CN112836346B - Motor fault diagnosis method based on CN and PCA, electronic equipment and medium - Google Patents
Motor fault diagnosis method based on CN and PCA, electronic equipment and medium Download PDFInfo
- Publication number
- CN112836346B CN112836346B CN202110020431.4A CN202110020431A CN112836346B CN 112836346 B CN112836346 B CN 112836346B CN 202110020431 A CN202110020431 A CN 202110020431A CN 112836346 B CN112836346 B CN 112836346B
- Authority
- CN
- China
- Prior art keywords
- data
- original data
- channel
- bit binary
- binary data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000003745 diagnosis Methods 0.000 title claims abstract description 56
- 239000011159 matrix material Substances 0.000 claims abstract description 44
- 238000013507 mapping Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 230000009467 reduction Effects 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000000513 principal component analysis Methods 0.000 description 34
- 230000008569 process Effects 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000002759 z-score normalization Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009347 mechanical transmission Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Control Of Electric Motors In General (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The embodiment of the invention relates to the technical field of fault detection and discloses a motor fault diagnosis method, electronic equipment and a medium based on CN and PCA. The method comprises the following steps: receiving the original data of the motor acquired by the sensor; normalizing the original data and converting the original data into 15-bit binary data; performing space mapping on binary data by using a CN algorithm to obtain a 10-dimensional space mapping matrix; performing dimension reduction processing on the space mapping matrix by using a PCA algorithm to obtain a 3-dimensional feature matrix; inputting the feature matrix into a pre-trained network model, and outputting a diagnosis result. By implementing the embodiment of the invention, the space separability of fault types can be improved, and the detection efficiency of a fault diagnosis algorithm can be improved.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a motor fault diagnosis method, electronic equipment and medium based on CN and PCA.
Background
Advanced manufacturing is the main engine and the main pusher for innovatively driving development and high-quality development of economy and society. In the fields of high-end equipment and intelligent manufacturing, the motor can directly convert electric energy into linear motion mechanical energy, and the motor has the advantages of high thrust, high force density, long stroke, low inertia, quick dynamic response, simple mechanical structure and the like.
The motor directly drives the motion equipment, a mechanical transmission mechanism is omitted, the physical limit of the speed and the acceleration of a mechanical transmission element is completely eliminated, and the motor is widely applied to a reciprocating servo system, an industrial robot and a high-precision positioning direct driving system.
The fault diagnosis technology includes the steps of judging whether the equipment works normally or not through various monitoring means in the running state or the working state of the equipment; if the fault is abnormal, indicating what fault occurs through analysis and judgment, so that the maintenance of management personnel is facilitated; or before the failure occurs, the prediction of possible failure is provided, so that management personnel can take measures as early as possible, the failure is avoided, or serious failure is avoided, and therefore shutdown and production stopping are caused, and serious economic loss is brought to engineering. This is the task of the fault diagnosis technology, and is the aim of developing the equipment fault diagnosis technology.
In the background of big data, the data-driven intelligent fault diagnosis method is more applicable due to the extremely high computational complexity and modeling complexity, and is characterized by the substantivity and effectiveness of carrying out statistical analysis and information extraction on massive, multi-source and high-dimensional data. The technology takes collected monitoring data with different sources and different types as a substrate, acquires hidden useful information by utilizing various data mining technologies, and characterizes a normal mode and a fault mode of system operation so as to achieve the purposes of detection and diagnosis.
The performance of the intelligent fault diagnosis method is greatly dependent on the quality of the extracted features, including real-time change, stepwise change, trend change, fault mode and the like of the features, namely the representation and learning of the data are the core of the intelligent fault diagnosis technology. The conventional feature representation learning method has the following problems:
(1) A proper characteristic extraction method can be designed only by prior information, expertise and deep mathematical foundation in the field;
(2) The extracted features are shallow features, and the generalization capability of the extracted features is limited to the complex classification problem;
(3) Limited by the physical characteristics of the mechanical system, component or fault condition changes can significantly alter the feature extraction method or its evaluation criteria;
(4) Feature extraction relies on original features and evaluation criteria, and has certain limitations on the mining of new features.
For massive state data and monitoring variables in production processes and equipment operation, information acquisition is usually in the form of multidimensional vectors, for example: vibration information of the base in the running process of the rotary equipment, vibration information of the driving end, current and voltage information in the running process of the equipment and the like. For multi-channel sensor information, how to fuse the fault information acquired by the sensor into a multi-channel matrix form is a key for realizing the fault diagnosis based on the convolutional neural network. In the convolutional neural network fault diagnosis method based on matrix input, the traditional matrix sample processing method realized by splicing fault data has certain randomness, and the deep network for fault diagnosis is necessarily required to have stronger feature extraction robustness and stronger classification generalization capability. The stronger robustness of feature extraction and the stronger generalization capability necessarily require a relatively complex network structure to meet the requirements. Complex convolutional networks necessarily require more powerful hardware support in the model pre-training and real-time fault diagnosis process with enough samples.
