CN111275665A - Blade grinding and polishing processing vibration detection system and method based on vision - Google Patents
Blade grinding and polishing processing vibration detection system and method based on vision Download PDFInfo
- Publication number
- CN111275665A CN111275665A CN201911313703.9A CN201911313703A CN111275665A CN 111275665 A CN111275665 A CN 111275665A CN 201911313703 A CN201911313703 A CN 201911313703A CN 111275665 A CN111275665 A CN 111275665A
- Authority
- CN
- China
- Prior art keywords
- image
- blade
- grinding
- polishing
- ccd camera
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
Abstract
The invention discloses a blade grinding and polishing processing vibration detection system based on vision, which comprises an illumination system, a CCD camera, an image acquisition system, an imaging system, a computer system and display equipment. The lighting system is used for providing a light source for the system; the imaging system is used for imaging the spatial structure information of the blade on the CCD camera; the CCD camera and the image acquisition system convert the acquired image optical signals into electric signals; after the CCD camera converts the analog image signal into a digital image signal, the digital image signal is transmitted to a computer system; the computer system receives the digital image signal, processes the image through an image processing algorithm to obtain blade characteristic parameters, and obtains blade vibration information according to the blade characteristic parameters; the display device displays blade vibration information. The invention also discloses a corresponding detection method. Through the scheme, the vibration of blade grinding and polishing processing can be effectively detected, and the blade grinding and polishing device has the advantages of convenience in measurement, wide measurement range, high precision and the like.
Description
Technical Field
The invention belongs to the technical field of robot machining detection, and particularly relates to a blade grinding and polishing machining vibration detection system and method based on vision.
Background
In the industrial field, blades play an important role in occasions such as aeroengines, steam turbines and gas turbines, and the blades are used as the most core parts of the blades and directly determine the overall working performance and the service life of the blades. The surface quality and the processing precision of the blade after grinding and polishing directly determine the use performance of the blade, and the improvement of the surface processing precision of the blade is an important problem to be solved urgently in the grinding and polishing of the blade. The curved surface of the blade belongs to a complex curved surface, the blade distortion degree is large, the processing precision is difficult to ensure, the traditional manual grinding and polishing processing quality difference is large, the consistency is poor, and the working environment is severe; the grinding and polishing of the numerical control machine tool has the advantages of high rigidity, high movement precision and the like, but the process programming difficulty is higher, and the processing requirements of small-batch and multi-specification blades are difficult to meet. With the improvement of the industrial robot technology, the grinding and polishing processing of the robot is more and more widely applied. The industrial robot has the advantages of large motion range, universality, flexibility, simple programming, low cost and the like, is convenient to realize flexible and high-bandwidth processing, and can meet the processing requirements of the blade by combining with related processing technologies.
However, in the actual grinding and polishing process, because the motion precision of the industrial robot is limited and the blade has a force impact phenomenon in the process of contacting with the grinding and polishing device, the robot has a vibration problem in the grinding and polishing process. The existence of the vibration problem makes the contact force during the blade processing difficult to realize accurate tracking, and influences the surface quality, the surface precision and the geometric outline shape of the blade after grinding and polishing processing. For precision workpieces such as blades with extremely strict requirements on machining precision, strict and standard detection on surface quality needs to be carried out during grinding and polishing, and the influence of vibration on grinding and polishing is restrained or eliminated. Therefore, the vibration detection of the blade grinding and polishing processing as a key link of the grinding and polishing processing has the effect of lifting the weight.
The vibration detection is mainly divided into two methods, namely contact detection and non-contact detection, the contact vibration detection mainly comprises piezoelectric acceleration sensors, piezoelectric ceramics, gyroscope sensors and the like, and the non-contact vibration detection mainly comprises laser detection, optical measurement, machine vision and the like. A great deal of research is carried out at home and abroad aiming at the vibration problem, and the invention patent with the application number of 201780035743.4 discloses a method and a system for detecting vibration by industrial vision, which comprises the steps of shooting and collecting Moire patterns generated on an image by a high-frequency distribution strip in an industrial vision detection area through a shooting device, analyzing whether the Moire patterns are changed, and further determining whether the industrial vision detection area is vibrated. The invention patent with application number 201810366707.2 discloses an optical fiber vibration sensing detection method and device, which comprises inputting optical pulse signals into a sensing optical path, returning optical signals with vibration information, analyzing the optical signals with periodically changed pulse widths to determine vibration positions, analyzing the vibration information from the optical signals according to the pulse widths, and calculating the vibration positions. In the research situation of the related field, relevant patent content about the vibration detection of the blade grinding and polishing processing process is not searched.
