CN112611584A - Fatigue failure detection method, device, equipment and medium for wind generating set - Google Patents

Fatigue failure detection method, device, equipment and medium for wind generating set Download PDF

Info

Publication number
CN112611584A
CN112611584A CN202010421806.3A CN202010421806A CN112611584A CN 112611584 A CN112611584 A CN 112611584A CN 202010421806 A CN202010421806 A CN 202010421806A CN 112611584 A CN112611584 A CN 112611584A
Authority
CN
China
Prior art keywords
predicted
generating set
wind generating
fatigue failure
fatigue
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010421806.3A
Other languages
Chinese (zh)
Other versions
CN112611584B (en
Inventor
徐建波
宋建军
俞海国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Jinfeng Software Technology Co ltd
Qinghai Green Energy Data Co ltd
Beijing Goldwind Smart Energy Service Co Ltd
Original Assignee
Jiangsu Jinfeng Software Technology Co ltd
Qinghai Green Energy Data Co ltd
Beijing Goldwind Smart Energy Service Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Jinfeng Software Technology Co ltd, Qinghai Green Energy Data Co ltd, Beijing Goldwind Smart Energy Service Co Ltd filed Critical Jiangsu Jinfeng Software Technology Co ltd
Priority to CN202010421806.3A priority Critical patent/CN112611584B/en
Publication of CN112611584A publication Critical patent/CN112611584A/en
Application granted granted Critical
Publication of CN112611584B publication Critical patent/CN112611584B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/70—Wind energy
    • Y02E10/72—Wind turbines with rotation axis in wind direction

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Wind Motors (AREA)

Abstract

The application provides a method, a device, equipment and a medium for detecting fatigue failure of a wind generating set. The fatigue failure detection method comprises the following steps: acquiring historical fault information of the wind generating set to be predicted as fault information to be predicted; predicting the fatigue failure condition of the wind generating set to be predicted according to the failure information to be predicted and the fatigue failure prediction model to obtain a first prediction result; acquiring historical transient data of the wind generating set to be predicted before a fault occurs, and taking the historical transient data as historical transient data to be predicted; determining aperiodic load characteristics of the wind generating set to be predicted under each aperiodic load stress; predicting the fatigue failure condition of the wind generating set to be predicted according to the aperiodic load characteristics to obtain a second prediction result; and obtaining a third prediction result according to the first prediction result and the second prediction result. The method and the device improve the identification accuracy rate of the wind generating set with higher fatigue failure risk.