Disclosure of Invention
Aiming at the defects, the embodiment of the invention discloses a motor fault diagnosis method, electronic equipment and medium based on CN and PCA, wherein a CN (Color Names) multi-color space model method is applied to map original data to a high-dimensional space, the dimension of a high-dimensional space mapping result is reduced by the PCA method, a fault data high-dimensional space principal component is finally obtained, the space separability of fault types is improved, and the detection efficiency of a fault diagnosis algorithm is improved.
The first aspect of the embodiment of the invention discloses a motor fault diagnosis method based on CN and PCA, which comprises the following steps:
receiving the original data of the motor acquired by the sensor;
normalizing the original data and converting the original data into 15-bit binary data;
Performing space mapping on the binary data by using a CN algorithm to obtain a 10-dimensional space mapping matrix;
performing dimension reduction processing on the space mapping matrix by using a PCA algorithm to obtain a 3-dimensional feature matrix;
And inputting the feature matrix into a pre-trained network model, and outputting a diagnosis result.
As an alternative implementation manner, in the first aspect of the embodiment of the present invention, the receiving the raw data of the motor acquired by the sensor includes:
Receiving single-channel or multi-channel original data of a motor acquired by one or more types of sensors;
The sensor is any one or more of a vibration sensor, a voltage transformer, a current transformer and an acceleration sensor.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the raw data is single-channel raw data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
normalizing the single-channel original data to 0-32, namely, each single-channel original data is represented by adopting 5-bit binary data;
selecting 3 adjacent 5-bit binary data to be connected in sequence to form 15-bit binary data:
Si＝{Mi-1,Mi,Mi+1}
Wherein S i is the composed 15 th binary data, and M i is the 5 th binary data normalized by the i original data of the single channel; i is more than or equal to 0 and less than or equal to L, wherein L is the length of single-channel original data; when i=0, M i-1 is obtained using the linear difference method, and when i=l, M i+1 is obtained using the linear difference method.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the raw data is two-channel raw data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
Normalizing the two-channel original data to 0-127 and 0-255 respectively, namely, the original data of one channel is represented by 7-bit binary data, and the original data of the other channel is represented by 8-bit binary data;
Selecting the normalized 7-bit binary data of one channel to be connected with the normalized 8-bit binary data corresponding to the other channel to form 15-bit binary data:
Si＝{Mi,Ni}
Wherein S i is the composed ith 15-bit binary data, and M i is 7-bit binary data obtained by normalizing the ith original data of one channel; n i is 8-bit binary data of the ith original data of another channel after normalization; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the original data is three-channel original data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
normalizing the three-channel original data to 0-32, namely representing the original data of each channel in the three-channel original data by adopting 5-bit binary data;
Selecting the corresponding original data of three channels for connection to form 15-bit binary data:
Si＝{Mi,Ni,Oi}
Wherein S i is the composed ith 15-bit binary data, and M i、Ni、Oi is the normalized 5-bit binary data of the ith original data of the three channels respectively; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, performing spatial mapping on the binary data by using a CN algorithm to obtain a 10-dimensional spatial mapping matrix, where the method includes:
and performing high-dimensional space mapping on the data set consisting of the 15-bit binary data by using a conversion matrix 32768×10 to obtain a mapped 10-bit space mapping matrix L×10, wherein L is the length of original data, namely the number of the data set consisting of the 15-bit binary data.
As an alternative implementation manner, in the first aspect of the embodiment of the present invention, the pre-trained network model includes:
Acquiring a plurality of groups of motor sample data with different fault types and motor sample data without faults, and constructing a sample set;
And creating a network initial model, and training the network initial model by using each motor sample data in the sample set to obtain a trained network model.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the length L of the raw data satisfies:
Wherein, beta is the sampling frequency of the sensor, and n is the motor rotation speed.
A second aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory to perform a motor fault diagnosis method based on CN and PCA disclosed in the first aspect of the embodiment of the present invention.
A third aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a motor fault diagnosis method based on CN and PCA disclosed in the first aspect of the embodiments of the present invention.
A fourth aspect of the embodiments of the present invention discloses a computer program product, which when run on a computer causes the computer to perform a CN and PCA based motor fault diagnosis method as disclosed in the first aspect of the embodiments of the present invention.
