CN111062447B - Method and device for diagnosing fault of wind driven generator in dimension reduction mode - Google Patents

Method and device for diagnosing fault of wind driven generator in dimension reduction mode Download PDF

Info

Publication number
CN111062447B
CN111062447B CN201911362110.1A CN201911362110A CN111062447B CN 111062447 B CN111062447 B CN 111062447B CN 201911362110 A CN201911362110 A CN 201911362110A CN 111062447 B CN111062447 B CN 111062447B
Authority
CN
China
Prior art keywords
sample data
data
equal
representing
space
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.)
Active
Application number
CN201911362110.1A
Other languages
Chinese (zh)
Other versions
CN111062447A (en
Inventor
刘远红
胡泽彪
殷海双
张彦生
路敬祎
刘庆强
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.)
Northeast Petroleum University
Original Assignee
Northeast Petroleum University
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 Northeast Petroleum University filed Critical Northeast Petroleum University
Priority to CN201911362110.1A priority Critical patent/CN111062447B/en
Publication of CN111062447A publication Critical patent/CN111062447A/en
Application granted granted Critical
Publication of CN111062447B publication Critical patent/CN111062447B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The disclosure relates to a method and a device for diagnosing faults of a wind driven generator in a dimension reduction mode. The method comprises the steps of constructing an original data space according to operation data of the wind driven generator in different operation states; performing feature selection on sample data in an original data space by using a first mode to obtain a new data space; constructing a corresponding symmetrical positive definite matrix manifold for any sample data in the new data space obtained based on the first mode by using a second mode; performing feature extraction on the symmetrical positive definite matrix manifold of the sample data by using a third mode to obtain a low-dimensional feature set of the sample data in the symmetrical positive definite matrix manifold; and inputting the obtained low-dimensional feature set into a support vector machine, and detecting the fault of the wind driven generator according to the output information of the support vector machine. The fault detection accuracy of the wind driven generator can be improved.

