has a moderate vibration anomaly relative to other wind turbines. If k = 3, and there is a second target parameter in the vibration evaluation parameter that is greater than the upper limit of the corresponding vibration evaluation parameter, it indicates that the target wind turbine has an extreme vibration anomaly relative to other wind turbines.

[0126] In some other embodiments, the vibration evaluation parameter limit can also be determined according to a pre-trained parameter upper limit prediction model and a parameter lower limit prediction model. The parameter upper limit prediction model can be obtained by training a neural network.

[0127] In some embodiments of the present invention, the DM can generate a second type of warning information according to the vibration anomaly level and send the second type of warning information to the target wind turbine, so that the target wind turbine can perform unit protection control according to the second type of warning information.

[0128] In some other embodiments of the present invention, the DM can also generate a second type of warning information according to the vibration anomaly level and the optimized control parameters, and send the second type of warning information to the target wind turbine, so that the target wind turbine can adjust the unit operation parameters according to the optimized control parameters.

[0129] Among them, the DM can obtain the unit operation parameters of the wind turbine corresponding to the minimum value of the vibration evaluation parameter in the wind farm, and use the unit operation parameters of the wind turbine corresponding to the minimum value of the vibration evaluation parameter as the optimized control parameters.

[0130] In some embodiments of the present invention, the DM can also store the second type of warning information in the database of the WFC to record the warning information; display the second type of warning information in the HMI interface of the WFC so that the management personnel can monitor the vibration monitoring process; and push the second type of warning information to the SCADA for storage to record the warning information.

[0131] In some other embodiments of the present invention, when the WFC communicates with the cloud server, the DM can also push the detection data and the second type of warning information of the target wind turbine generator to the cloud server for storage to record the detection data and warning information of the target wind turbine generator, and then it can be applied to the vibration monitoring of other wind turbine generators.

[0132] In summary, in the embodiments of the present invention, the diagnosis, warning, control protection, and control parameter optimization of the vibration of the wind turbine generator can be automatically performed at the wind farm level, thereby improving the power generation reliability of the wind farm.

[0133] In another embodiment of the present invention, in order to more accurately monitor the vibration of the wind turbine generator, the vibration trend analysis can also be combined with the historical vibration data in the cloud, such as time-domain vibration trend analysis and frequency-domain vibration trend analysis, so as to be able to predict the time-domain vibration change situation and frequency-domain modal change situation under specific future wind parameters, and obtain the vibration parameter prediction value of the target wind turbine generator as the vibration evaluation parameter.

[0134] In these embodiments, optionally, the detection data can also include operating environment data. Further, the operating environment data can include wind speed, air density, and turbulence. In these embodiments, optionally, the unit vibration data can include the vibration acceleration in the X direction of the nacelle and the vibration acceleration in the Y direction of the nacelle. In these embodiments, optionally, the unit operating data can include the unit operating state, the unit wind alignment deviation, the unit power, the unit pitch angle, the first generator speed, the second generator speed, and the impeller speed.

[0135] In these embodiments, optionally, the vibration parameter prediction value can include the time-domain amplitude prediction value in the X direction, the time-domain amplitude prediction value in the Y direction, the frequency-domain amplitude prediction value in the X direction, and the frequency-domain amplitude prediction value in the Y direction.

[0136] In some embodiments of the present invention, the detection data can also include operating environment data;

[0137] In these embodiments, before S320, the vibration monitoring method of the wind turbine generator can also include:

[0138] Obtain the target vibration characteristic data sent by the cloud server; wherein, the target vibration characteristic data may be the vibration characteristic data of a wind turbine configured the same as the target wind turbine generator set;

[0139] Generate the vibration characteristic data of the target wind turbine generator set according to the detection data.

[0140] In some embodiments, the target vibration characteristic data may include the vibration characteristic data of the wind turbine generator set in multiple historical preset time periods. The vibration characteristic data in each historical preset time period is the vibration characteristic data of the wind turbine generator set corresponding to the maximum value of the vibration evaluation parameter in that preset time period. The vibration characteristic data may include the maximum value of the vibration evaluation parameter and the characteristic values such as the wind speed value, the wind alignment deviation value, the power value, the pitch angle value, the air density value, the turbulence value, the first generator speed, the second generator speed, and the impeller speed corresponding to the maximum value of the vibration evaluation parameter.

