CN111665047B

CN111665047B - Method, device, equipment and medium for identifying vibration signals of wind generating set

Info

Publication number: CN111665047B
Application number: CN201910173392.4A
Authority: CN
Inventors: 叶月光
Original assignee: Beijing Goldwind Smart Energy Service Co Ltd
Current assignee: Beijing Goldwind Smart Energy Service Co Ltd
Priority date: 2019-03-07
Filing date: 2019-03-07
Publication date: 2024-04-02
Anticipated expiration: 2039-03-07
Also published as: CN111665047A

Abstract

The embodiment of the application provides a method, a device, equipment and a medium for identifying vibration signals of a wind generating set. The method comprises the following steps: acquiring real-time operation data of a wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the engine room, and the second direction is perpendicular to the first direction; determining standard deviation of first-direction vibration data and standard deviation of second-direction vibration data of the engine room according to the real-time operation data; and identifying a signal representing non-stationary vibration of the generator according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction. The method can realize the identification of the non-stationary vibration signals in the running process of the bearing of the wind generating set through the real-time running data of the wind generating set.

Description

Method, device, equipment and medium for identifying vibration signals of wind generating set

Technical Field

The application relates to the technical field of vibration detection, in particular to a method and a device for identifying vibration signals of a wind generating set, electronic equipment and a computer readable storage medium.

Background

The generator in the wind generating set is an important power generation equipment component in the wind power plant, and in the long-term operation of the actual wind power plant, the bearing of the generator inevitably has faults such as abrasion, cracking and the like, and most of generator bearings are not provided with a bearing vibration monitoring system and have no related monitoring data record. There is thus a safety risk for the operation of such critical mechanical rotating components.

The existing wind power plant is mainly characterized in that the bearing problem of the generator is discovered by replacing the bearing after an accident after the triggering of faults such as regular maintenance, regular test of bearing gaps, locking faults of the running bearing of the generator and the like. Preventive schemes adopted in the industry are also mostly vibration monitoring by adding monitoring equipment, and the scheme of this type increases the equipment operation cost, so that the scheme is not popularized and applied in wind power plants.

More schemes in abnormal operation vibration monitoring of the direct-driven generator bearing in the current industry adopt manual inspection, regular maintenance and vibration monitoring devices to realize external abnormal monitoring of the unit, so that the manual maintenance cost is increased, and real-time monitoring cannot be realized. The vibration fault early warning of the abnormal operation of the generator bearing in the current industry is mainly realized by adding a new bearing vibration monitoring system to the unit, and the detection of abnormal vibration signals is realized by adding additional technical improvement to the wind turbine unit, so that the cost is greatly increased by the technical improvement work, and the method is not popularized in engineering application in practice.

To sum up, the prior art has the defect that engine vibration cannot be monitored in real time or additional detection equipment is required.

Disclosure of Invention

Aiming at the defects of the existing mode, the application provides a method, a device, electronic equipment and a computer readable storage medium for identifying vibration signals of a wind generating set, which are used for solving the technical problems that engine vibration cannot be monitored in real time or detection equipment needs to be additionally added.

In a first aspect, the present application provides a method for identifying a vibration signal of a wind turbine generator system, including:

acquiring real-time operation data of a wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the engine room, and the second direction is perpendicular to the first direction;

determining standard deviation of first-direction vibration data and standard deviation of second-direction vibration data of the engine room according to the real-time operation data;

and identifying a signal representing non-stationary vibration of the generator according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction.

In a second aspect, the present application provides a device for identifying vibration signals of a wind turbine generator system, including:

the first processing module is used for acquiring real-time operation data of the wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the engine room, and the second direction is perpendicular to the first direction;

the second processing module is used for determining the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data of the engine room according to the real-time operation data;

and the third processing module is used for identifying a signal representing the non-stationary vibration of the generator according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction.

In a third aspect, the present application provides an electronic device, including: a processor, a memory, and a bus;

a bus for connecting the processor and the memory;

a memory for storing operation instructions;

and the processor is used for executing the identification method of the vibration signal of the wind generating set according to the first aspect of the application by calling the operation instruction.

In a fourth aspect, the present application provides a computer readable storage medium storing a computer program for executing the method for identifying a vibration signal of a wind turbine generator set according to the first aspect of the present application.

The technical scheme provided by the embodiment of the application has at least the following beneficial effects:

1) Acquiring real-time operation data of a wind generating set; determining standard deviation of first-direction vibration data and standard deviation of second-direction vibration data of the engine room according to the real-time operation data; according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction, a signal representing the non-stationary vibration of the generator is identified, and the whole process of the identification method in the embodiment of the application is started in real time and automatically executed; that is, the embodiment of the application realizes the real-time identification of the non-stationary vibration signal in the running process of the generator (including the bearing of the generator) of the wind generating set, thereby realizing the early discovery, early treatment and early solution of the vibration problem of the generator.

2) The monitoring of the non-stationary vibration signals of the running of the generator (including the bearing) of the wind generating set can be realized without adding additional detection equipment, the detection cost for detecting the non-stationary vibration of the generator is reduced, and the application range of the embodiment of the application is wider.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

fig. 1 is a schematic flow chart of a method for identifying vibration signals of a wind turbine generator set according to an embodiment of the present application;

FIG. 2 is a flowchart of another method for identifying vibration signals of a wind turbine generator set according to an embodiment of the present disclosure;

FIG. 3 is a flowchart illustrating a method for identifying vibration signals of a wind turbine generator set according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of fluctuation rate (relatively gentle fluctuation) of two vibration directions of a normal unit along with a rotation speed according to an embodiment of the present application;

fig. 5 is a schematic diagram of a fluctuation ratio of two vibration directions of an abnormal unit (a unit vibration fluctuation ratio change of 3MW bearing abrasion) changing along with a rotation speed provided in an embodiment of the present application;

FIG. 6 is a schematic diagram of a first-order mode of a direct-drive wind turbine provided in an embodiment of the present application showing an arch-shaped distribution characteristic in a specific rotational speed domain;

FIG. 7 is a schematic representation of the bearing wear characteristics of a 1.5Mw wind turbine provided by embodiments of the present application;

FIG. 8 is a schematic diagram of normal characteristic performance of a bearing of a 1.5Mw direct-drive wind turbine provided by an embodiment of the present application;

fig. 9 is a schematic structural diagram of a device for identifying vibration signals of a wind turbine generator system according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Examples of embodiments of the present application are illustrated in the accompanying drawings, in which like or similar reference numerals refer to like or similar elements or elements having like or similar functionality throughout. Further, if detailed description of the known technology is not necessary for the illustrated features of the present application, it will be omitted. The embodiments described below by referring to the drawings are exemplary only for the purpose of illustrating the present application and are not to be construed as limiting the present application.

It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.

First, the basic principle of the embodiment of the present application is described as follows:

standard deviation (Standard Deviation), also commonly known as mean square error in the Chinese environment, is the square root of the arithmetic mean from the mean square error, using σ _X And (3) representing. The standard deviation is the arithmetic square root of the variance. The standard deviation can reflect the degree of discretization of a data set. The standard deviation is not necessarily the same for two sets of data with the same average. The standard deviation is applied to investment and can be used as an index for measuring the return stability. The larger the standard deviation value, the more distant from the past average value the return is, and the more unstable the return is, the higher the risk is. Conversely, a smaller value of the standard deviation indicates a more stable return and less risk. The standard deviation is affected by the extremum. The smaller the standard deviation, the more aggregated the data; the larger the standard deviation, the more discrete the data. The degree of dispersion of a set of data is reflected by the standard deviation, and is also an important index representing accuracy. The standard deviation is calculated as follows:

In the formula, X _i Is a real number, the average value (arithmetic average value) is mu _X Standard deviation is sigma _X 。

Kurtosis (kurtosis), which is a characteristic number that characterizes the height of a peak of a probability density distribution curve at an average value, reflects the sharpness of the peak. The kurtosis of a sample is a statistic that is comparable to a normal distribution, and generally if the kurtosis is greater than three, the shape of the peak is sharper than the normal distribution peak, and vice versa. Kurtosis is the kurtosis of probability distribution of real random variables, and the calculation formula of kurtosis is as follows:

in the formula, X _i For real numbers, n is the sample size and StDev is the standard deviation estimated based on the samples.

