CN117884955A - Numerical control lathe processing auxiliary system based on machine vision - Google Patents
Numerical control lathe processing auxiliary system based on machine vision Download PDFInfo
- Publication number
- CN117884955A CN117884955A CN202410290316.2A CN202410290316A CN117884955A CN 117884955 A CN117884955 A CN 117884955A CN 202410290316 A CN202410290316 A CN 202410290316A CN 117884955 A CN117884955 A CN 117884955A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- bar
- image
- machine vision
- lathe
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000003754 machining Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims description 23
- 239000000463 material Substances 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005452 bending Methods 0.000 claims description 3
- 238000010191 image analysis Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 239000000306 component Substances 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Numerical Control (AREA)
Abstract
The invention discloses a numerical control lathe machining auxiliary system based on machine vision, which comprises: machine vision acquisition assemblyQThe machine vision acquisition assembly is arranged in the numerical control lathe to monitor the outer surface of a workpiece processed by the numerical control lathe and is configured in the numerical control lathe at a plurality of acquisition anglesQComprising a light assembly directed towards the axis of the spindleCLight assemblyCIrradiating the outer surface of the workpiece; virtual modelBMachine vision based acquisition assemblyQCollecting the outer surface bar image of the unprocessed barMAccording to bar imagesMEstablishing a virtual model of the bar according to bar characteristic information in the barBCorrecting the appearance state of the bar based on the bar characteristic information; the method and the device can acquire images of the rotating bar, analyze the bar images and acquire the bar images according to the bar imagesAnd (3) analyzing the processing quality of the workpiece according to the different characteristics, and scheduling the feeding speed and the spindle rotating speed of the turning tool after the processing quality of the workpiece at different positions of the bar is obtained.
Description
Technical Field
The invention relates to the technical field of numerical control machining image auxiliary processing, in particular to a numerical control lathe machining auxiliary system based on machine vision.
Background
The numerical control lathe mainly comprises the following structures:
numerical control device: the numerical control lathe is a core component of the numerical control lathe and is responsible for receiving, explaining, storing and executing numerical control programs and controlling the movement and the work of the numerical control lathe. The type and performance of the numerical control device determine the function and precision of the numerical control lathe.
Servo drive and motor: is an executive component of the numerical control lathe and is responsible for converting an instruction sent by the numerical control device into the movement of the numerical control lathe. The type and performance of the servo drive and motor determine the speed and response of the numerically controlled lathe.
Auxiliary device: is a matching component of the numerical control lathe and is responsible for ensuring the normal operation and the processing effect of the numerical control lathe. The type and performance of the auxiliary device determine the stability and reliability of the numerically controlled lathe.
Chinese patent publication No. CN114723692a discloses a machine vision based numerically controlled lathe machining auxiliary system, which comprises: a roughness detecting part, a data processing part and a workpiece processing data display part. The roughness detection part adopts a camera to shoot the surface of the workpiece, and uses a convolution Shensheng network model to detect the roughness; the data processing part is used for identifying the roughness of the workpiece and the end face size of the workpiece by a packaging machine vision algorithm; and the workpiece processing data display part is used for displaying the obtained roughness data so as to facilitate a processing master to monitor the processing condition of the workpiece in time.
The auxiliary system of the numerical control lathe mainly has the following functions: the processing efficiency is improved, the processing quality is improved, the processing flexibility is improved, and the processing safety is improved.
For machine vision, the most obvious improvement in the numerical control lathe machining process is machining quality, the image characteristics of the machined part are analyzed by utilizing a computer and image processing, the machining quality is identified according to the image characteristics, and the workpiece is further processed according to the image characteristics.
However, as the bar is in a rotating state in the processing process, the recognition of the image through machine vision needs to slow down the speed of the bar or make the bar in a static state, so that the image is collected, the characteristics in the image are extracted, the processing quality of the workpiece is analyzed, and the processing efficiency of the workpiece is reduced by analyzing the quality of the workpiece based on the characteristics.