Description

Method and device for diagnosing fault of wind driven generator in dimension reduction mode
The technical field is as follows:
the invention relates to a method and a device for detecting faults of a wind driven generator.
The background art comprises the following steps:
with the gradual improvement of manifold learning theory, manifold learning is widely applied to the field of fault diagnosis. Compared with the traditional feature extraction method, manifold learning takes the whole data set as a research object instead of single data, and can fully utilize local structure information among original data, but the application of manifold learning in fault diagnosis still has a plurality of problems. The method is particularly represented in that the existing manifold learning algorithm represents sample data in a vector form, so that structural information among sample data features can be ignored; meanwhile, representing sample data in a vector form causes a 'dimensional disaster' problem of the data; in addition, the existing manifold learning algorithms calculate K neighbors of any sample data in the euclidean space, which is contrary to the nonlinear characteristic of the manifold learning algorithm, and such a calculation method has a large error, so that the final low-dimensional feature set cannot accurately reflect the essential features of the original data, which seriously affects the fault diagnosis precision.
The invention content is as follows:
in order to solve the technical problems mentioned in the background art, the invention provides a method and a device for diagnosing the fault of the wind driven generator in a dimension reduction mode. Firstly, performing initial dimensionality reduction on original data by using a classical feature selection algorithm local linear embedding voting algorithm to obtain a new data space representation of the original sample data; and mapping the sample data of the new data space to the symmetrical positive definite matrix manifold, and obtaining a low-dimensional feature set corresponding to the original data by introducing a local linear embedding algorithm in a tangent space corresponding to the symmetrical positive definite matrix manifold. And inputting the obtained low-dimensional feature set into a support vector machine, and detecting the fault of the wind driven generator according to the output information of the support vector machine.
The invention discloses a method and a device for diagnosing faults of a wind driven generator in a dimension reduction mode, which comprises the following steps:
firstly, according to the operation data of the wind driven generator in different operation states, constructing an original data space, comprising the following steps of:
acquiring operation data of the wind driven generator in different operation states through at least one sensor;
intercepting operation data with preset length from operation data acquired by each sensor according to a preset period;
performing normalization processing on the intercepted running data with the preset length to obtain sample data X, and forming the original data space based on the sample data;
wherein, the expression of the normalization processing executed on the operation data is as the formula (1):
Figure BDA0002337437170000021
wherein, N is the number of the selected running data with preset length and the group number of the obtained sample data; x is a set of sample data obtained by normalization, and is expressed in a matrix set, where X ═ X1,x2,...,xN}; i is an integer greater than or equal to 1 and less than or equal to N; x is the number ofiRepresenting the operation data of the ith preset length;
secondly, finding K groups of sample data with the minimum distance to any sample data in the original data space according to the formula (2), and determining K neighbor sample data of the sample data, wherein K is an integer which is larger than zero and smaller than the total number N of the sample data:
Figure BDA0002337437170000022
wherein, dist (x)i,xj) Represents the distance, x, between any two sets of sample data in the original data spaceikAnd xjkRespectively representing sample data x in the original data spaceiAnd xjK represents the feature corresponding to any sample data, k is an integer greater than or equal to 1 and less than or equal to D, D represents the dimensionality of the original data space sample data, andthe number of feature groups of the original data space is obtained;
secondly, a local linear structure between any sample data and corresponding K neighbor sample data is obtained according to the formula (3), and the expression is as follows:
Figure BDA0002337437170000023
wherein i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; k denotes sample data xiThe number of groups of neighboring points; k is an integer which is more than or equal to 1 and less than or equal to N; j is an integer greater than or equal to 1 and less than or equal to K; x is the number ofi jRepresenting sample data xiJ-th neighbor, wijRepresenting sample data xiThe local linear structure of (1); lambda1、λ2Representing a non-negative regulation parameter; | | w2ij||1Denotes w2ijL of1The norm of the number of the first-order-of-arrival,
Figure BDA0002337437170000024
denotes w2ijL of2A norm;
then, the first local linear structure described in equation (3) is obtained by iterative calculation using equations (4) and (5):
X＝AW+λ||W||1… … … type (4)
W (j +1) ═ W (j) + γ δ (j) … … … formula (5)
Wherein X represents the normalized sample data; a represents K neighbor sample data X of sample data X1,x2,...,xKA set of (a); a ═ x1,x2,...,xK}; w represents a local linear structure of the sample data; w (j) is a local linear structure obtained by the jth iteration; gamma is an iteration step length; δ (j) is the iteration direction; j represents the iteration frequency, j is more than or equal to 1 and less than or equal to K; λ represents a coefficient, λ is 0 ≦ 1;
finally, based on the local linear structure of any sample data, obtaining a new data space of any sample data, wherein the path is as follows:
firstly, calculating the vote number of each characteristic of any sample data according to an equation (6):
Figure BDA0002337437170000031
wherein, VoterRepresenting the number of votes obtained by any characteristic of the sample data; i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; f. ofriRepresenting sample data xiJ is an integer greater than or equal to 1 and less than or equal to N, wijRepresenting sample data xiThe local linear structure of (1); f. ofrjRepresenting sample data xjThe r-th feature of (1);
then, according to Vote in equation (6)rObtaining the number of votes obtained by any feature of the sample data, and selecting d features with the least number of votes as a new data space of the original data;
thirdly, representing the new data space obtained in the second step by using a second mode to construct a corresponding symmetrical positive definite matrix manifold, wherein the second mode comprises the following steps:
firstly, mapping sample data of a new data space to a symmetrical positive definite matrix manifold according to an equation (7):
Figure BDA0002337437170000032
wherein the content of the first and second substances,
Figure BDA0002337437170000033
representing a representation of new data space sample data on a symmetrical positive definite matrix manifold; i is an integer greater than or equal to 1 and less than or equal to N;
Figure BDA0002337437170000034
representing a representation of any sample data of the new data space;
Figure BDA0002337437170000035
to represent
Figure BDA0002337437170000036
Transposing;
then, any sample data of the symmetrical positive definite matrix manifold is processed according to the equation (8)
Figure BDA0002337437170000037
Vectorization processing is carried out;
Figure BDA0002337437170000038
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0002337437170000039