First order modality: the vibration mode of the object is called first-order vibration mode or main vibration mode when the excitation frequency of the external force is equal to the natural frequency of the object. The modes are the natural vibration characteristics of the mechanical structure, and each mode corresponds to a specific natural frequency, mode shape and damping ratio. The concept of mode is generally used in the vibration field, and can be understood as a vibration state, each object has its own natural frequency, and under the excitation action of external force, the object can show different vibration characteristics. The first-order mode is generated when the excitation frequency of the external force is equal to the natural frequency (first order) of the object, and the vibration mode of the object is called a first-order vibration mode or a main vibration mode; the second-order mode is when the excitation frequency of the external force is twice the natural frequency (second order) of the object, and the vibration mode of the object is called a second-order vibration mode, and so on.

Correlation coefficient: the correlation coefficient is the amount of linear correlation between the study variables. The correlation coefficients are defined in several ways, depending on the subject.

Simple correlation coefficients, also known as correlation coefficients or linear correlation coefficients, are generally denoted by the letter r and are used to measure the linear relationship between two variables. The calculation formula of the correlation coefficient is as follows:

in the formula, cov (X, Y) is the covariance of X and Y, var [ X ] is the variance of X, and Var [ Y ] is the variance of Y.

The inventor of the application finds through research that the instability of the vibration of the unit in the power generation process can be represented by utilizing the standard deviation distribution characteristic of real-time vibration data of the direction of the cabin acceleration X, Y of the unit at a specific rotating speed. The method is mainly characterized by a specific small rotating speed region and a large rotating speed region, wherein the small rotating speed region is a vibration distribution which appears in an arc shape in a specific part of rotating speed regions of the generator in the process of increasing the speed, the large rotating speed region is a vibration distribution which appears in a linear increment in the specific part of rotating speed regions of the generator bearing in the process of increasing the speed, alternatively, the rotating speed in the process of increasing the rotating speed is 8rpm-17rpm, the rotating speed which is between 8rpm and 17rpm is the specific part of rotating speed, and rpm (revolutions per minute) represents the rotating times of equipment per minute. The description is given in two cases based on different characteristics.

1) The characteristic of the arc vibration instability in the generating process of the unit is mainly the vibration characteristic aiming at specific first-order bending torque.

Specifically, by a structural modal analysis method, vibration characteristics of each order mode of the mechanical structure in a frequency range which is easy to be affected and vibration response results of the mechanical structure in the frequency range and under the excitation action of various internal or external vibration sources can be obtained. The stator and the rotor of the permanent magnet direct-drive generator are of disc type structures, and the mode shape characteristics of the stator and the rotor have certain similarity. The low frequency modes are presented as first order bending, first order axial swinging, second order bending, first order torsion. The frequency is the modal frequency of the stator-rotor structure, and the frequency is coupled and changed under the action of electromagnetic force and impeller load. Because of the influence of uneven air gap and impeller load of the generator, the generator is easy to generate bending moment load excitation around a central shaft, and current fluctuation or unbalance of torque is easy to generate excitation in torsion direction. Therefore, the first-order bending and first-order torsion modes of the stator and the rotor easily cause forced vibration and resonance under electromagnetic excitation, and different impeller configurations and loads have the effect of inhibiting or amplifying the vibration. In the results of the acceleration frequency domain analysis, vibrations around 8.XHz are related to fundamental excitation and first order bending modes of the stator and the rotor, 8.X represents 8.0, 8.1, etc., x represents a positive integer and zero, and torsional vibrations around 14rpm are related to first order torsional modes of the rotor. The vibration amplitude is related to electromagnetic excitation, current unbalance and structural damping.

The problems of cracking of a stator bracket of the generator, high-frequency abnormal vibration of a bearing of the generator and the like which are possibly caused by first-order bending vibration of the generator are caused, and the electromagnetic torque of the generator generates a large amount of pulsation due to the influence of current harmonic waves and wind turbulence, so that the service life of mechanical parts such as the bearing of a transmission shafting is inevitably and obviously influenced.

2) For the linear non-stationarity linearity in the running of the generator bearing, the problem of bearing abrasion of the large direct-drive wind driven generator is mainly represented.

Specifically, when abrasion occurs in the unit bearing, when the sliding surface inside the bearing is not smooth enough, the phenomenon of unstable vibration inevitably occurs in the rotation process of the unit. The greater the rotational speed variation, the more pronounced the jerky behavior. This is because if spalling pits are formed in the raceway due to wear or spalling, and the spalling pits are located in the load region of the low-speed rolling bearing, the raceway is locally unloaded at the moment when the raceway is out of contact with the raceway and the raceway is locally overloaded at the moment when the raceway is in central contact with the raceway, and then the stress in the raceway where the spalling pits are located and the vicinity thereof is intermittently fluctuated. If this is done to some extent, the stresses, strains and contact stresses between the contact surfaces will change regularly to a large extent. Irregular movement caused by metal friction or deformation of rough surfaces and movement of cracks and swarf will result in the generation of stress waves. Because of the filtering algorithm of vibration added in the PLC (Programmable Logic Controller ) of the fan, a part of high-frequency signals can be removed, the PLC is an electronic system using digital operation in an industrial environment, and the PLC uses a programmable memory to internally store instructions designed by a user and is used for realizing special functions such as logic operation, sequential operation, timing, counting and arithmetic operation and controlling various types of machines and processes through digital or analog input and output. In the second-level data randomly sampled during the operation of the unit, the characteristic of the periodic signal is almost completely lost, and the vibration performance of the unit can be described by the turbulence of the vibration.

If the inner ring of the bearing is not coincident with the axis line, the bearing can easily generate alternating axial force action once every rotation, and a certain angle exists between the elevation angle and the horizontal direction of the unit, so that the vibration value of the unit in the X direction is more obvious in the rotating process, and if the contact surface of the bearing is worn, the fatigue wear of the bearing generates peeling, pits and temperature rise caused by the increase of gaps, or when the gaps between the inner sleeve of the bearing and the shaft neck are uneven or scars appear, the running vibration in the rotating plane direction can be influenced.

In the assembly process of the bearing and the main shaft of the generator, the temperature of the bearing ring is not completely restored to the ambient temperature to be assembled, so that the NJ bearing (NJ is a bearing type structure code number, N and J letters are combined together to represent an inner ring single flange, an outer ring double flange cylindrical roller bearing) is deformed, the bearing sleeve position is deviated, the outer ring and part of rolling bodies are damaged, and after disassembly, the NG (No Good, bad, i.e. abnormal) bearing inner ring is axially displaced and has a larger gap with the retainer.

The retainer ring of the raceway part of the NJ bearing of the generator is damaged, the retainer of the outer ring rolling body is riveted and broken, and the rolling bodies are scattered after the disassembly. The retainer loosens, influences rolling bodies for example, when the large-area retainer rivet joint breaks, friction is generated on the rolling bodies by the retainer, the rolling bodies are scratched, meanwhile, abrasion of the rolling bodies is increased, and bearing gaps are enlarged.