Description

Fatigue failure detection method, device, equipment and medium for wind generating set
Technical Field
The application relates to the technical field of fatigue detection methods, in particular to a method, a device, equipment and a medium for detecting fatigue failure of a wind generating set.
Background
With the rapid development of the wind power industry in recent years, the reliability of wind power generation equipment gradually becomes the focus of attention of people, the operating environment of the wind power generation equipment is complex and severe, the fatigue damage problem of the wind power generation equipment is continuous, the wind power generation equipment is always damaged in the effective life, and the maintenance cost of the wind power generator set is greatly increased.
The inventor finds out through research that the fatigue damage of the wind power generation equipment is mainly caused by the following points: firstly, careless mistakes exist in the design and production links of equipment, such as grinding, electroplating and the like, which do not meet the requirements; secondly, the equipment is in a severe operating environment, such as overlarge humidity, overhigh temperature, corrosive gas and liquid, and the like; and thirdly, the stress of the equipment is unbalanced during operation to generate abrasion, and the wind power generation equipment is scrapped within the effective life for a long time.
Aiming at the problem of fatigue damage of wind power generation equipment, the research direction in the prior art mainly focuses on fatigue estimation, and software such as finite elements is utilized to simulate the health state of each component in a wind power generation unit, so that an improvement scheme for each component is provided, however, the method has low identification accuracy for the wind power generation unit which has fatigue failure, and the real-time performance for monitoring the fatigue condition of each component in the wind power generation unit is poor.
Disclosure of Invention
The fatigue failure detection method, the fatigue failure detection device, the fatigue failure detection equipment and the fatigue failure detection medium are provided for overcoming the defects of the existing method, and are used for solving the technical problems that in the prior art, the identification accuracy of a fatigue failure wind generating set is low, and the real-time performance of monitoring the fatigue condition is poor.
In a first aspect, an embodiment of the present application provides a method for detecting fatigue failure of a wind turbine generator system, including:
acquiring historical fault information of the wind generating set to be predicted as fault information to be predicted;
predicting the fatigue failure condition of the wind generating set to be predicted according to the failure information to be predicted and the fatigue failure prediction model to obtain a first prediction result;
acquiring historical transient data of the wind generating set to be predicted before a fault occurs, and taking the historical transient data as historical transient data to be predicted;
determining aperiodic load characteristics of the wind generating set to be predicted under each non-periodic load stress according to historical transient data to be predicted;
predicting the fatigue failure condition of the wind generating set to be predicted according to the aperiodic load characteristics to obtain a second prediction result;
and obtaining a third prediction result according to the first prediction result and the second prediction result.
In a second aspect, an embodiment of the present application provides a fatigue failure detection apparatus for a wind turbine generator system, including:
the first data acquisition module is used for acquiring historical fault information of the wind generating set to be predicted as fault information to be predicted;
the first prediction module is used for predicting the fatigue failure condition of the wind generating set to be predicted according to the fault information to be predicted and the fatigue failure prediction model to obtain a first prediction result;
the second data acquisition module is used for acquiring history transient data of the wind generating set to be predicted before the fault occurs and taking the history transient data as the history transient data to be predicted;
the load characteristic determination module is used for determining the aperiodic load characteristics of the wind generating set to be predicted under each aperiodic load stress borne by the wind generating set to be predicted according to historical transient data to be predicted;
the second prediction module is used for predicting the fatigue failure condition of the wind generating set to be predicted according to the aperiodic load characteristics to obtain a second prediction result;
and the third prediction module is used for obtaining a third prediction result according to the first prediction result and the second prediction result.
In a third aspect, an embodiment of the present application provides a fatigue failure detection device for a wind turbine generator system, including:
a memory;
a processor electrically connected to the memory;
the memory stores a computer program, and the computer program is executed by the processor to implement the fatigue failure detection method for the wind turbine generator system provided by the first aspect of the embodiments of the present application.
In a fourth aspect, an embodiment of the present application provides a wind farm controller, including: the third aspect of the embodiments of the present application provides a fatigue failure detection device for a wind turbine generator system.
In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the method for detecting fatigue failure of a wind turbine generator system provided in the first aspect of the embodiment of the present application.
The technical scheme provided by the embodiment of the application at least has the following beneficial effects:
according to the method and the device, the fatigue failure condition of the wind generating set to be predicted is predicted by adopting two prediction modes based on historical fault information and historical transient data, after the prediction results (the first prediction result and the second prediction result) obtained by the two prediction modes are comprehensively considered, a comprehensive prediction result (the third prediction result) can be obtained, the two prediction modes are complementary to each other, the fatigue failure of the wind generating set can be detected more accurately, the identification accuracy of the wind generating set with higher fatigue failure risk is improved, the detection and identification real-time performance is higher, and a more efficient detection scheme and a more referential detection result are provided for later-period operation and maintenance.
When prediction is carried out based on historical fault information, prediction is carried out according to the fatigue failure prediction model, so that the prediction efficiency and accuracy can be improved, and the reliability of a prediction result can be improved; when prediction is carried out based on historical transient data, the non-periodic load characteristics of the wind power generation set to be predicted under each non-periodic load stress can be determined according to the historical transient data, the characteristics can reflect the vibration characteristics of the wind power generation equipment in different vibration directions under the non-periodic load stress, and the fatigue condition of the wind power generation equipment can be accurately predicted based on the characteristics.
Additional aspects and advantages of the present 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 present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a method for detecting fatigue failure of a wind turbine generator system according to an embodiment of the present disclosure;
FIG. 2 is a diagram showing a first distribution curve and a second distribution curve of a normal unit in the embodiment of the present application;
FIG. 3 is a diagram illustrating a first distribution curve and a second distribution curve of a failed unit in the embodiment of the present application;
FIG. 4 is a schematic diagram of a distribution curve of accumulated fatigue values of a normal unit and a failed unit in the embodiment of the present application;
fig. 5 is a schematic structural framework diagram of a fatigue failure detection device of a wind turbine generator system according to an embodiment of the present disclosure;
fig. 6 is a structural framework schematic diagram of a fatigue failure detection device of a wind turbine generator system according to an embodiment of the present application.
Detailed Description
The present application is described in detail below, and examples of embodiments of the present application are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar parts or parts having the same or similar functions throughout. In addition, if a detailed description of the known art is not necessary for illustrating the features of the present application, it is omitted. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
It will be understood by those within the art that, unless otherwise defined, 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. 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 the context clearly indicates otherwise. 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. As used herein, the term "and/or" includes all, or any and all combinations of one or more of the associated listed items.
The terms referred to in this application will first be introduced and explained:
entropy of Permutation (Permutation Entropy): the signal mutation detection method proposed for the spatial characteristics of the time series itself increases the value of the permutation entropy as the data is more disordered.
The inventor of the application researches and discovers that when the vibration distribution characteristics of a wind generating set at different rotating speeds are analyzed and subjected to characteristic verification to mine the difference of signals, generally, the signals of the generator bearing vibration show typical random signal characteristics, when the bearing has a local fault, an impact component which is characterized by bearing passing frequency appears in the signals, the impact magnitude depends on the degree of the fault and the magnitude of load, and the stronger the fault, the larger the impact, the more violent the vibration of a transmission system.
In order to represent the vibration change condition in a certain rotating speed interval, the concept of the array entropy is introduced, and experiments prove that the method can well show the disorder degree of vibration data.
The following describes the technical solution of the present application and how to solve the above technical problems with specific embodiments.
The embodiment of the application provides a fatigue failure detection method for a wind generating set, and as shown in fig. 1, the method comprises the following steps:
s101, acquiring historical fault information of the wind generating set to be predicted as fault information to be predicted.
Specifically, historical fault information of each component in a wind generating set to be predicted in a statistical period is obtained, wherein each component in the wind generating set comprises but is not limited to equipment which can show abnormal information of a generator main bearing, a hub, blades, a gear box, a yaw bearing, a pitch bearing, a tower barrel, a cabin and the like through vibration data, the generator main bearing is taken as an example, and related faults comprise temperature abnormity, grease leakage, abnormal sound and the like; and judging whether the wind power generation equipment has faults or not by taking the fault work order which is already issued as a standard.
Optionally, the historical fault information includes a name (or number) of the wind turbine generator system, a fault category of each fault, a fault occurrence frequency of each fault, and a fatigue failure tag of the wind turbine generator system, wherein the fault occurrence frequency of each fault can be obtained through statistics according to a historical occurrence time of each fault.
Alternatively, the time range of the statistical period may be set according to actual requirements, for example, the time range from a certain time to the current time on a certain day in a certain month in a certain year may be set as one statistical period, and the time range from the time when the corresponding wind power generation device starts to operate online to the current time may also be set as one statistical period.
The inventor of the present application has studied and found that fatigue failure of a wind power generation device is often caused by a plurality of aperiodic load stresses, and a failure of a wind power generation device over time can be regarded as an intuitive representation that a plurality of aperiodic load stresses act on the device. Therefore, the fatigue condition of the wind generating set can be detected based on the historical fault information of the wind generating equipment before fatigue failure, and the identification of the wind generating set with fatigue failure (hereinafter, simply referred to as a failure set) can be further realized.
S102, predicting the fatigue failure condition of the wind turbine generator set to be predicted according to the fault information to be predicted and the fatigue failure prediction model to obtain a first prediction result, and then executing the step S106.
Optionally, the fatigue failure prediction model is trained by:
acquiring historical fault information of each wind generating set and fatigue failure data of each wind generating set, and respectively using the historical fault information of each wind generating set and the fatigue failure data of each wind generating set as sample fault information and sample fatigue failure data; inputting the sample fault information into a fatigue failure prediction model, and obtaining a sample prediction result based on the output of the fatigue failure prediction model; determining the loss of a sample prediction result according to the sample fatigue failure data; and adjusting parameters of the fatigue failure prediction model according to the loss of the sample prediction result.
Optionally, the information included in the historical fault information is as described above, and taking a generator as an example, the obtained historical fault information of the generator in each wind turbine generator set is shown in table 1.
TABLE 1 historical fault information for generators
Figure BDA0002497230590000061
Figure BDA0002497230590000071
In table 1, wt1 to wt3 in the first row respectively represent wind generating sets 1 to 3, and the meanings of subsequent set names are analogized in sequence, and are not listed in table 1; in table 1, the numbers in the second row and the second column to the lower right corner indicate the frequency (i.e. the number) of the corresponding faults of the wind generating set, for example, 23 in the second row and the second column indicates the frequency of the abnormal generator winding temperature of the wind generating set 1, and other numbers are the same.