[0141] In some embodiments, the DM may perform feature extraction on the unit vibration data, the unit operation data, and the operation environment data to obtain the vibration characteristic data of the target wind turbine generator set. Specifically, the DM has screened, grouped, and cleaned the detection data. The DM may perform statistical classification on the effective grouped data to obtain the maximum value of the vibration evaluation parameter and the characteristic values such as the wind speed value, the wind alignment deviation value, the power value, the pitch angle value, the air density value, the turbulence value, the first generator speed, the second generator speed, and the impeller speed corresponding to the maximum value of the vibration evaluation parameter, and form the vibration characteristic data of the target wind turbine generator set. The vibration characteristic data of the target wind turbine generator set is a feature manifestation strongly related to the vibration of the target wind turbine generator set.

[0142] In some embodiments, the DM may obtain the target vibration characteristic data sent by the cloud server when the monitoring duration reaches the preset duration. Among them, the preset duration may include multiple preset time periods, thereby reducing the data processing volume of the DM.

[0143] In these embodiments, S320 may further include:

[0144] Perform vibration trend analysis on the vibration characteristic data according to the target vibration characteristic data to obtain the predicted value of the vibration parameter of the target wind turbine generator set;

[0145] Use the predicted value of the vibration parameter as the vibration evaluation parameter.

[0146] The DM can first train a preset neural network according to the target vibration characteristic data to obtain a parameter prediction model. Then, it acquires the vibration characteristic data of the current preset time period and the vibration characteristic data of multiple historical preset time periods of the wind turbine generator set, and inputs the acquired vibration characteristic data into the parameter prediction model for vibration trend analysis to obtain the predicted vibration parameter value of the target wind turbine generator set, and uses the predicted vibration parameter value as the vibration evaluation parameter.

[0147] Among them, both the current preset time period and the multiple historical preset time periods are time periods within a preset duration.

[0148] In these embodiments, optionally, after S320, the vibration monitoring method of the wind turbine generator set may further include:

[0149] Send the vibration characteristic data of the target wind turbine generator set to the cloud server.

[0150] Specifically, after authorization, the DM can push the vibration characteristic data of the target wind turbine generator set to the cloud server in the form of a network or a file, so that the cloud server can apply it to the vibration monitoring of other wind turbine generator sets.

[0151] In the embodiments of the present invention, since the DM pushes the vibration characteristic data of the target wind turbine generator set to the cloud server for storage, which is much less than the data volume of the detection data of the target wind turbine generator set, therefore, while providing direct and effective vibration information of the target wind turbine generator set to the cloud server, the data transmission and storage load of the cloud server is reduced.

[0152] In other embodiments of the present invention, the detection data may further include operating environment data;

[0153] Correspondingly, S320 may further include:

[0154] Generate the vibration characteristic data of the target wind turbine generator set according to the detection data;

[0155] Send the vibration characteristic data to the cloud server, so that the cloud server performs vibration trend analysis on the vibration characteristic data according to the target vibration characteristic data to obtain the predicted vibration parameter value of the target wind turbine generator set; among them, the target vibration characteristic data is the vibration characteristic data of a wind turbine generator set with the same configuration as the target wind turbine generator set;

[0156] Receive the predicted vibration parameter value fed back by the cloud server;

[0157] Use the predicted vibration parameter value as the vibration evaluation parameter.

[0158] Among them, the specific method for generating the vibration characteristic data of the target wind turbine generator has been introduced above and will not be elaborated here. The specific method for the cloud server to perform vibration trend analysis on the vibration characteristic data is similar to that of the DM for performing vibration trend analysis on the vibration characteristic data, and will not be elaborated here.

[0159] In some embodiments of the present invention, the DM can send the vibration characteristic data of each preset time period to the cloud server in real time. The cloud server can perform vibration trend analysis on the vibration characteristic data obtained within the preset time period when the monitoring duration reaches the preset duration. Since the base number of the vibration characteristic data in the cloud server is large, the accuracy of the vibration parameter prediction value can be improved.