Disclosure of Invention
One of the purposes of the invention is to provide a machine vision-based numerical control lathe machining auxiliary system, wherein a motion field in an image sequence is estimated through an optical flow method, the identification of the characteristics in an acquired image is carried out according to the change of the image, the analysis of the workpiece machining quality is carried out according to the identified image information, and the dispatching of numerical control lathe machining is carried out according to the workpiece machining quality characteristics in the image.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a machine vision-based numerically controlled lathe machining assist system, comprising:
machine vision acquisition assemblyQThe machine vision acquisition assembly is arranged in the numerical control lathe to monitor the outer surface of a workpiece processed by the numerical control lathe and is configured in the numerical control lathe at a plurality of acquisition anglesQComprising a light assembly directed towards the axis of the spindleCLight assemblyCIrradiating the outer surface of the workpiece;
virtual modelBMachine vision based acquisition assemblyQCollecting the outer surface bar image of the unprocessed barMAccording to bar imagesMEstablishing a virtual model of the bar according to bar characteristic information in the barBCorrecting the appearance state of the bar based on the bar characteristic information;
the image analysis model is used for collecting images of the surface of the workpiece after cutting processing and carrying out workpiece surface image H based on the rotation speed of the main shaft 3 Collecting a workpiece surface image H 3 Splicing to form workpiece appearance image information H 2 Workpiece external image through learning modelImage information H 2 Is analyzed to obtain the processing quality data H of the workpiece 1 According to the processing quality data H of the workpiece 1 Performing virtual modelsBIs corrected by the correction of (a);
feedback assembly for processing quality data H according to workpiece 1 Calculating the motion trail and the motion speed of the numerical control lathe to form lathe motion dataPAccording to lathe movement dataPAnd processing the workpiece.
In one or more embodiments of the invention, a light assemblyCIs arranged in the numerical control lathe in an up-down mode, and the light componentCThe included angle is 30-110 degrees, and the machine vision acquisition assemblyQLight assembly located at upper and lowerCOn the extension line of the middle angle of the included angle, acquiring bar images towards the axis of the main shaftM。
In one or more embodiments of the invention, a machine vision acquisition assemblyQAcquiring an image of the outer surface of the barMBy multiple bar imagesMImage pulling is carried out, arc surface images generated by shooting are pulled into plane images, and the images shot by multiple angles are used as image pulling basic proportion dataDCalculating image pulling base proportion data based on pixel area rangeD：
；
Wherein sn is the pixel area of the feature of the nth reference image, and the feature of the reference image is the image of the bar stockMThe area of the characteristic pixel point collected in the middle part is Sn which is the area of the characteristic pixel point of the nth pulling image, and the pulling image characteristic is positioned in the bar imageMAnd the area of the characteristic pixel points collected by the edge.
In one or more embodiments of the invention, the virtual modelBVirtual model is carried out according to spindle rotating speed and cutter feeding positionBI.e. virtual model is made in dependence on tool feed depthBIs used for simulating the cutting position of a bar material and is an image of the bar materialMThe surface performs characteristic simulation of the outer surface of the bar according to the characteristic information, simulates the bulges, pits and shapes of the outer surface of the bar, and is based onAnd (5) calculating the tool setting position by the bulges, the pits and the shapes of the outer surface of the bar.
In one or more embodiments of the invention, a machine vision acquisition assemblyQIn the process of workpiece rotation, image acquisition is carried out through an optical flow method, and a machine vision acquisition assemblyQShooting and collecting surface image H of workpiece 3 Machine vision acquisition assembly based on spindle rotation speed calculationQShooting interval, namely calculating the time of one rotation of the workpiece through the rotation speed of the main shaft:in which, in the process,rfor the rotation time of the main shaft,Tfor the rotation speed of the main shaft, the machine vision acquisition assembly is calculated through the time of one rotation of the workpieceQShooting interval.