Optionally, the fatigue failure data includes a record of whether the wind turbine generator set has fatigue failure within a statistical period, the record may be represented in the form of a label, and the label may be represented by words, numbers or other symbols; for example, the label "1" indicates that the wind turbine generator set has fatigue failure within the statistical period, and the label "0" indicates that the wind turbine generator set has not fatigue failure within the statistical period.
In one example, the fatigue failure data obtained for each wind turbine generator set is shown in table 2.
TABLE 2 fatigue failure data of each wind turbine
Name of unit Label (R)
wt1 1
wt2 1
wt3 0
wt4 1
wt5 0
…… ……
In table 2, wt1 to wt5 represent wind turbine generator systems 1 to 5, respectively, and the meanings of subsequent unit names are analogized, one for each, and are not listed in table 2.
Optionally, the fatigue failure prediction model is constructed based on a classification algorithm; the classification algorithm includes any one of logic regression, neural network, support vector machine and decision tree.
The construction of the fatigue failure prediction model is described below by taking a logistic regression algorithm as an example:
first, a linear boundary is constructed based on historical fault information, which can be represented by the following expression:
Figure BDA0002497230590000072
in the expression (1), theta is a historical fault frequency weight parameter vector; thetaiThe historical fault frequency weight parameter corresponding to the ith fault category can be obtained by calculation through maximum likelihood and gradient descent (referring to subsequent contents); x is the frequency of the historical fault, xiThe fault type is a historical fault frequency value of the ith fault type, and m is the total number of fault types; in the expression (1), i is [0, m ]]An integer within the range.
Secondly, constructing a prediction function based on the sigmoid mapping function as follows:
Figure BDA0002497230590000081
in the expression (2), hθ(x) And g (z) representing the obtained prediction result, wherein g (z) is a sigmoid mapping function, and the meanings of the rest parameters can be referred to as expression (1).
Then, a loss function is constructed as shown below:
Figure BDA0002497230590000082
in expression (3), y is a label representing whether the wind turbine generator set is fatigue-failed within a statistical period, COST (h)θ(x) Y) represents hθ(x) And y, and the meaning of the remaining parameters can be referred to expressions (1) and (2).
When the fatigue failure prediction model constructed according to the mode is trained, the historical fault frequency value, the initial historical fault frequency parameter vector and the total number of fault categories of each wind generating set are substituted into x, theta and m of the expression (2), and the prediction result h of the fatigue condition of each wind generating set is obtained through the expression (2)θ(x) Calculating the predicted result h according to expression (3)θ(x) And (5) adjusting the historical fault frequency weight parameter vector theta according to the obtained loss by a maximum likelihood method and a gradient descent method relative to the loss of the label y until a preset loss function convergence condition is met.
And when the historical fault frequency weight parameter vector theta is adjusted by a maximum likelihood method and a gradient descent method until a preset loss function convergence condition is met, firstly estimating an expression of the historical fault frequency weight parameter vector theta by using the maximum likelihood method, and then realizing iterative operation of theta by using the gradient descent method to obtain the final theta.
The core idea of maximum likelihood is to reversely deduce the parameter leading to the maximum result through the known result, while maximum likelihood estimation is the application of probability theory in statistics, it provides a method for estimating model parameters by giving observation data, namely, "model is determined, parameter is not determined", through several times of experimental observation, the probability of the sample appearing is maximized by using a certain parameter of the experiment, which is called maximum likelihood trajectory.
Logistic regression is a supervised learning, labeled. The method is characterized in that a result parameter capable of obtaining the maximum probability is derived from a known result, and the model can predict data more accurately as long as the parameter can be found.
Sigmoid function in the embodiment of the present application
Figure BDA0002497230590000091
The value of (b) can be regarded as the posterior probability (determined by the sigmoid function property) that the test tuple belongs to class "1" (i.e. the unit label in the above), and then:
Figure BDA0002497230590000092
expression (4) can be rewritten as:
p(y|X；θ)＝g(z)y(1-g(z))1-yexpression (5)
Expression (5) represents the posterior probability of tuple class labeled y under the parameter θ, and X represents the input sample data.
Assuming a sample is obtained at this time, the joint probability can be described as
Figure BDA0002497230590000093
The size of the model can reflect the loss cost of the model, and the larger the joint probability is, the closer the learning result is to the real situation is; the smaller the joint probability, the more the learning result deviates from the real situation.
Carrying out logarithm processing on the joint probability:
Figure BDA0002497230590000094
to this end, a loss cost function can be obtained:
Figure BDA0002497230590000095
expression (7) is a rewrite of expression (3), yiRepresenting the predicted value of the ith sample, wherein the value range is 0 or 1; z is a radical ofiI.e. thetaTXiA value obtained by substituting the ith sample into expression (1) is represented; in the expressions (6) and (7), i is [0, n ]]An integer within the range.
The basic principle of solving the parameter theta according to the gradient descent method is as follows: the negative direction of the gradient is the direction in which the loss function is reduced most rapidly, and the minimum value of the loss function is solved through iteration, so that the parameter theta can be obtained, and the parameter theta is also the final solution of the logistic regression.
The variation of each weight component is:
Figure BDA0002497230590000096
in expression (8), θjA value representing the jth dimension of the weight parameter θ; eta is learning rate and control step length.
Figure BDA0002497230590000101
Thus, the variable for updating the weights by the gradient descent method is available:
Figure BDA0002497230590000102
in expressions (9) and (10), j represents the dimension of the weight parameter θ, θjRepresenting the value of the weighting parameter theta in dimension j, thetaj: value assignment to theta after expression of equal signj，xijRepresents the ith sample in weightThe value in the j-th dimension of the parameter θ, and the other parameter meanings can be referred to the parameter meanings of the expressions.
The neural network, the support vector machine and the decision tree in the embodiment of the present application are all existing algorithms, and the application of these algorithms in the classification problem is the existing one, and a person skilled in the art can understand how to apply these algorithms to realize the classification in the embodiment of the present application, so as to construct a corresponding fatigue failure prediction model, and the above algorithms are not described one by one here.
S103, acquiring historical transient data of the wind generating set to be predicted before the fault occurs, and using the historical transient data as historical transient data to be predicted.
Specifically, historical transient data of each component in the wind generating set to be predicted before the fault occurs is obtained, and as mentioned above, the wind generating set component may be a generator main bearing, a hub, a blade, a gear box, a yaw bearing, a pitch bearing, a tower, a nacelle, and the like.
Optionally, the historical transient data comprises: rotational speed data, nacelle vibration data in a first direction, and nacelle vibration data in a second direction. Optionally, the historical transient data may also include wind speed data. The nacelle vibration data includes nacelle vibration acceleration.
The historical transient data in the embodiment of the application can adopt data with corresponding frequency according to actual requirements, for example, any one of second-level data, millisecond-level data and microsecond-level data, so as to improve the accuracy of subsequent calculation, and the higher the data frequency is, the more beneficial the improvement of the accuracy of the subsequent calculation is.
The first direction and the second direction may be selected according to an actual vibration direction or according to actual requirements, and in one example, based on an angle of facing the impeller of the wind turbine generator system, the first direction may be a left-to-right direction or a right-to-left direction of the wind turbine generator system, i.e., a radial direction of the nacelle, and the second direction may be a front-to-back direction or a back-to-front direction of the wind turbine generator system, i.e., an axial direction of the nacelle.
And S104, determining the non-periodic load characteristics of the wind generating set to be predicted under each non-periodic load stress according to the historical transient data to be predicted.
Optionally, determining a first arrangement entropy value of the cabin vibration data in the first direction under each rotating speed data, and a second arrangement entropy value of the cabin vibration data in the second direction under each rotating speed data; and determining the aperiodic load characteristics of the wind generating set to be predicted under each non-periodic load stress borne by the wind generating set according to the first arrangement entropy and the second arrangement entropy.
Optionally, before determining the above permutation entropy, the method may further include: and sequentially cleaning, filtering, sliding windowing and grouping the acquired historical transient data.
Optionally, during the cleaning process, null values and abnormal values in the historical transient data may be deleted, wherein whether a certain historical transient data is an abnormal value may be determined according to whether the data is in a preset normal value range, or according to the difference between the data and other data.
Optionally, in the filtering process, the historical transient data may be filtered based on a preset filtering rule, and the filtering rule may be set according to actual requirements; in one example, if the filtering rule is set as: enabling the absolute value of the vibration acceleration of the engine room to be between 0 and 0.45, deleting the vibration acceleration of the engine room, the absolute value of which does not accord with the rule, during filtering, and only keeping the vibration acceleration of the engine room, the absolute value of which is between 0 and 0.45; in another example, if the filtering rule is set as: and if the wind speed value is not less than 3m/s, deleting the wind speed data less than 3m/s during filtering, and only keeping the wind speed data more than or equal to 3 m/s.
Optionally, after the cleaning and filtering are completed, the remaining data amount may be detected, and it is determined whether the remaining data amount is less than 30% of the original data amount before the data cleaning and data filtering are performed, if the remaining data amount is greater than or equal to 30% of the original data amount, the subsequent steps are continuously performed, and if the remaining data amount is less than 30% of the original data amount, the cleaning or filtering rule may be reset, so that the remaining data amount after the data cleaning and data filtering are performed again is greater than or equal to 30% of the original data amount, so as to ensure that the subsequent calculation has a larger data amount basis, thereby making the calculation result more accurate.
Optionally, in the sliding windowing process, the historical transient data is divided into a plurality of data segments according to a time range, for example, historical transient data within one month is taken as data of one data segment, that is, each data segment has a data amount of one month in total, and the sliding step size of each data segment is one week.
Optionally, in the data grouping process, the historical transient data may be grouped based on the rotation speed data, specifically, one decimal is reserved for the rotation speed data, the rotation speed data with the same value after one decimal is reserved is grouped into one group, the first arrangement entropy calculation is performed on the nacelle vibration data in the first direction corresponding to the same group of rotation speed data, and the second arrangement entropy calculation is performed on the nacelle vibration data in the second direction corresponding to the same group of rotation speed data.
In one example, the speed data, the nacelle vibration data in the first direction, and the nacelle vibration data in the second direction are shown in the first, third, and fourth columns of table 1, and the data that retains a one-bit fraction of the speed data is shown in the second column of table 1, where the x-direction in table 1 represents the first direction and the y-direction represents the second direction.
TABLE 3 rotational speed data and nacelle vibration data
Figure BDA0002497230590000121
The grouping of the rotation speed data with one decimal and the corresponding cabin vibration data in table 3 is shown in table 4, the rotation speed data with the same value and the corresponding cabin vibration acceleration data in table 4 are in one group, and the arrangement entropy values are calculated respectively for the cabin vibration speeds in the x direction and the y direction of each group.
TABLE 4 rotational speed data and nacelle vibration data
Figure BDA0002497230590000131
Optionally, determining the aperiodic load characteristics of the wind turbine generator set to be predicted under each aperiodic load stress according to the first arrangement entropy and the second arrangement entropy, and including:
determining a first distribution curve of the first arrangement entropy along with the change of the rotating speed according to the first arrangement entropy and the corresponding rotating speed data; determining a second distribution curve of the second permutation entropy along with the change of the rotating speed according to the second permutation entropy and the corresponding rotating speed data; and determining the aperiodic load characteristic according to the number of the cross points of the first distribution curve and the second distribution curve.
The inventors of the present application have conducted studies to find that the application of aperiodic load stress causes vibration of the wind power generation equipment, and may possibly cause fatigue failure.
Meanwhile, when the inventor analyzes a large number of wind generating set cases, the arrangement entropy values of the cabin vibration data of a normal set (namely, a wind generating set without fatigue failure) and a failure set (or called an abnormal set, namely, a wind generating set with fatigue failure) in the same wind power plant are compared. Alternatively, the first direction may be an x-direction and the second direction may be a y-direction. A distribution curve (i.e., a first distribution curve) of the arrangement entropy values (hereinafter referred to as first arrangement entropy values) of the cabin vibration data of the normal unit in the first direction, as shown by a solid line in fig. 2; a distribution curve (i.e., a second distribution curve) of the arrangement entropy values (hereinafter referred to as second arrangement entropy values) of the cabin vibration data of the normal unit in the second direction, as shown by a dotted line in fig. 2; the first and second distribution curves of the failed unit are shown as solid and dashed lines in fig. 3, respectively.