[0160] In the embodiments of the present invention, the data processing amount of the DM can be reduced to save the resources of the DM.

[0161] Next, a specific example will be used to illustrate the overall process of the vibration monitoring method for the wind turbine generator provided in the embodiments of the present invention.

[0162] Figure 5 Fig. shows a schematic flowchart of a vibration monitoring control process provided by an embodiment of the present invention.

[0163] As Figure 5 shown, the vibration monitoring control process may include the following steps.

[0164] S501. Obtain the number of bindable wind turbine generators in the wind farm and the unit identifier of each bindable wind turbine generator, and establish bindable wind turbine generator index information according to the number of bindable wind turbine generators and the unit identifier.

[0165] S502. Obtain the vibration characteristic data of the wind turbine generators with the same configuration as the target wind turbine generator sent by the cloud server. In the case where the cloud server cannot be connected, the vibration characteristic data of each wind turbine generator with the same configuration as the target wind turbine generator stored in the database of the WFC can also be directly obtained, so as to perform vibration trend analysis using the vibration characteristic data in the database of the WFC to obtain the vibration parameter prediction value of the target wind turbine generator when the vibration characteristic data in the cloud server cannot be obtained.

[0166] S503. Sequentially use each bindable wind turbine generator as the target wind turbine generator according to the arrangement order of the bindable wind turbine generator index information, and obtain the detection data of the target wind turbine generator within the preset time period.

[0167] S504. Perform data preprocessing such as screening, grouping, and cleaning on the detection data.

[0168] S505. Perform vibration analysis on the detected data after data preprocessing to obtain multiple vibration evaluation parameters corresponding to the target wind turbine generator set.

[0169] S506. Determine whether there is a first target parameter greater than the corresponding preset parameter threshold among the multiple vibration evaluation parameters to determine whether the target wind turbine generator set has abnormal vibration. If so, execute S507; if not, execute S509.

[0170] S507. Generate a first type of warning message.

[0171] S508. Send the first type of warning message to the target wind turbine generator set, and then execute S509.

[0172] S509. Determine whether all bindable wind turbine generator sets have been traversed. If so, execute S510; if not, execute S503.

[0173] S510. When there is no first target parameter among the multiple vibration evaluation parameters corresponding to each bindable wind turbine generator set, determine the upper limits of the multiple vibration evaluation parameters corresponding to the multiple wind turbine generator sets.

[0174] S511. Determine whether there is a second target parameter greater than the corresponding vibration evaluation parameter upper limit among the multiple vibration evaluation parameters corresponding to any bindable wind turbine generator set to determine whether there is a wind turbine generator set with abnormal vibration relative to the wind farm. If so, execute S512; if not, end.

[0175] S512. Generate a second type of warning message.

[0176] S513. Send the second type of warning message to the wind turbine generator set with abnormal vibration relative to the wind farm.

[0177] In summary, in the embodiments of the present invention, by virtue of the advantages of rich computing resources at the wind farm end and the ability to efficiently connect to the main controller of the cloud server and wind turbines, the vibration states of each wind turbine in the wind farm can be monitored in real time and comprehensively, so as to better detect vibration-related problems of the wind turbines in advance. Not only can time-domain and frequency-domain analyses of vibrations be performed, but also the root causes of vibrations can be quickly located by means of correlation analysis. At the same time, trend analysis of the wind turbines can be carried out in combination with the data in the cloud server, and some common vibration problems of the wind turbines can be detected in advance. In addition, warning information can be pushed to the main controller of the wind turbine in real time to suppress or eliminate the vibration of the wind turbine in a timely manner. Further, the embodiments of the present invention can improve the stability, power generation, safety, and availability of the wind turbine through the combined application of the above strategies, thereby effectively enhancing the customer experience and the product competitiveness of the wind turbine.

[0178] Figure 6 FIG. 4 shows a schematic structural diagram of a vibration monitoring device for a wind turbine provided by an embodiment of the present invention. In some embodiments of the present invention, Figure 6 The device shown may be Figure 1 and Figure 2 the DM 122 of the WFC 120 shown in FIG.