The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Example 1

The embodiment of the application provides a method for identifying vibration signals of a wind generating set, a flow diagram of the method is shown in fig. 1, and the method comprises the following steps:

s101, acquiring real-time operation data of a wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the nacelle, and the second direction is perpendicular to the first direction.

S102, determining standard deviation of first-direction vibration data and standard deviation of Y-direction vibration data of the engine room according to real-time operation data.

Optionally, before determining the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data of the nacelle, further comprises: judging whether the quantity of the real-time vibration data meets a first threshold value or not and whether the real-time vibration data meets a preset data quality condition or not; when the quantity of the real-time vibration data meets a first threshold value and the real-time vibration data meets a data quality condition, screening the real-time vibration data to obtain screened real-time vibration data; and determining standard deviation of the vibration data in the first direction and standard deviation of the vibration data in the second direction based on the rotation speed according to the screened real-time vibration data and the real-time rotation speed.

Optionally, determining whether the real-time vibration data meets a preset data quality condition includes: and judging whether the number of the real-time vibration data with the absolute value of the vibration data in the second direction being larger than 1 is smaller than a second threshold value, wherein the vibration data comprises acceleration.

Optionally, screening the real-time vibration data to obtain screened real-time vibration data, including: according to the first direction vibration data and the second direction vibration data in the real-time vibration data, determining the real-time vibration data meeting the following first data retention conditions as the real-time vibration data after the first screening: the absolute value of the first direction vibration data and the absolute value of the second direction vibration data are both smaller than the high boundary value, and the absolute value of the second direction vibration data is larger than the low boundary value or the absolute value of the first direction vibration data is larger than the low boundary value.

Optionally, the real-time vibration data is screened to obtain screened real-time vibration data, and the method further includes: and determining real-time vibration data meeting the following second data retention conditions from the real-time vibration data after the first screening, wherein the real-time vibration data is used as the real-time vibration data after the second screening: the number of unique values of the first direction vibration data or the second direction vibration data is not less than a third threshold value, the maximum value of the unique values of the real-time wind speed is at least greater than a cut-in running wind speed point, the number of the real-time wind speed which is greater than the cut-in running wind speed point is at least greater than a fourth threshold value or the duration is not less than a first time period, and the real-time running data of the real-time wind speed which is greater than the threshold wind speed point is not less than a fifth threshold value.

S103, identifying a signal representing non-stationary vibration of the generator according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction.

Optionally, identifying a signal indicative of non-stationary vibration of the generator based on the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data, including: determining a first rotation speed interval according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data; determining a second rotating speed interval according to the first rotating speed interval, the rotating speed center position and the rotating speed center deviation position; judging whether the first arched condition and the second arched condition are met or not according to the standard deviation of the second-direction vibration data in the first rotating speed interval, the standard deviation of the second-direction vibration data in the second rotating speed interval, the rotating speed center position, the rotating speed center deviation position and the vibration standard deviation threshold value parameter; when the first and second arching conditions are satisfied, real-time vibration data satisfying the first and second arching conditions is determined as an arching signal indicative of non-stationary vibration of the generator.

Optionally, determining whether the first arch condition and the second arch condition are met according to the standard deviation of the second direction vibration data in the first rotation speed interval, the standard deviation of the second direction vibration data in the second rotation speed interval, the rotation speed center position, the rotation speed center deviation position and the vibration standard deviation threshold parameter includes: the first arching condition is determined to be satisfied when: the variation coefficient of the standard deviation of the second direction vibration data of the second rotation speed interval is larger than or equal to a sixth threshold value, the polar distance value of the standard deviation of the second direction vibration data of the second rotation speed interval is larger than or equal to a seventh threshold value, the number of the standard deviation of the second direction vibration data in the second rotation speed interval is larger than or equal to an eighth threshold value, the maximum value of the standard deviation data of the second direction vibration of the second rotation speed interval is larger than or equal to a ninth threshold value, the number of the standard deviation of the second direction vibration data in the first rotation speed interval is larger than or equal to a tenth threshold value, the absolute value of the kurtosis of the standard deviation of the second direction vibration data of the second rotation speed interval is larger than an eleventh threshold value, the position where the standard deviation of the second direction vibration data in the first rotation speed interval is the maximum value is larger than the first position value, and the position where the standard deviation of the second direction vibration data in the first rotation speed interval is the maximum value is smaller than the second position value; performing differential calculation on the standard deviation of the second-direction vibration data in the first rotation speed interval to obtain a differential calculation value; taking the maximum value in the absolute value of the differential calculated value as the adjacent point of the arch-shaped distribution characteristic to operate the maximum variation amplitude; and when the running maximum variation amplitude of the neighboring points of the arch-shaped distribution features is smaller than a twelfth threshold value, or the ratio of the running maximum variation amplitude of the neighboring points of the arch-shaped distribution features to the variation coefficient is smaller than or equal to a thirteenth threshold value, determining that the second arch-shaped condition is satisfied.

Optionally, identifying a signal indicative of non-stationary vibration of the generator based on the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data, including: determining a first rotation speed interval according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data; determining a relative vibration difference parameter of the first direction and the second direction according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data in the first rotation speed interval, a correlation coefficient of the overall linear increase of the non-stationary vibration of the second direction when the first direction vibration is stable based on the rotation speed, a multiple of a rotation speed domain range occupied by the turbulence degree of the second direction vibration relative to the first direction vibration, a rotation speed domain integral value of the non-stationary vibration of the second direction and a rotation speed interval proportion of the increase of the second direction vibration; judging whether a first linear condition is met or not according to the relative vibration difference parameters of the first direction and the second direction, the correlation coefficient, the multiple of the rotating speed domain range, the rotating speed domain integral value and the rotating speed interval proportion; when the first linear condition is satisfied, real-time vibration data satisfying the first linear condition is determined as a linear signal indicative of non-stationary vibration of the generator.

Optionally, determining whether the first linear condition is satisfied according to the first direction and the second direction relative vibration difference parameter, the correlation coefficient, the multiple of the rotation speed domain range, the rotation speed domain integral value, and the rotation speed interval proportion includes: the first linear condition is determined to be satisfied when the following is satisfied: the first-direction and second-direction relative-vibration difference parameter is equal to or greater than a fourteenth threshold, the first correlation coefficient is greater than a fifteenth threshold, the correlation coefficient that the non-stationary vibration of the second direction increases linearly as a whole based on the rotation speed when the vibration of the first direction is stabilized includes the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient, and the second correlation coefficient is equal to or less than the sixteenth threshold, and the third correlation coefficient is greater than the seventeenth threshold, and the multiple of the rotation speed domain range occupied by the degree of disorder of the vibration of the second direction relative to the vibration of the first direction is greater than the eighteenth threshold, and the rotation speed domain integral value of the non-stationary vibration of the second direction is greater than the nineteenth threshold, and the rotation speed interval proportion of the increase of the vibration of the second direction is greater than the twentieth threshold. By applying the first embodiment of the application, at least the following beneficial effects can be achieved:

1) In the method for identifying the non-stationary vibration information number, real-time operation data of the wind generating set are obtained; determining standard deviation of first-direction vibration data and standard deviation of second-direction vibration data of the engine room according to the real-time operation data; according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction, a signal representing the non-stationary vibration of the generator is identified, and the whole process of the identification method in the embodiment of the application is started in real time and automatically executed; that is, the embodiment of the application realizes the real-time identification of the non-stationary vibration signal in the running process of the generator (including the bearing of the generator) of the wind generating set, thereby realizing the early discovery, early treatment and early solution of the vibration problem of the generator.

2) Moreover, the embodiment of the application can realize the monitoring of the non-stationary vibration signals of the running of the generator (including the bearing) of the wind generating set without adding additional detection equipment, so that the detection cost for detecting the non-stationary vibration of the generator is reduced, and the application range of the embodiment of the application is wider.