vector representation of the said any sample data in the tangent space of the symmetrical positive definite matrix manifold;
Figure BDA00023374371700000310
representing a representation of any sample data of the new data space; log (.) represents the log operation; verc (.) denotes vectorization processing;
fourthly, extracting the characteristics of the vectorized data obtained in the third step by using a third mode to obtain a low-dimensional characteristic set of the manifold data of the symmetrical positive definite matrix, wherein the low-dimensional characteristic set is also the low-dimensional characteristic set of the original sample data; the third method uses a local linear embedding algorithm and is performed according to the following path:
firstly, finding K groups of sample data with the minimum data distance of any sample after vectorization processing by the formula (8) according to the formula (9), and determining K neighbor sample data of the sample data, wherein K is an integer which is greater than zero and less than the total number of the sample data:
Figure BDA00023374371700000311
wherein the content of the first and second substances,
Figure BDA00023374371700000312
representing the distance between any two groups of sample data after warp quantization, k is more than or equal to 1 and less than or equal to
Figure BDA00023374371700000313
The number of the integer (c) of (d),
Figure BDA00023374371700000314
representing the dimension of any sample data processed by the formula (8);
Figure BDA00023374371700000315
and
Figure BDA00023374371700000316
respectively representing the kth characteristics of the ith sample data and the jth sample data;
next, a local linear structure of any sample data after vectorization processing by equation (8) is calculated according to equation (10):
Figure BDA0002337437170000041
wherein i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; k represents sample data
Figure BDA0002337437170000042
K is more than or equal to 1 and less than or equal to N; j is an integer greater than or equal to 1 and less than or equal to K;
Figure BDA0002337437170000043
representing sample data
Figure BDA0002337437170000044
J-th neighbor, wijRepresenting sample data
Figure BDA0002337437170000045
The local linear structure of (1);
finally, the local structure w is maintained in the low-dimensional spaceijAnd (3) obtaining a low-dimensional feature set of the symmetrical positive definite matrix manifold data according to the formula (11) without changing, wherein the low-dimensional feature set is also the low-dimensional feature set of the original sample data:
Figure BDA0002337437170000046
wherein the content of the first and second substances,
Figure BDA0002337437170000047
representing the low-dimensional characteristics corresponding to the ith group of sample data in any sample data space after the vectorization processing of the formula (8); i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space;
Figure BDA0002337437170000048
a jth neighbor point representing an ith set of sample data; j is an integer greater than or equal to 1 and less than or equal to K; k is more than or equal to 1 and less than or equal to N; w is aijRepresenting a local linear structure of any sample data;
and fifthly, taking the low-dimensional feature set obtained in the fourth step as the input of a support vector machine, and carrying out fault detection on the wind driven generator through information output by the support vector machine.
The device for carrying out fault diagnosis on the wind driven generator in a dimension reduction mode comprises:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring operating data of the wind driven generator in different operating states and constructing an original data space, and the original data space comprises a plurality of groups of sample data determined based on the operating data;
the first obtaining module is used for selecting the characteristics of the original data by utilizing a first mode to obtain a new data space of the original sample data;
a second obtaining module, configured to construct a symmetrical positive definite matrix manifold space for a new data space of the original sample data obtained by the first obtaining module;
the third acquisition module is used for acquiring the representation of the data in the manifold space of the symmetric positive definite matrix by using the second acquisition module and performing feature extraction on the manifold space of the symmetric positive definite matrix by using a local linear embedding algorithm to acquire a low-dimensional feature set of sample data in the original data space;
and the detection module is used for inputting the low-dimensional feature set output by the third obtaining module into a support vector machine and carrying out fault detection on the wind driven generator through information output by the support vector machine.
The invention has the following beneficial effects: compared with the prior art, the method obtains a new data space of the original data by using a classical feature selection algorithm according to the characteristics of the data, so that the dimensionality of the original data is reduced, and the important features of the original data are also reserved; secondly, a symmetrical positive definite matrix manifold is constructed based on sample data of a new data space, the representation of any sample data on a tangent space corresponding to the symmetrical positive definite matrix manifold is calculated, and feature extraction is carried out in the tangent space by using the most common local linear embedded manifold learning algorithm, so that more features of original data are reserved in the obtained low-dimensional features, and the accuracy of fault detection is greatly improved.
Aiming at the method for diagnosing the manifold learning fault of the symmetrical positive definite matrix based on the feature selection, which is provided by the invention, the whole data set is taken as a research object, and the fusion of a classical feature selection algorithm, the symmetrical positive definite matrix and a local linear embedding algorithm is combined, so that the most essential feature of original data is reserved by the final low-dimensional feature. In addition, the feature selection algorithm provided by the invention obtains the representation of the original data in a new data space, and the calculation complexity of the subsequent fault diagnosis based on the low-dimensional feature set is greatly reduced. In addition, the data are mapped to the symmetrical positive definite matrix manifold, any sample data is expressed in a matrix form, local structure information among the sample data is considered, and meanwhile, the K neighbor point of any sample data is selected in the tangent space, so that the structure relation among the sample data can be more accurately disclosed, and the subsequent fault diagnosis precision is improved. In addition, the method can only process the data acquired by a single sensor, thereby reducing the hardware cost.
Description of the drawings:
FIG. 1 is a flow chart of a method for detecting a fault in a wind turbine according to the present invention;
FIG. 2 is a flowchart of step S10 in FIG. 1;
FIG. 3 is a flowchart of step S20 in FIG. 1;
FIG. 4 is a flowchart of step S30 in FIG. 1;
FIG. 5 is a flowchart of step S40 in FIG. 1;
FIG. 6 is a flowchart of step S50 in FIG. 1;
FIG. 7 is a block diagram illustrating a fault detection apparatus for a wind turbine according to the present invention;
FIG. 8 is a block diagram of one type of electronic device in which the present invention may be implemented;
FIG. 9 is a block diagram illustrating another electronic device in which the present invention may be implemented;
the specific implementation mode is as follows:
the invention will be further described with reference to the accompanying drawings in which:
in view of manifold learning, the dimension reduction of data is realized by mining the local linear geometry structure of the data in a high-dimensional space and maintaining the structural relationship in a low-dimensional space. Therefore, the local geometry of the data is critical to the final dimension reduction result. In the existing manifold learning research results, sample data is mostly represented in a vector form, and K neighbor points of any sample data are calculated by utilizing Euclidean distance between samples, so that local information between the sample data is ignored, and meanwhile, the selected K neighbor points have large errors, so that the final low-dimensional features cannot comprehensively reveal the intrinsic essential attributes of the original data, and the identifiability of the low-dimensional features is poor. Therefore, the invention provides a wind driven generator feature extraction method capable of combining feature selection, symmetrical positive definite matrix manifold and local linear embedding to realize real-time monitoring of the running state of a wind driven generator, wherein a classic feature selection algorithm can be adopted to obtain the representation of the original sample data in a new data space, so that the dimensionality of the original data is reduced, and meanwhile, the important information of the original data is reserved; and then constructing a symmetrical positive definite matrix manifold based on the new spatial representation, utilizing the representation of sample data in a tangent space of the symmetrical positive definite matrix manifold, and finally utilizing a local linear embedding algorithm to extract features in the tangent space to obtain a final low-dimensional feature set of the original data, and executing fault detection through the low-dimensional feature set, thereby improving the accuracy of fault detection. Compared with the prior art, the method has lower computational complexity, greatly reduces the space dimension of the original data, takes the whole data set as an object, represents any sample data in a matrix form, and fully considers the local information of the sample data, so the method is suitable for complex fault detection scenes.
Fig. 1 is a flowchart of a wind turbine generator fault detection method according to the present invention, which may be used to detect a fault condition of any type of generator, such as a wind turbine generator, a hydroelectric generator, or any other type of generator, and the disclosure is not limited thereto. In addition, the main body of the generator fault detection method according to the present invention may be any electronic device, for example, the generator fault detection method may be executed by a terminal device or a server or other processing device, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and the like. In some possible implementations, the generator fault detection method may be implemented by a processor calling computer readable instructions stored in a memory.
As shown in fig. 1, the method for detecting a fault of a wind turbine may include:
s10: according to the operating data of the wind driven generator in different operating states, constructing an original data space, wherein the original data space comprises a plurality of groups of sample data determined based on the operating data;
in some possible embodiments, the operating state of the wind turbine may include at least one of a normal state, an actuator fault state, and a sensor fault state. By providing different sensors on the generator or on individual components of the generator, operating data of the generator can be detected in different operating states. Wherein the sensor can detect corresponding operational data in real time. For example, the operational data may include at least one of a pitch angle, a generator torque, a generator rotational angular velocity, and a rotor angular velocity. The respective operating data can be detected by a corresponding type of sensor. Then, multiple groups of sample data can be obtained by utilizing each operation data, and an original data space is formed based on the foot-done sample data. In addition, in the embodiment of the present disclosure, each piece of operation data in the sample data in the same group is of the same type, and the types of operation data in the sample data in different groups may be the same or different.
In the embodiment of the present disclosure, each obtained set of sample data may construct an original data space, the original data space may be represented as a matrix model, each set of sample data may be represented as a feature vector, and the matrix model may be constructed by the feature vectors corresponding to the multiple sets of sample data.
S20: based on the original data space, selecting a new data space of the original data by using features based on local linear embedded voting;
in some possible embodiments, different feature selection methods may be used to obtain the representation of the sample data in the new data space. For example, if a certain sample data may be denoted as x, its K neighbor sample data may be denoted as a ═ { x ═ b1,x2,...,xKAnd if x is equal to AW, W is a local linear structure between the sample data x and its K neighbor sample data. x may be represented as a feature vector of the sample data, and K neighboring sample data corresponding to the feature vector is a matrix, where each column of the matrix is one neighboring sample data of x. And using the difference value of x and AW as the importance of any feature in the measured sample data, and selecting d features with the minimum difference value as the representation of the new data space of the original data.
The feature selection method employed in the embodiments of the present disclosure is a method based on local linear embedding scoring.
S30: constructing a symmetrical positive definite matrix manifold based on the new data space representation of the original data;
in some possible embodiments, a stream of symmetric positive definite matrices is constructed based on the new data space of the original data, and the invention adopts a form of constructing a symmetric positive definite matrix from any sample data.
S40: and constructing a symmetrical positive definite matrix manifold based on the expression of the original data in the new data space, and obtaining the low-dimensional characteristics of corresponding sample data by introducing a local linear embedding algorithm in a tangent space. The redundant dimensions of the data can be eliminated by describing the sample data through the low-dimensional features, the intrinsic essential features of the data are revealed, and the diagnosis precision of the system is improved.
S50: and obtaining a fault detection result of the wind driven generator based on the low-dimensional features.
And taking the obtained low-dimensional feature set as an input of a support vector machine, and carrying out wind driven generator fault detection through the category information output by the support vector machine. The support vector machine is referred to as SVM for short, and the specific path comprises the following steps:
firstly, two types of data are arbitrarily selected according to the low-dimensional features obtained in S40 to construct an input training sample set of the SVM. Wherein the input training sample set is represented as:
T＝{(y1,l1),...,(yk,lk),...,(yN,lc)}∈(Y,L)
wherein N represents the number of SVM input samples; k represents a class number, and k 1, 2.., l, l represents the class number; y isk∈Y＝RdD represents the dimension of the SVM input sample data; lk∈L＝{-1,1}。
Then, an optimal hyperplane is found by training the input of the SVM, so that the hyperplane can well solve the two classification problems, and the optimal hyperplane is obtained according to a decision function of the formula (12):
Figure BDA0002337437170000071