A fifth aspect of the embodiments of the present invention discloses an application publishing platform for publishing a computer program product, where the computer program product, when run on a computer, causes the computer to execute a motor fault diagnosis method based on CN and PCA disclosed in the first aspect of the embodiments of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
The fault diagnosis method based on the CN and the PCA has higher diagnosis precision, and simultaneously, the model converges faster, so that the separability among different types of data can be improved, and the fault diagnosis efficiency of an algorithm is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart diagram of a motor fault diagnosis method based on CN and PCA disclosed in an embodiment of the invention;
Fig. 2 is a structural diagram of a motor fault diagnosis apparatus based on CN and PCA according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made with reference to the accompanying drawings, in which it is evident that the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present invention are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
The fault diagnosis method based on the CN and the PCA has higher diagnosis precision, and meanwhile, the model converges faster, so that the separability among different types of data can be improved, and the fault diagnosis efficiency of an algorithm is further improved.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a motor fault diagnosis method based on CN and PCA according to an embodiment of the present invention. The execution main body of the method described in the embodiment of the invention is built by software/hardware, and can use devices with processing and storage functions such as a computer, a server and the like, and can also use a mobile phone, a tablet personal computer and the like under the condition of smaller data volume. As shown in fig. 1, the motor fault diagnosis method based on CN and PCA includes the steps of:
110, receiving the raw data of the motor collected by the sensor.
The sensor can collect internal parameter data of the motor, such as voltage, current, acceleration and the like, and can also collect vibration information of the base, the driving end and the like of the motor in the running process. The number of the sensors can be one or more, and when the number of the sensors is multiple, different types of sensors are preferably adopted, for example, the vibration sensors are used for collecting vibration information of the base, the voltage transformers are used for collecting voltage information of the motor, and the like, and of course, in some scenes, the same type of sensors can also be used for collecting parameter information of different positions of the motor.
The raw data of the motor collected by each sensor is called the raw data of one channel. It will be appreciated that: when one sensor is used to collect motor data, then this can be referred to as single channel raw data; when two sensors are used to collect motor data, then this may be referred to as dual channel raw data, or the like.
The length (or number) of the original data should satisfy:
wherein L is the length of the original data of each channel, beta is the sampling frequency of the sensor, and n is the motor rotation speed. In a preferred embodiment of the present invention, if a plurality of sensors are used to collect the raw data of the motor, the sampling frequencies of the plurality of sensors are the same, and the collection times are the same, so that the lengths of the raw data of the channels are equal.
120, Performing normalization processing on the original data, and converting the original data into 15-bit binary data.
In CN conversion, since the conversion matrix of CN conversion is 32768×10, that is, 2 15 ×10, the original data is constructed into 15-bit binary data, so that the subsequent conversion is utilized on one hand, and on the other hand, since the data is not isolated, there is necessarily a certain association between one or more data adjacent to each other or data of the same time of different channels, and if the original data in the channels or between the channels can be associated, the diagnosis can be made more accurate.
The step 120 is used for the conversion operation, normalizes the original data, and correlates the original data in the channels or between the channels.
Specifically:
For single channel raw data, i.e. raw data of the motor acquired by a single sensor, then correlation of the raw data within the channel can be achieved in the following way.
Normalizing the single-channel original data to 0-32, namely, each single-channel original data can be represented by adopting 5-bit binary data; adjacent 3 binary data with 5 bits are selected to be connected in sequence, so that binary data with 15 bits can be spliced:
Si＝{Mi-1,Mi,Mi+1}
Wherein S i is the composed 15 th binary data, and M i is the 5 th binary data normalized by the i original data of the single channel; i is more than or equal to 0 and less than or equal to L, wherein L is the length of single-channel original data; when i=0, M -1 is obtained using the linear difference method, and when i=l, M L+1 is obtained using the linear difference method.
For example, if the data obtained by the normalization processing of the i-1 th, i, i+1 th single-channel raw data is converted into binary data of 10001 th, 01110 th, 11010 th, respectively, the obtained binary data of the i 15 th bit is 100010111011010 th.
It will be appreciated that: the number of 15-bit binary system data obtained by normalizing and splicing the single-channel original data is equal to the number of the single-channel original data, and the single-channel original data has L data. The normalization process may use a Z-score normalization method.
Similarly, for the dual-channel original data, the following method can be used to realize the association of the original data among channels:
Normalizing the two-channel original data to 0-127 and 0-255 respectively, namely, the original data of one channel is represented by 7-bit binary data, and the original data of the other channel is represented by 8-bit binary data;
Selecting the normalized 7-bit binary data of one channel to be connected with the normalized 8-bit binary data corresponding to the other channel to form 15-bit binary data:
Si＝{Mi,Ni}
Wherein S i is the composed ith 15-bit binary data, and M i is 7-bit binary data obtained by normalizing the ith original data of one channel; n i is 8-bit binary data of the ith original data of another channel after normalization; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
For example, if the data obtained by normalizing the i-th original data of the 1 st channel original data and the i-th original data of the 2 nd channel is converted into binary data of 1000110, 11011100, respectively, the obtained i-th 15-bit binary data is 100011011011100.