Example two

Based on the same inventive concept as the first embodiment, the present embodiment describes the technical solution of the first embodiment by a specific example.

Referring to fig. 2, fig. 2 is a flow chart of another method for identifying vibration signals of a wind turbine generator set according to an embodiment of the present application, as shown in fig. 2, the method specifically includes:

s201, acquiring real-time operation data of the wind generating set.

Specifically, the period of the calculated data is set to be 10 days, namely, the real-time operation data of the wind generating set for 10 days is selected; the bearing of the generator does not belong to a consumable product, and the monitoring period does not need high-frequency monitoring.

Optionally, the fields of the real-time running data include the following correspondence: the real-time vibration data of the nacelle comprise X-direction vibration data and Y-direction vibration data, wherein the X-direction vibration data is the nacelle acceleration in the X direction, and the Y-direction vibration data is the nacelle acceleration in the Y direction.

Optionally, in the embodiment of the present application, the first direction is specifically an X direction, and the second direction is specifically a Y direction; the X direction is the axis direction of the engine room, the Y direction is perpendicular to the X direction, and the straight line where the Y direction is located is coplanar with the straight line where the X direction is located. The real-time data generated by the wind turbine generator PLC or second-level vibration data recorded by the central monitoring or SCADA (Supervisory Control And Data Acquisition, data acquisition and monitoring control system) of the wind power plant are utilized, the sampling frequency is generally acquired according to the second level, and the sampling period is between 1 and 10 seconds. The data at the time of the operation state is used as calculation data. The higher the sampling frequency, the better the data quality.

Optionally, the real-time operation data field is standardized, and renaming the time tag, the nacelle acceleration in the X direction, the nacelle acceleration in the Y direction, the real-time rotation speed of the generator, and the real-time wind speed are respectively defined as: rectime, x_ace, y_ acce, rpm, wind; or renaming field names according to the requirements of users for the compatibility of programs and the uniformity of program parameters of models.

S202, judging whether the quantity of the real-time vibration data is larger than or equal to a first threshold value; and when the number of the real-time vibration data is judged to be greater than or equal to the first threshold value, executing S203, and when the number of the real-time vibration data is judged to be less than the first threshold value, ending the flow.

Optionally, the first threshold is 10000.

S203, judging whether the real-time vibration data meets the data quality condition; when the real-time vibration data satisfies the data quality condition, S204 is performed; when the real-time vibration data does not satisfy the data quality condition, S211 is executed and the flow ends.

Specifically, when it is determined that the number of real-time vibration data whose absolute value of Y-direction vibration data y_space is greater than 1 is smaller than the second threshold, S204 is performed, and when it is determined that the number of real-time vibration data whose absolute value of Y-direction vibration data is greater than 1 is not smaller than the second threshold, the flow ends. Optionally, the second threshold is 10.

S204, performing first data screening to obtain real-time vibration data after the first screening.

Optionally, the real-time vibration data after the first screening satisfies: the absolute value of the X-direction vibration data and the absolute value of the Y-direction vibration data are both smaller than the high boundary value, and the absolute value of the Y-direction vibration data is larger than the low boundary value or the absolute value of the X-direction vibration data is larger than the low boundary value.

Specifically, a low boundary value low_set is set, a high boundary value high_set is set, the low boundary value and the high boundary value are both non-negative real numbers, the low boundary value is smaller than the high boundary value, and real-time vibration data between the absolute value of the vibration data in the X direction of the unit and the absolute value of the vibration data in the Y direction of the unit are not (low_set to high_set) (the boundary low_set is not included) are eliminated, so that the rest of the real-time vibration data meets the following logic conditions: (abs (x_ace) < high_set & abs (y_ace) < high_set) < abs (x_ace) > low_set|abs (y_ace) > low_set)).

S205, performing secondary data screening to obtain real-time vibration data after the secondary screening.

Optionally, the real-time vibration data after the second screening satisfies: the number of unique values of the X-direction vibration data or the Y-direction vibration data is not less than a third threshold value, the maximum value of the unique values of the real-time wind speed is at least greater than a cut-in running wind speed point, the number of the real-time wind speed which is greater than the cut-in running wind speed point is at least greater than a fourth threshold value or the duration is not less than a first time period, and the real-time running data of the real-time wind speed which is greater than the threshold wind speed point is not less than a fifth threshold value.

Specifically, the inventor of the application considers that the real-time vibration data has a certain wind speed interval and vibration requirements and cannot always vibrate or the wind speed cannot always show the condition of no wind blowing. Therefore, in the embodiment of the present application, the number of unique values of x_space or y_space is not less than 3 (belonging to the third threshold value), and the maximum value of the unique values of wind speed is at least greater than 3 (the cut-in running wind speed point of the unit), and the data volume of wind speed is greater than 3 (the cut-in running wind speed point of the unit) is at least greater than the fourth threshold value 80 (or the time is not less than 10 minutes in the first time period), and the data volume of wind speed is greater than the threshold value wind speed point 5 is not less than 30 pieces of the fifth threshold value. For example, if 0.1 has a plurality of identical values, only 0.1 is calculated for the unique values, and a total of 3 unique values are 0.1, 0.2 and 0.3, respectively.

S206, judging whether the non-empty real-time vibration data quantity meets the aggregation calculation condition; when the non-empty real-time vibration data amount satisfies the aggregation calculation condition, S207 is performed; when the non-empty real-time vibration data amount does not satisfy the aggregation calculation condition, S211 is executed and the flow ends.

Specifically, when the non-empty real-time vibration data amount is greater than 10 pieces, S207 is executed, otherwise the flow ends.

S207, performing aggregation calculation on the real-time vibration data after the second screening to obtain standard deviation of the X-direction vibration data and standard deviation of the Y-direction vibration data.

Specifically, aggregation calculation is performed according to the rotation speed (1 bit to a decimal point) of a generator of the (wind power generation) unit, so that standard deviation sd_xacc of X-direction vibration data and standard deviation sd_yacc of Y-direction vibration data under the same rotation speed are obtained, and vibration stability of the unit under different rotation speeds of the (wind power generation) unit is represented through the standard deviation.

When pattern recognition is performed on the dome-shaped unstable vibration signal at a specific rotational speed of the generator, the following S208 to S210 are employed for the recognition.

S208, setting a rotation speed interval.

Specifically, a specific rotation speed interval in the aggregation calculation result is selected, namely, a rotation speed area of a normal generator is selected.

For example, for a 1.5MW (megawatt) model, aggregate data is selected for a speed interval of 8.5 to 16.5 speed intervals. In the rotation speed segment, it is determined that the number of values of the rotation speed value range unique to the power generation rotation speed region in the aggregation calculation result is not less than 20 values, and the rotation speed span (rotation speed section after the rotation speed rounding) is not less than 4 rotation speed sections. If the condition is not satisfied, the calculation is not continued, which indicates that the data condition is not satisfied. If the condition is met, selecting the data mark of the first rotating speed interval 10-14 rotating speed intervals as rpm_xyacce; setting parameters: rotational speed center position (a position within a rotational speed interval is selected as a point in an abnormal vibration region which may occur) center_point=12.5, rotational speed center deviation position div_diff=0.5, and vibration standard deviation threshold parameter ypeak_value=0.01.

The second rotational speed interval is an interval between the first position value (center_point-div_diff) and the second position value (center_point+div_diff). The result of the speed lying in the second speed interval is marked rpm_cenacce; the number of data points in the calculation rpm_cenacce satisfying sd_yacc > =ypeak_value is marked as wake. The coefficient of variation of sd_yacc in rpm_cenacce was recalculated: i.e., the ratio of standard deviation to average value of sd_yacc, the result is labeled ycv.

