A wind turbine vibration anomaly determination method and system based on time series similar features

Abstract

The application relates to a wind turbine vibration abnormality judgment method and system based on time series similarity characteristics, which comprises: performing three-dimensional abnormality judgment on each measuring point of the wind turbine, namely, vibration value numerical abnormality judgment, trend abnormality judgment based on time series similarity characteristics, and frequency spectrum abnormality judgment; wherein the trend abnormality judgment based on time series similarity characteristics comprises: determining the similarity coefficient of the time series trend characteristics of a normal wind turbine and the time series trend characteristics of a wind turbine to be judged, and determining the trend abnormality judgment result according to the similarity coefficient of the time series trend characteristics; comprehensively determining whether the wind turbine is abnormal in vibration according to the judgment results of the three kinds of judgment; and the application solves the problem of low wind turbine vibration real-time operation state health evaluation level in the related art, guarantees the reliability of the wind turbine, and has important practical application value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unit state monitoring, in particular to a wind turbine vibration abnormality determination method and system based on time series similar features. BACKGROUND

[0002] With the increasing capacity of wind turbines, the length of the blades and the height of the tower increase, and the vibration problem becomes more and more important. Abnormal vibration phenomenon can cause damage to the structural components of the unit, and even cause the unit to stop running in severe cases, causing extremely serious economic losses. Accurate analysis and evaluation of the massive monitoring data recorded by the wind turbine are of great significance to the stable and reliable operation of the wind turbine.

[0003] A wind turbine is a large rotating device that includes wind, mechanical and electrical systems. Unit vibration state analysis and evaluation includes data acquisition, data processing and analysis, processing opinions and decisions, and can accurately locate the unit state through vibration data and symptoms. A complete vibration state analysis and evaluation process includes data acquisition through equipment, and then data mining and analysis, and the important process output is "knowledge" oriented to the field. The operation comprehensive evaluation method is an important application based on the field "knowledge", which is reflected in the form of unit state diagnosis and analysis. Effective data analysis and evaluation methods can at any time master the equipment state and degradation law of the wind turbine, and avoid the occurrence of sudden and gradual failures. In related technologies, the abnormal state determination method in the massive monitoring data of wind turbine vibration generally directly determines the numerical abnormality of the vibration value of the measuring point, and the health evaluation level of the real-time running state of the wind turbine vibration is low.

[0004] In view of the problem that the health evaluation level of the real-time running state of the wind turbine vibration is low in the related art, an effective solution has not been proposed. SUMMARY

[0005] The embodiments of the present application provide a wind turbine vibration abnormality determination method and system based on time series similar features, to at least solve the problem that the health evaluation level of the real-time running state of the wind turbine vibration is low in the related art.

[0006] In a first aspect, the embodiments of the present application provide a wind turbine vibration abnormality determination method based on time series similar features, which comprises:

[0007] The three dimensions of each measuring point of the wind turbine are determined respectively: vibration value numerical abnormality determination, trend abnormality determination based on time series similar features, and frequency spectrum abnormality determination;

[0008] The trend abnormality determination based on the time series similarity features comprises: determining a similarity coefficient of a time series trend feature of a normal wind turbine and a time series trend feature of a wind turbine to be determined; and determining a trend abnormality determination result according to the similarity coefficient of the time series trend features.

[0009] The determination results of the three determinations are integrated to determine whether the wind turbine is abnormal.

[0010] In some embodiments, the process of determining the similarity coefficient of the time series trend feature of the normal wind turbine and the time series trend feature of the wind turbine to be determined comprises:

[0011] For the wind turbine in a normal state, a target group number of time series trend features are collected at the same measurement point position of the wind turbine to obtain a first time series trend feature library;

[0012] For the wind turbine to be determined, a target group number of time series trend features are collected at the same measurement point position of the wind turbine to obtain a second time series trend feature library;

[0013] According to an extended time series distance algorithm, the similarity coefficient is determined based on data of the same time period in each cycle of the first time series trend feature library and the second time series trend feature library.

[0014] In some embodiments, the process of the spectrum abnormality determination comprises:

[0015] The waveform time series to be determined is subjected to fast Fourier transform to obtain a frequency component value, and the frequency component value of the waveform time series is determined according to the spectrum feature.

[0016] It is determined whether the frequency component value falls within a frequency allowable range in a spectrum abnormality determination feature table of each measurement point of the wind turbine to obtain a spectrum abnormality determination result.