wherein, yk∈y＝RdY represents a training sample set of the SVM inputs; w is a*Representing a weight vector of the final optimal hyperplane; w is a*TDenotes w*Transposing; b*An offset representing the final optimal plane; alpha (alpha) ("alpha")kRepresents a Lagrangian factor, and is alphakIs greater than 0; k represents a class number, and k 1, 2.., l, l represents the number of class numbers; sgn (.) represents a step function.
Then, according to the input test sample yiThe categories of the two data can be distinguished by using the optimal classification function. Therefore, the faults of the two wind driven generators can be detected.
And finally, combining the low-dimensional features of other classes input by the SVM two by two to perform the three steps until all the classes are finished, and detecting the fault of the wind driven generator according to the class to which the sample belongs.
The present invention will now be described in detail with reference to the accompanying drawings.
Fig. 2 shows a flowchart of step S10. Wherein, the constructing the original data space according to the operating data of the generator in different operating states may include:
s101: acquiring operation data of the generator in different operation states through at least one sensor;
during specific implementation, one sensor can be used for acquiring the running data of the generator in different states, or different sensors can be used for acquiring different types of running data of the generator in different running states. Hardware cost can be reduced by arranging a single sensor, and more comprehensive fault detection can be realized by arranging multiple sensors.
The corresponding operation data can be detected by the sensor in real time and stored in real time. For example, the angular velocity of the generator in different operating states may be detected by an angle sensor, the torque of the generator may be detected by a displacement sensor, and the like.
S102: intercepting operation data with preset length from operation data collected by each sensor according to a preset period;
in some possible embodiments, one or more preset lengths of operation data may be selected from each kind of operation data, or multiple sets of preset lengths of operation data may be periodically intercepted. The preset length may be a preset value, for example, 10, or 5, and the preset period corresponds to the preset length, which is not specifically limited in this disclosure.
S103: and performing normalization processing on the intercepted running data with the preset length to obtain the sample data, and forming the sample data based on the sample data.
In some possible embodiments, the intercepted operation data with the preset length may be directly used as sample data, or the operation data with the preset length may also be subjected to normalization processing to obtain corresponding sample data, and an original data space is formed based on the sample data.
Because units of different dimensions of the operation data are possibly different, actual data of all dimensions are possibly not in the same order of magnitude, the original data are directly analyzed, the influence of dimensions with larger order of magnitude in analysis is easy to be larger, and important decimal dimension information is ignored, so that the final processing result of the data is influenced. In addition, the existence of a large amount of large numerical data also reduces the calculation speed of the algorithm. Therefore, before analyzing the original operation data, normalization processing is usually required to unify the selected operation data in the same area. The commonly used data normalization method is implemented by linear transformation using the maximum and minimum values in the data, and the normalization method relying only on individual data points is greatly affected by singular values in the data. The embodiment of the present disclosure introduces an l2 norm of a vector to perform normalization processing on data, and a specific calculation formula is as follows:
Figure BDA0002337437170000091
wherein, N is the number of the selected running data with preset length and the group number of the obtained sample data; x represents a set of sample data obtained after normalization; x is the number ofiRepresenting any of the sample data. Because all the running data with the preset length participate in the normalization process, the influence of individual abnormal data can be reduced, and the robustness of the normalization algorithm is improved.
Under the condition of obtaining various sample data, the feature selection can be carried out on the original sample data to obtain a new data space. The embodiment of the disclosure utilizes a feature selection method based on local linear embedded voting to select m features from the original data space as a new data space of the original data.
As shown in fig. 3, determining a new data space of any sample data in the original data space includes:
s201: obtaining the distance between any two groups of sample data in the multiple groups of sample data in the original data space;
as described in the foregoing embodiment, each group of sample data may be represented in a vector form, and the distance between corresponding vectors may be used as the distance between sample data, that is, the distance between each group of sample data and the remaining sample data, such as the euclidean distance, may be obtained, or another distance may also be used, where the distance may represent the similarity between two sample data. The smaller the distance, the higher the similarity.
S202: for any sample data, determining K groups of sample data with the minimum distance to the any sample data as K neighbor sample data of the any sample data.
In some possible embodiments, the K sets of sample data having the smallest distance to the sample data may be used as the K neighbor sample data of the sample data. I.e. the K sets of sample data that are most similar to each sample data are determined.
Under the condition of obtaining the K neighbor sample data of each group of sample data, a local linear structure between the sample data and the K neighbor sample data can be obtained, and a product between the local linear structure and the K neighbor sample data can be the sample data. The corresponding local linear structure may also represent a vector, where each value within the local linear structure represents a weight corresponding to each sample data in the K neighboring sample data.
S203: calculating a corresponding local linear structure of K neighboring points of any sample data by using an expression (3), wherein the expression is as follows:
Figure BDA0002337437170000101
wherein i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of the sample data of the original data space; k denotes sample data xiK is more than or equal to 1 and less than or equal to N; j is an integer greater than or equal to 1 and less than or equal to K; x is the number ofi jRepresenting sample data xiJ-th neighbor, wijRepresenting sample data xiThe local linear structure of (1); lambda [ alpha ]1、λ2Representing a non-negative regulation parameter; i W2ij||1Denotes w2ijL of1The norm of the number of the first-order-of-arrival,
Figure BDA0002337437170000102
denotes w2ijL of2A norm;
s204: obtaining a local linear structure of any sample data based on the formula (3), and executing the following operations to obtain a new data space of any sample data:
firstly, the score of each characteristic of any sample data is calculated according to the formula (6):
Figure BDA0002337437170000103
wherein, VoterRepresenting the number of votes obtained by any characteristic of the sample data; i is an integer greater than or equal to 1 and less than or equal to N; n represents the original data nullThe number of groups of sample data in between; f. ofriRepresenting sample data xiJ is an integer greater than or equal to 1 and less than or equal to N, wijRepresenting sample data xiThe local linear structure of (1); f. ofrjRepresenting sample data xjThe r-th feature of (1);