Kurtosis of sd_yacc in rpm_xyacce is calculated and the result is labeled peak_py.

Calculating the number of data points in sd_yacc > ypeak_value in rpm_xyacce, and recording the result as warlen_py; and calculates the maximum value, minimum value, and pole pitch (difference between maximum and minimum) in sd_yacc in rpm_xyacce, recorded as yacc_max, yacc_min, and ydange, respectively.

Calculating the rotation speed point of maximum vibration instability: labeled yrpm_pointmax, i.e., the rotational speed point corresponding to when yd_yacc is the maximum in rpm_xyacce.

Calculating the maximum allowable variation amplitude in the variation of stable lifting in the vibration unstable point arch distribution characteristic: marked yvmax_diff; the sd_yacc in the rpm_xyacce is subjected to differential calculation, and the maximum value in the absolute value of the calculation result is taken as the adjacent point of the arch distribution characteristic to operate the maximum variation amplitude, so that the characteristic of jump, such as the phenomenon of jump caused by unstable vibration of the rotating speed point, can be avoided.

S209, judging whether the real-time vibration data simultaneously meets a first arch condition and a second arch condition; when the real-time vibration data satisfies both the first arch condition and the second arch condition, executing S210; when the real-time vibration data does not satisfy the first arch condition and the second arch condition at the same time, S211 is executed and the flow ends.

In particular, real-time vibration data satisfying the first and second arching conditions is determined as an arching signal indicative of non-stationary vibration of the generator. And when the real-time vibration data is judged to meet the first arch condition and the second arch condition, executing S210, otherwise, ending the flow.

The first arch condition war_xlwtj is determined to be satisfied when the following is satisfied: a variation coefficient ycv of the standard deviation of the Y-direction vibration data of the second rotation speed section is equal to or greater than a sixth threshold, optionally, the sixth threshold is 0.14; and the polar distance value yrange of the standard deviation of the Y-direction vibration data of the second rotating speed interval is larger than or equal to a seventh threshold value, and optionally, the seventh threshold value is 0.004; and the standard deviation of the Y-direction vibration data in the second rotating speed interval is larger than or equal to the number of vibration standard deviation threshold parameters, namely the number of the vibration parameters is larger than or equal to an eighth threshold value, and optionally, the eighth threshold value is 1; and the maximum value yacc_max of the standard deviation data of the Y-direction vibration of the second rotation speed section is equal to or larger than a ninth threshold value, optionally, the ninth threshold value is 0.01; and the number of the vibration standard deviation threshold parameters, warlen_py, of the Y-direction vibration data in the first rotation speed interval is larger than or equal to a tenth threshold value, optionally, the tenth threshold value is 1; and an absolute value abs (peak_py) of the kurtosis of the standard deviation of the Y-direction vibration data of the second rotation speed section is greater than an eleventh threshold value, optionally, the eleventh threshold value is 0.25; and the position yrpm_pointmax where the standard deviation of the Y-direction vibration data is the maximum value in the first rotation speed interval is larger than the first position value, and the position yrpm_pointmax where the standard deviation of the Y-direction vibration data is the maximum value in the first rotation speed interval is smaller than the second position value.

For example, the first arch condition may be expressed as:

war_xlwtj＝ycv>＝0.14&yrange>＝0.004&warleny>＝1&yacc_max>＝0.01&warlen_py>1&abs(peak_py)>0.25&yrpm_pointmax>(center_point-div_diff)&yrpm_pointmax<(center_point+div_diff)。

the first arched condition is that non-stationary vibration occurs in a specific rotation speed interval, and the non-stationary vibration phenomenon is represented by arched distribution.

Optionally, performing differential calculation on the standard deviation of the Y-direction vibration data in the first rotation speed interval to obtain a differential calculation value; taking the maximum value in the absolute value of the differential calculated value as the adjacent point of the arch distribution characteristic to operate the maximum variation amplitude yvmax_diff; when the running maximum variation amplitude yvmax_diff of the neighboring points of the arch-shaped distribution feature is smaller than a twelfth threshold, optionally, the twelfth threshold is 0.003; or when the ratio of the maximum variation amplitude yvmax_diff of the running of the neighboring points of the arch distribution characteristic and the variation coefficient ycv is smaller than or equal to a thirteenth threshold value, optionally, the thirteenth threshold value is 0.015, and it is determined that the second arch condition is satisfied. Specifically, the second arch condition is war_xlwtj 2= (yvmax_diff <0.003|yvmax_diff/ycv < = 0.015), and the second arch condition is allowable local fluctuation amplitude representing arch characteristics.

S210, triggering an alarm, namely, abnormal vibration in the process of non-stable speed rise of the generator.

S211, ending the flow.

Referring to fig. 3, fig. 3 is a flow chart of a method for identifying a vibration signal of a wind generating set according to an embodiment of the present application, and as shown in fig. 3, the method specifically includes:

S301, acquiring real-time operation data of the wind generating set.

The specific method of this step is identical to the specific method of step S201 described above, and will not be described here again.

S302, judging whether the quantity of the real-time vibration data is larger than or equal to a first threshold value; when the number of real-time vibration data is determined to be greater than or equal to the first threshold, S303 is executed, and when the number of real-time vibration data is determined to be less than the first threshold, the flow of S314 is executed.

The specific method in this step is the same as the specific method in step S202, and will not be described here again.

S303, judging whether the real-time vibration data meets the data quality condition; when the real-time vibration data satisfies the data quality condition, S304 is performed; when the real-time vibration data does not satisfy the data quality condition, the execution S314 flow ends.

The specific method of this step is identical to the specific method of step S203, and will not be described here.

S304, performing first data screening to obtain real-time vibration data after the first screening.

The specific method in this step is identical to the specific method in step S204, and will not be described here again.

S305, performing secondary data screening to obtain real-time vibration data after the secondary screening.

The specific method of this step is identical to the specific method of step S205 described above, and will not be described here again.

S306, judging whether the non-empty real-time vibration data quantity meets the aggregation calculation condition; executing S307 when the non-empty real-time vibration data amount satisfies the aggregation calculation condition; when the non-empty real-time vibration data amount does not satisfy the aggregation calculation condition, the execution S314 flow ends.

The specific method in this step is the same as the specific method in step S206, and will not be described here again.

S307, performing aggregation calculation on the real-time vibration data after the second screening to obtain the standard deviation of the X-direction vibration data and the standard deviation of the Y-direction vibration data.

The specific method of this step is identical to the specific method of step S207 described above, and will not be described here again.

When pattern recognition is performed on the linear unstable state of the generator bearing wear, the following S308 to S310 are employed for the recognition.

S308, the rotation speed section is set.

Specifically, a specific rotating speed region in an aggregation calculation result is selected, namely, a rotating speed region of a normal generator is selected, and a first rotating speed region is selected for 8.5-13 rotating speeds by taking 2.5MW and 3MW machine types as examples; the vibration condition of the vibration rotating speed range data in the X, Y direction is calculated, and the calculation method is as follows: the number of the unique rotating speed value fields in the power generation rotating speed area is not lower than 20, and the rotating speed span (rotating speed interval after the rotating speed rounding) is not lower than 4 rotating speed intervals. If the condition is not satisfied, the calculation is not continued, which indicates that the data condition is not satisfied. If the condition is satisfied, calculating a deviation value sd_ yjx =sd_yacc-sd_xacc of the stability of the Y-direction vibration compared to the X-direction vibration; for the convenience of statistics, the sd_ yjx can be marked as red, otherwise, the sd_ yjx is marked as green, and then the label numbers of red and green are respectively counted and marked as tab_red and tab_green; calculating a multiple of tab_red being a multiple of a rotation speed domain range occupied by the disturbance degree of Y-direction vibration relative to X-direction vibration; if tab_red >0 and tab_green >0, then multiple_rg=tab_red/tab_green; otherwise, judging whether tab_green is 0 and tab_red >0, if the judging result is true, setting multiple_rg=100, otherwise, multiple_rg=0. The vibration in the Y direction is more irregular and more obvious along with the increase of the rotating speed. The rotational speed domain integrated value multiple_th with a large Y-direction vibration unevenness is calculated as follows: if tab_red >0 and tab_green >0, the sum of all sd_ yjx >0.0002 records sd_ yjx is calculated and marked as a large_th, the sum of all sd_ yjx < -0.0002 is calculated and marked as a small_th, multiple_th=large_th/small_th, when tab_green is 0 and tab_red >0, multiple_th is set to 100, otherwise, 0 is set.