[0017] In some embodiments, the process of determining whether the frequency component value falls within the frequency allowable range in the spectrum abnormality determination feature table of each measurement point of the wind turbine comprises:

[0018] In the case that the frequency component value falls within the frequency allowable range, the wind turbine is determined to be in a normal state.

[0019] In the case that the frequency component value exceeds the frequency allowable range, but the proportion of the frequency component value to the boundary value of the frequency allowable range does not exceed a preset proportion, the wind turbine is determined to be in an abnormal state.

[0020] In the case that the frequency component value exceeds the frequency allowable range, and the proportion of the frequency component value to the boundary value of the frequency allowable range exceeds the preset proportion, the wind turbine is determined to be in a fault state.

[0021] In some embodiments, the determination of whether the wind turbine is abnormal in vibration is based on the results of the three determinations.

[0022] In the case where the vibration value is abnormal in value and the frequency spectrum is abnormal, or in the case where the vibration value is abnormal in value and the trend is abnormal, or in the case where the trend is abnormal and the frequency spectrum is abnormal, it is determined that the wind turbine is abnormal in vibration.

[0023] In a second aspect, the embodiments of the present application provide a wind turbine vibration abnormality determination system based on time series similarity features, which comprises:

[0024] a determination module configured to determine, for each measuring point of the wind turbine, three dimensions of abnormality, i.e., vibration value abnormality, trend abnormality based on time series similarity features, and frequency spectrum abnormality;

[0025] In the determination module, the determination of the trend abnormality based on time series similarity features comprises: determining a similarity coefficient of the time series trend features of a normal wind turbine and the time series trend features of the wind turbine to be determined, and determining a trend abnormality determination result according to the similarity coefficient of the time series trend features.

[0026] a comprehensive module configured to comprehensively determine the results of the three determinations to determine whether the wind turbine is abnormal in vibration.

[0027] In some embodiments, in the determination module, the determination of the similarity coefficient of the time series trend features of the normal wind turbine and the time series trend features of the wind turbine to be determined comprises:

[0028] For the wind turbine in a normal state, a target group number of time series trend features are collected at the same measuring point of the wind turbine to obtain a first time series trend feature library.

[0029] For the wind turbine to be determined, a target group number of time series trend features are collected at the same measuring point of the wind turbine to obtain a second time series trend feature library.

[0030] According to the extended time series distance algorithm, the similarity coefficient is determined based on the data of the same time period in each cycle of the first time series trend feature library and the second time series trend feature library.

[0031] In some embodiments, in the determination module, the determination of the frequency spectrum abnormality comprises:

[0032] performing fast Fourier transform on the waveform time series to be determined to obtain a frequency spectrum feature, and determining a frequency component value of the waveform time series according to the frequency spectrum feature;

[0033] determining whether the frequency component value falls within a frequency allowed range in a spectrum abnormality determination feature table of each measuring point of the wind turbine, to obtain a spectrum abnormality determination result.

[0034] In a third aspect, an electronic device is provided, including a memory and a processor, the memory storing a computer program, and the processor is configured to run the computer program to perform the wind turbine vibration abnormality determination method based on time series similar features.

[0035] In a fourth aspect, a storage medium is provided, the storage medium storing a computer program, and the computer program is configured to perform the wind turbine vibration abnormality determination method based on time series similar features when running.

[0036] Compared with the low level of real-time running state health evaluation of wind turbine vibration in the related art, the embodiments of the present application determine the abnormality of each measuring point of the wind turbine in three dimensions: vibration value abnormality determination, trend abnormality determination based on time series similar features, and spectrum abnormality determination. The trend abnormality determination based on time series similar features includes determining the similarity coefficient of the time series trend features of the normal wind turbine and the time series trend features of the wind turbine to be determined, and determining the trend abnormality determination result according to the similarity coefficient of the time series trend features. Finally, the determination results of the three determinations are integrated to determine whether the wind turbine is abnormal, thereby solving the problem of low level of real-time running state health evaluation of wind turbine vibration in the related art, realizing real-time evaluation of wind turbine vibration running state, providing a monitoring means for stable operation of the wind turbine, ensuring the reliability of the wind turbine, and having important practical application value. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate the illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0038] Figure 1 is a schematic diagram of a wind turbine vibration abnormality determination method based on time series similar features according to the first embodiment of the present application;

[0039] Figure 2 is a schematic diagram of determining whether the wind turbine is abnormal according to the integrated determination results of multiple determinations according to the second embodiment of the present application;