Disclosure of Invention
In response to the above-identified deficiencies in the art or needs for improvement, the present invention provides a vision-based blade burnishing and polishing vibration detection system. The robot grinding and polishing system mainly comprises an industrial robot and a grinding and polishing device, the industrial robot mainly comprises an industrial robot mechanical arm and a robot control cabinet, a grinding and polishing tool for grinding and polishing is installed and fixed on a flange at the tail end of the industrial robot mechanical arm, and the robot control cabinet is mainly used for motion control and application planning of the robot mechanical arm. And the blade to be ground and polished is fixed on a special blade clamp, and the mechanical arm of the industrial robot drives the grinding and polishing device arranged at the tail end to move relative to the blade so as to finish the grinding and polishing operation. The visual vibration detection device is arranged on one side of a blade to be processed, real-time image acquisition is carried out through a camera, blade information is mapped to an imaging plane from a three-dimensional space, and vibration measurement information is obtained from an image by using methods such as an optical imaging technology, image processing and the like, so that the visual vibration measurement of the blade is realized;
the industrial robot is used for driving a grinding and polishing device mounted on a flange at the tail end of a mechanical arm to move in three dimensions in space, the robot control cabinet is used for planning a motion path of the industrial robot and controlling the motion of the industrial robot, and the robot control cabinet and the industrial robot are matched with each other to finish grinding and polishing processing on the blade;
the blade to be ground and polished is arranged on a special clamp, plays a role in fixing during the grinding and polishing process of the blade, different blade clamps are used by different blades, and the blade to be ground and polished is clamped on the blade clamp and moves relative to a grinding and polishing device arranged on a flange at the tail end of an industrial robot mechanical arm to finish the grinding and polishing operation;
under the action of an illumination system, the visual vibration detection device acquires information such as the size, the motion position and the coordinates of a coordinate system where the grinding and polishing blade is located through image acquisition and image analysis processing technologies of a camera, realizes visual measurement through the mapping relation of information such as space geometric information and image gray scale, and completes vibration analysis in the grinding and polishing process;
according to one aspect of the invention, a visual sense-based blade grinding and polishing processing vibration detection system is provided, which is applied to a blade to be detected and polished, and comprises: an illumination system, a CCD camera, an image acquisition system, an imaging system, a computer system and a display device, wherein,
the lighting system is used for providing a light source for the system so that the obtained image has discrimination;
the imaging system is used for imaging the spatial structure information of the blade on the CCD camera;
the CCD camera and the image acquisition system convert the acquired image optical signals into electric signals, and after the CCD camera converts the analog image signals into digital image signals, the digital image signals are transmitted to a computer system;
the computer system receives the digital image signal, processes the image through an image processing algorithm to obtain the blade characteristic parameters, and obtains blade vibration information according to the blade characteristic parameters;
the display device displays the blade vibration information.
Further, the lighting system provides a light source with uniform luminosity, the characteristic quantity of the blade is highlighted by the illumination of the light source, and the detected part is obviously distinguished from the non-detected part.
Further, the imaging system for imaging the spatial structure information of the blade on the CCD camera comprises:
the imaging system maps the information of the blade on the optical sensitive element of the CCD camera to obtain the optical signal of the image.
Further, the parameter calibration operation of the CCD camera before the vibration detection includes:
the parameter calibration is a process of establishing a relation between the spatial position information and the image coordinates;
the method specifically comprises the following steps: coordinate transformation from base coordinate system to camera coordinate system:
rotating the matrix R ═ R according to the overall coordinates1R2R3Obtaining:
wherein R is1For an inter-coordinate rotation transformation matrix, R2Is a rotation matrix around the x-axis, R3Is a rotation matrix around the y-axis, where T is a translation transformation matrix between coordinate systems, Xo、Yo、ZoRespectively representing coordinate values, X, in a base coordinate systemw、Yw、ZwRespectively, coordinate values in the camera coordinate system.
Further, the transformation formula for converting the camera coordinate system to the image coordinate system is:
accordingly, the coordinate transformation formula for converting from the base coordinate system to the image coordinate system is:
wherein x and y respectively represent coordinate values of the camera coordinate system, dx and dy respectively represent physical dimensions of each pixel on the x axis and the y axis,determined by the camera itself, f denotes the focal length value, u, v denote the coordinate values of the image coordinate system, u, respectively0、v0Respectively, represent the center of the image coordinate system.
Further, the step of converting the image light signal collected by the CCD camera and the image collecting system into an electrical signal, and after converting the analog image signal into a digital image signal by the CCD camera, transmitting the digital image signal to the computer system includes:
the optical sensitive element and the image acquisition system of the CCD camera convert the optical signals of the blade into electric signals, and the built-in image acquisition card of the CCD camera converts analog image signals into digital image signals and then transmits the digital image signals to a computer system.