As can be seen from fig. 2 and fig. 3, in each rotational speed data segment, both the first arrangement entropy value in the x direction and the second arrangement entropy value in the y direction change substantially linearly, and when the x direction is the left-right direction of the wind turbine generator set and the y direction is the front-back direction of the wind turbine generator set, the first arrangement entropy value is slightly higher than the second arrangement entropy value; for the normal unit shown in fig. 2, there is substantially no intersection between the first distribution curve and the second distribution curve, and for the failed unit shown in fig. 3, in some rotation speed intervals (the rotation speed interval is not fixed), the first arrangement entropy and the second arrangement entropy are irregular, and there are many intersections between the first distribution curve and the second distribution curve, such as intersections in a circle in fig. 3.
Therefore, for the wind generating set to be predicted, the characteristic that the vibration of the component fluctuates along with the rotating speed can be characterized by the intersection point of a first distribution curve of a first arrangement entropy value and a second distribution curve of a second arrangement entropy value obtained based on the vibration data of the engine room in the x direction and the y direction, and therefore the application determines the non-periodic load characteristic of the non-periodic load stress causing the vibration according to the intersection point of the first distribution curve and the second distribution curve.
In an alternative embodiment, the intersection points intersections num of the first distribution curve and the second distribution curve may be taken as aperiodic loading characteristics; in another alternative embodiment, the intersection intersections num may be multiplied by a certain coefficient according to actual requirements, and the result is used as the aperiodic load characteristic.
And S105, predicting the fatigue failure condition of the wind generating set to be predicted according to the aperiodic load characteristics to obtain a second prediction result.
Optionally, predicting the fatigue failure condition of the wind turbine generator set to be predicted according to the aperiodic load characteristics includes:
determining a fatigue value of the wind generating set to be predicted under each aperiodic load stress according to the aperiodic load characteristics; determining an accumulated fatigue value of the wind generating set to be predicted under each aperiodic load stress according to the fatigue value of the wind generating set to be predicted under each aperiodic load stress; determining characteristic parameters of the wind generating set to be predicted, wherein the accumulated fatigue value of the wind generating set under each aperiodic load stress changes along with the non-periodic load stress; and comparing the characteristic parameters with the characteristic parameter threshold value, and predicting the fatigue failure condition of the wind generating set to be predicted according to the comparison result.
In an optional embodiment, the accumulated fatigue value of the wind power generation equipment over time can be calculated according to the aperiodic load characteristic and the Miner-Palmgren fatigue theory; specifically, according to the aperiodic load characteristics, by using the dynamics principle, the fatigue value under each aperiodic load stress can be obtained as follows:
Figure BDA0002497230590000151
in expression (11), S represents a fatigue value under a certain aperiodic load stress, d represents an aperiodic load characteristic under the aperiodic load stress, and α represents a material constant in terms of dynamics.
According to the Miner-Palmgren fatigue theory, the fatigue damage of the wind power generation equipment generated under each aperiodic load stress can be linearly superposed in the following way to obtain the accumulated fatigue value under each aperiodic load stress:
Figure BDA0002497230590000152
in expression (12), F represents an accumulated fatigue value of the wind power generation equipment under each aperiodic load stress, and when F is 1, fatigue failure of the wind power generation equipment occurs; n represents the number of aperiodic load stresses, i represents the i-th aperiodic load stress of the n aperiodic load stresses, and S (i) represents the fatigue value under the i-th aperiodic load stress.
The accumulated fatigue value F of the wind power generation equipment is continuously increased along with the time, a series of data of the accumulated fatigue values F can be obtained, when the inventor analyzes a large batch of wind power generation set cases, the accumulated fatigue values F of a normal set and a failure set of the same wind power plant are compared as shown in fig. 4, a curve wt1 in fig. 4 is a distribution curve of the accumulated fatigue values of the failure set, wt2, wt3 and wt4 are distribution curves of the accumulated fatigue values of 3 normal sets respectively, and the abscissa in fig. 4 is the frequency of generation of the aperiodic load, namely the number of the aperiodic load stress; it can be seen from fig. 4 that the variation range of the accumulated fatigue value of the failed unit is higher than that of the normal unit.
Therefore, the fatigue failure condition of each component in the wind generating set to be predicted can be predicted based on the change trend of the accumulated fatigue value.
Optionally, determining a characteristic parameter of the wind turbine generator system to be predicted, which varies with the aperiodic load stress under each aperiodic load stress, includes:
performing linear fitting on the accumulated fatigue value of the wind generating set to be predicted under each aperiodic load stress to obtain an accumulated fatigue value linear equation of the wind generating set to be predicted; and extracting the slope value of the linear equation of the accumulated fatigue value as a characteristic parameter.
In an optional implementation mode, a linear regression algorithm is adopted to perform linear fitting on the accumulated fatigue values of the wind generating set to be predicted at each aperiodic load acting moment, so that a linear equation of the accumulated fatigue values of the wind generating set to be predicted is obtained.
Optionally, the characteristic parameter threshold is determined by:
acquiring historical transient data of each wind generating set before a fault occurs, and taking the historical transient data as sample historical transient data; determining aperiodic load characteristics of each wind generating set under each stress load stress born by the wind generating set according to the historical transient data of the sample; determining the accumulated fatigue value of each wind generating set under each aperiodic load stress according to the aperiodic load characteristics; determining an accumulated fatigue value distribution curve of the accumulated fatigue value of each wind generating set along with the variation of the aperiodic load stress; and determining a characteristic parameter threshold according to the distribution parameters of the accumulated fatigue value distribution curve.
Optionally, according to the sample historical transient data, the aperiodic load characteristic of each wind turbine generator set under each load stress is determined, and the principle and the optional implementation thereof are similar to those of the foregoing step S104 and the optional implementation of the step S104, for example, by determining the arrangement entropy of the nacelle vibration data in the sample historical transient data, the aperiodic load characteristic of each wind turbine generator set under each load stress is further determined, and the related content of the step S104 may be referred to specifically.
Optionally, determining an accumulated fatigue value of each wind generating set at each non-periodic load acting time according to the non-periodic load characteristics, including:
for each wind generating set, determining a fatigue value of the wind generating set under each aperiodic load stress according to the aperiodic load characteristics of the wind generating set under each aperiodic load stress; and determining the accumulated fatigue value of the wind generating set under each aperiodic load stress according to the fatigue value of the wind generating set under each aperiodic load stress.
In an alternative embodiment, the manner of calculating the fatigue value under each aperiodic loading stress according to the aperiodic loading characteristics can refer to the related content of the aforementioned expression (11), and is not described herein again.
In an optional embodiment, the accumulated fatigue value of the wind turbine generator set under each aperiodic load stress is determined according to the fatigue value of the wind turbine generator set under each aperiodic load stress, and specific manner of the accumulated fatigue value of the wind turbine generator set under each aperiodic load stress may refer to the related content of the aforementioned expression (12), and details thereof are omitted here.
In an alternative embodiment, a cumulative fatigue value profile of the cumulative fatigue value of each wind energy installation as a function of the non-periodic loading is determined, the profile of which can be referred to the profile in fig. 4.
In an alternative embodiment, determining the characteristic parameter threshold according to the distribution parameter of the accumulated fatigue value distribution curve includes:
for each wind generating set, carrying out linear fitting on the accumulated fatigue value of the wind generating set at each aperiodic load acting moment to obtain a linear equation of the accumulated fatigue value of the wind generating set; extracting a slope value of a linear equation of the accumulated fatigue values of the wind generating sets; deleting the slope value of the linear equation of the accumulated fatigue value with the slope value being in the first 20 percent to prevent the accurate estimation of the subsequent normal distribution parameters from being influenced due to the overlarge slope value corresponding to the failed unit; estimating normal distribution parameters of the slope values of the rest wind generating sets according to a maximum likelihood estimation method (according to research, the corresponding slope values of the normal sets generally present normal distribution), wherein the normal distribution parameters comprise a mean value mu and a standard difference sigma; from the found normal distribution parameter, the characteristic parameter threshold value μ +4 σ can be set (and may be set to other values depending on the actual situation).
In one example, after the characteristic parameter of the wind generating set to be predicted is compared with the characteristic parameter threshold, if the comparison result is that the characteristic parameter is greater than the characteristic parameter threshold, the obtained second prediction result is that the risk of fatigue failure of the wind generating set to be predicted is higher; and if the comparison result is that the characteristic parameter is smaller than or equal to the characteristic parameter threshold value, the risk that the wind generating set to be predicted has fatigue failure is low according to the obtained second prediction result.
Optionally, when the fatigue failure condition of the wind turbine generator set to be predicted is predicted according to the aperiodic load characteristic, the accumulated fatigue value F of the wind turbine generator set to be predicted may be calculated according to the aperiodic load characteristic, and the specific calculation manner may refer to the foregoing embodiment, where the accumulated fatigue value F of the wind turbine generator set to be predicted is used as an input, and an outlier detection algorithm (such as an isolated forest algorithm) is used to perform anomaly identification, so as to predict the risk of fatigue failure of the wind turbine generator set to be predicted.
Optionally, when the fatigue failure condition of the wind turbine generator set to be predicted is predicted according to the aperiodic load characteristic, the accumulated fatigue value F of the wind turbine generator set to be predicted at each time point or under each aperiodic load stress can be used as an input, and abnormality identification is performed according to any one of algorithms such as a logistic regression algorithm, a support vector machine and a neural network, so that the risk of fatigue failure of the wind turbine generator set to be predicted is predicted.
The outlier detection algorithm, the logistic regression algorithm, the support vector machine, the neural network and other algorithms in the embodiment of the application are all existing algorithms, and a person skilled in the art can understand how to apply the algorithms to realize the abnormality identification of the accumulated fatigue value F of the wind generating set to be predicted in the embodiment of the application, and the algorithms are not described one by one.
And S106, obtaining a third prediction result according to the first prediction result and the second prediction result.
Optionally, weights are respectively set for the first prediction result and the second prediction result; and combining the first prediction result and the second prediction result based on the weight to obtain a third prediction result.
In an alternative embodiment, the third prediction may be determined by:
l (x) ═ α h (x) +(1- α) f (x) expression (13)
In the expression (13), h (x) represents a first prediction result, when h (x) is 1, the risk that the wind generating set to be predicted has fatigue failure is large, and when h (x) is 0, the risk that the wind generating set to be predicted has fatigue failure is small; (x) shows a second prediction result, wherein if f (x) is 1, the risk of fatigue failure of the wind generating set to be predicted is high, and if f (x) is 0, the risk of fatigue failure of the wind generating set to be predicted is low; α is a weight of h (x), which can be determined according to actual needs or empirical values, in an alternative embodiment, the weight has a value in the range of [0,1], in another alternative embodiment, the weight has a value in the range of [0,0.5 ]; l (x) represents a third prediction, and L (x) has a value between 0 and 1.
Optionally, the fatigue failure detection method for the wind turbine generator system provided in the embodiment of the present application, on the basis of the above steps S101 to S106, further includes: and comparing the third prediction result with a result threshold, and sending out fatigue failure early warning of the wind generating set to be predicted when the third prediction result is greater than the result threshold.
In an alternative implementation, the result threshold of the present application can be set to a value between 0 and 1.
The third prediction result comprehensively considers the two prediction results obtained by the two prediction modes, so that the fatigue condition of the wind generating set to be predicted can be more accurately reflected, and the fatigue failure can be more accurately predicted and early warned.