In one or more embodiments of the invention, the workpiece surface image H 3 Image traction is carried out, an arc image is drawn into a plane image, and a workpiece surface image H after traction is carried out 3 Analyzing the surface features and marking the coordinates of the surface featuresx n ， y n ) Wherein, the method comprises the steps of, wherein,x n is the firstnOf individual surface featuresxThe coordinates of the two points of the coordinate system,y n is the firstnOf individual surface featuresyCoordinates of adjacent workpiece surface images H 3 Calculating the motion position of the surface feature, namely motion feature coordinatesx n +L，y n +L）。
In one or more embodiments of the invention, the method is based on surface feature coordinatesx n ，y n ) Performing workpiece surface image H 3 Form the complete workpiece appearance image information H 2 By means of the workpiece-appearance image information H 2 Performing virtual modelsBIs corrected according to the surface characteristic coordinatesx n ，y n ) Synchronizing to a virtual modelBIn the whole workpiece appearance image information H 2 Analysis of the learning model is carried out to obtain the workpiece appearance image information H 2 Surface features of different positions in the workpiece are obtained, and then the processing quality data H of the workpiece is obtained 1 。
In one or more embodiments of the invention, the axis size of the surface feature is calculated, the influence range of the surface feature is obtained, and the size marking is carried out according to the end face position of the workpiece, namely the surface feature coordinates [ ]x n ，y n ) Move to different motion characteristic coordinatesx n +L，y n +L) When the surface characteristic coordinates are obtainedx n ，y n ) Collecting surface characteristic coordinatesx n ，y n ) Is used to calculate the surface feature coverage.
In one or more embodiments of the invention, a light assemblyCReflective belts with different reflective states are formed on the surface of a workpiece, and machine vision acquisition assemblyQAt the completion of the workpiece surface image H 3 After the collection of the surface, the reflective strip is extracted, the fluctuation state of the reflective strip is obtained, the fluctuation position of the pixel point of the reflective strip is extracted, the convex and concave positions of the surface of the workpiece are obtained, and the bending state of the reflective strip is related to the processing quality of the workpiece.
In one or more embodiments of the invention, lathe motion data is performed based on workpiece processing quality informationPFirstly, counting the movement speed of the previous lathe tool and the rotation speed of the main shaft, and calculating lathe movement data according to the movement speed of the previous lathe tool and the rotation speed of the main shaftP：
；
FFor the data of the movement of the tool of the lathe,Kfor the movement speed of the previous cutting tool,g1g2 is the fluctuation range of the outer contour pixel points of the standard cutting position;
；
Bis the motion data of the main shaft of the lathe,Ythe motion speed of the previous main shaft.
Through the technical scheme, the invention has the following beneficial effects:
1. according to the method and the device, the rotating bar can be subjected to image acquisition, bar images are analyzed, the workpiece processing quality is analyzed according to the difference of the characteristics in the bar images, and after the workpiece processing quality of different positions of the bar is obtained, the feeding speed and the spindle rotating speed of the turning tool are used for scheduling, so that the processing degree can be changed according to the difference of the outer surface conditions of the workpiece.
2. Before bar machining is performed, virtual bar is formed by collecting the characteristics of the surface of the bar, namely, the images of the outer surface of the bar in the low-speed rotation process, the characteristics are combined to form the surface of the bar, when machining is performed, corresponding correction can be performed according to the characteristics of the virtual bar, correction of the virtual state is performed according to the state of the bar, and quality estimation of the virtual bar can be performed before bar machining.
3. The external surface state of the bar is used for being assisted by light, when the image acquisition is carried out, the state that the light is positioned on the external surface of the bar is acquired, and the image information acquired by an optical flow method in the rotation process of the bar can be used for monitoring the external surface quality of the bar in the rotation process of the bar, and then the quality data can be acquired in the rotation process.
4. When the processing quality of the surface of the workpiece is acquired, the image characteristic information of each circle at different positions is acquired through the time difference corresponding to the rotating speed of the main shaft, the bar outside image is formed according to the different image characteristic information, the characteristic information in the image is analyzed to analyze the processing quality of the workpiece, and further the improvement of the quality of the workpiece can be carried out according to the image characteristic information.