Further, the processing the image through an image processing algorithm to obtain the blade characteristic parameters includes:
completing image analysis and image preprocessing through an image processing algorithm to obtain the characteristic parameters of the blade;
the blade characteristic parameters mainly comprise measured vibration signal data.
Further, the image pre-processing includes, but is not limited to, image filtering, image enhancement, and image restoration operations; the image analysis includes, but is not limited to, image feature extraction, image segmentation, image representation and description operations.
According to another aspect of the invention, a visual-based blade grinding and polishing machining vibration detection method is provided, which is applied to a blade to be detected and polished, and comprises the following steps:
s1: irradiating the grinding and polishing blade to be detected by using a light source;
s2: imaging the spatial structure information of the grinding and polishing blade to be detected to obtain an image optical signal;
s3: converting the image optical signal into an electric signal, further converting an analog image signal into a digital image signal, and then sending the digital image signal to a computer system;
s4: the computer system receives the digital image signal, processes the image through an image processing algorithm to obtain characteristic parameters of the to-be-detected grinding and polishing blade, and obtains blade vibration information according to the characteristic parameters of the blade;
s5: and displaying the blade vibration information.
Further, the image processing in step S4 includes:
s41: calculating the number of pixels of each gray level of the interested ROI of the blade image;
s42: calculating the proportion of the number of pixels of each blade gray level in the ROI area of interest in S41;
s43: calculating the inter-class variance of each gray level of the leaf image to obtain a corresponding threshold value;
s44: and according to the obtained threshold value, carrying out binarization on the obtained blade image to obtain the characteristic parameter information of the blade image.
Generally, compared with the prior art, the technical solution conceived by the present invention mainly has the following technical effects:
1. the visual vibration detection device belongs to non-contact measurement, can realize remote real-time detection, does not change the original characteristics of the blade, and has no damage to the blade subjected to vibration detection;
2. by adopting a mode of measuring vibration visually, the wide measuring range can be realized, and the invisible vibration can be measured. The method can simultaneously acquire a plurality of information acquisition points on the blade, and realize the measurement operation of the three-dimensional dense space of the blade;
3. the visual vibration measuring device has the advantages of high automation level, good detection efficiency and high measurement precision. The measuring mode is simple, the operator is convenient to operate and use, the labor intensity of the operator is reduced, and the monitoring, measuring and other work can be finished for a long time.
Drawings
FIG. 1 is a schematic diagram of a structural configuration of a visual vibration detection apparatus constructed in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a computer-acquired image processing analysis algorithm in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an industrial robot assembly according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a CCD camera used in the image capturing device according to the embodiment of the present invention;
FIG. 5 is a schematic view of a bracket structure of a CCD camera used in an embodiment of the present invention;
FIG. 6 is a schematic structural view of a blade of one type for grinding and polishing in an embodiment of the present invention;
fig. 7 is a flowchart of a method for detecting blade polishing vibration based on vision in an embodiment of the present invention.
In all the figures, the same reference numerals denote the same features, in particular: 31-a robot control cabinet, 32-a robot arm end flange, 33-an industrial robot arm and 34-an industrial robot.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, the blade grinding and polishing machining vibration detection system based on vision provided by the embodiment of the invention mainly comprises a robot grinding and polishing system and a vision vibration detection device. The robot grinding and polishing system mainly comprises an industrial robot and a grinding and polishing device, the industrial robot mainly comprises an industrial robot mechanical arm and a robot control cabinet, a grinding and polishing tool for grinding and polishing processing is installed and fixed on a flange at the tail end of the industrial robot mechanical arm, and the robot control cabinet is mainly used for motion control and application planning of the robot mechanical arm. And the blade to be ground and polished is fixed on a special blade clamp, and the mechanical arm of the industrial robot drives the grinding and polishing device arranged at the tail end to move relative to the blade so as to finish the grinding and polishing operation.