Based on the same inventive concept, the fatigue failure detection device of the wind turbine generator system provided in the embodiment of the present application, as shown in fig. 5, includes: a first data acquisition module 501, a first prediction module 502, a second data acquisition module 503, a payload characteristic determination module 504, a second prediction module 505, and a third prediction module 506.
The first data obtaining module 501 is configured to obtain historical fault information of the wind turbine generator system to be predicted, where the historical fault information is used as fault information to be predicted.
The first prediction module 502 is configured to predict a fatigue failure condition of the wind turbine generator set to be predicted according to the fault information to be predicted and the fatigue failure prediction model, so as to obtain a first prediction result.
The second data obtaining module 503 is configured to obtain historical transient data of the wind turbine generator set before the fault occurs, where the historical transient data is used as historical transient data to be predicted.
And the load characteristic determining module 504 is configured to determine aperiodic load characteristics of the wind turbine generator system to be predicted under each aperiodic load stress borne by the wind turbine generator system to be predicted according to the historical transient data to be predicted.
And the second prediction module 505 is configured to predict the fatigue failure condition of the wind turbine generator to be predicted according to the aperiodic load characteristic, so as to obtain a second prediction result.
And a third prediction module 506, configured to obtain a third prediction result according to the first prediction result and the second prediction result.
Optionally, the fatigue failure detection apparatus 500 of the wind turbine generator system provided in this application further includes: and an early warning module.
The early warning module is used for: and comparing the third prediction result with a result threshold, and sending out fatigue failure early warning of the wind generating set to be predicted when the third prediction result is larger than the result threshold.
Optionally, the fatigue failure detection apparatus 500 of the wind turbine generator system provided in this application further includes: and a model training module.
The model training module is used for training the fatigue failure prediction model in the following modes:
acquiring historical fault information of each wind generating set and fatigue failure data of each wind generating set, and respectively using the historical fault information of each wind generating set and the fatigue failure data of each wind generating set as sample fault information and sample fatigue failure data; inputting the sample fault information into a fatigue failure prediction model, and obtaining a sample prediction result based on the output of the fatigue failure prediction model; determining the loss of a sample prediction result according to the sample fatigue failure data; and adjusting parameters of the fatigue failure prediction model according to the loss of the sample prediction result.
Optionally, the load characteristic determining module 504 is specifically configured to: determining a first arrangement entropy value of the cabin vibration data in the first direction under each rotating speed data and a second arrangement entropy value of the cabin vibration data in the second direction under each rotating speed data; and determining the non-periodic load characteristics of the wind generating set to be predicted under each non-periodic load stress according to the first arrangement entropy value and the second arrangement entropy value.
Optionally, the load characteristic determining module 504 is specifically configured to: determining a first distribution curve of the first arrangement entropy along with the change of the rotating speed according to the first arrangement entropy and the corresponding rotating speed data; determining a second distribution curve of the second arrangement entropy along with the change of the rotating speed according to the second arrangement entropy and the corresponding rotating speed data; and determining the aperiodic load characteristic according to the number of the intersection points of the first distribution curve and the second distribution curve.
Optionally, the second prediction module 505 is specifically configured to: determining a fatigue value of the wind generating set to be predicted under the action of each aperiodic load according to the aperiodic load characteristics; determining the accumulated fatigue value of the wind generating set to be predicted at each non-periodic load acting moment according to the fatigue value of the wind generating set to be predicted under each non-periodic load acting moment; determining characteristic parameters of the wind generating set to be predicted, wherein the accumulated fatigue value of the wind generating set at each non-periodic load acting moment changes along with the non-periodic load; and comparing the characteristic parameters with the characteristic parameter threshold value, and predicting the fatigue failure condition of the wind generating set to be predicted according to the comparison result.
Optionally, the second prediction module 505 is specifically configured to: performing linear fitting on the accumulated fatigue values of the wind generating set to be predicted at each non-periodic load acting moment to obtain an accumulated fatigue value linear equation of the wind generating set to be predicted; and extracting the slope value of the linear equation of the accumulated fatigue value as a characteristic parameter.
Optionally, the second prediction module 505 is specifically configured to determine the feature parameter threshold by:
acquiring historical transient data of each wind generating set before a fault occurs, and taking the historical transient data as sample historical transient data; determining aperiodic load characteristics of each wind generating set under each load stress borne according to the historical transient data of the sample; determining the accumulated fatigue value of each wind driven generator set at each non-periodic load acting moment according to the non-periodic load characteristics; determining an accumulated fatigue value distribution curve of the accumulated fatigue value of each wind generating set along with the variation of the aperiodic load; and determining a characteristic parameter threshold according to the distribution parameters of the accumulated fatigue value distribution curve.
Optionally, the third prediction module 506 is specifically configured to: respectively setting weights for the first prediction result and the second prediction result; and combining the first prediction result and the second prediction result based on the weight to obtain a third prediction result.
The fatigue failure detection device 500 of the wind generating set of the present embodiment can execute any one of the fatigue failure detection methods of the wind generating set provided by the embodiments of the present application, which are similar to the principle of the present embodiment, and the content not shown in detail in the present embodiment may refer to the previous method embodiments, which are not described herein again.
Based on the same inventive concept, the embodiment of the application provides a wind power plant controller, which comprises: fatigue failure detection equipment of the wind generating set; the apparatus comprises: the storage and the processor are electrically connected.
The memory stores a computer program executed by the processor to implement any one of the methods for detecting fatigue failure of a wind turbine generator system provided by the embodiments of the present application.
Those skilled in the art will appreciate that the electronic devices provided in the embodiments of the present application may be specially designed and manufactured for the required purposes, or may comprise known devices in general-purpose computers. These devices have stored therein computer programs that are selectively activated or reconfigured. Such a computer program may be stored in a device (e.g., computer) readable medium or in any type of medium suitable for storing electronic instructions and respectively coupled to a bus.
In an alternative embodiment, the present application provides a fatigue failure detection apparatus of a wind turbine generator system, as shown in fig. 6, the fatigue failure detection apparatus including: the memory 601 and the processor 602 are electrically connected, such as by a bus 603.
Optionally, the memory 601 is used for storing application program codes for executing the scheme of the present application, and the processor 602 controls the execution. The processor 602 is configured to execute the application program code stored in the memory 601 to implement any one of the methods for detecting fatigue failure of a wind turbine generator system provided by the embodiments of the present application.
Memory 601 may be a ROM (Read-Only Memory) or other type of static storage device that may store static information and instructions, which may be, but is not limited to, RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read-Only Memory) or other optical disk storage, optical disk storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The Processor 602 may be a CPU (Central Processing Unit), a general purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure herein. The processor 602 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
Bus 603 may include a path that transfers information between the above components. The bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus.
Optionally, the fatigue failure detection device 600 of the wind park may further comprise a transceiver 604. The transceiver 604 may be used for reception and transmission of signals. The transceiver 604 may allow the electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. It should be noted that the transceiver 604 is not limited to one in practical applications.
Optionally, the fatigue failure detection device 600 of the wind park may further comprise an input unit 605. The input unit 605 may be used to receive input numeric, character, image and/or sound information or to generate key signal inputs related to user settings and function control of the fatigue failure detecting apparatus 600 of the wind turbine generator set. The input unit 605 may include, but is not limited to, one or more of a touch screen, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, a camera, a microphone, and the like.
Optionally, the fatigue failure detection apparatus 600 of the wind turbine generator set may further comprise an output unit 606. The output unit 606 may be used to output or present information processed by the processor 602. The output unit 806 may include, but is not limited to, one or more of a display device, a speaker, a vibration device, and the like.
Although fig. 6 illustrates a fatigue failure detection apparatus 600 for a wind power plant having various devices, it should be understood that not all of the illustrated devices are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
The fatigue failure detection device 600 of the wind generating set provided by the embodiment of the present application has the same inventive concept as that of the foregoing embodiments, and the content not shown in detail in the fatigue failure detection device may refer to the foregoing embodiments, and is not described again here.
Based on the same inventive concept, the embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements any one of the fatigue failure detection methods of the wind turbine generator system provided by the embodiment of the present application.
The computer-readable medium can include, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magnetic-optical disks, ROMs, RAMs, EPROMs (Erasable Programmable Read-Only memories), EEPROMs, flash Memory, magnetic 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 embodiment of the application provides a computer-readable storage medium suitable for any one of the above methods for detecting fatigue failure of a wind generating set. And will not be described in detail herein.
By applying the embodiment of the application, at least the following beneficial effects can be realized:
1) according to the method and the device, the fatigue failure condition of the wind generating set to be predicted is predicted by two prediction modes based on historical fault information and historical transient data, after the prediction results (the first prediction result and the second prediction result) obtained by the two prediction modes are comprehensively considered, the obtained comprehensive prediction result (the third prediction result) is obtained, the two prediction modes are mutually complementary, the fatigue failure of the wind generating set can be more accurately detected, the identification accuracy of the wind generating set with higher fatigue failure risk is improved, the detection and identification real-time performance is higher, and a more efficient detection scheme and a more referential detection result are provided for later-period operation and maintenance.
2) According to the embodiment of the application, when prediction is carried out based on historical fault information, prediction is carried out according to the fatigue failure prediction model, the fatigue failure prediction model can be trained based on the historical fault information and the fatigue failure data of each wind generating set, the algorithm advantages of statistics and machine learning are combined, the trained fatigue failure prediction model is adopted for prediction, the prediction accuracy can be improved, and the reliability of prediction results is improved.
3) According to the embodiment of the application, when prediction is carried out based on historical transient data, the aperiodic load characteristics of the wind generating set to be predicted under each aperiodic load stress can be determined according to the historical transient data, the characteristics can reflect the vibration characteristics of the wind generating equipment in different vibration directions under the aperiodic load stress, and the accumulated fatigue value of the wind generating equipment can be obtained based on the characteristics and the Miner-Palmgren fatigue theory, so that the fatigue condition of the wind generating equipment can be accurately predicted.
Those of skill in the art will understand that various operations, methods, steps in the processes, measures, solutions discussed in the present application may be alternated, modified, combined, or deleted. Further, other steps, measures, schemes in various operations, methods, flows that have been discussed in this application may be alternated, modified, rearranged, decomposed, combined, or deleted. Further, steps, measures, schemes in the prior art having various operations, methods, procedures disclosed in the present application may also be alternated, modified, rearranged, decomposed, combined, or deleted.
In the description of the present application, it is to be understood that the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figures may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, in different orders, and may be performed alternately or in turns with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.