Drawings
FIG. 1 is a schematic diagram of a process assist system of the present invention.
Detailed Description
Various embodiments of the invention are disclosed in the accompanying drawings, and for purposes of explanation, numerous practical details are set forth in the following description. However, it should be understood that these practical details are not to be taken as limiting the invention. That is, in some embodiments of the invention, these practical details are unnecessary. And features of different embodiments may be interactively applied, if implementation is possible.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have their ordinary meaning as understood by one of ordinary skill in the art. Furthermore, the definitions of the words and phrases used herein should be understood and interpreted to have a meaning consistent with the understanding of the relevant art and technology. These terms are not to be construed as idealized or overly formal meanings unless expressly so defined.
Referring to fig. 1, the invention provides a machine vision-based numerically controlled lathe processing auxiliary system, which acquires characteristic information of a workpiece surface by acquiring quality information of the workpiece surface in a rotation process, and analyzes a learning model according to different characteristic information, so as to obtain workpiece surface quality data, thereby adjusting workpiece processing. Comprising the following steps:
machine vision acquisition assemblyQThe machine vision acquisition assembly is arranged in the numerical control lathe to monitor the outer surface of a workpiece processed by the numerical control lathe and is configured in the numerical control lathe at a plurality of acquisition anglesQComprising a light assembly directed towards the axis of the spindleCLight assemblyCIrradiating the outer surface of the workpiece;
virtual modelBMachine vision based acquisition assemblyQCollecting the outer surface bar image of the unprocessed barMAccording to bar imagesMEstablishing a virtual model of the bar according to bar characteristic information in the barBCorrecting the appearance state of the bar based on the bar characteristic information;
the image analysis model is used for collecting images of the surface of the workpiece after cutting processing and carrying out workpiece surface image H based on the rotation speed of the main shaft 3 Collecting a workpiece surface image H 3 Splicing to form workpiece appearance image information H 2 Workpiece exterior image information H by learning model 2 Is analyzed to obtain the processing quality data H of the workpiece 1 According to the processing quality data H of the workpiece 1 Performing virtual moldA kind of electronic device with a display unitBIs corrected by the correction of (a);
feedback assembly for processing quality data H according to workpiece 1 Calculating the motion trail and the motion speed of the numerical control lathe to form lathe motion dataPAccording to lathe movement dataPAnd processing the workpiece.
In this embodiment, the machine vision acquisition assemblyQForm the collection to work piece surface image, in the in-process of gathering, light subassemblyCThe light reflection state detection device can irradiate the surface of the workpiece based on different directions, and can acquire states of different positions of the workpiece according to different light reflection states of the surface of the workpiece when the image is acquired.
Before bar processing, the main shaft drives the bar to rotate at a low speed, and bar images at different positions on the outer surface of the bar are collectedMAccording to bar imagesMTo build a virtual modelBVirtual modelBAfter formation, can be based on a virtual modelBAnalyzing the state of the numerical control lathe in the moving process, correcting the state of the corresponding bar according to the movement of the cutter and the lathe, and performing a virtual model according to the movement of the cutter and the numerical control latheBIs a modification of (a).
In one embodiment, a light assemblyCIs arranged in the numerical control lathe in an up-down mode, and the light componentCThe included angle is 30-110 degrees, and the machine vision acquisition assemblyQLight assembly located at upper and lowerCOn the extension line of the middle angle of the included angle, acquiring bar images towards the axis of the main shaftM。
In this embodiment, the light assemblyCSet up to different contained angle angles can shine to different scope, at machine vision collection subassemblyQDuring the collection process, the light componentCThe length between the light reflection strips at the outer side of the workpiece can be changed due to the change of the irradiated angle, and the machine vision acquisition assemblyQBar images in different ranges can be obtainedMImage H of the surface of the workpiece 3 Collecting images of different barsMWorkpiece surface image H 3 The range is collected to schedule spindle movement speed.