The industrial robot is used for driving the grinding and polishing device for mounting the flange at the tail end of the mechanical arm to move three-dimensionally in space, the robot control cabinet is used for planning the motion path of the industrial robot and controlling the motion of the industrial robot, and the grinding and polishing of the blade are completed by mutually matching the robot control cabinet and the industrial robot. The blade to be ground and polished is arranged on a special clamp, the blade to be ground and polished plays a role in fixing in the grinding and polishing process of the blade, different blade clamps are used for different blades, the blade to be ground and polished is clamped on the blade clamp and moves relative to a grinding and polishing device arranged on a flange at the tail end of an industrial robot mechanical arm to finish the grinding and polishing operation;
as shown in fig. 1, the visual vibration detection apparatus provided in the embodiment of the present invention mainly includes an illumination system, a blade to be polished and polished, an imaging system, a CCD camera, a computer system, a display device, an analysis feedback system, and the like. The visual vibration detection device is arranged on one side of a blade to be processed, real-time video image acquisition is carried out through a camera, blade information is mapped to an imaging plane from a three-dimensional space, and vibration measurement information is obtained from an image by using methods such as an optical imaging technology, image processing and the like, so that visual vibration measurement of the blade is realized;
under the action of a light source of an illumination system, an optical imaging system is utilized to image spatial structure information of a grinding and polishing blade on a photosensitive element of a CCD camera, the optical sensitive element of the CCD camera can convert optical information of the blade into an electric signal, an image acquisition card is arranged in the CCD camera to complete digital-to-analog signal conversion, an analog image signal is converted into a digital image signal and transmitted to a computer, an image processing technology is utilized to operate an acquired image, corresponding characteristic parameters of the grinding and polishing blade are acquired from an interested part of the image, the acquired characteristic parameters are analyzed, processed and output and stored, and the basic process of visual vibration measurement is completed;
the illumination system mainly refers to an illumination light source which determines the measurement effect of the vision measurement system, and the illumination light source can make the characteristic quantity of the blade prominent, so that the detected part and the non-detected part are obviously distinguished, and the obtained image has distinction degree. The lighting system also has better luminous intensity, the provided light brightness is uniform, the collected image details are clear, and a CCD camera can conveniently obtain images with better quality;
the imaging system maps the information of the blade on a photosensitive imaging plane of the CCD camera, and can control the range of the image acquired by the CCD camera. The most important part of the imaging system is an optical lens, which directly affects the measurement resolution and the overall performance of the measurement system and plays an important role in the visual vibration measurement device. The optical lens provided by the embodiment of the invention is an optical lens of H0514-MP type, and has higher resolution and better performance;
the CCD camera and the image acquisition device convert the acquired optical signals into electric signals, then the signal processing unit and the image acquisition card of the CCD camera realize the image acquisition and digital processing (from the leaves) of the blades, and then the digital images are transmitted to the display device. The CCD camera provided by the embodiment of the invention selects the model TXG06c, and the resolution is 776 multiplied by 582 pixels;
the computer system for visual vibration detection is a core component of the visual vibration detection device, and the computer control system is required to control the movement and trajectory planning of the industrial robot and also control the operation of each part of the detection device. Meanwhile, a computer system receives and stores digital image information acquired from a CCD camera through a corresponding data interface, then the acquired video image is processed and analyzed through an image processing technology of the computer system, the acquired image data is subjected to operations such as preprocessing, blade image feature extraction and the like through a related algorithm in the computer, and measured vibration signal data of the blade is obtained and stored in a file. The data obtained after the processing and analysis by the computer system is displayed on the display equipment through the data interface, so that an operator can conveniently analyze the vibration information of the next step;
as shown in fig. 2, the image processing analysis algorithm of the computer system provided by the embodiment of the present invention mainly includes image acquisition, image analysis processing, and information display. The image acquisition provided by the embodiment of the invention mainly comprises the steps of setting related parameters of a CCD camera, acquiring the video image information of the blade of the image acquisition device and the like;
the CCD camera parameter calibration refers to a process of determining camera related parameters by using a camera imaging model, a relation between space position information and image coordinates is established, internal parameters and external parameters of the CCD camera are mainly determined, and the accuracy of the calibration parameters determines the precision of image analysis and processing;
further, the visual vibration detection is converted from a base coordinate system to an image coordinate system, so there is a translation between the respective coordinate systems. First, the conversion from the base coordinate system to the camera coordinate system where the CCD camera is located is as shown in the following formula:
wherein: r1For the rotation transformation matrix between coordinates, the rotation matrix around the x-axis and the y-axis can be obtained by the same method
From the above analysis, the total coordinate rotation matrix can be obtained as R ═ R1R2R3Obtaining a specific coordinate transformation from the base coordinate system to the camera coordinate system:
wherein: t is a translation transformation matrix between coordinate systems, R1For an inter-coordinate rotation transformation matrix, R2Is a rotation matrix around the x-axis, R3Is a rotation matrix around the y-axis, Xo、Yo、ZoRespectively representing coordinate values, X, in a base coordinate systemw、Yw、ZwRespectively, coordinate values in the camera coordinate system.