It is also understood that: the number of the 15-bit binary data obtained by normalizing and splicing the two-channel original data is equal to the number of the original data of each channel of the two channels, and the two channels are provided with L data. The normalization process may use a Z-score normalization method.
Likewise, for three-channel raw data, the correlation of the raw data between channels can be achieved in the following manner.
Normalizing the original data of each channel of the three channels to 0-32, namely, the original data of each channel in the three-channel original data can be represented by adopting 5-bit binary data;
Selecting the corresponding original data of three channels for connection to form 15-bit binary data:
Si＝{Mi,Ni,Oi}
Wherein S i is the composed ith 15-bit binary data, and M i、Ni、Oi is the normalized 5-bit binary data of the ith original data of the three channels respectively; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
For example, if the data obtained by normalizing the i-th original data of the 1 st channel original data, the i-th original data of the 2 nd channel, and the i-th original data of the 3 rd channel are converted into binary data of 10001, 01110, 11010, respectively, the obtained i-th 15-bit binary data is 100010111011010.
It will be appreciated that: the number of 15-bit binary system data obtained by normalizing and splicing the three-channel original data is equal to the number of the single-channel original data, and the three-channel original data has L data. The normalization process may use a Z-score normalization method.
For four or more channels of original data, a processing mode similar to that of two or three channels of original data can be adopted, for example, for four channels, the original data of each channel can be respectively normalized to 0-9, 0-9 and 0-16, that is, three-bit binary and four-bit binary representation can be respectively adopted, and then the normalized data of the same position are spliced to obtain 15-bit binary data. Five channels can be normalized to 0-9.
If fifteen channels are exceeded, it is no longer within the scope of the invention.
130, Performing spatial mapping on the binary data by using a CN algorithm to obtain a 10-dimensional spatial mapping matrix.
In recent years, CN (Color Names) has been widely used in the fields of object detection, image recognition, and motion recognition. They are language color labels, and according to the conclusions drawn by the study of Berlin and Kay, color nomenclature consists of 11 basic components: black, blue, brown, gray, green, orange, pink, purple, red, white, and yellow. Color names are assigned manually for rendering colors in the real world. Based on the color attribute method, the original RGB image can be converted into an 11-dimensional color space with the probability sum of 1 after being mapped by the mapping of the image learning searched and retrieved by the Google image:
X0(i,j)＝W2C32768×10·X1(i,j)
In the field of computer vision, gray values in conventional object trackers always need to be normalized within [ -0.5,0.5] [6 ]. The color names are normalized by a technique to achieve better performance. The technique is a normalization process by an orthogonal standard that projects color names into this 10-dimensional subspace. Thus, the 11-dimensional space can be reduced to 10 dimensions. At the same time, the projection can center the color feature.
When the CN algorithm is applied to the embodiment of the invention, the obtained decimal value corresponding to 15-bit binary data is calculated, the index value corresponding to the decimal value and the index value in the CN conversion matrix 32768 multiplied by 10 is determined, the high-dimensional space mapping matrix corresponding to the decimal value is further constructed, and finally the result mapping matrix MR [0:L,0:10] is obtained.
140, Performing dimension reduction processing on the space mapping matrix by using a PCA algorithm to obtain a 3-dimensional feature matrix.
In most research areas of research, a large amount of data is required to find rules between them. It is clear that a large amount of data will provide a large amount of information and make it easier to analyze. There may be a correlation between many variables and therefore it is necessary to discard useless data and reduce the amount of data to reduce the variables and thus the amount of computation. If the data to be analyzed or its dimensions are randomly reduced, a missing PCA that will inevitably lead to useful information is used to solve the above-mentioned problem.
The principle of PCA (PRINCIPLE COMPONENT ANALYSIS principal component analysis) is to project the original sample data into a new space, i.e. to map a set of matrices to another coordinate system. In the new space or coordinates not all the original samples are needed, but only the space coordinates corresponding to the largest linearly independent set of eigenvalues of the original samples. The computation of eigenvalues and their corresponding eigenvectors is a key part of the PCA algorithm, which refers to eigenvalues of the covariance matrix corresponding to the raw data here.
This text becomes the 10-dimensional data of lx10 after CN operation. If PCA is to be used to reduce the size, a10×10 covariance matrix needs to be calculated first. And secondly, calculating to obtain the eigenvalue and the corresponding eigenvector of the covariance matrix. If the first 3 eigenvalues have accounted for more than 99% of all eigenvalues, only eigenvectors corresponding to the first 9 eigenvalues are extracted, the selected eigenvectors constituting a10×3 transformation matrix. Finally, the corresponding coordinates of the original sample data in the new feature space can be obtained by multiplying the L×10 data subjected to CN projection by a10×3 transformation matrix, and the 10-dimensional data is successfully reduced to 3-dimensional on the basis of no loss of useful information.
150, Inputting the feature matrix into a pre-trained network model, and outputting a diagnosis result.
Because the general network model is directed to the processing of image data, the feature matrix may be converted into a three-channel image, for example, features in each of the 3-dimensional feature matrices are normalized to 0-255, then the 3-dimensional feature matrices respectively represent pixel values of images of R, G, B channels, thereby constructing a R, G, B pixel value matrix of three channels, and then a preset number of pixels satisfying the network model, for example, 100 pixels, are selected to construct an image of 10×10, thereby obtaining a R, G, B image of three channels.
The network model may preferably employ a MobileNetV small network architecture.
And selecting a sample set consisting of sample data of a plurality of motors to train the model. Preferably, the sample data includes a plurality of data sources, including, for example, a plurality of single channel sample data, a plurality of dual channel sample data, a plurality of three channel sample data, a plurality of four channel sample data, etc., and the sample data should include a plurality of different fault types, such as sample data for loss of magnet, air gap variation, stator winding faults, etc., and also should include a plurality of motor sample data when not faulty.
The length of each sample data in the sample data set should also satisfy:
The processing procedure of the steps 120-140 is also needed for the sample data, then the obtained 3-dimensional feature matrix is converted into three-channel images, the three-channel images are input into the network initial model for training, the trained label is the failure type of the sample, for example, the label of the sample data without failure is defined as 0, the label of the sample data with loss of magnetic field failure is defined as1, the label with air gap change failure is defined as 2 … …, and the output result of the network initial model is back propagated by using the label, so that the proper function or value of each parameter of the network initial model is determined, and the final network model is obtained.
And inputting the three-channel image processed by the original data into a trained network model, so that the state of the motor corresponding to the original data can be obtained, and if the state is a fault state, the fault type can be determined.
In order to verify that CN+PCA can improve the spatial separability of various types of original data, the embodiment of the invention applies a CN+PCA method to process rolling bearing fault data of the university of West storage, and constructs a training and testing sample set. Meanwhile, training sample data sets and test sample data sets are directly constructed according to the original data of the West storage university. Two different data sets are simulated and verified on a lightweight CNN network (the whole structure is five layers), and the results of simulation experiments show that the fault diagnosis method based on CN+PCA fault data processing has higher diagnosis precision and faster model convergence. The recognition accuracy and error iteration relationship are shown in table 1. The western data storage experimental result proves that the separability of sample data of different categories can be improved by the method of performing dimension reduction construction on sample data by applying PCA through high-dimension space mapping realized by CN. Thereby improving the fault diagnosis efficiency of the algorithm.
Table 1: failure diagnosis training, test loss and accuracy based on CN and PCA
| Number of iterations | Training loss | Training accuracy | Loss of test | Test accuracy |
| 1 | 0.0217 | 99.5438 | 0.0004 | 100.000 |
| 2 | 0.0011 | 99.9983 | 0.0001 | 100.000 |
| 3 | 0.0007 | 99.9983 | 0.0006 | 100.000 |
| 4 | 0.0005 | 100.000 | 0.0000 | 100.000 |
| 5 | 0.0004 | 100.000 | 0.0000 | 100.000 |
| 6 | 0.0005 | 99.9983 | 0.0000 | 100.000 |
| 7 | 0.0003 | 99.9983 | 0.0000 | 100.000 |
| 8 | 0.0003 | 100.000 | 0.0000 | 100.000 |
| 9 | 0.0002 | 99.9983 | 0.0000 | 100.000 |
| 10 | 0.0002 | 100.000 | 0.0000 | 100.000 |
| 11 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 12 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 13 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 14 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 15 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 16 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 17 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 18 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 19 | 0.0001 | 100.000 | 0.0000 | 100.000 |
| 20 | 0.0001 | 100.000 | 0.0000 | 100.000 |
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a motor fault diagnosis device based on CN and PCA according to an embodiment of the present invention. As shown in fig. 2, the apparatus may include:
a receiving unit 210, configured to receive raw data of the motor acquired by the sensor;
a normalization unit 220, configured to normalize the raw data and convert the raw data into 15-bit binary data;
A mapping unit 230, configured to spatially map the binary data by using a CN algorithm, to obtain a 10-dimensional spatial mapping matrix;
the dimension reduction unit 240 is configured to perform dimension reduction processing on the spatial mapping matrix by using a PCA algorithm to obtain a 3-dimensional feature matrix;
And the diagnosis unit 250 is used for inputting the feature matrix into a pre-trained network model and outputting a diagnosis result.
As an alternative embodiment, receiving the raw data of the motor collected by the sensor includes:
Receiving single-channel or multi-channel original data of a motor acquired by one or more types of sensors;
The sensor is any one or more of a vibration sensor, a voltage transformer, a current transformer and an acceleration sensor.
As an alternative embodiment, the raw data is single-channel raw data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
normalizing the single-channel original data to 0-32, namely, each single-channel original data is represented by adopting 5-bit binary data;
selecting 3 adjacent 5-bit binary data to be connected in sequence to form 15-bit binary data:
Si＝{Mi-1,Mi,Mi+1}
Wherein S i is the composed 15 th binary data, and M i is the 5 th binary data normalized by the i original data of the single channel; i is more than or equal to 0 and less than or equal to L, wherein L is the length of single-channel original data; when i=0, M i-1 is obtained using the linear difference method, and when i=l, M i+1 is obtained using the linear difference method.
As an alternative embodiment, the raw data is two-channel raw data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
Normalizing the two-channel original data to 0-127 and 0-255 respectively, namely, the original data of one channel is represented by 7-bit binary data, and the original data of the other channel is represented by 8-bit binary data;
Selecting the normalized 7-bit binary data of one channel to be connected with the normalized 8-bit binary data corresponding to the other channel to form 15-bit binary data:
Si＝{Mi,Ni}
Wherein S i is the composed ith 15-bit binary data, and M i is 7-bit binary data obtained by normalizing the ith original data of one channel; n i is 8-bit binary data of the ith original data of another channel after normalization; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
As an alternative embodiment, the raw data is three-channel raw data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
Normalizing the three-channel original data to 0-32, namely representing the original data of each channel in the three-channel original data by adopting 5-bit binary data;
Selecting the corresponding original data of three channels for connection to form 15-bit binary data:
Si＝{Mi,Ni,Oi}
Wherein S i is the composed ith 15-bit binary data, and M i、Ni、Oi is the normalized 5-bit binary data of the ith original data of the three channels respectively; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
As an alternative implementation manner, the binary data is spatially mapped by using a CN algorithm to obtain a 10-dimensional spatial mapping matrix, which includes:
and performing high-dimensional space mapping on the data set consisting of the 15-bit binary data by using a conversion matrix 32768×10 to obtain a mapped 10-bit space mapping matrix L×10, wherein L is the length of original data, namely the number of the data set consisting of the 15-bit binary data.
As an alternative embodiment, a pre-trained network model, comprising:
Acquiring a plurality of groups of motor sample data with different fault types and motor sample data without faults, and constructing a sample set;
And creating a network initial model, and training the network initial model by using each motor sample data in the sample set to obtain a trained network model.
As an alternative embodiment, the length L of the raw data satisfies:
Wherein, beta is the sampling frequency of the sensor, and n is the motor rotation speed.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the invention. As shown in fig. 3, the electronic device may include:
A memory 310 in which executable program code is stored;
A processor 320 coupled to the memory 310;
Wherein the processor 320 invokes executable program code stored in the memory 310 to perform some or all of the steps in the CN and PCA based motor fault diagnosis method of embodiment one.
An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute part or all of the steps in the motor fault diagnosis method based on CN and PCA in the first embodiment.
The embodiment of the invention also discloses a computer program product, wherein the computer program product enables a computer to execute part or all of the steps in the motor fault diagnosis method based on CN and PCA in the embodiment I.
The embodiment of the invention also discloses an application release platform, wherein the application release platform is used for releasing a computer program product, and the computer program product is used for enabling the computer to execute part or all of the steps in the motor fault diagnosis method based on the CN and the PCA in the embodiment I when running on the computer.
In various embodiments of the present invention, it should be understood that the size of the sequence numbers of the processes does not mean that the execution sequence of the processes is necessarily sequential, and the execution sequence of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the method according to the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that some or all of the steps of the various methods of the described embodiments may be implemented by hardware associated with a program that may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), one-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), electrically erasable rewritable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), or any other optical disk Memory, magnetic disk Memory, tape Memory, or computer-readable medium capable of carrying or storing data.
The foregoing describes in detail a motor fault diagnosis method, an electronic device and a medium based on CN and PCA disclosed in the embodiments of the present invention, and specific examples are applied herein to illustrate the principles and embodiments of the present invention, where the foregoing description of the embodiments is only for helping to understand the method and core idea of the present invention; meanwhile, the person skilled in the art will change the specific embodiments and application scope according to the idea of the present invention, and the present invention should not be construed as being limited to the description above.
Claims (6)
1. A motor fault diagnosis method based on CN and PCA, comprising:
receiving the original data of the motor acquired by the sensor;
normalizing the original data and converting the original data into 15-bit binary data;
Performing space mapping on the binary data by using a CN algorithm to obtain a 10-dimensional space mapping matrix;
performing dimension reduction processing on the space mapping matrix by using a PCA algorithm to obtain a 3-dimensional feature matrix;
inputting the feature matrix into a pre-trained network model, and outputting a diagnosis result;
Receiving the original data of the motor acquired by the sensor, comprising:
receiving single-channel or multi-channel original data of a motor acquired by one or more sensors;
the sensor is any one or more of a vibration sensor, a voltage transformer, a current transformer and an acceleration sensor;
When the original data is single-channel original data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
normalizing the single-channel original data to 0-32, namely, each single-channel original data is represented by adopting 5-bit binary data;
selecting 3 adjacent 5-bit binary data to be connected in sequence to form 15-bit binary data:
Si＝{Mi-1,Mi,Mi+1}
Wherein S i is the composed ith 15-bit binary data, and M i is the 5-bit binary data normalized by the ith original data of a single channel; i is more than or equal to 0 and less than or equal to L, wherein L is the length of single-channel original data; when i=0, M i-1 is obtained using a linear difference method, and when i=l, M i+1 is obtained using a linear difference method;
When the original data is the double-channel original data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
normalizing the two-channel original data to 0-127 and 0-255 respectively, namely, the original data of one channel is represented by 7-bit binary data, and the original data of the other channel is represented by 8-bit binary data;
Selecting the normalized 7-bit binary data of one channel to be connected with the normalized 8-bit binary data corresponding to the other channel to form 15-bit binary data:
Si＝{Mi,Ni}
Wherein S i is the composed ith 15-bit binary data, and M i is 7-bit binary data obtained by normalizing the ith original data of one channel; n i is 8-bit binary data of the ith original data of another channel after normalization; i is more than or equal to 0 and less than or equal to L, wherein L is the length of original data of each channel;
When the original data is three-channel original data;
The normalizing processing is carried out on the original data and the original data is converted into 15-bit binary data, and the normalizing processing comprises the following steps:
normalizing the three-channel original data to 0-32, namely representing the original data of each channel in the three-channel original data by adopting 5-bit binary data;
Selecting the corresponding original data of three channels for connection to form 15-bit binary data:
Si＝{Mi,Ni,Oi}
Wherein S i is the composed ith 15-bit binary data, and M i、Ni、Oi is the normalized 5-bit binary data of the ith original data of the three channels respectively; i is more than or equal to 0 and less than or equal to L, wherein L is the length of the original data of each channel.
2. The CN and PCA based motor fault diagnosis method according to claim 1, wherein performing spatial mapping on the binary data using a CN algorithm to obtain a 10-dimensional spatial mapping matrix, comprising:
And performing high-dimensional space mapping on the data set consisting of the 15-bit binary data by using a conversion matrix 32768×10 to obtain a mapped 10-bit space mapping matrix L×10, wherein L is the length of original data, namely the number of the data set consisting of the 15-bit binary data.
3. The CN and PCA based motor fault diagnosis method according to claim 1, wherein the pre-trained network model comprises:
Acquiring a plurality of groups of motor sample data with different fault types and motor sample data without faults, and constructing a sample set;
And creating a network initial model, and training the network initial model by using each motor sample data in the sample set to obtain a trained network model.
4. The CN and PCA based motor fault diagnosis method according to claim 1, wherein the length L of the raw data satisfies:
Wherein, beta is the sampling frequency of the sensor, and n is the motor rotation speed.
5. An electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor invokes the executable program code stored in the memory for performing a CN and PCA based motor fault diagnosis method according to any of claims 1 to 4.
6. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a CN and PCA-based motor fault diagnosis method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020431.4A CN112836346B (en) | 2021-01-07 | 2021-01-07 | Motor fault diagnosis method based on CN and PCA, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020431.4A CN112836346B (en) | 2021-01-07 | 2021-01-07 | Motor fault diagnosis method based on CN and PCA, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112836346A CN112836346A (en) | 2021-05-25 |
| CN112836346B true CN112836346B (en) | 2024-04-23 |
Family
ID=75928342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110020431.4A Active CN112836346B (en) | 2021-01-07 | 2021-01-07 | Motor fault diagnosis method based on CN and PCA, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112836346B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114236386B (en) * | 2021-12-16 | 2023-10-31 | 河北工业大学 | Fault diagnosis method for power converter of switched reluctance motor |
| CN117849617B (en) * | 2024-01-10 | 2024-06-14 | 关兴 | Star connection motor resistance sensing fault detection method, system, equipment and medium |
| CN117991093B (en) * | 2024-04-03 | 2024-06-18 | 成都航天凯特机电科技有限公司 | Permanent magnet synchronous motor fault diagnosis method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108994088A (en) * | 2018-06-12 | 2018-12-14 | 武汉科技大学 | HAGC cylinder method for diagnosing faults and device based on PCA dimensionality reduction Yu DBN network |
| CN109272044A (en) * | 2018-09-19 | 2019-01-25 | 郑州云海信息技术有限公司 | A kind of image similarity determines method, apparatus, equipment and storage medium |
| CN110895701A (en) * | 2019-06-12 | 2020-03-20 | 河南理工大学 | Forest fire online identification method and device based on CN and FHOG |
| CN111191725A (en) * | 2019-12-31 | 2020-05-22 | 北京市燃气集团有限责任公司 | RBF fault diagnosis method, system, terminal and computer storage medium based on PCA data processing |
-
2021
- 2021-01-07 CN CN202110020431.4A patent/CN112836346B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108994088A (en) * | 2018-06-12 | 2018-12-14 | 武汉科技大学 | HAGC cylinder method for diagnosing faults and device based on PCA dimensionality reduction Yu DBN network |
| CN109272044A (en) * | 2018-09-19 | 2019-01-25 | 郑州云海信息技术有限公司 | A kind of image similarity determines method, apparatus, equipment and storage medium |
| CN110895701A (en) * | 2019-06-12 | 2020-03-20 | 河南理工大学 | Forest fire online identification method and device based on CN and FHOG |
| CN111191725A (en) * | 2019-12-31 | 2020-05-22 | 北京市燃气集团有限责任公司 | RBF fault diagnosis method, system, terminal and computer storage medium based on PCA data processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112836346A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112836346B (en) | Motor fault diagnosis method based on CN and PCA, electronic equipment and medium | |
| CN111721535B (en) | Bearing fault detection method based on convolution multi-head self-attention mechanism | |
| CN110516305B (en) | Intelligent fault diagnosis method under small sample based on attention mechanism meta-learning model | |
| CN112200244B (en) | Intelligent detection method for anomaly of aerospace engine based on hierarchical countermeasure training | |
| Guo et al. | Bearing intelligent fault diagnosis based on wavelet transform and convolutional neural network | |
| CN113780412A (en) | Fault diagnosis model training method and system and fault diagnosis model training method and system | |
| CN116503399B (en) | Insulator pollution flashover detection method based on YOLO-AFPS | |
| CN114091504A (en) | Rotary machine small sample fault diagnosis method based on generation countermeasure network | |
| CN114360030A (en) | Face recognition method based on convolutional neural network | |
| CN111595541A (en) | Multi-dimensional structure damage identification method based on mass vibration transmissibility data convolutional neural network processing | |
| CN114067286A (en) | High-order camera vehicle weight recognition method based on serialized deformable attention mechanism | |
| CN115392301A (en) | Converter transformer state identification method, converter transformer state identification device, converter transformer state identification equipment, converter transformer state identification medium and program product | |
| Bao et al. | A transformer model-based approach to bearing fault diagnosis | |
| Yang et al. | Few-shot learning for rolling bearing fault diagnosis via siamese two-dimensional convolutional neural network | |
| CN117473411A (en) | Bearing life prediction method based on improved transducer model | |
| Lu et al. | Rotating Machinery Fault Diagnosis Under Multiple Working Conditions via A Time Series Transformer Enhanced by Convolutional Neural Network | |
| CN113705695A (en) | Power distribution network fault data identification method based on convolutional neural network | |
| CN116503398B (en) | Insulator pollution flashover detection method and device, electronic equipment and storage medium | |
| CN117763494A (en) | Bearing diagnosis method and system based on multi-mode and multi-scale fusion network | |
| CN112733706B (en) | Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium | |
| CN115638965A (en) | Rotating machine fault diagnosis method based on one-dimensional attention mechanism and convolutional neural network | |
| Zhang et al. | TSViT: A Time Series Vision Transformer for Fault Diagnosis | |
| CN113033397A (en) | Target tracking method, device, equipment, medium and program product | |
| CN117056814B (en) | Transformer voiceprint vibration fault diagnosis method | |
| CN111340111B (en) | Method for recognizing face image set based on wavelet kernel extreme learning machine |
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 |