In one embodiment, machine vision is employedCollection assemblyQAcquiring an image of the outer surface of the barMBy multiple bar imagesMImage pulling is carried out, arc surface images generated by shooting are pulled into plane images, and the images shot by multiple angles are used as image pulling basic proportion dataDCalculating image pulling base proportion data based on pixel area rangeD：
；
Wherein sn is the pixel area of the feature of the nth reference image, and the feature of the reference image is the image of the bar stockMThe area of the characteristic pixel point collected in the middle part is Sn which is the area of the characteristic pixel point of the nth pulling image, and the pulling image characteristic is positioned in the bar imageMAnd the area of the characteristic pixel points collected by the edge.
In this embodiment, the machine vision acquisition assemblyQPerforming bar imageMDuring collection, multiple bar images are collectedMIn the process of bar imageMBy including the bar image during the drawingMBar image of medium featuresMCollecting required drawing bar material imagesMEdge feature pixel area and other bar imagesMCalculating the image traction basic proportion data of the maximum point of the area of the characteristic pixel pointDAfter the image pulling basic proportion data is obtainedDThen, the basic proportion data is pulled according to the imageDAs a desired pulling bar imageMTo form a planar bar imageM。
After the pulling range is acquired, the bar material image can be obtainedMSplicing according to the bar imagesMCan acquire the size data of the bar stock, and form a virtual model according to the size dataBThereby obtaining a relatively stable size virtual modelBThe virtual model can be modified during tool feedBIs a piece of information of (a).
In one embodiment, the virtual modelBVirtual model is carried out according to spindle rotating speed and cutter feeding positionBI.e. virtual model is made in dependence on tool feed depthBIs used for simulating the cutting position of a bar material and is an image of the bar materialMAnd carrying out characteristic simulation on the outer surface of the bar according to the characteristic information, simulating the protrusion, the pit and the shape of the outer surface of the bar, and calculating the tool setting position based on the protrusion, the pit and the shape of the outer surface of the bar.
In this embodiment, the bar image is passed throughMPerforming virtual modelsBThe bulge, the pit and the shape of the outer surface can be corrected when the bar is subjected to tool setting, the tool setting depth position can be corrected, the consumption of the bar when the bar is subjected to tool setting can be reduced, the problem that the pit on the surface of the bar still cannot be removed when the bar is subjected to tool setting for many times can be avoided, the tool setting efficiency is reduced, and the machining efficiency is ensured.
In one embodiment, a machine vision acquisition assemblyQIn the process of workpiece rotation, image acquisition is carried out through an optical flow method, and a machine vision acquisition assemblyQShooting and collecting surface image H of workpiece 3 Machine vision acquisition assembly based on spindle rotation speed calculationQShooting interval, namely calculating the time of one rotation of the workpiece through the rotation speed of the main shaft:in which, in the process,rfor the rotation time of the main shaft,Tfor the rotation speed of the main shaft, the machine vision acquisition assembly is calculated through the time of one rotation of the workpieceQShooting interval.
In this embodiment, the machine vision acquisition assemblyQBy shooting at different time intervals, images of different rotation angle positions of the workpiece can be shot to perform the surface image H of the workpiece 3 Collecting a large number of workpiece surface images H 3 To splice into complete workpiece appearance image information H 2 Thereby judging the quality of the outer surface of the workpiece and according to the complete image information H of the outer surface of the workpiece 2 Quality data of different positions of the workpiece can be obtained.
In the calculation of the photographing interval, the workpiece surface image H is performed by increasing the interval time by one rotation of the workpiece 3 The acquisition is carried out, the interval time is increased after one turn, and the workpiece surface images H of different angle positions of the workpiece can be acquired 3 Thereby ensuring the collection of the workpieceSurface image H 3 Is described herein).