Further, the projection transformation process from the camera coordinate system to the image coordinate system is a process of transforming from a three-dimensional space to a two-dimensional space, and the specific transformation process is as follows:
further, in conjunction with the above analysis, the coordinate transformation formula for converting from the base coordinate system to the pixel coordinate system is as follows:
wherein x and y respectively represent coordinate values of a camera coordinate system, dx and dy respectively represent physical dimensions of each pixel on an x axis and a y axis, determined by the camera itself, f represents a focal length value, u and v respectively represent coordinate values of an image coordinate system, and u and v respectively represent coordinate values of an image coordinate system0、v0Respectively, represent the center of the image coordinate system.
The above formula is the calibration process of the CCD camera, and the calibration process comprises the required camera internal parameters and the camera external parameters;
the image analysis preprocessing in the computer system mainly comprises operations of image filtering, image ROI determination, image enhancement and the like. The blade image is easily interfered by noise in the process of acquisition and transmission, the influence of the noise is inevitable, and in order to obtain a better image effect, the image needs to be filtered to eliminate the noise component in the image. In order to obtain a clearer and better-effect image without destroying the original structural information of the blade, the image filtering selection median filtering method provided by the embodiment of the invention can better remove noise in the image, does not lose the original characteristic information of the blade, and retains the original information of the blade to a greater extent;
the blade image information data are more, and a data acquisition mode of an interested area is adopted, so that the method can improve the image information acquisition efficiency and save the time for processing a large amount of data. Image ROI determines the image information of the blade obtained by acquiring the data of the interested image part of the blade and optimizing the corresponding ROI algorithm;
image enhancement is a key step in image pre-processing operations, by which certain features of the detected blade image can be emphasized while other non-critical information of the blade is suppressed in order to obtain a visual effect that facilitates analysis. The image enhancement provided by the embodiment of the invention adopts a direct gray level conversion method, and the method directly processes the gray level value of the leaf image in the leaf image space, so that the processed leaf image is clearer and the image level is clearer.
The image analysis processing in the computer system also comprises the extraction of vibration information, the obtained blade information is firstly segmented, and the image segmentation is the operation of segmenting the blade image into a plurality of specific parts with unique properties according to certain principles according to the characteristics of gray scale, color and the like of the pixels of the blade image. By adopting the image segmentation method, the same regions of the segmented leaves have good similarity, and different regions have larger difference, so that the image information can be conveniently obtained and analyzed. The image segmentation provided by the embodiment of the invention adopts a threshold segmentation method, and the specific image segmentation steps are as follows:
s1, calculating the number of pixels of each gray level of the interested ROI of the blade image;
s2 calculating the proportion of the number of pixels of each blade gray level in the ROI area of interest in S1;
s3, calculating the inter-class variance of each gray level of the blade image to obtain a corresponding threshold value;
and S4, binarizing the obtained blade image according to the obtained threshold value to obtain the characteristic parameter information of the blade image.
After the steps are analyzed, extracting blade vibration information, converting the blade vibration information into actual coordinate data by combining an imaging model analyzed in the front and parameters calibrated by a CCD camera, and obtaining a displacement curve of each characteristic point along with each frame of picture in the grinding and polishing process of the blade.
Through the technical scheme, the following technical effects are achieved:
1. the visual vibration detection device belongs to non-contact measurement, can realize remote real-time detection, does not change the original characteristics of the blade, and has no damage to the blade subjected to vibration detection;
2. by adopting a mode of measuring vibration visually, the wide measuring range can be realized, and the invisible vibration can be measured. The method can simultaneously acquire a plurality of information acquisition points on the blade, and realize the measurement operation of the three-dimensional dense space of the blade;
3. the visual vibration measuring device has the advantages of high automation level, good detection efficiency and high measurement precision. The measuring mode is simple, the operator is convenient to operate and use, the labor intensity of the operator is reduced, and the monitoring, measuring and other work can be finished for a long time.
As shown in fig. 5, the CCD camera stand according to the embodiment of the present invention is used to mount, fix and support a camera, and is mainly used to adjust the position and angle of the space where the CCD camera is located, so that the CCD camera is placed at a better position to acquire image information of a blade;
as shown in fig. 7, a method for detecting blade grinding and polishing machining vibration based on vision is provided for an embodiment of the present invention, and specifically includes:
s710: irradiating the grinding and polishing blade to be detected by using a light source;
s720: imaging the spatial structure information of the grinding and polishing blade to be detected to obtain an image optical signal;
s730: converting the image optical signal into an electric signal, further converting an analog image signal into a digital image signal, and then sending the digital image signal to a computer system;
s740: the computer system receives the digital image signal, processes the image through an image processing algorithm to obtain characteristic parameters of the to-be-detected grinding and polishing blade, and obtains blade vibration information according to the characteristic parameters of the blade;
s750: and displaying the blade vibration information.