[0040] Figure 3 A schematic diagram of determining whether the wind turbine is abnormal in vibration according to the third embodiment of the present application by synthesizing multiple determination results;

[0041] Figure 4 A schematic diagram of determining whether the wind turbine is abnormal in vibration according to the fourth embodiment of the present application by synthesizing multiple determination results;

[0042] Figure 5 is a structural block diagram of a wind turbine vibration abnormality determination system based on time series similarity features according to the fifth embodiment of the present application;

[0043] Figure 6 is an internal structure schematic diagram of an electronic device according to the embodiments of the present application. DETAILED DESCRIPTION

[0044] In order to make the objects, technical solutions and advantages of the present application clearer, the present application is described and explained below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present application.

[0045] Obviously, the drawings in the following description are only some examples or embodiments of the present application, and for those of ordinary skill in the art, the present application can be applied to other similar scenarios without making creative efforts based on these drawings. In addition, it can be understood that although the efforts made in this development process can be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some designs, manufacturing or production changes based on the technical content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the present application.

[0046] In the present application, the phrase "embodiments" means that the specific features, structures or properties described in combination with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment to other embodiments. Those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0047] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the ordinary meanings as understood by one of ordinary skill in the art to which the present application pertains. The terms "a", "an", "one", "this", and similar terms as used herein do not denote a limitation of quantity but denote the presence of at least one of the referenced items. The terms "include", "comprise", "have", and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, product, or device that comprises a list of steps or units does not necessarily comprise only those steps or units but can include additional steps or units not expressly listed or inherent to such process, method, product, or device. The terms "connect", "connected", "coupling", and similar terms as used herein are not limited to direct or physical connections but can include indirect connections or connections through intervening elements. The term "multiple" as used herein means two or more. The term "and / or" as used herein describes association between associated objects, indicating that there can be three relationships, for example, "A and / or B" can indicate that A exists alone, A and B exist together, and B exists alone. The character " / " generally indicates an "or" relationship between the associated objects. The terms "first", "second", "third", and the like as used herein merely distinguish similar objects, and do not represent a specific order.

[0048] The present application provides a wind turbine vibration anomaly determination method based on time series similar characteristics. In wind turbine vibration online monitoring, due to different factors such as sensor measurement points, vibration intensity and amplitude, time series will be different in form. However, since the wind turbine vibration frequency is basically similar in similar fault conditions, the time series characteristics can be used to mark the corresponding fault, and the trend characteristics can be identified by identifying the vibration time series characteristics. Figure 1 is a schematic diagram of a wind turbine vibration anomaly determination method based on time series similar characteristics according to the first embodiment of the present application, as Figure 1 shown, the flow includes the following steps:

[0049] Step S101, three-dimensional anomaly determination is performed on each measurement point of the wind turbine: vibration value numerical anomaly determination, trend anomaly determination based on time series similar characteristics, and frequency spectrum anomaly determination;

[0050] Among them, the trend anomaly determination based on time series similar characteristics includes: determining the similarity coefficient of the time series trend characteristics of the normal wind turbine and the time series trend characteristics of the wind turbine to be determined, and determining the trend anomaly determination result according to the similarity coefficient of the time series trend characteristics;

[0051] Step S102, the three kinds of determination results are comprehensively determined to determine whether the wind turbine is abnormally vibrated.

[0052] Through the steps S101-S102, compared with the problem of low wind turbine vibration real-time running state health evaluation level in the related art, the embodiment of the application determines the abnormality of the wind turbine in three dimensions respectively: vibration value numerical abnormality determination, trend abnormality determination based on time series similar characteristics, and frequency spectrum abnormality determination. The trend abnormality determination based on time series similar characteristics includes: determining the similarity coefficient of the time series trend characteristics of the normal wind turbine and the time series trend characteristics of the wind turbine to be determined, and determining the trend abnormality determination result according to the similarity coefficient of the time series trend characteristics. Finally, the three kinds of determination results are comprehensively determined to determine whether the wind turbine is abnormally vibrated, thereby solving the problem of low wind turbine vibration real-time running state health evaluation level in the related art, realizing real-time evaluation of the wind turbine vibration running state, providing a monitoring method for stable operation of the wind turbine, ensuring the reliability of the wind turbine, and having important practical application value.