Claims (15)

1. A fatigue failure detection method of a wind generating set is characterized by comprising the following steps:
acquiring historical fault information of the wind generating set to be predicted as fault information to be predicted;
predicting the fatigue failure condition of the wind generating set to be predicted according to the fault information to be predicted and the fatigue failure prediction model to obtain a first prediction result;
acquiring historical transient data of the wind generating set to be predicted before the fault occurs, and taking the historical transient data as historical transient data to be predicted;
determining aperiodic load characteristics of the wind generating set to be predicted under each aperiodic load stress borne by the wind generating set to be predicted according to the historical transient data to be predicted;
predicting the fatigue failure condition of the wind generating set to be predicted according to the aperiodic load characteristics to obtain a second prediction result;
and obtaining a third prediction result according to the first prediction result and the second prediction result.
2. The fatigue failure detection method of claim 1, wherein the fatigue failure prediction model is trained by:
acquiring historical fault information of each wind generating set and fatigue failure data of each wind generating set, and respectively using the historical fault information of each wind generating set and the fatigue failure data of each wind generating set as sample fault information and sample fatigue failure data;
inputting the sample fault information into the fatigue failure prediction model, and obtaining a sample prediction result based on the output of the fatigue failure prediction model;
determining the loss of the sample prediction result according to the sample fatigue failure data;
and adjusting parameters of the fatigue failure prediction model according to the loss of the sample prediction result.
3. The fatigue failure detection method of claim 2, wherein the fatigue failure prediction model is constructed based on a classification algorithm;
the classification algorithm comprises any one algorithm of logistic regression, neural networks, support vector machines and decision trees.
4. The fatigue failure detection method of claim 1, wherein the historical transient data comprises: the method comprises the steps of obtaining rotation speed data, cabin vibration data in a first direction and cabin vibration data in a second direction;
and determining the non-periodic load characteristics of the wind generating set to be predicted under each non-periodic load stress according to the historical transient data, wherein the determining comprises the following steps:
determining a first arrangement entropy value of the cabin vibration data in the first direction under each rotating speed data, and a second arrangement entropy value of the cabin vibration data in the second direction under each rotating speed data;
and determining the aperiodic load characteristics of the wind generating set to be predicted under each aperiodic load stress according to the first arrangement entropy and the second arrangement entropy.
5. The fatigue failure detection method according to claim 4, wherein the determining the aperiodic load characteristic of the wind turbine generator set to be predicted at each aperiodic load stress according to the first arrangement entropy and the second arrangement entropy comprises:
determining a first distribution curve of the first arrangement entropy along with the change of the rotating speed according to the first arrangement entropy and the corresponding rotating speed data;
determining a second distribution curve of the second permutation entropy along with the change of the rotating speed according to the second permutation entropy and the corresponding rotating speed data;
and taking the number of the intersection points of the first distribution curve and the second distribution curve as the aperiodic load characteristic.
6. The fatigue failure detection method according to claim 1, wherein the predicting the fatigue failure condition of the wind turbine generator set to be predicted according to the aperiodic load characteristic comprises:
determining fatigue values of the wind generating set to be predicted under each aperiodic load stress according to the aperiodic load characteristics;
determining an accumulated fatigue value of the wind generating set to be predicted under each aperiodic load stress according to the fatigue value of the wind generating set to be predicted under each aperiodic load stress;
determining characteristic parameters of the wind generating set to be predicted, wherein the accumulated fatigue values of the wind generating set to be predicted under the aperiodic load stress vary with the aperiodic load stress;
and comparing the characteristic parameters with characteristic parameter thresholds, and predicting the fatigue failure condition of the wind generating set to be predicted according to the comparison result.
7. The fatigue failure detection method according to claim 6, wherein the determining the characteristic parameter of the wind turbine generator set to be predicted, in which the accumulated fatigue value under each aperiodic load stress varies with the aperiodic load stress, comprises:
performing linear fitting on the accumulated fatigue values of the wind generating set to be predicted under each aperiodic load stress to obtain an accumulated fatigue value linear equation of the wind generating set to be predicted;
and extracting a slope value of the linear equation of the accumulated fatigue value as the characteristic parameter.
8. The fatigue failure detection method of claim 6, wherein the characteristic parameter threshold is determined by:
acquiring historical transient data of each wind generating set before a fault occurs, and taking the historical transient data as sample historical transient data;
determining aperiodic load characteristics of each wind generating set under each born aperiodic load stress according to the historical transient data of the sample;
determining an accumulated fatigue value of each wind generating set under each aperiodic load stress according to the aperiodic load characteristics;
determining an accumulated fatigue value profile of the accumulated fatigue value of each of the wind turbine generators as a function of the aperiodic load stress;
and determining the characteristic parameter threshold according to the distribution parameters of the accumulated fatigue value distribution curve.
9. The fatigue failure detection method according to claim 1, wherein obtaining a third predicted result from the first predicted result and the second predicted result comprises:
setting weights for the first prediction result and the second prediction result respectively;
and combining the first prediction result and the second prediction result based on the weight to obtain a third prediction result.
10. The fatigue failure detection method of claim 1, further comprising:
and comparing the third prediction result with a result threshold value, and sending out fatigue failure early warning of the wind generating set to be predicted when the third prediction result is larger than the result threshold value.
11. A wind generating set's fatigue failure detection device characterized in that includes:
the first data acquisition module is used for acquiring historical fault information of the wind generating set to be predicted as fault information to be predicted;
the first prediction module is used for predicting the fatigue failure condition of the wind generating set to be predicted according to the fault information to be predicted and the fatigue failure prediction model to obtain a first prediction result;
the second data acquisition module is used for acquiring historical transient data of the wind generating set to be predicted before the fault occurs and taking the historical transient data as the historical transient data to be predicted;
the load characteristic determination module is used for determining the aperiodic load characteristics of the wind generating set to be predicted under each aperiodic load stress borne by the wind generating set to be predicted according to the historical transient data to be predicted;
the second prediction module is used for predicting the fatigue failure condition of the wind generating set to be predicted according to the aperiodic load characteristics to obtain a second prediction result;
and the third prediction module is used for obtaining a third prediction result according to the first prediction result and the second prediction result.
12. The fatigue failure detection apparatus of claim 11, further comprising:
and the early warning module is used for comparing the third prediction result with a result threshold value and sending out fatigue failure early warning of the wind generating set to be predicted when the third prediction result is larger than the result threshold value.
13. A wind generating set's fatigue failure check out test set, characterized by, includes:
a memory;
a processor electrically connected with the memory;
the memory stores a computer program for execution by the processor to implement the method of fatigue failure detection of a wind park according to any of claims 1-10.
14. A wind farm controller, comprising: a fatigue failure detection apparatus for a wind turbine generator set as claimed in claim 13.
15. A computer-readable storage medium, characterized in that a computer program is stored which, when being executed by a processor, carries out the method of fatigue failure detection of a wind park according to any one of claims 1-10.
CN202010421806.3A 2020-05-18 2020-05-18 Fatigue failure detection method, device, equipment and medium for wind generating set Active CN112611584B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010421806.3A CN112611584B (en) 2020-05-18 2020-05-18 Fatigue failure detection method, device, equipment and medium for wind generating set