The invention provides an illumination system which provides uniform luminosity for the grinding and polishing blade to be detected, so that the characteristic quantity of the blade is outstanding, and the detected part and the non-detected part are obviously different.
It should be noted that before detection, the grinding and polishing devices mounted at the ends of the flanges of the industrial robot and the robot arm need to be calibrated to determine the position of the CCD camera, and perform parameter calibration on the CCD camera, which mainly includes conversion calculation of a coordinate system.
In the process of grinding and polishing the blade, under the illumination effect of the light source of the illumination system, the spatial structure information of the grinding and polishing blade is imaged on a photosensitive element of a CCD camera by using the optical imaging system so as to obtain an image optical signal. An optical sensitive element of a CCD camera of the image acquisition device can convert optical information of the blade into an electric signal, and an image acquisition card is arranged in the CCD camera to complete digital-analog signal conversion and convert an analog image signal into a digital image signal;
the image information collected by the image collecting device is transmitted to the system through the data interface, and then the collected image is operated by utilizing the image processing technology of the computer system, wherein the image processing technology is analyzed as above. And acquiring characteristic parameters corresponding to the grinding and polishing blade from the interested part of the image after the image optimization processing, analyzing, processing, displaying and storing the acquired characteristic parameters, and analyzing the blade vibration information according to the characteristic parameters.
And finally, extracting vibration information of the blade, obtaining a displacement curve of each characteristic point along with each frame of picture in the grinding and polishing process of the blade, and displaying the obtained related image information and the vibration information on display equipment.
Through the technical scheme, the following technical effects are achieved:
1. the visual vibration detection device belongs to non-contact measurement, can realize remote real-time detection, does not change the original characteristics of the blade, and has no damage to the blade subjected to vibration detection;
2. by adopting a mode of measuring vibration visually, the wide measuring range can be realized, and the invisible vibration can be measured. The method can simultaneously acquire a plurality of information acquisition points on the blade, and realize the measurement operation of the three-dimensional dense space of the blade;
3. the visual vibration measuring device has the advantages of high automation level, good detection efficiency and high measurement precision. The measuring mode is simple, the operator is convenient to operate and use, the labor intensity of the operator is reduced, and the monitoring, measuring and other work can be finished for a long time.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. The utility model provides a blade grinds and throws processing vibration detecting system based on vision, is applied to and waits to detect to grind and throw processing blade, its characterized in that includes: an illumination system, a CCD camera, an image acquisition system, an imaging system, a computer system and a display device, wherein,
the lighting system is used for providing a light source for the system so that the obtained image has discrimination;
the imaging system is used for imaging the spatial structure information of the blade on the CCD camera;
the CCD camera and the image acquisition system convert the acquired image optical signals into electric signals, and after the CCD camera converts the analog image signals into digital image signals, the digital image signals are transmitted to a computer system;
the computer system receives the digital image signal, processes the image through an image processing algorithm to obtain the blade characteristic parameters, and obtains blade vibration information according to the blade characteristic parameters;
the display device displays the blade vibration information.
2. The vision-based blade grinding and polishing vibration detection system as claimed in claim 1, wherein the illumination system provides a uniform light source, the illumination by the light source makes the characteristic quantity of the blade prominent, and makes the detected part and the non-detected part have obvious distinction.
3. The vision-based blade grinding and polishing vibration detection system as claimed in claim 1, wherein the imaging system for imaging the spatial structure information of the blade on the CCD camera comprises:
the imaging system maps the information of the blade on the optical sensitive element of the CCD camera to obtain the optical signal of the image.
4. The vision-based blade grinding and polishing vibration detection system as claimed in claim 4, wherein the parameter calibration operation of the CCD camera before vibration detection comprises:
the parameter calibration is a process of establishing a relation between the spatial position information and the image coordinates;
the method specifically comprises the following steps: coordinate transformation from base coordinate system to camera coordinate system:
rotating the matrix R ═ R according to the overall coordinates1R2R3Obtaining:
wherein R is1For an inter-coordinate rotation transformation matrix, R2Is a rotation matrix around the x-axis, R3Is a rotation matrix around the y-axis, where T is a translation transformation matrix between coordinate systems, Xo、Yo、ZoRespectively representing coordinate values, X, in a base coordinate systemw、Yw、ZwRespectively, coordinate values in the camera coordinate system.
5. The vision-based blade grinding and polishing vibration detection system as claimed in claim 4, wherein the transformation formula for converting the camera coordinate system to the image coordinate system is as follows:
accordingly, the coordinate transformation formula for converting from the base coordinate system to the image coordinate system is:
wherein x and y respectively represent coordinate values of a camera coordinate system, dx and dy respectively represent physical dimensions of each pixel on an x axis and a y axis, determined by the camera itself, f represents a focal length value, u and v respectively represent coordinate values of an image coordinate system, and u and v respectively represent coordinate values of an image coordinate system0、v0Respectively, represent the center of the image coordinate system.
6. The vision-based blade grinding and polishing vibration detection system as claimed in claim 1, wherein the CCD camera and the image acquisition system convert the acquired image optical signal into an electrical signal, and after the CCD camera converts the analog image signal into a digital image signal, the digital image signal is transmitted to a computer system, and the system comprises:
the optical sensitive element and the image acquisition system of the CCD camera convert the optical signals of the blade into electric signals, and the built-in image acquisition card of the CCD camera converts analog image signals into digital image signals and then transmits the digital image signals to a computer system.
7. The vision-based blade grinding and polishing machining vibration detection system as claimed in any one of claims 1 to 6, wherein the processing the image through an image processing algorithm to obtain the blade characteristic parameters comprises:
completing image analysis and image preprocessing through an image processing algorithm to obtain the characteristic parameters of the blade;
the blade characteristic parameters mainly comprise measured vibration signal data.
8. The vision-based blade burnishing processing vibration detecting system of claim 7,
the image pre-processing includes but is not limited to image filtering, image enhancement and image restoration operations;
the image analysis includes, but is not limited to, image feature extraction, image segmentation, image representation and description operations.
9. A blade grinding and polishing machining vibration detection method based on vision is applied to a grinding and polishing machining blade to be detected, and is characterized by comprising the following steps:
s1: irradiating the grinding and polishing blade to be detected by using a light source;
s2: imaging the spatial structure information of the grinding and polishing blade to be detected to obtain an image optical signal;
s3: converting the image optical signal into an electric signal, further converting an analog image signal into a digital image signal, and then sending the digital image signal to a computer system;
s4: the computer system receives the digital image signal, processes the image through an image processing algorithm to obtain characteristic parameters of the to-be-detected grinding and polishing blade, and obtains blade vibration information according to the characteristic parameters of the blade;
s5: and displaying the blade vibration information.
10. The visual-based blade grinding and polishing vibration detection method as claimed in claim 9, wherein the image processing in step S4 includes:
s41: calculating the number of pixels of each gray level of the interested ROI of the blade image;
s42: calculating the proportion of the number of pixels of each blade gray level in the ROI area of interest in S41;
s43: calculating the inter-class variance of each gray level of the leaf image to obtain a corresponding threshold value;
s44: and according to the obtained threshold value, carrying out binarization on the obtained blade image to obtain the characteristic parameter information of the blade image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911313703.9A CN111275665A (en) | 2019-12-19 | 2019-12-19 | Blade grinding and polishing processing vibration detection system and method based on vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911313703.9A CN111275665A (en) | 2019-12-19 | 2019-12-19 | Blade grinding and polishing processing vibration detection system and method based on vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111275665A true CN111275665A (en) | 2020-06-12 |
Family
ID=71001497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911313703.9A Pending CN111275665A (en) | 2019-12-19 | 2019-12-19 | Blade grinding and polishing processing vibration detection system and method based on vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111275665A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884727A (en) * | 2021-01-28 | 2021-06-01 | 华北电力大学（保定） | Wind turbine blade vibration monitoring method |
| CN112943559A (en) * | 2021-01-28 | 2021-06-11 | 华北电力大学（保定） | Vibration monitoring method |
| CN112966207A (en) * | 2021-01-28 | 2021-06-15 | 北京清源能控科技有限公司 | Vibration monitoring method based on image acquisition |
| CN115026683A (en) * | 2022-08-09 | 2022-09-09 | 湖南大学 | Aviation blade grinding and polishing device based on multi-robot cooperation and control method |