S309, determining relative vibration difference parameters of the X direction and the Y direction.

Specifically, X, Y two-direction relative vibration difference parameter is marked as ncahr_ygth, when sd_yac > sd_xacc is set, the vibration relative difference parameter is 1, otherwise, is 0; the frequency of 1 appearing in the rotation speed interval (8.5-13.0) set by the calculated vector is marked as ncahr_ygth, and the number of points in the rotation speed interval of the relative unstable vibration rotation speed in two directions is expressed.

S310, it is determined that the non-stationary vibration in the Y direction increases linearly as a whole based on the rotation speed when the vibration in the X direction is stationary.

Specifically, when the X-direction vibration is stabilized, the non-stationary vibration in the Y-direction is marked as cor_coef, cor_coefx, and cor_coefy based on the correlation coefficient of the overall linear increase of the rotation speed, and the linear scale coefficient and the correlation coefficient of the power generation rotation speed point and sd_ yjx of the first rotation speed interval 8.5 to 13 are marked as lm_coef, cor_coef, respectively; the correlation coefficients of the rotation speed point and sd_xacc, the rotation speed point and sd_yac are respectively marked as cor_coefx and cor_coefy, and the linear scaling coefficients adopt a linear regression fitting method.

S311, the rotation speed section ratio at which the Y-direction vibration increases is determined.

Specifically, the rotation speed section proportion of the increase in the Y-direction vibration is marked as rpm_increase, when tab_red >0 and tab_green > =0, rpm_increase=tab_red/(tab_red+tab_green), otherwise rpm_increase=0.

S312, judging whether the real-time vibration data meets a first linear condition; when the real-time vibration data satisfies the first linear condition, S313 is performed; when the real-time vibration data does not satisfy the first linear condition, S314 is executed and the flow ends.

Optionally, the first linear condition measult is determined to be satisfied when: the X-direction and Y-direction relative vibration difference parameter nchar_ygth is equal to or greater than a fourteenth threshold value, and the first correlation coefficient cor_coef is greater than a fifteenth threshold value, and when the X-direction vibration is stabilized, correlation coefficients in which the Y-direction non-stationary vibration increases linearly as a whole based on the rotation speed include the first correlation coefficient cor_coef, the second correlation coefficient cor_coefx, and the third correlation coefficient cor_coefy, and the second correlation coefficient cor_coefx is equal to or less than a sixteenth threshold value, and the third correlation coefficient cor_coefy is greater than a seventeenth threshold value, and the multiple of the rotation speed domain range occupied by the degree of disorder of the Y-direction vibration relative to the X-direction vibration is greater than an eighteenth threshold value, and the rotation speed domain integral value mutiple_th in which the Y-direction vibration is unevenly increased is greater than a nineteenth threshold value, and the rotation speed domain proportion rpm_increment in which the Y-direction vibration is increased is greater than a twentieth threshold value.

Specifically, the first linear condition is satisfied that the ratio of real=nchar_ygth > =25 & cor_coef >0.6& cor_coefx < = 0.75& cor_coefx >0.9& multiple_rg >1.5& multiple_th >2& rpm_increment > =0.6, namely, the meaning of representing vibration as the rotation speed increases through the coefficient parameter of correlation and the linear fitting coefficient is that the vibration instability is increased, and when the correlation coefficient setting in the X direction is lower and the correlation coefficient in the Y direction is higher, the Y direction vibration instability is more obvious and the changing speed is faster and the Y direction vibration instability exceeds more than half of the X direction.

S313, triggering the abnormal abrasion and vibration of the generator bearing.

S314, ending the flow.

The data parameters related to this embodiment are the expressions of first-order torsion and first-order bending. For the operation data with the common sampling period of 5-7 seconds in the current wind power plant, the calculation can be carried out once every 7-14 days, and the data quantity of 7 days and more can be adopted once. In practical applications, the data amount and the data sampling period can be adjusted according to the effect.

The visual graphs of the bearing wear early warning result of the 3MW wind driven generator output by the identification method of the non-stationary vibration signal provided by the embodiment are shown in fig. 4 and 5. Fig. 4 is a schematic diagram of fluctuation rate (relatively gentle fluctuation) of two vibration directions of a normal unit along with a change of a rotation speed, and as shown in fig. 4, fluctuation of an X-direction cabin acceleration x_ace and a Y-direction cabin acceleration y_ace of the normal unit along with the change of the rotation speed is relatively gentle. Fig. 5 is a schematic diagram of a fluctuation ratio (a fluctuation ratio change of a unit vibration with 3MW bearing wear) of two vibration directions of an abnormal unit according to an embodiment of the present application, and as shown in fig. 5, the fluctuation ratio change of the unit vibration with 3MW bearing wear is represented as a linear growth characteristic that the instability of the cabin acceleration y_ace in the Y direction increases with the increase of the rotation speed.

For example, the visual graphs of the monitoring result of the unstable vibration signal in the generating process of the wind generating set output by the method for identifying the unstable vibration signal provided by the above embodiment are shown in fig. 6, fig. 7 and fig. 8.

Specifically, fig. 6 is a schematic diagram of an arch distribution feature of a first-order mode of a direct-drive wind turbine provided by the embodiment of the present application in a specific rotation speed domain, and as shown in fig. 6, the first-order mode of the direct-drive wind turbine presents an arch distribution feature (an arch feature is presented near 12 turns) in the specific rotation speed domain, and the first-order mode or first-order bending of the direct-drive wind turbine easily causes fatigue damage to a stator and a rotor support of the turbine, and finally causes serious influence of mechanical cracking.

FIG. 7 is a schematic diagram of a bearing wear feature of a 1.5Mw wind turbine provided in an embodiment of the present application, where as shown in FIG. 7, the bearing wear feature of the 5Mw wind turbine (an arch feature appears near 12.5 revolutions) has a discrete difference of 0.0028 and a discrete variation ratio of 0.007, and the bearing wear of the 1.5Mw wind turbine can be oriented to abnormal manifestations of large bearing gaps, bearing Bush indentations, etc. of the wind turbine in actual engineering.

FIG. 8 is a schematic diagram showing normal characteristics of a bearing of a 1.5Mw direct-drive wind turbine according to an embodiment of the present application, where no arched characteristic appears in the 11-14 revolution range as shown in FIG. 8. In fig. 6, 7 and 8, sd-space represents the standard deviation sd_xacc of X-direction vibration data or the standard deviation sd_yacc of Y-direction vibration data, rpm (revolutions per minute ) represents the number of revolutions per minute of the direct-drive wind turbine, x_space represents the X-direction nacelle acceleration, y_space represents the Y-direction nacelle acceleration, and max-space represents the instantaneous maximum acceleration.

By applying the third embodiment of the present application, at least the following beneficial effects can be achieved:

the embodiment of the application can realize the monitoring of the non-stationary vibration signals of the running of the generator (including the bearing) of the wind generating set without adding additional detection equipment, reduces the detection cost for detecting the non-stationary vibration of the generator, and ensures that the application range of the embodiment of the application is wider.