[0053] In some embodiments, regarding wind vibration value abnormality determination, the implementation method is as follows: the running condition data of the wind turbine with measurement is taken as the analysis and evaluation object, all state data are subjected to numerical determination analysis according to the known wind turbine each measurement point vibration abnormality determination characteristic table, and the fault in the wind turbine running is judged. The wind turbine each measurement point vibration abnormality determination characteristic table is shown in Table 1:

[0054] Table 1 wind turbine each measurement point vibration abnormality determination characteristic table

[0055]

[0056] If V≤Va, the unit is determined to be in a normal state; if Va

[0057] In some embodiments, the trend abnormality determination based on time series similar characteristics includes:

[0058] Five groups of known normal state time series trend characteristics collected from the same measurement point position of the wind turbine are selected and marked as X={s i}(i=1,...,5); the trend state time series to be identified is marked as Y={s′ i(i = 1,..., n), the N+1th point of the X, Y sequence is identified according to the Nth point known on the X, Y sequence, wherein the sequences A and B are located in the same period in the respective cycles;

[0059] The similarity degree of the five groups of time sequences to be identified is determined, and the Euclidean distance D(A, B) between the sequences is calculated using the extended time sequence distance algorithm:

[0060]

[0061]

[0062]

[0063] Wherein:

[0064] Wherein i = 1,..., 5

[0065] Let the weight of each point of the sequence be W = {w i (i = 1,..., 5); the prediction value of the N+1th point of the S sequence is: N = a0x N + b0; according to the periodic change rule of the vibration time sequence and the characteristics that the influence of the time sequence at the current time on each other is large, the target sequence composed of the first N sampling data to be identified is selected for similarity calculation, the sequence with the most similar change trend is found, and the similarity coefficient N i (A, B) between the X and Y direction time sequences is obtained, and the similarity coefficient N

[0066]

[0067]

[0068] Combined with the trend abnormal state calculation result table, the value N i (A, B) is closer to 1, the more obvious the trend abnormal state of the time sequence to be identified is, and greater than 0.5, the trend abnormality is considered; the trend abnormal state calculation result table is shown in Table 2:

[0069] Table 2 Trend Abnormal State Calculation Result Table

[0070]

[0071] From this, it is determined whether the amplitude of the trend waveform has obvious periodic impact components, obvious distortion, asymmetry, and other abnormal states, and whether the collected signal is distorted. At the same time, the time sequence corresponding to the waveform and the sensor installation position characteristics are obtained.

[0072] In some embodiments, the spectrum anomaly determination process includes: screening out the abnormal state waveform time series marked as x(t) i , sensor installation position feature P(i); marking x(t) i Performing a fast Fourier transform (FFT) to obtain a spectrum feature, obtaining x(t) i Frequency component F i According to the spectrum anomaly determination feature table of each measuring point of the wind turbine, the spectrum anomaly state is determined; the spectrum anomaly determination feature table of each measuring point of the wind turbine is shown in Table 3:

[0073] Table 1 Spectrum anomaly determination feature table of each measuring point of the wind turbine

[0074]

[0075] If Vf≤Vaf, it is determined that the unit is in a normal state; if Vaf

[0076] In some embodiments, the vibration time series trend anomaly judgment logic includes, in the case of vibration value numerical anomaly and spectrum anomaly, or in the case of vibration value numerical anomaly and trend anomaly, or in the case of trend anomaly and spectrum anomaly, determining that the vibration of the detection position is abnormal.

[0077] For example, Figure 2 According to the second embodiment of the present application, the schematic diagram of determining whether the wind turbine is vibration abnormal according to the comprehensive determination results of multiple kinds is shown in Figure 2 If the vibration value determination anomaly and the spectrum anomaly state determination anomaly of the position measuring point occur at the same time, it is determined that the vibration of the position is measured to be abnormal. Figure 3 According to the third embodiment of the present application, the schematic diagram of determining whether the wind turbine is vibration abnormal according to the comprehensive determination results of multiple kinds is shown in Figure 3 If the vibration abnormal trend calculation result corresponding to the time series trend feature and the spectrum determination are abnormal at the same time, it is determined that the vibration of the position is measured to be abnormal. Figure 4 According to the fourth embodiment of the present application, the schematic diagram of determining whether the wind turbine is vibration abnormal according to the comprehensive determination results of multiple kinds is shown in Figure 4 If the vibration abnormal trend calculation result corresponding to the time series trend feature and the spectrum determination are abnormal at the same time, it is determined that the vibration of the position is measured to be abnormal.