| CN115933534A (en) * | 2023-02-09 | 2023-04-07 | 山东山科世鑫科技有限公司 | Numerical control intelligent detection system and method based on Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105241389A (en) * | 2015-10-12 | 2016-01-13 | 贵州大学 | Machine visual sense based detection system for blunt round radius of cutting edge of milling cutter |
| CN108519225A (en) * | 2018-03-19 | 2018-09-11 | 江苏大学 | A kind of detection device and method of blade of aviation engine high-temperature vibrating fatigue properties |
| CN108876777A (en) * | 2018-06-14 | 2018-11-23 | 重庆科技学院 | A kind of visible detection method and system of wind electricity blade end face of flange characteristic size |
| CN109883533A (en) * | 2019-01-21 | 2019-06-14 | 哈尔滨工业大学（深圳） | Low frequency vibration measurement method based on machine vision |
| CN110211101A (en) * | 2019-05-22 | 2019-09-06 | 武汉理工大学 | A kind of rail surface defect rapid detection system and method |
-
2019
- 2019-12-19 CN CN201911313703.9A patent/CN111275665A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105241389A (en) * | 2015-10-12 | 2016-01-13 | 贵州大学 | Machine visual sense based detection system for blunt round radius of cutting edge of milling cutter |
| CN108519225A (en) * | 2018-03-19 | 2018-09-11 | 江苏大学 | A kind of detection device and method of blade of aviation engine high-temperature vibrating fatigue properties |
| CN108876777A (en) * | 2018-06-14 | 2018-11-23 | 重庆科技学院 | A kind of visible detection method and system of wind electricity blade end face of flange characteristic size |
| CN109883533A (en) * | 2019-01-21 | 2019-06-14 | 哈尔滨工业大学（深圳） | Low frequency vibration measurement method based on machine vision |
| CN110211101A (en) * | 2019-05-22 | 2019-09-06 | 武汉理工大学 | A kind of rail surface defect rapid detection system and method |
Non-Patent Citations (1)
| Title |
|---|
| 万刚等: "《无人机测绘技术及应用》", 31 December 2015 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884727A (en) * | 2021-01-28 | 2021-06-01 | 华北电力大学（保定） | Wind turbine blade vibration monitoring method |
| CN112943559A (en) * | 2021-01-28 | 2021-06-11 | 华北电力大学（保定） | Vibration monitoring method |
| CN112966207A (en) * | 2021-01-28 | 2021-06-15 | 北京清源能控科技有限公司 | Vibration monitoring method based on image acquisition |
| CN115026683A (en) * | 2022-08-09 | 2022-09-09 | 湖南大学 | Aviation blade grinding and polishing device based on multi-robot cooperation and control method |
| CN115026683B (en) * | 2022-08-09 | 2022-10-25 | 湖南大学 | Aviation blade grinding and polishing device based on multi-robot cooperation and control method |
| CN115933534A (en) * | 2023-02-09 | 2023-04-07 | 山东山科世鑫科技有限公司 | Numerical control intelligent detection system and method based on Internet of things |
| CN115933534B (en) * | 2023-02-09 | 2023-11-07 | 山东山科世鑫科技有限公司 | Numerical control intelligent detection system and method based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111275665A (en) | Blade grinding and polishing processing vibration detection system and method based on vision | |
| CN109297413B (en) | Visual measurement method for large-scale cylinder structure | |
| CN110672040B (en) | High-precision rotation angle measuring method based on vision | |
| CN109883533B (en) | Low-frequency vibration measurement method based on machine vision | |
| CN105783723B (en) | Precision die surface processing accuracy detection device and method based on machine vision | |
| CN102135236B (en) | Automatic non-destructive testing method for internal wall of binocular vision pipeline | |
| CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
| CN101561249B (en) | Method for automatically detecting fit dimension of surgical knife blade | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN110146017B (en) | Industrial robot repeated positioning precision measuring method | |
| CN113251926B (en) | Method and device for measuring size of irregular object | |
| CN108188835B (en) | Machine vision-based numerical control machine tool spindle thermal elongation testing device and testing method | |
| CN103617611A (en) | Automatic threshold segmentation detection method for center and size of light spot | |
| CN110608685A (en) | Object size rapid measurement method based on raspberry pie | |
| CN110763136B (en) | High-precision three-dimensional workpiece size detection system and method | |
| CN108582075A (en) | A kind of intelligent robot vision automation grasping system | |
| CN112303423B (en) | Intelligent three-dimensional information acquisition equipment stable in rotation | |
| CN111879264A (en) | Flatness measurement and evaluation system based on line structured light | |
| CN110375674A (en) | A kind of vision detection system of precision manufactureing equipment | |
| CN113066132B (en) | 3D modeling calibration method based on multi-equipment acquisition | |
| CN113375584A (en) | Monocular three-dimensional acquisition structure, monocular three-dimensional multi-gauge visual system and extensometer | |
| CN114485433A (en) | Three-dimensional measurement system, method and device based on pseudo-random speckles | |
| CN112254676B (en) | Portable intelligent 3D information acquisition equipment | |
| CN112254638B (en) | Intelligent visual 3D information acquisition equipment that every single move was adjusted | |
| WO2021179400A1 (en) | Computer vision-based adaptive measurement system and method for geometric parameters in assembly process |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200612 |
|
| RJ01 | Rejection of invention patent application after publication |