Example III

Based on the same inventive concept, the embodiment of the present application further provides a device for identifying a vibration signal of a wind turbine generator set, where a schematic structural diagram of the device for identifying a vibration signal of a wind turbine generator set is shown in fig. 9, and the device 1300 for identifying a vibration signal of a wind turbine generator set includes a first processing module 1301, a second processing module 1302, and a third processing module 1303.

The first processing module 1301 is configured to obtain real-time operation data of the wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the engine room, and the second direction is perpendicular to the first direction;

A second processing module 1302, configured to determine, according to the real-time operation data, a standard deviation of the first direction vibration data and a standard deviation of the Y direction vibration data of the nacelle;

the third processing module 1303 is configured to identify a signal representing non-stationary vibration of the generator according to the standard deviation of the vibration data in the first direction and the standard deviation of the vibration data in the second direction.

Optionally, the identifying device 1300 of the vibration signal of the wind generating set further comprises a screening module.

Optionally, the screening module is configured to determine whether the number of the real-time vibration data meets a first threshold value, and whether the real-time vibration data meets a preset data quality condition; when the quantity of the real-time vibration data meets a first threshold value and the real-time vibration data meets a data quality condition, screening the real-time vibration data to obtain screened real-time vibration data; and determining standard deviation of the vibration data in the first direction and standard deviation of the vibration data in the second direction based on the rotation speed according to the screened real-time vibration data and the real-time rotation speed.

Optionally, the screening module is specifically configured to determine whether the number of real-time vibration data with the absolute value of the second direction vibration data being greater than 1 is less than a second threshold, where the vibration data includes acceleration.

Optionally, the screening module is specifically configured to determine, according to the first direction vibration data and the second direction vibration data in the real-time vibration data, the real-time vibration data that meets the following first data retention conditions, as the real-time vibration data after the first screening: the absolute value of the first direction vibration data and the absolute value of the second direction vibration data are both smaller than the high boundary value, and the absolute value of the second direction vibration data is larger than the low boundary value or the absolute value of the first direction vibration data is larger than the low boundary value.

Optionally, the screening module is specifically configured to determine, from the real-time vibration data after the first screening, the real-time vibration data that meets the following second data retention condition, as the real-time vibration data after the second screening: the number of unique values of the first direction vibration data or the second direction vibration data is not less than a third threshold value, the maximum value of the unique values of the real-time wind speed is at least greater than a cut-in running wind speed point, the number of the real-time wind speed which is greater than the cut-in running wind speed point is at least greater than a fourth threshold value or the duration is not less than a first time period, and the real-time running data of the real-time wind speed which is greater than the threshold wind speed point is not less than a fifth threshold value.

Optionally, the third processing module 1303 is specifically configured to determine a first rotation speed interval according to a standard deviation of the first direction vibration data and a standard deviation of the second direction vibration data; determining a second rotating speed interval according to the first rotating speed interval, the rotating speed center position and the rotating speed center deviation position; judging whether the first arched condition and the second arched condition are met or not according to the standard deviation of the second-direction vibration data in the first rotating speed interval, the standard deviation of the second-direction vibration data in the second rotating speed interval, the rotating speed center position, the rotating speed center deviation position and the vibration standard deviation threshold value parameter; when the first and second arching conditions are satisfied, real-time vibration data satisfying the first and second arching conditions is determined as an arching signal indicative of non-stationary vibration of the generator.

Optionally, the third processing module 1303 is specifically configured to determine that the first arch condition is satisfied when: the variation coefficient of the standard deviation of the second direction vibration data of the second rotation speed interval is larger than or equal to a sixth threshold value, the polar distance value of the standard deviation of the second direction vibration data of the second rotation speed interval is larger than or equal to a seventh threshold value, the number of the standard deviation of the second direction vibration data in the second rotation speed interval is larger than or equal to an eighth threshold value, the maximum value of the standard deviation data of the second direction vibration of the second rotation speed interval is larger than or equal to a ninth threshold value, the number of the standard deviation of the second direction vibration data in the first rotation speed interval is larger than or equal to a tenth threshold value, the absolute value of the kurtosis of the standard deviation of the second direction vibration data of the second rotation speed interval is larger than an eleventh threshold value, the position where the standard deviation of the second direction vibration data in the first rotation speed interval is the maximum value is larger than the first position value, and the position where the standard deviation of the second direction vibration data in the first rotation speed interval is the maximum value is smaller than the second position value; performing differential calculation on the standard deviation of the second-direction vibration data in the first rotation speed interval to obtain a differential calculation value; taking the maximum value in the absolute value of the differential calculated value as the adjacent point of the arch-shaped distribution characteristic to operate the maximum variation amplitude; and when the running maximum variation amplitude of the neighboring points of the arch-shaped distribution features is smaller than a twelfth threshold value, or the ratio of the running maximum variation amplitude of the neighboring points of the arch-shaped distribution features to the variation coefficient is smaller than or equal to a thirteenth threshold value, determining that the second arch-shaped condition is satisfied.

Optionally, the third processing module 1303 is specifically configured to determine a first rotation speed interval according to a standard deviation of the first direction vibration data and a standard deviation of the second direction vibration data; determining a relative vibration difference parameter of the first direction and the second direction according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data in the first rotation speed section, a correlation coefficient that the non-stationary vibration of the Y direction increases linearly as a whole based on the rotation speed when the first direction vibration is stable, a multiple of a rotation speed domain range occupied by the turbulence degree of the second direction vibration relative to the first direction vibration, a rotation speed domain integral value with the non-stationary vibration of the second direction being larger and a rotation speed section proportion with the vibration of the second direction being increased; judging whether a first linear condition is met or not according to the relative vibration difference parameters of the first direction and the second direction, the correlation coefficient, the multiple of the rotating speed domain range and the rotating speed interval proportion; when the first linear condition is satisfied, real-time vibration data satisfying the first linear condition is determined as a linear signal indicative of non-stationary vibration of the generator.

The identification device for a vibration signal of a wind turbine generator set provided in this embodiment of the present application may refer to the identification method for a vibration signal of a wind turbine generator set described above, and the beneficial effects that the identification device for a vibration signal of a wind turbine generator set provided in this embodiment of the present application may achieve are the same as the identification method for a vibration signal of a wind turbine generator set described above, which is not described herein again.

Based on the same inventive concept, the embodiment of the present application further provides an electronic device, a schematic structural diagram of which is shown in fig. 10, where the electronic device 1400 includes at least one processor 1401, a memory 1402 and a bus 1403, and at least one processor 1401 is electrically connected to the memory 1402; the memory 1402 is configured to store at least one computer executable instruction and the processor 1401 is configured to execute the at least one computer executable instruction to perform the steps of the method for identifying any wind turbine generator set vibration signal as provided in any one of the first to second embodiments or any one of the alternative implementations of the present application.

Further, processor 1403 may be an FPGA (Field-Programmable Gate Array, field programmable gate array) or other device with logic processing capabilities, such as an MCU (Microcontroller Unit, micro control unit), CPU (Central Process Unit, central processing unit).

Based on the same inventive concept, the embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the method for identifying a vibration signal of a wind turbine generator set provided by the embodiments of the present application.

Computer readable media includes, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks, ROM, RAM, EPROM (Erasable Programmable Read-Only Memory), EEPROMs, flash Memory, magnetic cards, or optical cards. That is, a readable medium includes any medium that stores or transmits information in a form readable by a device (e.g., a computer).

The computer readable storage medium provided in this embodiment has the same inventive concept and the same advantages as those of the foregoing embodiments, and is not described herein.