s205: vote in accordance with equation (6)rObtaining the number of votes obtained by any one feature of the sample data, and selecting d features with the least number of votes obtained as a new data space of the original data;
fig. 4 shows a flowchart of step S30 in accordance with an embodiment of the present disclosure. Wherein constructing a corresponding symmetric positive definite matrix representation for each data sample based on the new data space of the original data comprises:
s301: for any sample data in the new data space of the original data, a symmetrical positive definite matrix manifold is constructed by the formula (7), and the expression is as follows:
Figure BDA0002337437170000104
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0002337437170000105
representing a representation of the new data space sample data on a symmetric positive definite matrix manifold; i is an integer greater than or equal to 1 and less than or equal to N;
Figure BDA0002337437170000106
representing a representation of said any sample data in a new data space;
Figure BDA0002337437170000107
to represent
Figure BDA0002337437170000108
Transposing;
s302: then, any sample data of the symmetrical positive definite matrix manifold is processed according to the formula (8)
Figure BDA0002337437170000109
Vectorization processing is carried out;
Figure BDA00023374371700001010
wherein the content of the first and second substances,
Figure BDA0002337437170000111
representing the new data space to represent the vector representation of any sample data in a stream shape tangent space of a symmetric positive definite matrix; log (.) represents the log operation;
Figure BDA0002337437170000112
representing a representation of said any sample data in a new data space; verc (.) denotes vectorization processing;
fig. 5 shows a flowchart of step S40 according to an embodiment of the present disclosure. After vectorization processing data is obtained according to the formula (8), a local linear embedding algorithm is used to obtain a low-dimensional feature set of sample data in the original data space, and the processing is performed according to the following path:
s401: firstly, finding K groups of sample data with the minimum data distance of any sample after vectorization processing by the formula (8) according to the formula (9), and determining K neighbor sample data of the sample data, wherein K is an integer which is greater than zero and less than the total number N of the sample data:
Figure BDA0002337437170000113
wherein the content of the first and second substances,
Figure BDA0002337437170000114
represents the distance between any two groups of sample data after warp quantization processing, k is more than or equal to 1 and less than or equal to
Figure BDA0002337437170000115
The number of the integer (c) of (a),
Figure BDA0002337437170000116
representing the dimension of any sample data processed by the formula (8);
Figure BDA0002337437170000117
and
Figure BDA0002337437170000118
respectively representing the kth characteristics of the ith sample data and the jth sample data;
s402: calculating the local linear structure of any sample data according to the formula (10):
Figure BDA0002337437170000119
wherein i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; k represents sample data x &iK is more than or equal to 1 and less than or equal to N; j is an integer greater than or equal to 1 and less than or equal to K; x EjExpress sample data x EiJ-th neighbor, wijExpress sample data x EiThe local linear structure of (1);
s403: according to the maintenance of local structures w in a low-dimensional spaceijAnd (3) obtaining a low-dimensional feature set of the sample data according to an equation (11) without changing:
Figure BDA00023374371700001110
wherein the content of the first and second substances,
Figure BDA00023374371700001111
representing the low-dimensional characteristics corresponding to the ith group of sample data in the original data space; i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space;
Figure BDA00023374371700001112
a jth neighbor point representing an ith set of sample data; j is greater than or equal to1 and an integer less than or equal to K; k is more than or equal to 1 and less than or equal to N; w is aijRepresenting a local linear structure of any sample data;
fig. 6 shows a flowchart of step S50 in accordance with an embodiment of the present disclosure. And taking the low-dimensional feature set obtained in the fourth step as the input of a support vector machine, and carrying out wind driven generator fault detection through the information output by the support vector machine.
Fig. 7 shows a block diagram of a generator fault device according to an embodiment of the present disclosure, and as shown in fig. 7, the fault detection device includes:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring operating data of the wind driven generator in different operating states and constructing an original data space, and the original data space comprises a plurality of groups of sample data determined based on the operating data;
the first obtaining module is used for selecting the characteristics of the original data by utilizing a first mode to obtain a new data space of the original sample data;
a second obtaining module, configured to construct a symmetric positive definite matrix manifold space for a new data space of the original sample data obtained by the first obtaining module;
the third obtaining module is used for obtaining the representation of the data in the manifold space of the symmetric positive definite matrix by utilizing the second obtaining module, and performing feature extraction on the manifold space of the symmetric positive definite matrix by utilizing a local linear embedding algorithm to obtain a low-dimensional feature set of sample data in the original data space;
and the detection module is used for inputting the low-dimensional feature set output by the third obtaining module into a support vector machine and carrying out fault detection on the wind driven generator through information output by the support vector machine.
Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium. The electronic device includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured as the above method. The electronic device may be provided as a terminal, server, or other form of device.
Fig. 8 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal. Referring to fig. 6, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802. The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800. The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability. The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals. The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button. The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor. The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
The electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
A memory 804 comprising computer program instructions executable by the processor 820 of the electronic device 800 to perform the methods described above.
FIG. 9 illustrates a block diagram of another electronic device in which the present invention may be implemented. For example, electronic device 1900 may be provided as a server. Referring to fig. 9, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, that are executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method. The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like. A memory 1932 comprising computer program instructions executable by a processing component 1922 of an electronic device 1900 to perform the above-described method.
Apparatus for implementing the invention may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure. Among other things, the computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as punch cards or in-groove raised structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be interpreted as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or an electrical signal transmitted through an electrical wire. The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Claims (1)