In one embodiment, a workpiece surface image H 3 Image traction is carried out, an arc image is drawn into a plane image, and a workpiece surface image H after traction is carried out 3 Analyzing the surface features and marking the coordinates of the surface featuresx n ，y n ) Wherein, the method comprises the steps of, wherein,x n is the firstnOf individual surface featuresxThe coordinates of the two points of the coordinate system,y n is the firstnOf individual surface featuresyCoordinates of adjacent workpiece surface images H 3 Calculating the motion position of the surface feature, namely motion feature coordinatesx n +L，y n +L）。
In the embodiment, different surface feature coordinates are obtainedx n ，y n ) Can be according to the surface characteristic coordinatesx n ，y n ) Image H on different workpiece surfaces 3 The position in the process is used for calculating the characteristic coverage range, and the workpiece processing quality data H is obtained 1 When the outer surface of the workpiece is processed, the processing quality data H of the workpiece can be used 1 And the surface of the workpiece is processed, so that the surface quality of the workpiece is corrected, and the processing quality of the workpiece is further ensured.
The workpiece is driven by the main shaft to rotate continuously during the processing, so the surface feature coordinates [ ]x n ，y n ) The axial dimension span of the tool is the area range influenced by the surface characteristics, and the position and the speed of cutting of the tool can be obtained according to the area range influenced by the surface characteristics in the process of turning the tool.
In one embodiment, the method is based on surface feature coordinatesx n ，y n ) Performing workpiece surface image H 3 Form the complete workpiece appearance image information H 2 By means of the workpiece-appearance image information H 2 Performing virtual modelsBIs corrected according to the surface characteristic coordinatesx n ，y n ) Synchronizing to a virtual modelBIn (3) completeWorkpiece exterior image information H 2 Analysis of the learning model is carried out to obtain the workpiece appearance image information H 2 Surface features of different positions in the workpiece are obtained, and then the processing quality data H of the workpiece is obtained 1 。
In this embodiment, the surface feature coordinates [ ]x n ，y n ) Can synchronize to the virtual model according to the difference of the positions of the coordinate pointsBThe outer surface can further obtain more accurate surface feature coordinatesx n ，y n ) In the process of turning tool processing, the change can be accurately started at a certain position, and the surface characteristic coordinates are reducedx n ，y n ) Further ensuring a stable processing range.
The learning model contains image features of different qualities of various materials, so that the depth of the quality problem of the surface of the workpiece and information of data related to the turning tool and the spindle can be analyzed, and when the surface of the workpiece is unsmooth, the influence factors of the surface quality of the workpiece, namely the feeding speed of the turning tool is high, are obtained, and the influence factors of the surface quality of the workpiece are marked.
In one embodiment, the surface characteristic axis size is calculated, the influence range of the surface characteristic is obtained, and the size marking is carried out according to the position of the end face of the workpiece, namely the surface characteristic coordinate is calculatedx n ，y n ) Move to different motion characteristic coordinatesx n +L，y n +L) When the surface characteristic coordinates are obtainedx n ，y n ) Collecting surface characteristic coordinatesx n ，y n ) Is used to calculate the surface feature coverage.
In this embodiment, the surface feature coordinates [ ]x n ，y n ) Can calculate the surface feature length, i.e.:，Ax max for the surface features to be near the end point of the spindle,Ax min the workpiece takes the end face as the initial position, namely the size origin, to calculate the length of the surface feature according to the maximum size position covered by the surface feature to the minimum size position covered by the surface featureAL。
Since the end surface of the turning tool formed after the completion of tool setting is the initial position, the feeding length of the turning tool is identical to the workpiece size, and the calculation of the position of the turning tool movement can be performed based on the position of the surface feature when machining is performed.
In one embodiment, a light assemblyCReflective belts with different reflective states are formed on the surface of a workpiece, and machine vision acquisition assemblyQAt the completion of the workpiece surface image H 3 After the collection of the surface, the reflective strip is extracted, the fluctuation state of the reflective strip is obtained, the fluctuation position of the pixel point of the reflective strip is extracted, the convex and concave positions of the surface of the workpiece are obtained, and the bending state of the reflective strip is related to the processing quality of the workpiece.