[0179] As Figure 6 shown, the vibration monitoring device 600 for the wind turbine may include a first acquisition module 610, a first analysis module 620, a second acquisition module 630, and a first transmission module 640.

[0180] The first acquisition module 610 is configured to acquire detection data of a target wind turbine among a plurality of wind turbines within a preset time period; wherein, the detection data includes unit vibration data and unit operation data.

[0181] The first analysis module 620 is configured to perform vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine.

[0182] The second acquisition module 630 is configured to acquire a plurality of preset parameter thresholds; wherein, one preset parameter threshold corresponds to one vibration evaluation parameter.

[0183] The first transmission module 640 is configured to send a first type of warning information to the target wind turbine when there is a first target parameter among the plurality of vibration evaluation parameters; wherein, the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold.

[0184] In an embodiment of the present invention, the DM of the WFC can obtain the detection data of the target wind turbine generator set during each preset time period in the operation process of the target wind turbine generator set, and perform vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set, and then perform real-time vibration monitoring on the target wind turbine generator set. At the same time, when it is detected that there is a first target parameter greater than the corresponding preset parameter threshold among the plurality of vibration evaluation parameters, a first type of early warning information can be sent to the target wind turbine generator set to perform control protection and control optimization on the wind turbine generator set in real time.

[0185] In some embodiments of the present invention, the first analysis module 620 may specifically be used for:

[0186] Perform time-domain analysis on the vibration data of the unit to obtain the time-domain amplitude of the target wind turbine generator set, and use the time-domain amplitude as a vibration evaluation parameter; and / or,

[0187] Perform frequency-domain analysis on the vibration data of the unit according to the operation data of the unit to obtain the frequency-domain amplitude of the target wind turbine generator set, and use the frequency-domain amplitude as a vibration evaluation parameter; and / or,

[0188] Perform correlation analysis on the vibration data of the unit to obtain the generalized eigenvalue principal component of the target wind turbine generator set, and use the generalized eigenvalue principal component as a vibration evaluation parameter.

[0189] In some embodiments of the present invention, the vibration data of the unit may include the vibration acceleration in the X direction before and after the nacelle and the vibration acceleration in the Y direction left and right of the nacelle, and the operation data of the unit may include the first generator speed, the second generator speed, and the impeller speed. Among them, the first generator speed is determined according to the generator voltage, and the second generator speed is determined according to the generator current;

[0190] Among them, the time-domain amplitude may include the time-domain amplitude in the X direction and the time-domain amplitude in the Y direction, and the frequency-domain amplitude may include the frequency-domain amplitude in the X direction and the frequency-domain amplitude in the Y direction.

[0191] In some embodiments of the present invention, the detection data may further include operation environment data;

[0192] Among them, the vibration monitoring device 600 of the wind turbine generator set may further include a third acquisition module and a first generation module.

[0193] The third acquisition module is used to acquire the target vibration characteristic data sent by the cloud server; among them, the target vibration characteristic data is the vibration characteristic data of a wind turbine generator set with the same configuration as the target wind turbine generator set.

[0194] The first generation module is used to generate the vibration characteristic data of the target wind turbine generator set according to the detection data.

[0195] Accordingly, the first analysis module 620 can also be used for:

[0196] Based on the target vibration characteristic data, performing vibration trend analysis on the vibration characteristic data to obtain a predicted value of the vibration parameters of the target wind turbine generator; and using the predicted value of the vibration parameters as a vibration evaluation parameter.

[0197] In some embodiments of the present invention, the detection data may further include operating environment data;

[0198] Wherein, the first analysis module 620 can also be used for:

[0199] Generating vibration characteristic data of the target wind turbine generator according to the detection data;

[0200] Sending the vibration characteristic data to the cloud server so that the cloud server performs vibration trend analysis on the vibration characteristic data according to the target vibration characteristic data to obtain a predicted value of the vibration parameters of the target wind turbine generator; wherein, the target vibration characteristic data is the vibration characteristic data of a wind turbine generator with the same configuration as the target wind turbine generator;

[0201] Receiving the predicted value of the vibration parameters fed back by the cloud server;

[0202] Using the predicted value of the vibration parameters as a vibration evaluation parameter.