[0078] This embodiment also provides a wind turbine vibration anomaly determination system based on time series similarity features. Figure 5 This is a structural block diagram of a wind turbine vibration anomaly determination system based on time series similarity features according to the fifth embodiment of this application, as shown below. Figure 5 As shown, the system includes a judgment module 501 and a synthesis module 502. The judgment module 501 is used to perform three-dimensional anomaly judgments on each measuring point of the wind turbine: vibration value numerical anomaly judgment, trend anomaly judgment based on time series similarity features, and spectrum anomaly judgment. The trend anomaly judgment based on time series similarity features includes: determining the similarity coefficient between the time series trend features of the normal wind turbine and the time series trend features of the wind turbine to be judged, and determining the trend anomaly judgment result based on the similarity coefficient of the time series trend features. The synthesis module 502 is used to synthesize the judgment results of the three judgments to determine whether the wind turbine has vibration anomalies.

[0079] In some embodiments, in the determination module 501, the process of determining the similarity coefficient between the time series trend features of a normal wind turbine and the time series trend features of the wind turbine to be determined includes: for a wind turbine in normal condition, collecting the time series trend features of a target number of groups at the same measuring point location of the wind turbine to obtain a first time series trend feature library; for the wind turbine to be determined, collecting the time series trend features of a target number of groups at the same measuring point location of the wind turbine to obtain a second time series trend feature library; and determining the similarity coefficient based on the data of the same time period within the respective periods of the first time series trend feature library and the second time series trend feature library according to the extended time series distance algorithm.

[0080] In some embodiments, the determination module 501 includes the following process for determining spectral anomalies: performing a fast Fourier transform on the waveform time series to be determined to obtain spectral features; determining the frequency component values ​​of the waveform time series based on the spectral features; determining whether the frequency component values ​​fall within the frequency allowable range in the spectral anomaly determination feature table for each measurement point of the wind turbine, and obtaining the spectral anomaly determination result.

[0081] In conjunction with the wind turbine vibration anomaly determination method based on time series similarity features in the above embodiments, this application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements any of the wind turbine vibration anomaly determination methods based on time series similarity features in the above embodiments.

[0082] In one embodiment, a computer device is provided, which can be a terminal. The computer device comprises a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a wind turbine vibration anomaly determination method based on time series similar features. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0083] In one embodiment, Figure 6 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, as Figure 6 shown, an electronic device is provided, which can be a server, and the internal structure diagram thereof can be as Figure 6 shown. The electronic device comprises a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is configured to provide computing and control capabilities, the network interface is configured to communicate with an external terminal through a network connection, the internal memory is configured to provide an environment for running the operating system and the computer program, and the computer program is executed by the processor to implement a wind turbine vibration anomaly determination method based on time series similar features, and the database is configured to store data.

[0084] Those skilled in the art can understand that Figure 6 the structure shown in the above is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0086] Those skilled in the art should understand that, for the sake of brevity, not all possible combinations of the technical features in the above-mentioned embodiments are described, and as long as the combinations of the technical features do not contradict each other, they should be considered as falling within the scope of the present disclosure.

[0087] The above-mentioned embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A wind turbine generator vibration anomaly determination method based on time series similar features, characterized by, The method includes: Anomaly detection was performed on each measuring point of the wind turbine in three dimensions: vibration value anomaly detection, trend anomaly detection based on time series similarity characteristics, and spectrum anomaly detection. The process of determining trend anomalies based on time series similarity features includes: determining the similarity coefficient between the time series trend features of normal wind turbines and the time series trend features of wind turbines to be determined; and determining the trend anomaly determination result based on the similarity coefficient of the time series trend features. Based on the combined results of the anomaly assessments from these three dimensions, it is determined whether the wind turbine is experiencing abnormal vibration. The process of determining the similarity coefficient between the time series trend characteristics of normal wind turbine units and the time series trend characteristics of wind turbine units to be judged includes: For wind turbines under normal conditions, time series trend features of the target number of groups are collected at the same measuring point location of the wind turbine to obtain the first time series trend feature library; For the wind turbine unit to be judged, at the same measuring point location of the wind turbine unit, the time series trend features of the target group number are collected to obtain the second time series trend feature library; According to the extended time series distance algorithm, the similarity coefficient is determined based on the data of the same time period within the respective periods of the first time series trend feature library and the second time series trend feature library; The process of determining whether a wind turbine is vibrating abnormally by comprehensively considering the anomaly assessment results from the three dimensions mentioned above includes: In the case where the vibration value is abnormal and the spectrum is abnormal, or in the case where the vibration value is abnormal and the trend is abnormal, or in the case where the trend is abnormal and the spectrum is abnormal, the vibration at the detection location is determined to be abnormal.

