CN112733706A - Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium - Google Patents

Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium Download PDF

Info

Publication number
CN112733706A
CN112733706A CN202110020414.0A CN202110020414A CN112733706A CN 112733706 A CN112733706 A CN 112733706A CN 202110020414 A CN202110020414 A CN 202110020414A CN 112733706 A CN112733706 A CN 112733706A
Authority
CN
China
Prior art keywords
data
lbp
channel
bilinear
processing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110020414.0A
Other languages
Chinese (zh)
Other versions
CN112733706B (en
Inventor
赵运基
许孝卓
吴中华
王莉
苏波
刘晓光
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.)
Henan University of Technology
Original Assignee
Henan University of Technology
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 Henan University of Technology filed Critical Henan University of Technology
Priority to CN202110020414.0A priority Critical patent/CN112733706B/en
Publication of CN112733706A publication Critical patent/CN112733706A/en
Application granted granted Critical
Publication of CN112733706B publication Critical patent/CN112733706B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • 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
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Control Of Electric Motors In General (AREA)

Abstract

The embodiment of the invention relates to the technical field of fault detection, and discloses a motor fault diagnosis method based on bilinear LBP, electronic equipment and a medium. The method comprises the following steps: receiving single-channel original data of the motor, which are acquired by a sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data which is called as pre-processing data; processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data; constructing three-channel characteristic data by the pre-processing data, the first LBP data and the second LBP data; and constructing a three-channel characteristic image by using the three-channel characteristic data, inputting the three-channel characteristic image into a pre-trained network model, and outputting a diagnosis result. By implementing the embodiment of the invention, the spatial resolution of the single-channel original data can be enhanced, the spatial separability of the fault categories is improved, and the detection efficiency of the fault diagnosis algorithm is finally improved.

Description

Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium
Technical Field
The invention relates to the technical field of fault detection, in particular to a motor fault diagnosis method based on bilinear LBP, electronic equipment and a medium.
Background
Advanced manufacturing is the primary engine and prime mover for innovation-driven development and high-quality development of the economic society. In the field of high-end equipment and intelligent manufacturing, an electric motor can directly convert electric energy into mechanical energy of linear motion, and the electric motor has the advantages of large 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 limits of the speed and the acceleration of a mechanical transmission element are completely eliminated, and the motor is widely applied to a reciprocating servo system, an industrial robot and a high-precision positioning direct drive system.
The fault diagnosis technology comprises the following contents that whether the equipment works normally or not is judged by various monitoring means under the running state or working state of the equipment; if the fault is abnormal, the fault is indicated through analysis and judgment, and the maintenance is convenient for managers; or the forecast of possible faults is provided before the faults do not occur, so that management personnel can take measures as early as possible to avoid the faults or avoid major faults, shutdown and production halt are caused, and major economic losses are brought to the engineering. This is the task of the fault diagnosis technology and the purpose of developing the fault diagnosis technology of the equipment.
Under the background of the generation of big data, the method is accompanied by great computational complexity and modeling complexity, and the data-driven intelligent fault diagnosis method is more applicable to the directness and the effectiveness of statistical analysis and information extraction on massive, multi-source and high-dimensional data. The technology takes the collected monitoring data of different sources and types as a substrate, and various data mining technologies are utilized to obtain implicit useful information, so as to represent a normal mode and a fault mode of system operation, and further achieve the purposes of detection and diagnosis.
The performance of the intelligent fault diagnosis method greatly depends on the quality of the extracted features, including real-time change, stage change, trend change, fault modes and the like of the features, namely, the representation learning of data is the core of the intelligent fault diagnosis technology. The conventional feature expression learning method has the following problems:
(1) the proper feature extraction method can be designed only by needing prior information, professional knowledge and deep mathematical basis of the field;
(2) most of the extracted features are shallow features, and the generalization capability of the extracted features is limited to a certain extent aiming at the problem of complex classification;
(3) subject to the physical characteristics of the mechanical system, component or fault condition variations can significantly alter the feature extraction method or its evaluation criteria;
(4) the feature extraction depends on the original features and evaluation standards, and has certain limitation on the mining of new features.
For massive state data and monitoring variables in the production process and equipment operation, information acquisition is usually in the form of multidimensional vectors, such as: 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 single-channel mass data, due to poor spatial resolution, more times of diagnosis are needed to obtain accurate diagnosis results, the diagnosis accuracy is low, and the diagnosis efficiency is low.
Disclosure of Invention
Aiming at the defects, the embodiment of the invention discloses a motor fault diagnosis method based on bilinear LBP, electronic equipment and a medium, wherein single-channel original data and LBP data with local features extracted are fused, so that the description capability of the local features can be improved, the spatial resolution of the single-channel original data is enhanced, the spatial separability of fault categories is improved, and the detection efficiency of a fault diagnosis algorithm is finally improved.
The embodiment of the invention discloses a motor fault diagnosis method based on bilinear LBP in a first aspect, which comprises the following steps:
receiving single-channel original data of the motor, which are acquired by a sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data which is called as preprocessing data;
processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data;
constructing three-channel characteristic data by the pre-processing data, the first LBP data and the second LBP data;
and constructing a three-channel characteristic image by the three-channel characteristic data, inputting the three-channel characteristic image 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 sensor is any one 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 processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data includes:
selecting continuous 9 pieces of pre-processing data, and comparing the size of the intermediate data with the size of the adjacent front and back four data to form first LBP data and second LBP data:
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4}
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4}
wherein S isiAnd QiI-th first LBP data and second LBP data, respectively, if Mi≥MjThen XjIf M is equal to 1i<MjThen Xj0; if M isi<MjThen Y isjIf M is equal to 1i≥MjThen Y isj＝0；j＝{i-4,i-3,i-2,i-1,i+1,i+2,i+3,i+4}；MiAnd MjRespectively the ith and the j pre-processing data, wherein i is more than or equal to 0 and less than or equal to L, and L is the length of single-channel original data;
when i is less than 4, obtaining M by using a linear difference modek，i-4≤k≤-1；
When i is greater than L-4, M is obtained by using a linear difference modec，L+1≤c≤i+4；
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4Denotes combining X withi-4、Xi-3、Xi-2、Xi-1、Xi+1、Xi+2、Xi+3And Xi+48-bit binary numbers formed by sequential connection;
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4represents a general formulai-4、Yi-3、Yi-2、Yi-1、Yi+1、Yi+2、Yi+3And Yi+4The 8-bit binary numbers are connected in sequence.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, three-channel feature data is constructed from the preprocessed data, the first LBP data, and the second LBP data; the method comprises the following steps:
respectively converting the first LBP data and the second LBP data into decimal numbers, wherein the decimal numbers corresponding to the first LBP data and the second LBP data are in the range of [0, 255 ];
and respectively taking the pre-processing data, the first LBP data converted into decimal numbers and the second LBP data as the characteristic data of one channel to form three-channel characteristic data.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, constructing a three-channel feature image from the three-channel feature data includes:
and respectively corresponding the three-channel characteristic data to R, G, B three-channel pixel point values to form a three-channel characteristic image.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the pre-trained network model includes:
acquiring multiple 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 the sample data of each motor in the sample set to obtain the trained network model.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the length L of the single-channel original data satisfies:
Figure BDA0002888322610000041
wherein, beta is the sampling frequency of the sensor, and n is the rotating speed of the motor.
The second aspect of the embodiment of the invention discloses a motor fault diagnosis device based on bilinear LBP, which comprises:
the receiving unit is used for receiving single-channel original data of the motor, which are acquired by the sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data which is called as pre-processing data;
the processing unit is used for processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data;
the construction unit is used for constructing three-channel characteristic data from the pre-processing data, the first LBP data and the second LBP data;
and the diagnosis unit is used for constructing a three-channel characteristic image from the three-channel characteristic data, inputting the three-channel characteristic image into a pre-trained network model and outputting a diagnosis result.
A third aspect of an embodiment of the present invention discloses an electronic device, including: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory for executing the bilinear LBP-based motor fault diagnosis method disclosed by the first aspect of the embodiment of the invention.
A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium storing a computer program, where the computer program enables a computer to execute the method for diagnosing a motor fault based on bilinear LBP disclosed in the first aspect of the embodiments of the present invention.
A fifth aspect of the embodiments of the present invention discloses a computer program product, which, when running on a computer, causes the computer to execute the method for diagnosing a motor fault based on bilinear LBP disclosed in the first aspect of the embodiments of the present invention.
A sixth aspect of the present invention discloses an application publishing platform, where the application publishing platform is configured to publish a computer program product, and when the computer program product runs on a computer, the computer is enabled to execute the motor fault diagnosis method based on bilinear LBP disclosed in the first aspect of the present invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
the bilinear LBP method is applied to carry out channel expansion on the original single-channel data, the spatial resolution of the single-channel original data is enhanced, the spatial separability of fault categories is improved, and finally the detection efficiency of the fault diagnosis algorithm is improved.
The LBP-based feature extraction method can effectively extract local features. In single-channel original data, taking vibration data as an example, when a fault occurs, the vibration amplitude exceeds the amplitude of a stable state, so that the sampled data has deviation from normal data, and the deviation is the core description information of fault diagnosis. To highlight the effect of the relative maxima and minima in the data, we therefore consider converting the LBP in matrix form to a linear LBP. The bilinear LBP highlights a local maximum value and a local minimum value in the operation process; the single-channel original data and the LBP data with the extracted local features are fused, and the local feature description capability can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used 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 it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a bilinear LBP-based motor fault diagnosis method disclosed in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a bilinear LBP-based motor fault diagnosis device disclosed in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device disclosed in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first", "second", "third", "fourth", and the like in the description and the claims of the present invention are used for distinguishing different objects, and are not used for describing a specific order. The terms "comprises," "comprising," and any other variation 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, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
A motor fault diagnosis method, electronic equipment and a medium based on bilinear LBP are used for judging whether a motor is in fault and the fault type according to detection data.
The LBP algorithm is proposed to improve the local feature description capability of the feature extraction method. The LBP algorithm has been successfully applied to the recognition algorithm and the tracking algorithm based on the feature extraction, and a better effect is achieved. The LBP algorithm can effectively extract effective characteristics of dark points in a brighter background and bright points in a darker background, and the characteristic extraction result contains relative information among local pixel points.
The LBP is processed by comparing the pixel point value in the 3 x 3 area with the central pixel point value, wherein one processing mode is that the peripheral pixel point value is 1 if larger than the central value, and the other processing mode is that the peripheral pixel point value is 0 if larger than the central value, then arranging eight-digit binary numbers around the central point in a fixed sequence, and converting the arrangement result into decimal number, namely the LBP value of the central point pixel.
In the fault diagnosis, the data form is generally one-dimensional data of a time series, so that the LBP value is calculated by selecting a comparison area as a vector form of 9 multiplied by 1, and comparing eight motor data values before and after a middle value to finally determine the LBP value corresponding to the center point.
Due to the fluctuation of the motor data, two different LBP value determining methods are selected to process the original time series motor data, the LBP time series data corresponding to the original motor data is constructed, and the purpose of data channel expansion and feature extraction is achieved. Which is described in detail below.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart of a motor fault diagnosis method based on bilinear LBP 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 equipment with processing and storage functions such as a computer and a server, and can also use a mobile phone, a tablet computer and the like under the condition of small data volume. As shown in fig. 1, the method for diagnosing the motor fault based on the bilinear LBP comprises the following steps:
110, receiving single-channel original data of the motor collected by a sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data, which is called as preprocessing data.
The sensor can acquire internal parameter data of the motor, such as voltage, current, acceleration and the like, and can also acquire vibration information of the base, the driving end and the like of the motor in the operation process. The sensor may be one.
The raw data of the motor collected by one sensor is called single-channel raw data.
The length (or number) of the single-channel original data should satisfy:
Figure BDA0002888322610000081
wherein, L is the length of the raw data of each channel, beta is the sampling frequency of the sensor, and n is the rotating speed of the motor.
The single-channel raw data is normalized to 0-255, the normalization is used for subsequent conversion into images, and the 0-255 is R, G, B pixel value ranges of each channel image and is also a pixel value range of a gray scale image. The normalization process may use a Z-score normalization method.
For the convenience of distinction, normalized single-channel raw data is referred to as pre-processing data.
And 120, processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data.
The LBP (Local Binary pattern) aims at performing channel expansion on original single-channel data, enhancing the spatial resolution of the single-channel original data, improving the spatial separability of fault categories and finally improving the detection efficiency of a fault diagnosis algorithm on the one hand, and can effectively extract Local features and highlight Local maximum values and Local minimum values on the other hand; the single-channel original data and the LBP data with the extracted local features are fused, and the local feature description capability can be improved.
Specifically, 9 consecutive pieces of pre-processing data are selected, and the size of the intermediate data and four adjacent front and back data thereof are compared to form first LBP data and second LBP data:
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4}
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4}
wherein S isiAnd QiI-th first LBP data and second LBP data, respectively, if Mi≥MjThen XjIf M is equal to 1i<MjThen Xj0; if M isi<MjThen Y isjIf M is equal to 1i≥MjThen Y isj＝0；j＝{i-4,i-3,i-2,i-1,i+1,i+2,i+3,i+4}；MiAnd MjRespectively the ith and the j pre-processing data, wherein i is more than or equal to 0 and less than or equal to L, and L is the length of single-channel original data;
when i is less than 4, obtaining M by using a linear difference modek，i-4≤k≤-1；
When i is greater than L-4, M is obtained by using a linear difference modec，L+1≤c≤i+4；
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4Denotes combining X withi-4、Xi-3、Xi-2、Xi-1、Xi+1、Xi+2、Xi+3And Xi+48-bit binary numbers formed by sequential connection;
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4represents a general formulai-4、Yi-3、Yi-2、Yi-1、Yi+1、Yi+2、Yi+3And Yi+4The 8-bit binary numbers are connected in sequence.
As can be seen from the above, the first LBP data and the second LBP data are the same as the pre-processing data in number, and are all L data.
And 130, constructing three-channel characteristic data by using the pre-processing data, the first LBP data and the second LBP data.
Since the first LBP data and the second LBP data are both binary data, which is different from the binary system of the preprocessed data, and a decimal image is also used when a three-channel image is subsequently constructed, it is necessary to convert the first LBP data and the second LBP data into a decimal number first.
And then preprocessing the data, and converting the first LBP data and the second LBP data into decimal numbers to respectively form the characteristic data of one channel, and constructing and forming a three-channel characteristic image.
And 140, constructing a three-channel characteristic image by the three-channel characteristic data, inputting the three-channel characteristic image into a pre-trained network model, and outputting a diagnosis result.
As a general network model is directed to processing of image data, three-channel feature data can be converted into a three-channel image, for example, as the feature data of each channel of the three-channel feature data conversion is between 0 and 255, the three-channel feature data respectively correspond to R, G, B three-channel pixel point values, and then a preset number of pixel points, for example, 100 pixel points, satisfying the network model are selected to construct a 10 × 10 image, thereby obtaining a R, G, B image of three channels. The network model can preferably adopt a network structure of MobileNet V3 small.
And selecting a sample set consisting of sample data of a plurality of motors to train the model. Preferably, the sample data comprises a plurality of data sources, the sample data should be single-channel sample data, the sample data should comprise a plurality of sample data of different fault types such as loss of field, air gap variation, stator winding fault and the like, and the sample data of the motor should also comprise a plurality of sample data of the motor without fault.
The length of each sample data in the sample data set should also satisfy:
Figure BDA0002888322610000101
the sample data also needs the processing process of the above-mentioned step 110-130, including normalization, bilinear LBP processing, and three-channel feature data construction, then the obtained three-channel feature data is converted into a three-channel image, input into the network initial model for training, the trained label is the fault type of the sample, for example, the label of the sample data without fault is defined as 0, the label of the sample data with loss of field fault is defined as 1, the label of the fault with air gap change is defined as 2 … …, and the label is used to perform back propagation on the output result of the network initial model, thereby determining the appropriate function or value of each parameter of the network initial model, and obtaining the final network model.
And inputting the three-channel image obtained by processing the single-channel original data into the 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 conclusion, the bilinear LBP method can be used for carrying out channel expansion on single-channel original data, the spatial resolution of the single-channel original data is enhanced, the spatial separability of fault categories is improved, and finally the detection efficiency of the fault diagnosis algorithm is improved.
The LBP-based feature extraction method can effectively extract local features. In single-channel original data, taking vibration data as an example, when a fault occurs, the vibration amplitude exceeds the amplitude of a stable state, so that the sampled data has deviation from normal data, and the deviation is the core description information of fault diagnosis. To highlight the effect of the relative maxima and minima in the data, we therefore consider converting the LBP in matrix form to a linear LBP. The bilinear LBP highlights a local maximum value and a local minimum value in the operation process; the fusion of single-channel original data and LBP data with extracted local features can improve the local feature description capability
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a motor fault diagnosis device based on bilinear LBP according to an embodiment of the present invention. As shown in fig. 2, the apparatus may include:
the receiving unit 210 is configured to receive single-channel raw data of the motor acquired by the sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data which is called as pre-processing data;
a processing unit 220, configured to process the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data;
a constructing unit 230, configured to construct three-channel feature data from the preprocessed data, the first LBP data, and the second LBP data;
and the diagnosis unit 240 is used for constructing a three-channel characteristic image from the three-channel characteristic data, inputting the three-channel characteristic image into a pre-trained network model, and outputting a diagnosis result.
As an alternative embodiment, the sensor is any one of a vibration sensor, a voltage transformer, a current transformer and an acceleration sensor.
As an optional implementation manner, processing the preprocessed data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data includes:
selecting continuous 9 pieces of pre-processing data, and comparing the size of the intermediate data with the size of the adjacent front and back four data to form first LBP data and second LBP data:
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4}
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4}
wherein S isiAnd QiI-th first LBP data and second LBP data, respectively, if Mi≥MjThen XjIf M is equal to 1i<MjThen Xj0; if M isi<MjThen Y isjIf M is equal to 1i≥MjThen Y isj＝0；j＝{i-4,i-3,i-2,i-1,i+1,i+2,i+3,i+4}；MiAnd MjRespectively the ith and the j pre-processing data, wherein i is more than or equal to 0 and less than or equal to L, and L is the length of single-channel original data;
when i is less than 4, obtaining M by using a linear difference modek，i-4≤k≤-1；
When i is greater than L-4, M is obtained by using a linear difference modec，L+1≤c≤i+4；
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4Denotes combining X withi-4、Xi-3、Xi-2、Xi-1、Xi+1、Xi+2、Xi+3And Xi+48-bit binary numbers formed by sequential connection;
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4represents a general formulai-4、Yi-3、Yi-2、Yi-1、Yi+1、Yi+2、Yi+3And Yi+4The 8-bit binary numbers are connected in sequence.
As an optional implementation manner, constructing three-channel feature data from the preprocessed data, the first LBP data and the second LBP data; the method comprises the following steps:
respectively converting the first LBP data and the second LBP data into decimal numbers, wherein the decimal numbers corresponding to the first LBP data and the second LBP data are in the range of [0, 255 ];
and respectively taking the pre-processing data, the first LBP data converted into decimal numbers and the second LBP data as the characteristic data of one channel to form three-channel characteristic data.
As an optional implementation, constructing a three-channel feature image from the three-channel feature data includes:
and respectively corresponding the three-channel characteristic data to R, G, B three-channel pixel point values to form a three-channel characteristic image.
As an alternative embodiment, the pre-trained network model includes:
acquiring multiple 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 the sample data of each motor in the sample set to obtain the trained network model.
As an optional implementation manner, the length L of the single-channel original data satisfies:
Figure BDA0002888322610000131
wherein, beta is the sampling frequency of the sensor, and n is the rotating speed of the motor.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. As shown in fig. 3, the electronic device may include:
a memory 310 storing executable program code;
a processor 320 coupled to the memory 310;
in which processor 320 calls executable program code stored in memory 310 to perform some or all of the steps of the bilinear LBP-based motor fault diagnosis method in the first embodiment.
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute part or all of the steps in the motor fault diagnosis method based on bilinear LBP in the first embodiment.
The embodiment of the invention also discloses a computer program product, wherein when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps in the motor fault diagnosis method based on the bilinear LBP in the first embodiment.
The embodiment of the invention also discloses an application publishing platform, wherein the application publishing platform is used for publishing the computer program product, and when the computer program product runs on a computer, the computer is enabled to execute part or all of the steps in the motor fault diagnosis method based on the bilinear LBP in the first embodiment.
In various embodiments of the present invention, it should be understood that the sequence numbers of the processes do not mean the execution sequence necessarily in order, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
The units described as separate parts may or may not be physically separate, and parts displayed 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part 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, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.
Those of ordinary skill in the art will appreciate that some or all of the steps in the various methods of the embodiments described herein may be implemented by programming and instructing associated hardware, the program may be stored in a computer-readable storage medium including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable rewritable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or any other medium capable of being used to carry or store data.
The motor fault diagnosis method, the electronic device and the medium based on the bilinear LBP disclosed by the embodiment of the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as limiting the present invention.

Claims (10)

1. A motor fault diagnosis method based on bilinear LBP is characterized by comprising the following steps:
receiving single-channel original data of the motor, which are acquired by a sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data which is called as preprocessing data;
processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data;
constructing three-channel characteristic data by the pre-processing data, the first LBP data and the second LBP data;
and constructing a three-channel characteristic image by the three-channel characteristic data, inputting the three-channel characteristic image into a pre-trained network model, and outputting a diagnosis result.
2. The bilinear LBP-based motor fault diagnosis method of claim 1, wherein the sensor is any one of a vibration sensor, a voltage transformer, a current transformer, and an acceleration sensor.
3. The method for diagnosing motor faults based on bilinear LBP of claim 1, wherein the step of processing the pre-processing data by using a bilinear LBP algorithm to obtain a first LBP data and a second LBP data comprises the steps of:
selecting continuous 9 pieces of pre-processing data, and comparing the size of the intermediate data with the size of the adjacent front and back four data to form first LBP data and second LBP data:
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4}
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4}
wherein S isiAnd QiI-th first LBP data and second LBP data, respectively, if Mi≥MjThen XjIf M is equal to 1i<MjThen Xj0; if M isi<MjThen Y isjIf M is equal to 1i≥MjThen Y isj＝0；j＝{i-4,i-3,i-2,i-1,i+1,i+2,i+3,i+4}；MiAnd MjRespectively the ith and the j pre-processing data, wherein i is more than or equal to 0 and less than or equal to L, and L is the length of single-channel original data;
when i is less than 4, obtaining M by using a linear difference modek，i-4≤k≤-1；
When i is greater than L-4, M is obtained by using a linear difference modec，L+1≤c≤i+4；
Si＝{Xi-4,Xi-3,Xi-2,Xi-1,Xi+1,Xi+2,Xi+3,Xi+4Denotes combining X withi-4、Xi-3、Xi-2、Xi-1、Xi+1、Xi+2、Xi+3And Xi+48-bit binary numbers formed by sequential connection;
Qi＝{Yi-4,Yi-3,Yi-2,Yi-1,Yi+1,Yi+2,Yi+3,Yi+4represents a general formulai-4、Yi-3、Yi-2、Yi-1、Yi+1、Yi+2、Yi+3And Yi+4The 8-bit binary numbers are connected in sequence.
4. The bilinear LBP-based motor fault diagnosis method of claim 1, wherein three-channel feature data is constructed from the pre-processing data, the first LBP data and the second LBP data; the method comprises the following steps:
respectively converting the first LBP data and the second LBP data into decimal numbers, wherein the decimal numbers corresponding to the first LBP data and the second LBP data are in the range of [0, 255 ];
and respectively taking the pre-processing data, the first LBP data converted into decimal numbers and the second LBP data as the characteristic data of one channel to form three-channel characteristic data.
5. The bilinear LBP-based motor fault diagnosis method of claim 1, wherein the three-channel feature data is constructed into a three-channel feature image, and the method comprises the following steps:
and respectively corresponding the three-channel characteristic data to R, G, B three-channel pixel point values to form a three-channel characteristic image.
6. A bilinear LBP-based motor fault diagnosis method according to any one of claims 1 to 5, wherein the pre-trained network model comprises:
acquiring multiple 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 the sample data of each motor in the sample set to obtain the trained network model.
7. A bilinear LBP-based motor fault diagnosis method according to any one of claims 1 to 5, wherein a length L of said single-channel raw data satisfies:
Figure FDA0002888322600000031
wherein, beta is the sampling frequency of the sensor, and n is the rotating speed of the motor.
8. A motor fault diagnosis device based on bilinear LBP is characterized by comprising the following components:
the receiving unit is used for receiving single-channel original data of the motor, which are acquired by the sensor; normalizing the single-channel original data to 0-255 to obtain normalized single-channel original data which is called as pre-processing data;
the processing unit is used for processing the pre-processing data by using a bilinear LBP algorithm to obtain first LBP data and second LBP data;
the construction unit is used for constructing three-channel characteristic data from the pre-processing data, the first LBP data and the second LBP data;
and the diagnosis unit is used for constructing a three-channel characteristic image from the three-channel characteristic data, inputting the three-channel characteristic image into a pre-trained network model and outputting a diagnosis result.
9. An electronic device, comprising: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory for executing a bilinear LBP-based motor fault diagnosis method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a bilinear LBP-based motor fault diagnosis method of any one of claims 1 to 7.
CN202110020414.0A 2021-01-07 2021-01-07 Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium Active CN112733706B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110020414.0A CN112733706B (en) 2021-01-07 2021-01-07 Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110020414.0A CN112733706B (en) 2021-01-07 2021-01-07 Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium

Publications (2)

Publication Number Publication Date
CN112733706A true CN112733706A (en) 2021-04-30
CN112733706B CN112733706B (en) 2022-09-16

Family

ID=75589659

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110020414.0A Active CN112733706B (en) 2021-01-07 2021-01-07 Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium

Country Status (1)

Country Link
CN (1) CN112733706B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113835029A (en) * 2021-09-22 2021-12-24 西安工业大学 Motor fault diagnosis evaluation standard construction method and system and computer storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020186039A1 (en) * 2001-05-01 2002-12-12 Devaney Michael J. Motor bearing damage detection via wavelet analysis of the starting current transient
CN108960320A (en) * 2018-06-26 2018-12-07 湖北工业大学 Train coupling cock fault picture real-time detection method
CN110617960A (en) * 2019-10-12 2019-12-27 华北电力大学 Wind turbine generator gearbox fault diagnosis method and system
WO2020244134A1 (en) * 2019-06-05 2020-12-10 华南理工大学 Multi-task feature sharing neural network-based intelligent fault diagnosis method
US20200387785A1 (en) * 2019-06-05 2020-12-10 Wuhan University Power equipment fault detecting and positioning method of artificial intelligence inference fusion

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020186039A1 (en) * 2001-05-01 2002-12-12 Devaney Michael J. Motor bearing damage detection via wavelet analysis of the starting current transient
CN108960320A (en) * 2018-06-26 2018-12-07 湖北工业大学 Train coupling cock fault picture real-time detection method
WO2020244134A1 (en) * 2019-06-05 2020-12-10 华南理工大学 Multi-task feature sharing neural network-based intelligent fault diagnosis method
US20200387785A1 (en) * 2019-06-05 2020-12-10 Wuhan University Power equipment fault detecting and positioning method of artificial intelligence inference fusion
CN110617960A (en) * 2019-10-12 2019-12-27 华北电力大学 Wind turbine generator gearbox fault diagnosis method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YANPING CAI ET AL: "A Novel Improved Local Binary Pattern and Its Application to the Fault Diagnosis of Diesel Engine", 《SHOCK AND VIBRATION》 *
张静: "基于压力及浓度分布信号的气固两相流流型辨识方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)基础科学辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113835029A (en) * 2021-09-22 2021-12-24 西安工业大学 Motor fault diagnosis evaluation standard construction method and system and computer storage medium
CN113835029B (en) * 2021-09-22 2024-05-24 西安工业大学 Motor fault diagnosis evaluation standard construction method, system and computer storage medium

Also Published As

Publication number Publication date
CN112733706B (en) 2022-09-16

Similar Documents

Publication Publication Date Title
Guo et al. Intelligent fault diagnosis method based on full 1-D convolutional generative adversarial network
CN111721535B (en) Bearing fault detection method based on convolution multi-head self-attention mechanism
Surendran et al. Deep learning based intelligent industrial fault diagnosis model.
CN110598037B (en) Image searching method, device and storage medium
Gao et al. ASM1D-GAN: An intelligent fault diagnosis method based on assembled 1D convolutional neural network and generative adversarial networks
CN112417954A (en) Bearing fault mode diagnosis method and system for small sample data set
CN112836346B (en) Motor fault diagnosis method based on CN and PCA, electronic equipment and medium
CN111652225B (en) Non-invasive camera shooting and reading method and system based on deep learning
CN114548190B (en) Wind turbine fault diagnosis method and device based on self-adaptive residual error neural network
CN116593157A (en) Complex working condition gear fault diagnosis method based on matching element learning under small sample
CN112733706B (en) Motor fault diagnosis method based on bilinear LBP, electronic equipment and medium
Xue et al. Rolling bearing fault diagnosis method based on self-calibrated coordinate attention mechanism and multi-scale convolutional neural network under small samples
CN117033657A (en) Information retrieval method and device
CN116152611A (en) Multistage multi-scale point cloud completion method, system, equipment and storage medium
Tan et al. Attention augmented convolutional neural network for acoustics based machine state estimation
CN117149996A (en) Man-machine interface digital conversation mining method and AI system for artificial intelligence application
KR102005952B1 (en) Apparatus and Method for refining data of removing noise data in Machine learning modeling
CN115358473A (en) Power load prediction method and prediction system based on deep learning
CN117784710B (en) Remote state monitoring system and method for numerical control machine tool
Azad et al. An efficient way to convert 1D signal to 2D digital image using energy values
CN117798654B (en) Intelligent adjusting system for center of steam turbine shafting
CN116071825B (en) Action behavior recognition method, system, electronic equipment and storage medium
CN117576279B (en) Digital person driving method and system based on multi-mode data
CN117760731A (en) Unbalanced sample rolling bearing fault diagnosis method and system based on Soft-Intro VAE and 1D-2DA-FCNN
Evangeline et al. A deep residual neural network model for synchronous motor fault diagnostics

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