The application of the embodiment of the application has at least the following beneficial effects:

3) On the real-time second-level vibration data conventionally collected in a wind generating set of a wind power plant, mode identification can be realized on vibration signals of bending, torsion and the like in a first-order structural mode of a permanent magnet direct-driven wind power generator on mechanical damage, and meanwhile, similar Bush indentation of a bearing in the running process of the generator can also realize mode identification.

Those of skill in the art will appreciate that the various operations, methods, steps in the flow, actions, schemes, and alternatives discussed in the present application may be alternated, altered, combined, or eliminated. Further, other steps, means, or steps in a process having various operations, methods, or procedures discussed in this application may be alternated, altered, rearranged, split, combined, or eliminated. Further, steps, measures, schemes in the prior art with various operations, methods, flows disclosed in the present application may also be alternated, altered, rearranged, decomposed, combined, or deleted.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. The method for identifying the vibration signal of the wind generating set is characterized by comprising the following steps of:

acquiring real-time operation data of a wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the cabin, and the second direction is perpendicular to the first direction;

Determining standard deviation of first direction vibration data and standard deviation of second direction vibration data of the engine room according to the real-time operation data;

identifying a signal representing non-stationary vibration of the generator according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data;

the identifying a signal indicative of non-stationary vibration of the generator based on the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data, comprising:

determining a first rotation speed interval according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data;

determining a second rotating speed interval according to the first rotating speed interval, the rotating speed center position and the rotating speed center deviation position;

judging whether a first arch condition and a second arch condition are met or not according to the standard deviation of second-direction vibration data in the first rotating speed interval, the standard deviation of second-direction vibration data in the second rotating speed interval, the rotating speed center position, the rotating speed center deviation position and the vibration standard deviation threshold parameter;

when the first and second arching conditions are satisfied, determining the real-time vibration data satisfying the first and second arching conditions as an arching signal indicative of non-stationary vibration of the generator.

2. The method of claim 1, further comprising, prior to said determining the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data of the nacelle:

judging whether the quantity of the real-time vibration data meets a first threshold value or not and whether the real-time vibration data meets a preset data quality condition or not;

when the number of real-time vibration data satisfies a first threshold and the real-time vibration data satisfies the data quality condition,

screening the real-time vibration data to obtain screened real-time vibration data;

and determining standard deviation of the vibration data in the first direction and standard deviation of the vibration data in the second direction based on the rotation speed according to the screened real-time vibration data and the real-time rotation speed.

3. The method of claim 2, wherein determining whether the real-time vibration data satisfies a preset data quality condition comprises:

and judging whether the number of real-time vibration data with the absolute value of the vibration data in the second direction being larger than 1 is smaller than a second threshold value, wherein the vibration data comprises acceleration.

4. A method according to claim 3, wherein said screening the real-time vibration data to obtain screened real-time vibration data comprises:

According to the first direction vibration data and the second direction vibration data in the real-time vibration data, determining the real-time vibration data meeting the following first data retention conditions as the real-time vibration data after the first screening: the absolute value of the first direction vibration data and the absolute value of the second direction vibration data are both smaller than a high boundary value, and the absolute value of the second direction vibration data is larger than a low boundary value or the absolute value of the first direction vibration data is larger than the low boundary value.

5. The method of claim 4, wherein the screening the real-time vibration data to obtain screened real-time vibration data further comprises:

and determining real-time vibration data meeting the following second data retention conditions from the real-time vibration data after the first screening, wherein the real-time vibration data is used as the real-time vibration data after the second screening: the number of unique values of the first direction vibration data or the second direction vibration data is not less than a third threshold value, the maximum value of the unique values of the real-time wind speed is at least greater than a cut-in running wind speed point, the number of the real-time wind speed which is greater than the cut-in running wind speed point is at least greater than a fourth threshold value or the duration is not less than a first time period, and the real-time running data of the real-time wind speed which is greater than the threshold wind speed point is not less than a fifth threshold value.

6. The method according to claim 1, wherein the determining whether the first arch condition and the second arch condition are satisfied based on a standard deviation of the second-direction vibration data in the first rotation speed section, a standard deviation of the second-direction vibration data in the second rotation speed section, the rotation speed center position, the rotation speed center deviation position, and a vibration standard deviation threshold parameter includes:

determining that the first arch condition is satisfied when: the variation coefficient of the standard deviation of the second direction vibration data in the second rotation speed interval is larger than or equal to a sixth threshold, the polar distance value of the standard deviation of the second direction vibration data in the second rotation speed interval is larger than or equal to a seventh threshold, the number of the standard deviation threshold parameters of the second direction vibration data in the second rotation speed interval is larger than or equal to an eighth threshold, the maximum value of the standard deviation data of the second direction vibration in the second rotation speed interval is larger than or equal to a ninth threshold, the number of the standard deviation threshold parameters of the second direction vibration data in the first rotation speed interval is larger than or equal to a tenth threshold, the absolute value of the kurtosis of the standard deviation of the second direction vibration data in the second rotation speed interval is larger than an eleventh threshold, the position where the standard deviation of the second direction vibration data in the first rotation speed interval is the maximum value is larger than the first position value, and the position where the standard deviation of the second direction vibration data in the first rotation speed interval is the maximum value is smaller than the second position value;

Performing differential calculation on the standard deviation of the second-direction vibration data in the first rotation speed interval to obtain a differential calculation value;

taking the maximum value in the absolute value of the differential calculated value as the adjacent point of the arch-shaped distribution characteristic to operate the maximum variation amplitude;

and when the maximum variation amplitude of the running of the neighboring points of the arch-shaped distribution features is smaller than a twelfth threshold value, or the ratio of the maximum variation amplitude of the running of the neighboring points of the arch-shaped distribution features to the variation coefficient is smaller than or equal to a thirteenth threshold value, determining that the second arch-shaped condition is satisfied.

7. The method of claim 1, wherein the identifying a signal indicative of non-stationary vibration of the generator based on the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data comprises:

determining a relative vibration difference parameter of the first direction and the second direction according to the standard deviation of the first direction vibration data and the standard deviation of the second direction vibration data in the first rotation speed interval, a correlation coefficient of the overall linear increase of the non-stationary vibration of the second direction when the first direction vibration is stable, a multiple of a rotation speed range occupied by the turbulence degree of the second direction vibration relative to the first direction vibration, a rotation speed range integral value of the non-stationary vibration of the second direction and a rotation speed interval proportion of the increase of the second direction vibration;

Judging whether a first linear condition is met or not according to the relative vibration difference parameters of the first direction and the second direction, the correlation coefficient, the multiple of the rotating speed domain range, the rotating speed domain integral value and the rotating speed interval proportion;

when the first linear condition is satisfied, determining the real-time vibration data satisfying the first linear condition as a linear signal indicative of non-stationary vibration of the generator.

8. A device for identifying vibration signals of a wind turbine generator system, said device comprising:

the first processing module is used for acquiring real-time operation data of the wind generating set; the real-time operation data includes: the real-time vibration data of the engine room, the real-time rotating speed of the generator and the real-time wind speed; the real-time vibration data comprises first direction vibration data and second direction vibration data; the first direction is the axial direction of the cabin, and the second direction is perpendicular to the first direction;

the third processing module is used for identifying a signal representing the non-stationary vibration of the generator according to the standard deviation of the first-direction vibration data and the standard deviation of the second-direction vibration data;

The third processing module is specifically configured to:

9. An electronic device, comprising: a processor, a memory, and a bus;

the bus is used for connecting the processor and the memory;

the memory is used for storing operation instructions;

the processor is configured to execute the method for identifying a vibration signal of a wind turbine generator set according to any one of claims 1 to 7 by invoking the operation instruction.

10. A computer-readable storage medium, characterized in that a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out a method of identifying a vibration signal of a wind park according to any one of claims 1-7.