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010421806.3A CN112611584B (en) 2020-05-18 2020-05-18 Fatigue failure detection method, device, equipment and medium for wind generating set

Publications (2)

Publication Number Publication Date
CN112611584A true CN112611584A (en) 2021-04-06
CN112611584B CN112611584B (en) 2023-06-02

Family

ID=75224357

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010421806.3A Active CN112611584B (en) 2020-05-18 2020-05-18 Fatigue failure detection method, device, equipment and medium for wind generating set

Country Status (1)

Country Link
CN (1) CN112611584B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113155196A (en) * 2021-04-26 2021-07-23 南京邮电大学 Bridge operation real-time monitoring system based on AIoT and monitoring method thereof
CN113761713A (en) * 2021-08-05 2021-12-07 上海发电设备成套设计研究院有限责任公司 Method, device and system for simulating operation impact load of wind generating set
CN115796609A (en) * 2023-02-08 2023-03-14 澹泊科技(苏州)有限公司 Remote control system and method for new energy equipment
CN116432361A (en) * 2021-12-27 2023-07-14 北京金风科创风电设备有限公司 Service life assessment method and device of wind generating set
CN117390519A (en) * 2023-12-06 2024-01-12 中汽研汽车检验中心（天津）有限公司 Wheel hub motor fault condition prediction method