[0203] In some embodiments of the present invention, the operating environment data may include wind speed, air density, and turbulence, the unit vibration data may include the vibration acceleration in the X direction of the nacelle and the vibration acceleration in the Y direction of the nacelle, and the unit operation data may include the unit operation state, the wind alignment deviation of the unit, the unit power, the unit pitch angle, the rotational speed of the first generator, the rotational speed of the second generator, and the rotational speed of the impeller, wherein the rotational speed of the first generator is determined according to the generator voltage, and the rotational speed of the second generator is determined according to the generator current;

[0204] Wherein, the predicted value of the vibration parameters may include the predicted value of the time-domain amplitude in the X direction, the predicted value of the time-domain amplitude in the Y direction, the predicted value of the frequency-domain amplitude in the X direction, and the predicted value of the frequency-domain amplitude in the Y direction.

[0205] In some embodiments of the present invention, the vibration monitoring device 600 of the wind turbine generator may further include a second sending module, and the second sending module is used to send the vibration characteristic data to the cloud server.

[0206] In some embodiments of the present invention, the vibration monitoring device 600 of the wind turbine generator may further include a first determination module, a second generation module, and a third generation module.

[0207] The first determination module is used to determine the type of the vibration source of the target wind turbine generator according to the first target parameter.

[0208] The second generation module is used to generate target control information according to the vibration source type.

[0209] The third generation module is used to generate the first type of early warning information according to the target control information.

[0210] In some embodiments of the present invention, the vibration monitoring device 600 of the wind turbine may further include a second determination module and a third sending module.

[0211] The second determination module is used to determine the upper limits of the multiple vibration evaluation parameters corresponding to the multiple wind turbines when the first target parameter does not exist among the multiple vibration evaluation parameters; wherein, one upper limit of the vibration evaluation parameter corresponds to one vibration evaluation parameter.

[0212] The third sending module is used to send the second type of early warning information to the target wind turbine when the second target parameter exists among the multiple vibration evaluation parameters; wherein, the second target parameter is the vibration evaluation parameter greater than the corresponding upper limit of the vibration evaluation parameter.

[0213] Figure 6 The shown vibration monitoring device 600 of the wind turbine can execute each step in the method embodiment described in the embodiments of the present invention, and implement each process and effect in the method embodiment described in the embodiments of the present invention, which will not be elaborated herein.

[0214] Figure 7 The hardware structure diagram of the vibration monitoring device of the wind turbine provided by the embodiment of the present invention is shown.

[0215] The vibration monitoring device of the wind turbine may include a processor 701 and a memory 702 storing computer program instructions.

[0216] Specifically, the above-mentioned processor 701 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 invention.

[0217] The memory 702 may include a mass memory for data or instructions. By way of example and not limitation, the memory 702 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 702 may include removable or non-removable (or fixed) media. Where appropriate, the memory 702 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, the memory 702 is a non-volatile solid-state memory. In a particular embodiment, the memory 702 includes a read-only memory (ROM). Where appropriate, 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.

[0218] The processor 701 reads and executes the computer program instructions stored in the memory 702 to implement any one of the vibration monitoring methods of the wind turbine generator set in the above embodiments.

[0219] In one example, the vibration monitoring device of the wind turbine generator set may further include a communication interface 703 and a bus 710. Among them, as Figure 7 shown, the processor 701, the memory 702, and the communication interface 703 are connected through the bus 710 and complete communication with each other.

[0220] The communication interface 703 is mainly used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present invention.

[0221] The bus 710 includes hardware, software, or both, and couples the components of the vibration monitoring device of the wind turbine generator set 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 710 may include one or more buses. Although the embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0222] It should be noted that the vibration monitoring device of the wind turbine can execute the vibration monitoring method of the wind turbine in the embodiments of the present invention, so as to implement the combination Figures 3 to 6 of the vibration monitoring method and device of the wind turbine described above.