2. The method of claim 1, wherein, The process of determining spectral anomalies includes: A fast Fourier transform is performed on the waveform time series to be judged to obtain spectral features, and the frequency component values ​​of the waveform time series are determined based on the spectral features. Determine whether the frequency component values ​​fall within the frequency allowable range in the frequency anomaly judgment feature table for each measurement point of the wind turbine, and obtain the frequency anomaly judgment result.

3. The method of claim 2, wherein, The process of determining whether the frequency component value falls within the frequency allowable range in the frequency anomaly judgment feature table of each measuring point of the wind turbine includes: If the frequency component values ​​fall within the allowable frequency range, the unit is determined to be in normal condition. If the value of a frequency component exceeds the allowable frequency range, but the proportion of that component to the boundary value of the allowable frequency range does not exceed a preset proportion, the unit is determined to be in an abnormal state. If the value of a frequency component exceeds the allowable frequency range and the proportion of that component to the boundary value of the allowable frequency range exceeds a preset proportion, the unit is determined to be in a fault state.

4. A wind turbine generator vibration anomaly determination system based on time series similar features, characterized by, The system includes: The judgment module is used to perform anomaly judgment on each measuring point of the wind turbine in three dimensions: vibration value numerical anomaly judgment, trend anomaly judgment based on time series similarity characteristics, and spectrum anomaly judgment. The trend abnormality determination based on the time sequence similar features comprises: determining a similarity coefficient of a time sequence trend feature of a normal wind turbine and a time sequence trend feature of a wind turbine to be determined; and determining a trend abnormality determination result according to the similarity coefficient of the time sequence trend features. The comprehensive module is configured to comprehensively determine the determination results of the three dimensions of abnormality determination to determine whether the wind turbine is abnormal in vibration. The process of determining the similarity coefficient of the time sequence trend feature of the normal wind turbine and the time sequence trend feature of the wind turbine to be determined comprises: For the wind turbine in the normal state, a target group number of time sequence trend features are collected at the same measuring point position of the wind turbine to obtain a first time sequence trend feature library. For the wind turbine to be determined, a target group number of time sequence trend features are collected at the same measuring point position of the wind turbine to obtain a second time sequence trend feature library. The similarity coefficient is determined according to the extended time sequence distance algorithm based on the data of the same time period in each cycle of the first time sequence trend feature library and the second time sequence trend feature library. The process of comprehensively determining the determination results of the three dimensions of abnormality determination to determine whether the wind turbine is abnormal in vibration comprises: In the case of the vibration value numerical abnormality and the frequency spectrum abnormality, or in the case of the vibration value numerical abnormality and the trend abnormality, or in the case of the trend abnormality and the frequency spectrum abnormality, it is determined that the vibration at the detection position is abnormal.

5. The system of claim 4, wherein, In the determination module, the process of determining the similarity coefficient of the time sequence trend feature of the normal wind turbine and the time sequence trend feature of the wind turbine to be determined comprises: For the wind turbine in the normal state, a target group number of time sequence trend features are collected at the same measuring point position of the wind turbine to obtain a first time sequence trend feature library. For the wind turbine to be determined, a target group number of time sequence trend features are collected at the same measuring point position of the wind turbine to obtain a second time sequence trend feature library. The similarity coefficient is determined according to the extended time sequence distance algorithm based on the data of the same time period in each cycle of the first time sequence trend feature library and the second time sequence trend feature library.

6. The system of claim 4, wherein, In the determination module, the process of the frequency spectrum abnormality determination comprises: The frequency component value of the waveform time sequence to be determined is obtained by performing fast Fourier transform on the waveform time sequence; and the frequency component value of the waveform time sequence is determined according to the frequency spectrum feature. It is determined whether the frequency component value falls within the frequency allowed range in the frequency spectrum abnormality determination feature table of each measuring point of the wind turbine to obtain a frequency spectrum abnormality determination result. 7.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to run the computer program to execute the wind turbine vibration abnormality determination method based on time sequence similar features according to any one of claims 1 to 3.

8. A storage medium, characterized by The storage medium stores a computer program, wherein the computer program is configured to execute the wind turbine vibration abnormality determination method based on time sequence similar features according to any one of claims 1 to 3 when running.

Images