1. A method for carrying out fault diagnosis on a wind driven generator in a dimension reduction mode comprises the following steps:
the method comprises the following steps of firstly, constructing an original data space according to operation data of the wind driven generator in different operation states, wherein the method comprises the following steps:
acquiring operation data of the wind driven generator in different operation states through at least one sensor;
intercepting operation data with preset length from operation data collected by each sensor according to a preset period;
performing normalization processing on the intercepted running data with the preset length to obtain sample data X, and forming the original data space based on the sample data;
wherein, the expression of the normalization processing executed on the operation data is as the formula (1):
Figure FDA0003576017750000011
wherein, N is the number of the selected running data with preset length and the group number of the obtained sample data; x is a set of sample data obtained by normalization, and is expressed in a matrix set, where X ═ X1,x2,...,xN}; i is an integer greater than or equal to 1 and less than or equal to N; x is the number ofiRepresenting the operation data of the ith preset length;
secondly, finding K groups of sample data with the minimum distance to any sample data in the original data space according to the formula (2), and determining K neighbor sample data of the sample data, wherein K is an integer which is larger than zero and smaller than the total number N of the sample data:
Figure FDA0003576017750000012
wherein, dist (x)i,xj) Represents the distance, x, between any two sets of sample data in the original data spaceikAnd xjkRespectively representing sample data x in the original data spaceiAnd xjK represents a feature corresponding to any sample data, k is an integer greater than or equal to 1 and less than or equal to D, D represents a dimension of the original data space sample data and is also the original data spaceNumber of feature groups in between;
secondly, a local linear structure between any sample data and corresponding K neighbor sample data is obtained according to the formula (3), and the expression is as follows:
Figure FDA0003576017750000021
wherein i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; k denotes sample data xiThe number of groups of neighbors; k is an integer which is more than or equal to 1 and less than or equal to N; j is an integer greater than or equal to 1 and less than or equal to K;
Figure FDA0003576017750000022
representing sample data xiJ-th neighbor, wijRepresenting sample data xiThe local linear structure of (1); lambda [ alpha ]1、λ2Represents a non-negative regulation parameter; i Wij||1Denotes wijL of1The number of the norm is calculated,
Figure FDA0003576017750000023
denotes wijL of2A norm;
then, a first local linear structure in equation (3) is obtained by iterative calculation using equations (4) and (5):
X＝AW+λ||W||1… … … type (4)
W (j +1) ═ W (j) + γ δ (j) … … … formula (5)
Wherein X represents the normalized sample data; a represents K neighbor sample data X of sample data X1,x2,...,xKA set of (a); a ═ x1,x2,...,xK}; w represents a local linear structure of the sample data; w (j) is a local linear structure obtained by the jth iteration; gamma is an iteration step length; δ (j) is the iteration direction; j represents the iteration times, and j is more than or equal to 1 and less than or equal to K; λ represents a coefficient, λ is 0 ≦ 1;
finally, based on the local linear structure of any sample data, obtaining a new data space of any sample data, wherein the path is as follows:
firstly, calculating the vote number of each characteristic of any sample data according to an equation (6):
Figure FDA0003576017750000024
wherein, VoterRepresenting the number of votes obtained by any characteristic of the sample data; i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; f. ofriRepresenting sample data xiJ is an integer greater than or equal to 1 and less than or equal to N, wijRepresenting sample data xiThe local linear structure of (1); f. ofrjRepresenting sample data xjThe r-th feature of (1);
then, according to Vote in equation (6)rObtaining the number of votes obtained by any one feature of the sample data, and selecting d features with the least number of votes obtained as a new data space of the original data;
thirdly, representing the new data space obtained in the second step by using a second mode to construct a corresponding symmetrical positive definite matrix manifold, wherein the second mode comprises the following steps:
firstly, mapping sample data of a new data space to a symmetrical positive definite matrix manifold according to an equation (7):
Figure FDA0003576017750000031
wherein the content of the first and second substances,
Figure FDA0003576017750000032
representing a representation of new data space sample data on a symmetrical positive definite matrix manifold; i is an integer greater than or equal to 1 and less than or equal to N;
Figure FDA0003576017750000033
representing a representation of any sample data of the new data space;
Figure FDA0003576017750000034
to represent
Figure FDA0003576017750000035
Transposing;
then, any sample data of the symmetrical positive definite matrix manifold is processed according to the formula (8)
Figure FDA00035760177500000318
Vectorization processing is carried out;
Figure FDA0003576017750000036
wherein the content of the first and second substances,
Figure FDA0003576017750000037
vector representation of the any sample data in a symmetrical positive definite matrix manifold tangent space;
Figure FDA0003576017750000038
representing a representation of any sample data of the new data space; log (.) represents the log operation; verc (.) denotes vectorization processing;
fourthly, extracting the characteristics of the vectorized data obtained in the third step by using a third mode to obtain a low-dimensional characteristic set of the manifold data of the symmetric positive definite matrix, which is also a low-dimensional characteristic set of the sample data X; the third mode is carried out by utilizing a local linear embedding algorithm according to the following paths:
firstly, finding out K groups of sample data with the minimum distance of any sample data after vectorization processing by the expression (8) according to the expression (9), and determining K neighbor sample data of the sample data, wherein K is an integer which is greater than zero and less than the total number of the sample data:
Figure FDA0003576017750000039
wherein the content of the first and second substances,
Figure FDA00035760177500000310
representing the distance between any two groups of sample data after warp quantization, k is more than or equal to 1 and less than or equal to
Figure FDA00035760177500000311
The number of the integer (c) of (a),
Figure FDA00035760177500000312
representing the dimension of any sample data processed by the formula (8);
Figure FDA00035760177500000313
and
Figure FDA00035760177500000314
respectively representing the kth characteristics of the ith sample data and the jth sample data;
next, a local linear structure of any sample data after vectorization processing by equation (8) is calculated according to equation (10):
Figure FDA00035760177500000315
wherein i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space; k represents sample data
Figure FDA00035760177500000316
K is more than or equal to 1 and less than or equal to N; j is an integer greater than or equal to 1 and less than or equal to K;
Figure FDA00035760177500000317
representing sample data
Figure FDA0003576017750000041
J-th neighbor, wijRepresenting sample data
Figure FDA0003576017750000042
The local linear structure of (1);
finally, the local structure w is maintained in the low-dimensional spaceijAnd (3) obtaining a low-dimensional feature set of the symmetrical positive definite matrix manifold data according to the formula (11) without change, wherein the low-dimensional feature set is also a low-dimensional feature set of the original sample data:
Figure FDA0003576017750000043
wherein the content of the first and second substances,
Figure FDA0003576017750000044
representing the low-dimensional characteristics corresponding to the ith group of sample data in any sample data space after the vectorization processing of the formula (8); i is an integer greater than or equal to 1 and less than or equal to N; n represents the group number of sample data of the original data space;
Figure FDA0003576017750000045
a jth neighbor point representing an ith set of sample data; j is an integer greater than or equal to 1 and less than or equal to K; k is more than or equal to 1 and less than or equal to N; w is aijRepresenting a local linear structure of any sample data;
and fifthly, taking the low-dimensional feature set obtained in the fourth step as the input of a support vector machine, and carrying out fault detection on the wind driven generator through information output by the support vector machine.
CN201911362110.1A 2019-12-26 2019-12-26 Method and device for diagnosing fault of wind driven generator in dimension reduction mode Active CN111062447B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911362110.1A CN111062447B (en) 2019-12-26 2019-12-26 Method and device for diagnosing fault of wind driven generator in dimension reduction mode