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130136594A1 (en) * 2011-06-03 2013-05-30 Wilic S.Ar.L. Wind turbine and control method for controlling the same
EP2743500A1 (en) * 2012-12-16 2014-06-18 Areva Wind GmbH Device and method for fatigue monitoring, system for managing a fatigue life distribution, method of operating a plurality of wind turbines
CN105701337A (en) * 2015-12-31 2016-06-22 北京金风科创风电设备有限公司 Fatigue life prediction method and device for wind turbine generator
CN105760617A (en) * 2016-03-07 2016-07-13 华北电力大学（保定） Calculation method applied to multi-parameter fault prediction and judgment indexes of wind generating set
CN107843745A (en) * 2017-09-20 2018-03-27 新疆金风科技股份有限公司 The method for diagnosing faults and device of the anemobiagraph of wind power generating set, storage medium
US20180142674A1 (en) * 2015-05-27 2018-05-24 Vestas Wind Systems A/S Control of a wind turbine taking fatigue measure into account
CN109118384A (en) * 2018-07-16 2019-01-01 湖南优利泰克自动化***有限公司 A kind of Wind turbines healthy early warning method
CN109253048A (en) * 2018-08-31 2019-01-22 北京金风科创风电设备有限公司 Operation control method, device and equipment of wind generating set and storage medium
WO2019165753A1 (en) * 2018-02-28 2019-09-06 北京金风科创风电设备有限公司 Load prediction method and apparatus for wind power generator set
CN110296053A (en) * 2018-03-23 2019-10-01 北京金风慧能技术有限公司 The fatigue damage detection method and apparatus of blade of wind-driven generator
CN110541794A (en) * 2018-05-29 2019-12-06 北京金风慧能技术有限公司 early warning method, device, equipment, medium and wind generating set for blade abnormity
CN110968069A (en) * 2018-09-28 2020-04-07 新疆金风科技股份有限公司 Fault prediction method of wind generating set, corresponding device and electronic equipment
CN112131753A (en) * 2020-09-29 2020-12-25 上海电气风电集团股份有限公司 Method, system and device for evaluating fatigue life of fan and readable medium
US20210097453A1 (en) * 2018-06-12 2021-04-01 Tsinghua University Method for quantile probabilistic short-term power load ensemble forecasting, electronic device and storage medium

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130136594A1 (en) * 2011-06-03 2013-05-30 Wilic S.Ar.L. Wind turbine and control method for controlling the same
EP2743500A1 (en) * 2012-12-16 2014-06-18 Areva Wind GmbH Device and method for fatigue monitoring, system for managing a fatigue life distribution, method of operating a plurality of wind turbines
US20180142674A1 (en) * 2015-05-27 2018-05-24 Vestas Wind Systems A/S Control of a wind turbine taking fatigue measure into account
CN105701337A (en) * 2015-12-31 2016-06-22 北京金风科创风电设备有限公司 Fatigue life prediction method and device for wind turbine generator
CN105760617A (en) * 2016-03-07 2016-07-13 华北电力大学（保定） Calculation method applied to multi-parameter fault prediction and judgment indexes of wind generating set
CN107843745A (en) * 2017-09-20 2018-03-27 新疆金风科技股份有限公司 The method for diagnosing faults and device of the anemobiagraph of wind power generating set, storage medium
WO2019165753A1 (en) * 2018-02-28 2019-09-06 北京金风科创风电设备有限公司 Load prediction method and apparatus for wind power generator set
CN110296053A (en) * 2018-03-23 2019-10-01 北京金风慧能技术有限公司 The fatigue damage detection method and apparatus of blade of wind-driven generator
CN110541794A (en) * 2018-05-29 2019-12-06 北京金风慧能技术有限公司 early warning method, device, equipment, medium and wind generating set for blade abnormity
US20210097453A1 (en) * 2018-06-12 2021-04-01 Tsinghua University Method for quantile probabilistic short-term power load ensemble forecasting, electronic device and storage medium
CN109118384A (en) * 2018-07-16 2019-01-01 湖南优利泰克自动化***有限公司 A kind of Wind turbines healthy early warning method
CN109253048A (en) * 2018-08-31 2019-01-22 北京金风科创风电设备有限公司 Operation control method, device and equipment of wind generating set and storage medium
CN110968069A (en) * 2018-09-28 2020-04-07 新疆金风科技股份有限公司 Fault prediction method of wind generating set, corresponding device and electronic equipment
CN112131753A (en) * 2020-09-29 2020-12-25 上海电气风电集团股份有限公司 Method, system and device for evaluating fatigue life of fan and readable medium

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
刘骊等: "基于多尺度排列熵和支持向量机的风力发电机组齿轮箱振动故障诊断", 《电网与清洁能源》 *
金晓航;孙毅;单继宏;吴根勇;: "风力发电机组故障诊断与预测技术研究综述" *
金晓航等: "风力发电机组故障诊断与预测技术研究综述", 《仪器仪表学报》 *
陈国初;金建;徐余法;: "基于证据熵多源组合规则的风力发电机组故障诊断方法" *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113155196A (en) * 2021-04-26 2021-07-23 南京邮电大学 Bridge operation real-time monitoring system based on AIoT and monitoring method thereof
CN113761713A (en) * 2021-08-05 2021-12-07 上海发电设备成套设计研究院有限责任公司 Method, device and system for simulating operation impact load of wind generating set
CN116432361A (en) * 2021-12-27 2023-07-14 北京金风科创风电设备有限公司 Service life assessment method and device of wind generating set
CN116432361B (en) * 2021-12-27 2024-05-24 北京金风科创风电设备有限公司 Service life assessment method and device of wind generating set
CN115796609A (en) * 2023-02-08 2023-03-14 澹泊科技(苏州)有限公司 Remote control system and method for new energy equipment
CN117390519A (en) * 2023-12-06 2024-01-12 中汽研汽车检验中心（天津）有限公司 Wheel hub motor fault condition prediction method
CN117390519B (en) * 2023-12-06 2024-04-09 中汽研汽车检验中心（天津）有限公司 Wheel hub motor fault condition prediction method

Also Published As

Publication number Publication date
CN112611584B (en) 2023-06-02

Similar Documents

Publication Publication Date Title
CN112611584B (en) Fatigue failure detection method, device, equipment and medium for wind generating set
Ma et al. Discriminative deep belief networks with ant colony optimization for health status assessment of machine
Ma et al. Predicting the remaining useful life of an aircraft engine using a stacked sparse autoencoder with multilayer self‐learning
CN107111311B (en) Gas turbine sensor fault detection using sparse coding methods
US11340602B2 (en) Sensor data fusion for prognostics and health monitoring
Ayodeji et al. Causal augmented ConvNet: A temporal memory dilated convolution model for long-sequence time series prediction
CN110110804B (en) Flight control system residual life prediction method based on CNN and LSTM
CN112393934B (en) Wind turbine generator fault diagnosis method based on sparse self-coding and extreme learning machine
de Moura et al. Classification of imbalance levels in a scaled wind turbine through detrended fluctuation analysis of vibration signals
CN107229017A (en) A kind of wind generating set pitch control battery abnormal failure Forecasting Methodology
Joshuva et al. A study of various blade fault conditions on a wind turbine using vibration signals through histogram features
CN113469230A (en) Method, system and medium for diagnosing deep migration fault of rotor system
Wang et al. Deep forest based multivariate classification for diagnostic health monitoring
Song et al. Intelligent diagnosis method for machinery by sequential auto-reorganization of histogram
Ogaili et al. A methodological approach for detecting multiple faults in wind turbine blades based on vibration signals and machine learning
Zhao et al. A capsnet-based fault diagnosis method for a digital twin of a wind turbine gearbox
CN112633362B (en) Rotary machine self-adaptive fault diagnosis method, device, equipment and medium
Liu et al. Semi-supervised deep learning recognition method for the new classes of faults in wind turbine system
KR102383675B1 (en) Anomaly detection system of time-series data
Yafei et al. Fault Diagnosis of Axial Piston Pump Based on Extreme‐Point Symmetric Mode Decomposition and Random Forests
CN113297291A (en) Monitoring method, monitoring system, readable storage medium and wind driven generator
CN110348005B (en) Distribution network equipment state data processing method and device, computer equipment and medium
Zhou et al. Degradation State Recognition of Rolling Bearing Based on K‐Means and CNN Algorithm
CN114637620B (en) Database system abnormal classification prediction method based on SVM algorithm
CN113469263B (en) Prediction model training method and device suitable for small samples and related equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant