CN117054095A - Engine vibration sensing and fault diagnosis method, system, equipment and medium - Google Patents
Engine vibration sensing and fault diagnosis method, system, equipment and medium Download PDFInfo
- Publication number
- CN117054095A CN117054095A CN202310932765.8A CN202310932765A CN117054095A CN 117054095 A CN117054095 A CN 117054095A CN 202310932765 A CN202310932765 A CN 202310932765A CN 117054095 A CN117054095 A CN 117054095A
- Authority
- CN
- China
- Prior art keywords
- engine
- vibration
- engine vibration
- module
- fault diagnosis
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003745 diagnosis Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 8
- 238000000926 separation method Methods 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 230000001131 transforming effect Effects 0.000 claims description 5
- 239000007788 liquid Substances 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 2
- 230000003321 amplification Effects 0.000 description 5
- 238000003199 nucleic acid amplification method Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011065 in-situ storage Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application provides a method, a system, equipment and a medium for engine vibration sensing and fault diagnosis, which relate to the technical field of vibration sensing and comprise the following steps: step S1: acquiring a video when the engine runs, and processing the acquired video to obtain a processing result; step S2: according to the processing result, the vibration amplitude is amplified on the premise of not changing the vibration frequency, and then the engine vibration information is extracted; step S3: and diagnosing whether faults occur according to the extracted engine vibration information. The application can avoid the problems that the deviation exists in the vibration information obtained when the traditional sensor measures the vibration of the engine, and the normal operation of equipment is affected.
Description
Technical Field
The application relates to the technical field of vibration sensing, in particular to a method, a system, equipment and a medium for engine vibration sensing and fault diagnosis.
Background
The service state of the engine can be known by analyzing the vibration information of the engine, and the engine with abnormal running state can be intervened in time. Because the engine vibration is weak, accurate and quick, the engine vibration information is sensed, and whether the vibration information corresponds to a fault state or not is difficult to identify, a proper detection principle needs to be selected, a corresponding feasible detection scheme is designed, and the on-line monitoring of the running state of the engine is realized.
Currently, a laser displacement sensor, an acceleration sensor and other sensors are generally used for measuring vibration information, the laser displacement sensor uses a triangulation principle, visible red laser is shot to the surface of an object through a lens, laser scattered by the surface is received by an internal CCD linear camera, and the distance between the sensor and the object is calculated according to the angle and known distance information; the acceleration sensor first measures vibration acceleration, and then obtains vibration displacement through secondary integration. The traditional measuring method has better measuring precision, however, because the sensor needs to be deployed on or near the surface of the tested equipment, the measured vibration information has deviation due to the introduction of additional mass, and the deployment of the sensor affects the normal operation of the equipment.
And detecting abrasive particles in the oil liquid by using a ferrograph, positioning a fault part by analyzing abrasive particle elements, and establishing the correlation between the vibration signal form and the fault type on the basis.
Disclosure of Invention
Aiming at the defects in the prior art, the application provides an engine vibration sensing and fault diagnosis method, system, equipment and medium.
According to the method, the system, the equipment and the medium for engine vibration sensing and fault diagnosis provided by the application, the scheme is as follows:
in a first aspect, there is provided a method of engine vibration sensing and fault diagnosis, the method comprising:
step S1: acquiring a video when the engine runs, and processing the acquired video to obtain a processing result;
step S2: according to the processing result, the vibration amplitude is amplified on the premise of not changing the vibration frequency, and then the engine vibration information is extracted;
step S3: and diagnosing whether faults occur according to the extracted engine vibration information.
Preferably, the step S1 includes:
step S1.1: calibrating a camera, and acquiring an engine area operation time video to be analyzed by using the calibrated camera;
step S1.2: and decomposing the acquired video into time sequence single-frame images according to the frame rate, and separating the foreground and the background of the single-frame images by using a spatial decomposition filter to obtain the foreground characteristics and the background characteristics.
Preferably, the step S2 includes:
step S2.1: after the foreground features and the background features obtained by processing the video, amplifying the foreground features obtained by separation by adopting a linear amplifying method;
step S2.2: fusing the amplified foreground features with the background features, and outputting a reconstructed image;
step S2.3: extracting an interested region from each reconstructed image to obtain a banded data characteristic, wherein the interested region needs to select a region with obvious color difference and edge characteristics according to actual conditions, so that calculation errors are eliminated conveniently;
step S2.4: combining the acquired band-shaped data of the region of interest according to a time sequence to form a new data synthesis picture; performing binarization processing on the reconstructed image by using threshold segmentation to obtain a binarized image, and setting a dynamic threshold to avoid accidental factor interference, enhance boundary properties and facilitate feature identification;
step S2.5: extracting boundary features based on the binarized image, and determining upper and lower boundary positions in pixels by combining the reconstructed image when the color value is changed;
step S2.6: and (3) deriving the extracted upper and lower boundary pixel position information, transforming to a real distance under a world coordinate system based on camera calibration parameters, and calculating the time interval between two adjacent frames of images based on the video frame rate.
Preferably, the step S3 includes: recording real position coordinates of a world coordinate system corresponding to upper and lower boundary pixels in each reconstructed image, sorting the real position coordinates into engine vibration signals according to time sequence, calculating characteristic parameters of vibration frequency, amplitude, skewness and kurtosis based on the obtained engine vibration signals, and performing engine fault diagnosis;
the vibration frequency is the reciprocal of the time interval between two adjacent maximum values or minimum values of the signal, the amplitude is half of the difference between the maximum value and the minimum value of the adjacent position of the signal, the deflection degree measures the deflection direction and degree of data distribution, reflects the asymmetry degree of the data distribution, and has a calculation formula of;
wherein E represents solving mathematical expectations; x represents an engine vibration signal; μ represents an engine vibration signal mean; sigma represents the standard deviation of the engine vibration signal;
the kurtosis measures the statistical characteristics of the sharpness of data distribution, reflects the sharpness of the data distribution form, and has a calculation formula of:
the skewness and kurtosis of the vibration signal in the normal running state are close to 0, the increase of the skewness indicates that friction or collision exists on the engine, and the kurtosis deviation indicates that impact vibration exists on the engine; and detecting abrasive particles in the oil liquid by using a ferrograph, positioning a fault part by analyzing abrasive particle elements, and establishing the association between the vibration signal form and the fault type.
In a second aspect, an engine vibration sensing and fault diagnosis system is provided, the system comprising:
module M1: acquiring a video when the engine runs, and processing the acquired video to obtain a processing result;
module M2: according to the processing result, the vibration amplitude is amplified on the premise of not changing the vibration frequency, and then the engine vibration information is extracted;
module M3: and diagnosing whether faults occur according to the extracted engine vibration information.
Preferably, the module M1 comprises:
module M1.1: calibrating a camera, and acquiring an engine area operation time video to be analyzed by using the calibrated camera;
module M1.2: and decomposing the acquired video into time sequence single-frame images according to the frame rate, and separating the foreground and the background of the single-frame images by using a spatial decomposition filter to obtain the foreground characteristics and the background characteristics.
Preferably, the module M2 comprises:
module M2.1: after the foreground features and the background features obtained by processing the video, amplifying the foreground features obtained by separation by adopting a linear amplifying method;
module M2.2: fusing the amplified foreground features with the background features, and outputting a reconstructed image;
module M2.3: extracting an interested region from each reconstructed image to obtain a banded data characteristic, wherein the interested region needs to select a region with obvious color difference and edge characteristics according to actual conditions, so that calculation errors are eliminated conveniently;
module M2.4: combining the acquired band-shaped data of the region of interest according to a time sequence to form a new data synthesis picture; performing binarization processing on the reconstructed image by using threshold segmentation to obtain a binarized image, and setting a dynamic threshold to avoid accidental factor interference, enhance boundary properties and facilitate feature identification;
module M2.5: extracting boundary features based on the binarized image, and determining upper and lower boundary positions in pixels by combining the reconstructed image when the color value is changed;
module M2.6: and (3) deriving the extracted upper and lower boundary pixel position information, transforming to a real distance under a world coordinate system based on camera calibration parameters, and calculating the time interval between two adjacent frames of images based on the video frame rate.
Preferably, the module M3 comprises: recording real position coordinates of a world coordinate system corresponding to upper and lower boundary pixels in each reconstructed image, sorting the real position coordinates into engine vibration signals according to time sequence, calculating characteristic parameters of vibration frequency, amplitude, skewness and kurtosis based on the obtained engine vibration signals, and performing engine fault diagnosis;
the vibration frequency is the reciprocal of the time interval between two adjacent maximum values or minimum values of the signal, the amplitude is half of the difference between the maximum value and the minimum value of the adjacent position of the signal, the deflection degree measures the deflection direction and degree of data distribution, reflects the asymmetry degree of the data distribution, and has a calculation formula of;
wherein E represents solving mathematical expectations; x represents an engine vibration signal; μ represents an engine vibration signal mean; sigma represents the standard deviation of the engine vibration signal;
the kurtosis measures the statistical characteristics of the sharpness of data distribution, reflects the sharpness of the data distribution form, and has a calculation formula of:
the skewness and kurtosis of the vibration signal under normal running state should be close to 0, the increase of the skewness indicates that friction or collision exists on the engine, and the kurtosis deviation indicates that impact vibration exists on the engine.
In a third aspect, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the engine vibration sensing and fault diagnosis method.
In a fourth aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the engine vibration sensing and fault diagnosis method.
Compared with the prior art, the application has the following beneficial effects:
1. according to the application, only the engine operation video is required to be acquired, and complex sensor installation and deployment are not required;
2. the application accurately and rapidly acquires the vibration information of the engine in an in-situ non-contact measurement mode;
3. the application can be suitable for different engine models, and realizes quick deployment application.
Other advantages of the present application will be set forth in the description of specific technical features and solutions, by which those skilled in the art should understand the advantages that the technical features and solutions bring.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a flow of an engine weak vibration information amplification algorithm;
fig. 2 is a diagram of a motion amplification algorithm using a neural network.
Detailed Description
The present application will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present application, but are not intended to limit the application in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present application.
The embodiment of the application provides an engine vibration sensing and fault diagnosis method which is mainly used for acquiring engine vibration information and monitoring the service state of an engine. The application aims to realize non-contact vibration sensing and fault diagnosis in place and avoid the problem that the deviation exists in the vibration information obtained when the traditional sensor measures the vibration of the engine, and the normal operation of equipment is affected.
Referring to fig. 1 and 2, the method of the present application comprises: the method comprises the steps of integrating image processing, a neural network and the like, acquiring videos when an engine runs, processing the acquired videos, amplifying vibration amplitude on the premise of not changing vibration frequency, further extracting engine vibration information, and diagnosing whether faults occur.
Specifically, the steps are as follows:
s1, calibrating a camera, and acquiring an engine area operation time video to be analyzed by using the calibrated camera;
s2, decomposing the acquired video according to the frame rate, namely acquiring video screenshots with the number of frame rates at equal time intervals of every second, including but not limited to using ffmpeg command lines, openCV video frame reading and Adobe premier. For a time sequence single frame image, performing image foreground and background separation by using a spatial decomposition filter, wherein the spatial decomposition filter comprises a convolution module and a residual error module, and the shape characteristics and the texture characteristics of the images are obtained after the two adjacent frames of images are input and processed by the convolution module and the residual error module, wherein the shape characteristics are the required foreground characteristics, and the texture characteristics are background characteristics;
s3, obtaining a differential image of two adjacent frames of images by adopting a linear amplification method, and adding the differential image with the original image after directly multiplying the differential image by an amplification factor. Amplifying the foreground motion characteristic obtained by separation;
s4, fusing the amplified foreground features with the background features, and outputting a reconstructed image, wherein the reconstruction module comprises an up-sampling module, a merging module, a residual error module and a convolution module, the up-sampling module is used for reducing memory occupation and receptive field size, the merging module combines the foreground features with the background features, the residual error module is used for improving output quality, and the convolution module enables the method to operate under any resolution.
S5, extracting an interested region (Region of Interest, ROI) from each reconstructed image to obtain the banded data characteristics, wherein the interested region needs to select regions with obvious color difference and edge characteristics according to actual conditions, so that calculation errors are conveniently removed;
and S6, merging the acquired band-shaped data of the region of interest according to a time sequence to form a new data synthesis picture. Performing binarization processing on the reconstructed image by using threshold segmentation, avoiding accidental factor interference by setting a dynamic threshold, setting the threshold to 30% of the overall brightness of the reconstructed image, enhancing boundary properties, and facilitating feature identification;
s7, extracting boundary features based on the binarized image, and determining the upper and lower boundary positions by combining the reconstructed image when the color value is changed, wherein the units are pixels;
and S8, deriving the extracted upper and lower boundary pixel position information, and transforming to the real distance under the world coordinate system based on the camera calibration parameters. Calculating the reciprocal of the video frame rate, wherein the calculation result is the time interval between two adjacent frames of images;
and S9, calculating characteristic parameters such as vibration frequency, amplitude, skewness, kurtosis and the like based on the obtained engine vibration information, and performing engine fault diagnosis.
The vibration frequency is the reciprocal of the time interval between two adjacent maximum values or minimum values of the signal, the amplitude is half of the difference between the maximum value and the minimum value of the adjacent position of the signal, the deflection degree measures the deflection direction and degree of data distribution, reflects the asymmetry degree of the data distribution, and has a calculation formula of;
wherein E represents solving a mathematical expectation; x represents an engine vibration signal; μ represents an engine vibration signal mean; sigma represents the standard deviation of the engine vibration signal;
the kurtosis measures the statistical characteristics of the sharpness of data distribution, reflects the sharpness of the data distribution form, and has a calculation formula of:
the skewness and kurtosis of the vibration signal under normal running state should be close to 0, the increase of the skewness indicates that friction or collision exists on the engine, and the kurtosis deviation indicates that impact vibration exists on the engine. And detecting abrasive particles in the oil liquid by using a ferrograph, positioning a fault part by analyzing abrasive particle elements, and establishing the association between the vibration signal form and the fault type.
The present application also provides an engine vibration sensing and fault diagnosis system, which may be implemented by executing the flow steps of the engine vibration sensing and fault diagnosis method, i.e. those skilled in the art may understand the engine vibration sensing and fault diagnosis method as a preferred embodiment of the engine vibration sensing and fault diagnosis system.
The system is mainly used for acquiring the vibration information of the engine and monitoring the service state of the engine. The application aims to realize non-contact vibration sensing and fault diagnosis in place and avoid the problem that the deviation exists in the vibration information obtained when the traditional sensor measures the vibration of the engine, and the normal operation of equipment is affected. The method comprises the steps of integrating image processing, a neural network and the like, acquiring a video when the engine runs, processing the acquired video, amplifying the vibration amplitude on the premise of not changing the vibration frequency, further extracting the vibration information of the engine, and diagnosing whether the engine has faults or not. The method does not need to carry out complex sensor installation and deployment, does not influence the operation of the engine, and can realize accurate and rapid perception of weak engine vibration information so as to carry out fault diagnosis. The method comprises the following steps:
m1, calibrating a camera, and acquiring an engine area operation time video to be analyzed by using the calibrated camera;
m2, decomposing the acquired video into time sequence single-frame images according to a frame rate, and separating the foreground and the background of the images by using a spatial decomposition filter, wherein the spatial decomposition filter comprises a convolution module and a residual error module;
m3, amplifying the foreground motion features obtained by separation by adopting a linear amplification method;
m4, fusing the amplified foreground features and background features, and outputting a reconstruction image, wherein the reconstruction module comprises an up-sampling module, a merging module, a residual error module and a convolution module;
m5, extracting an interested region (Region of Interest, ROI) from each reconstructed image, and acquiring the banded data characteristics, wherein the interested region needs to select a region with obvious color difference and edge characteristics according to actual conditions, so that calculation errors are conveniently removed;
and M6, merging the acquired band-shaped data of the region of interest according to the time sequence to form a new data synthesis picture. The image is subjected to binarization processing by using threshold segmentation, accidental factor interference is avoided by setting a dynamic threshold, boundary attribute is enhanced, and characteristics are convenient to identify;
m7, extracting boundary features based on the binarized image, and determining upper and lower boundary positions in pixels by combining the image when the color value changes;
m8, deriving the extracted upper and lower boundary pixel position information, converting to a real distance under a world coordinate system based on camera calibration parameters, calculating the reciprocal of the video frame rate, and calculating the result to be the time interval between two adjacent frames of images;
and M9, calculating characteristic parameters such as vibration frequency, amplitude, kurtosis, skewness, kurtosis and the like based on the obtained engine vibration information, and performing engine fault diagnosis.
The embodiment of the application provides a method, a system, equipment and a medium for sensing engine vibration and diagnosing faults, which solve the problems that the measurement results of the traditional sensors such as a laser displacement sensor, an acceleration sensor and the like have deviation and influence on the operation of tested equipment when sensing engine vibration information and diagnosing faults. The application integrates methods such as image processing, neural network and the like, and can acquire the vibration information of the engine and diagnose faults in time by shooting the video when the engine runs, thereby realizing in-situ non-contact measurement.
Those skilled in the art will appreciate that the application provides a system and its individual devices, modules, units, etc. that can be implemented entirely by logic programming of method steps, in addition to being implemented as pure computer readable program code, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, the system and various devices, modules and units thereof provided by the application can be regarded as a hardware component, and the devices, modules and units for realizing various functions included in the system can also be regarded as structures in the hardware component; means, modules, and units for implementing the various functions may also be considered as either software modules for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present application. It is to be understood that the application is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the application. The embodiments of the application and the features of the embodiments may be combined with each other arbitrarily without conflict.
Claims (10)
1. An engine vibration sensing and fault diagnosing method, comprising:
step S1: acquiring a video when the engine runs, and processing the acquired video to obtain a processing result;
step S2: according to the processing result, the vibration amplitude is amplified on the premise of not changing the vibration frequency, and then the engine vibration information is extracted;
step S3: and diagnosing whether faults occur according to the extracted engine vibration information.
2. The engine vibration sensing and fault diagnosis method according to claim 1, wherein the step S1 includes:
step S1.1: calibrating a camera, and acquiring an engine area operation time video to be analyzed by using the calibrated camera;
step S1.2: and decomposing the acquired video into time sequence single-frame images according to the frame rate, and separating the foreground and the background of the single-frame images by using a spatial decomposition filter to obtain the foreground characteristics and the background characteristics.
3. The engine vibration sensing and fault diagnosis method according to claim 1, wherein the step S2 includes:
step S2.1: after the foreground features and the background features obtained by processing the video, amplifying the foreground features obtained by separation by adopting a linear amplifying method;
step S2.2: fusing the amplified foreground features with the background features, and outputting a reconstructed image;
step S2.3: extracting an interested region from each reconstructed image to obtain a banded data characteristic, wherein the interested region needs to select a region with obvious color difference and edge characteristics according to actual conditions, so that calculation errors are eliminated conveniently;
step S2.4: combining the acquired band-shaped data of the region of interest according to a time sequence to form a new data synthesis picture; performing binarization processing on the reconstructed image by using threshold segmentation to obtain a binarized image, and setting a dynamic threshold to avoid accidental factor interference, enhance boundary properties and facilitate feature identification;
step S2.5: extracting boundary features based on the binarized image, and determining upper and lower boundary positions in pixels by combining the reconstructed image when the color value is changed;
step S2.6: and (3) deriving the extracted upper and lower boundary pixel position information, transforming to a real distance under a world coordinate system based on camera calibration parameters, and calculating the time interval between two adjacent frames of images based on the video frame rate.
4. The engine vibration sensing and fault diagnosis method according to claim 2, wherein the step S3 includes: recording real position coordinates of a world coordinate system corresponding to upper and lower boundary pixels in each reconstructed image, sorting the real position coordinates into engine vibration signals according to time sequence, calculating characteristic parameters of vibration frequency, amplitude, skewness and kurtosis based on the obtained engine vibration signals, and performing engine fault diagnosis;
the vibration frequency is the reciprocal of the time interval between two adjacent maximum values or minimum values of the signal, the amplitude is half of the difference between the maximum value and the minimum value of the adjacent position of the signal, the deflection degree measures the deflection direction and degree of data distribution, reflects the asymmetry degree of the data distribution, and has a calculation formula of;
wherein E represents solving mathematical expectations; x represents an engine vibration signal; μ represents an engine vibration signal mean; sigma represents the standard deviation of the engine vibration signal;
the kurtosis measures the statistical characteristics of the sharpness of data distribution, reflects the sharpness of the data distribution form, and has a calculation formula of:
the skewness and kurtosis of the vibration signal under normal running state should be close to 0, the increase of the skewness indicates that friction or collision exists on the engine, and the kurtosis deviation indicates that impact vibration exists on the engine.
5. An engine vibration sensing and fault diagnosis system, comprising:
module M1: acquiring a video when the engine runs, and processing the acquired video to obtain a processing result;
module M2: according to the processing result, the vibration amplitude is amplified on the premise of not changing the vibration frequency, and then the engine vibration information is extracted;
module M3: and diagnosing whether faults occur according to the extracted engine vibration information.
6. The engine vibration sensing and fault diagnosis system according to claim 5, wherein the module M1 includes:
module M1.1: calibrating a camera, and acquiring an engine area operation time video to be analyzed by using the calibrated camera;
module M1.2: and decomposing the acquired video into time sequence single-frame images according to the frame rate, and separating the foreground and the background of the single-frame images by using a spatial decomposition filter to obtain the foreground characteristics and the background characteristics.
7. The engine vibration sensing and fault diagnosis system according to claim 5, wherein the module M2 includes:
module M2.1: after the foreground features and the background features obtained by processing the video, amplifying the foreground features obtained by separation by adopting a linear amplifying method;
module M2.2: fusing the amplified foreground features with the background features, and outputting a reconstructed image;
module M2.3: extracting an interested region from each reconstructed image to obtain a banded data characteristic, wherein the interested region needs to select a region with obvious color difference and edge characteristics according to actual conditions, so that calculation errors are eliminated conveniently;
module M2.4: combining the acquired band-shaped data of the region of interest according to a time sequence to form a new data synthesis picture; performing binarization processing on the reconstructed image by using threshold segmentation to obtain a binarized image, and setting a dynamic threshold to avoid accidental factor interference, enhance boundary properties and facilitate feature identification;
module M2.5: extracting boundary features based on the binarized image, and determining upper and lower boundary positions in pixels by combining the reconstructed image when the color value is changed;
module M2.6: and (3) deriving the extracted upper and lower boundary pixel position information, transforming to a real distance under a world coordinate system based on camera calibration parameters, and calculating the time interval between two adjacent frames of images based on the video frame rate.
8. The engine vibration sensing and fault diagnosis system according to claim 5, wherein the module M3 includes: recording real position coordinates of a world coordinate system corresponding to upper and lower boundary pixels in each reconstructed image, sorting the real position coordinates into engine vibration signals according to time sequence, calculating characteristic parameters of vibration frequency, amplitude, skewness and kurtosis based on the obtained engine vibration signals, and performing engine fault diagnosis;
the vibration frequency is the reciprocal of the time interval between two adjacent maximum values or minimum values of the signal, the amplitude is half of the difference between the maximum value and the minimum value of the adjacent position of the signal, the deflection degree measures the deflection direction and degree of data distribution, reflects the asymmetry degree of the data distribution, and has a calculation formula of;
wherein E represents solving mathematical expectations; x represents an engine vibration signal; μ represents an engine vibration signal mean; sigma represents the standard deviation of the engine vibration signal;
the kurtosis measures the statistical characteristics of the sharpness of data distribution, reflects the sharpness of the data distribution form, and has a calculation formula of:
the skewness and kurtosis of the vibration signal in the normal running state are close to 0, the increase of the skewness indicates that friction or collision exists on the engine, and the kurtosis deviation indicates that impact vibration exists on the engine; and detecting abrasive particles in the oil liquid by using a ferrograph, positioning a fault part by analyzing abrasive particle elements, and establishing the association between the vibration signal form and the fault type.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the engine vibration sensing and fault diagnosis method of any one of claims 1 to 4.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the engine vibration sensing and fault diagnosis method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310932765.8A CN117054095A (en) | 2023-07-26 | 2023-07-26 | Engine vibration sensing and fault diagnosis method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310932765.8A CN117054095A (en) | 2023-07-26 | 2023-07-26 | Engine vibration sensing and fault diagnosis method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117054095A true CN117054095A (en) | 2023-11-14 |
Family
ID=88663649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310932765.8A Pending CN117054095A (en) | 2023-07-26 | 2023-07-26 | Engine vibration sensing and fault diagnosis method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117054095A (en) |
-
2023
- 2023-07-26 CN CN202310932765.8A patent/CN117054095A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chierchia et al. | PRNU-based detection of small-size image forgeries | |
| KR102256583B1 (en) | System for Measuring Position of Subject | |
| US11928805B2 (en) | Information processing apparatus, information processing method, and storage medium for defect inspection and detection | |
| CN110598613B (en) | Expressway agglomerate fog monitoring method | |
| JP2015041164A (en) | Image processor, image processing method and program | |
| CN111652098A (en) | Product surface defect detection method and device | |
| CN116228780B (en) | Silicon wafer defect detection method and system based on computer vision | |
| US20150055754A1 (en) | X-ray inspection method and x-ray inspection device | |
| EP3480782A1 (en) | Method and device for reducing noise in a depth image | |
| US20220067514A1 (en) | Inference apparatus, method, non-transitory computer readable medium and learning apparatus | |
| CN117274258B (en) | Method, system, equipment and storage medium for detecting defects of main board image | |
| CN104754327A (en) | Method for detecting and eliminating defective pixels of high spectral image | |
| CN112132925A (en) | Method and device for reconstructing underwater image color | |
| CN105787429A (en) | Method and apparatus for inspecting an object employing machine vision | |
| CN118365597A (en) | Image anomaly detection method, device, electronic equipment and storage medium | |
| CN115375608A (en) | Detection method and device, detection equipment and storage medium | |
| CN115947066B (en) | Belt tearing detection method, device and system | |
| US7646892B2 (en) | Image inspecting apparatus, image inspecting method, control program and computer-readable storage medium | |
| CN117054095A (en) | Engine vibration sensing and fault diagnosis method, system, equipment and medium | |
| WO2016092783A1 (en) | Information processing apparatus, method for processing information, discriminator generating apparatus, method for generating discriminator, and program | |
| JP6818263B2 (en) | Fracture surface analysis device and fracture surface analysis method | |
| JP7475901B2 (en) | Method and system for detecting defects on a test piece | |
| CN115249241A (en) | Gluing defect detection method and device | |
| CN112966700A (en) | Millimeter wave image target detection method | |
| Streeter | Towards generalised time-of-flight range imaging at the edge of moving objects |
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 |