[0223] In addition, in combination with the vibration monitoring method of the wind turbine in the above embodiments, the embodiments of the present invention can be implemented by providing a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the vibration monitoring methods of the wind turbine in the above embodiments is implemented.

[0224] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown 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 shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. 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 invention.

[0225] The functional blocks shown in the above 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 functional card, etc. When implemented in software, the elements of the present invention 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 on a transmission medium or a communication link. A "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, etc.

[0226] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention 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.

[0227] As described above, this is only the specific implementation manner of the present invention. 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 invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A vibration monitoring method for a wind turbine generator set, characterized in that, the method is applied to a wind farm controller, and the method includes: obtaining detection data of a target wind turbine generator set among a plurality of wind turbine generator sets within a preset time period; wherein, the detection data includes unit vibration data and unit operation data; performing vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set; obtaining a plurality of preset parameter thresholds; wherein, one of the preset parameter thresholds corresponds to one of the vibration evaluation parameters; when there is a first target parameter among the plurality of vibration evaluation parameters, sending a first type of early warning information to the target wind turbine generator set; wherein, the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold; the detection data further includes operation environment data; the performing vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set includes: obtaining target vibration feature data sent by a cloud server; wherein, the target vibration feature data is vibration feature data of a wind turbine generator set having the same configuration as the target wind turbine generator set, generating vibration feature data of the target wind turbine generator set according to the detection data, performing vibration trend analysis on the vibration feature data according to the target vibration feature data to obtain a vibration parameter prediction value of the target wind turbine generator set; or, generating vibration feature data of the target wind turbine generator set according to the detection data, sending the vibration feature data to the cloud server so that the cloud server performs vibration trend analysis on the vibration feature data according to the target vibration feature data to obtain a vibration parameter prediction value of the target wind turbine generator set; receiving the vibration parameter prediction value fed back by the cloud server; using the vibration parameter prediction value as the vibration evaluation parameter; the performing vibration trend analysis on the vibration feature data according to the target vibration feature data to obtain a vibration parameter prediction value of the target wind turbine generator set includes: training a preset neural network according to the target vibration feature data to obtain a parameter prediction model, and inputting the vibration feature data into the parameter prediction model for vibration trend analysis to obtain a vibration parameter prediction value of the target wind turbine generator set.

2. The method according to claim 1, characterized in that, the performing vibration analysis on the detection data to obtain a plurality of vibration evaluation parameters corresponding to the target wind turbine generator set includes at least one of the following: performing time domain analysis on the unit vibration data to obtain a time domain amplitude of the target wind turbine generator set, and using the time domain amplitude as the vibration evaluation parameter; performing frequency domain analysis on the unit vibration data according to the unit operation data to obtain a frequency domain amplitude of the target wind turbine generator set, and using the frequency domain amplitude as the vibration evaluation parameter; performing correlation analysis on the unit vibration data to obtain a generalized eigenvalue principal component of the target wind turbine generator set, and using the generalized eigenvalue principal component as the vibration evaluation parameter.

3. The method according to claim 2, wherein, the vibration data of the unit includes the vibration acceleration in the X direction of the nacelle and the vibration acceleration in the Y direction of the nacelle, and the operation data of the unit includes the first generator speed, the second generator speed, and the impeller speed, wherein, the first generator speed is determined according to the generator voltage, and the second generator speed is determined according to the generator current; wherein, the time-domain amplitude includes the time-domain amplitude in the X direction and the time-domain amplitude in the Y direction, and the frequency-domain amplitude includes the frequency-domain amplitude in the X direction and the frequency-domain amplitude in the Y direction.

4. The method according to claim 1, wherein, the operation environment data includes wind speed, air density, and turbulence, the vibration data of the unit includes the vibration acceleration in the X direction of the nacelle and the vibration acceleration in the Y direction of the nacelle, and the operation data of the unit includes the operation state of the unit, the wind alignment deviation of the unit, the power of the unit, the pitch angle of the unit, the first generator speed, the second generator speed, and the impeller speed, wherein, the first generator speed is determined according to the generator voltage, and the second generator speed is determined according to the generator current; wherein, the predicted value of the vibration parameter includes the predicted value of the time-domain amplitude in the X direction, the predicted value of the time-domain amplitude in the Y direction, the predicted value of the frequency-domain amplitude in the X direction, and the predicted value of the frequency-domain amplitude in the Y direction.