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911362110.1A CN111062447B (en) 2019-12-26 2019-12-26 Method and device for diagnosing fault of wind driven generator in dimension reduction mode

Publications (2)

Publication Number Publication Date
CN111062447A CN111062447A (en) 2020-04-24
CN111062447B true CN111062447B (en) 2022-07-19

Family

ID=70303707

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911362110.1A Active CN111062447B (en) 2019-12-26 2019-12-26 Method and device for diagnosing fault of wind driven generator in dimension reduction mode

Country Status (1)

Country Link
CN (1) CN111062447B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116720109B (en) * 2023-08-09 2023-10-20 傲拓科技股份有限公司 FPGA-based improved local linear embedded fan bearing fault diagnosis method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102930285A (en) * 2012-09-18 2013-02-13 四川大学 Early failure identification method based on SILLE (Supervised Increment Locally Linear Embedding) dimensionality reduction
CN107092923A (en) * 2017-03-22 2017-08-25 东北大学 The electric melting magnesium furnace process monitoring method of method is locally linear embedding into based on improvement supervision core
CN107316057A (en) * 2017-06-07 2017-11-03 哈尔滨工程大学 Based on the nuclear power unit method for diagnosing faults being locally linear embedding into K nearest neighbor classifiers
CN109815934A (en) * 2019-02-12 2019-05-28 西华大学 A kind of multiple dimensioned OGLPE feature extracting method applied to fault of converter
CN110610245A (en) * 2019-07-31 2019-12-24 东北石油大学 AFPSO-K-means-based long oil pipeline leakage detection method and system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9818242B2 (en) * 2014-12-16 2017-11-14 University Of Southern California Gas turbine engine anomaly detections and fault identifications

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102930285A (en) * 2012-09-18 2013-02-13 四川大学 Early failure identification method based on SILLE (Supervised Increment Locally Linear Embedding) dimensionality reduction
CN107092923A (en) * 2017-03-22 2017-08-25 东北大学 The electric melting magnesium furnace process monitoring method of method is locally linear embedding into based on improvement supervision core
CN107316057A (en) * 2017-06-07 2017-11-03 哈尔滨工程大学 Based on the nuclear power unit method for diagnosing faults being locally linear embedding into K nearest neighbor classifiers
CN109815934A (en) * 2019-02-12 2019-05-28 西华大学 A kind of multiple dimensioned OGLPE feature extracting method applied to fault of converter
CN110610245A (en) * 2019-07-31 2019-12-24 东北石油大学 AFPSO-K-means-based long oil pipeline leakage detection method and system

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
(十二)LLE局部线性嵌入降维算法;躺在稻田里的小白菜;《https://www.jianshu.com/p/25a2a47bb60b》;20181227;第1-5页 *
Learning the Geometric Structure of Manifolds with Singularities Using the Tensor Voting Graph;Shay Deutsch等;《Journal of Mathematical Imaging and Vision》;20170301;第57卷(第3期);402-422 *
LLE score:a new filter-based unsupervised feature selection method based on non-liner manifold embedding and its application to image recognition;Yao C等;《IEEE Transactions on Image Processing》;20171231;第26卷(第11期);5257-5269 *
Locally linear embedding vote: A novel filter method for feature selection;Zebiao Hu等;《DOI: 10.1016/j.measurement.2021.110535》;20211224;1-6 *
Robust locally linear embedding algorithm for machinery fault diagnosis;Yansheng Zhang等;《Preprint submitted to Neurocomputing》;20170818;1-26 *
基于机器学习的滚动轴承智能诊断方法研究;吴武林;《中国优秀硕士学位论文全文数据库_工程科技Ⅱ辑》;20170515;C029-47 *

Also Published As

Publication number Publication date
CN111062447A (en) 2020-04-24

Similar Documents

Publication Publication Date Title
CN113743535B (en) Neural network training method and device and image processing method and device
CN107491541B (en) Text classification method and device
US20210248718A1 (en) Image processing method and apparatus, electronic device and storage medium
WO2022011892A1 (en) Network training method and apparatus, target detection method and apparatus, and electronic device
WO2020119026A1 (en) Image processing method and apparatus, electronic device and storage medium
CN110909815B (en) Neural network training method, neural network training device, neural network processing device, neural network training device, image processing device and electronic equipment
CN110502651B (en) Image processing method and device, electronic equipment and storage medium
CN111310616A (en) Image processing method and device, electronic equipment and storage medium
Yin et al. A subgrid-oriented privacy-preserving microservice framework based on deep neural network for false data injection attack detection in smart grids
CN111931844B (en) Image processing method and device, electronic equipment and storage medium
CN110532956B (en) Image processing method and device, electronic equipment and storage medium
CN113792207A (en) Cross-modal retrieval method based on multi-level feature representation alignment
CN110162600B (en) Information processing method, session response method and session response device
CN114416260B (en) Image processing method, device, electronic equipment and storage medium
CN111242303A (en) Network training method and device, and image processing method and device
CN112926310A (en) Keyword extraction method and device
CN111062447B (en) Method and device for diagnosing fault of wind driven generator in dimension reduction mode
CN110991566B (en) Method and device for diagnosing fault of wind driven generator in information fusion mode
CN111538998B (en) Text encryption method and device, electronic equipment and computer readable storage medium
CN111047049B (en) Method, device and medium for processing multimedia data based on machine learning model
CN111142020B (en) Method and device for diagnosing fault of wind driven generator in multi-structure mode
CN112863523B (en) Voice anti-counterfeiting method and device, terminal equipment and storage medium
EP3848778B1 (en) Fingertip detection method, fingertip detection means, fingertip detection device, and medium
CN112884068A (en) Fault diagnosis method and device, electronic equipment and storage medium
CN112269730A (en) Abnormal log detection method, abnormal log detection device, and storage medium

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