5. The method according to claim 1, wherein, after performing vibration analysis on the detection data to obtain multiple vibration evaluation parameters corresponding to the target wind turbine generator, the method further includes: sending the vibration characteristic data to the cloud server.

6. The method according to claim 1, wherein, before sending the first type of early warning information to the target wind turbine generator, the method further includes: determining the vibration source type of the target wind turbine generator according to the first target parameter; generating target control information according to the vibration source type; generating the first type of early warning information according to the target control information.

7. The method according to claim 1, wherein, after obtaining multiple preset parameter thresholds, the method further includes: when the first target parameter does not exist among the multiple vibration evaluation parameters, determining the upper limits of the multiple vibration evaluation parameters corresponding to the multiple wind turbine generators; wherein, one upper limit of the vibration evaluation parameter corresponds to one vibration evaluation parameter; when a second target parameter exists among the multiple vibration evaluation parameters, sending a second type of early warning information to the target wind turbine generator; wherein, the second target parameter is a vibration evaluation parameter greater than the corresponding upper limit of the vibration evaluation parameter.

8. A vibration monitoring device for a wind turbine generator, wherein, the device is applied to a wind farm controller, and the device includes: a first acquisition module, configured to acquire detection data of a target wind turbine generator among multiple wind turbine generators within a preset time period; wherein, the detection data includes the vibration data of the unit and the operation data of the unit; a first analysis module, configured to perform vibration analysis on the detection data to obtain multiple vibration evaluation parameters corresponding to the target wind turbine generator; A second acquisition module, configured to acquire a plurality of preset parameter thresholds; wherein, one of the preset parameter thresholds corresponds to one of the vibration evaluation parameters; A first sending module, configured to send a first type of warning information to the target wind turbine generator when there is a first target parameter among the plurality of vibration evaluation parameters; wherein, the first target parameter is a vibration evaluation parameter greater than the corresponding preset parameter threshold; The detection data further includes operation environment data; The vibration monitoring device of the wind turbine generator further includes a third acquisition module and a first generation module; The third acquisition module is configured to acquire target vibration characteristic data sent by a cloud server; wherein, the target vibration characteristic data is vibration characteristic data of a wind turbine generator having the same configuration as the target wind turbine generator; The first generation module is configured to generate vibration characteristic data of the target wind turbine generator according to the detection data; The first analysis module is further configured to perform vibration trend analysis on the vibration characteristic data according to the target vibration characteristic data, to obtain a vibration parameter prediction value of the target wind turbine generator; and use the vibration parameter prediction value as a vibration evaluation parameter; The first analysis module is further configured to generate vibration characteristic data of the target wind turbine generator according to the detection data; send the vibration characteristic data to the cloud server, so that the cloud server performs vibration trend analysis on the vibration characteristic data according to the target vibration characteristic data, to obtain a vibration parameter prediction value of the target wind turbine generator; receive the vibration parameter prediction value fed back by the cloud server; and use the vibration parameter prediction value as a vibration evaluation parameter; The performing vibration trend analysis on the vibration characteristic data according to the target vibration characteristic data, to obtain a vibration parameter prediction value of the target wind turbine generator, includes: Training a preset neural network according to the target vibration characteristic data, to obtain a parameter prediction model, and inputting the vibration characteristic data into the parameter prediction model for vibration trend analysis, to obtain a vibration parameter prediction value of the target wind turbine generator.

9. A vibration monitoring device for a wind turbine generator characterized in that the device includes: a processor; a memory storing a computer program, which when executed by the processor, implements the vibration monitoring method for a wind turbine generator according to any one of claims 1-7.

10. A computer-readable storage medium characterized in that computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the vibration monitoring method for a wind turbine generator according to any one of claims 1-7 is implemented.

Images