In this embodiment, the smooth state of the outer surface of the workpiece can be directly fed back by the reflective tape, so that the workpiece processing quality data H can be obtained according to the pixel position of the reflective tape 1 The workpiece processing quality data H 1 The problem of different quality of the workpiece at different positions can be reflected, namely, the outer contour combination of different pixel points of the reflective strip of the workpiece at different positions.
According to the arrangement of the outer contour pixel points, the fluctuation range of the surface of the reflection belt can be obtained, the larger the fluctuation range is, the lower the machining quality of the workpiece at the position is, the smaller the fluctuation range is, and the better the machining quality of the workpiece at the position is.
In one embodiment, lathe motion data is performed based on workpiece processing quality informationPFirstly, counting the movement speed of the previous lathe tool and the rotation speed of the main shaft, and calculating lathe movement data according to the movement speed of the previous lathe tool and the rotation speed of the main shaftP：
；
FFor the data of the movement of the tool of the lathe,Kfor the movement speed of the previous cutting tool,g1g2 is the fluctuation range of the outer contour pixel points of the standard cutting position;
；
Bis the motion data of the main shaft of the lathe,Ythe motion speed of the previous main shaft.
In the present embodiment, lathe motion data is performedPCan acquire the motion data of the numerically controlled lathe through analysisPLathe motion dataPThe feedback component can be fed back into the control system of the numerically controlled lathe to change the control state of the control system, so that the processing quality data H of the workpiece can be analyzed 1 Re-correction of lathe motion dataPFurther, the control of the numerical control lathe control system on the main shaft and the cutter can be automatically changed.
In summary, the technical solution disclosed in the above embodiment of the present invention has at least the following advantages:
1. the method and the device can acquire images of the rotating bar, and analyze the images of the barMAccording to bar imagesMThe method is characterized in that the workpiece processing quality is analyzed according to the difference of the characteristics, and after the workpiece processing quality of different positions of the bar is obtained, the method is used for scheduling the feeding speed of the turning tool and the rotating speed of the main shaft, so that the processing degree can be changed according to the difference of the conditions of the outer surface of the workpiece.
2. Before bar machining is performed, virtual bar is formed by collecting the characteristics of the surface of the bar, namely, the images of the outer surface of the bar in the low-speed rotation process, the characteristics are combined to form the surface of the bar, when machining is performed, corresponding correction can be performed according to the characteristics of the virtual bar, correction of the virtual state is performed according to the state of the bar, and quality estimation of the virtual bar can be performed before bar machining.
3. The external surface state of the bar is used for being assisted by light, when the image acquisition is carried out, the state that the light is positioned on the external surface of the bar is acquired, and the image information acquired by an optical flow method in the rotation process of the bar can be used for monitoring the external surface quality of the bar in the rotation process of the bar, and then the quality data can be acquired in the rotation process.
4. When the processing quality of the surface of the workpiece is acquired, the image characteristic information of each circle at different positions is acquired through the time difference corresponding to the rotating speed of the main shaft, the bar outside image is formed according to the different image characteristic information, the characteristic information in the image is analyzed to analyze the processing quality of the workpiece, and further the improvement of the quality of the workpiece can be carried out according to the image characteristic information.
Although the present invention has been described in connection with the above embodiments, it should be understood that the invention is not limited thereto, but may be variously modified and modified by those skilled in the art without departing from the spirit and scope of the invention, and the scope of the invention is accordingly defined by the appended claims.
Claims (10)
1. A machine vision-based numerically controlled lathe machining assist system, comprising:
machine vision acquisition assemblyQThe machine vision acquisition assembly is arranged in the numerical control lathe to monitor the outer surface of a workpiece processed by the numerical control lathe and is configured in the numerical control lathe at a plurality of acquisition anglesQComprising a light assembly directed towards the axis of the spindleCLight assemblyCIrradiating the outer surface of the workpiece;
virtual modelBMachine vision based acquisition assemblyQCollecting the outer surface bar image of the unprocessed barMAccording to bar imagesMEstablishing a virtual model of the bar according to bar characteristic information in the barBCorrecting the appearance state of the bar based on the bar characteristic information;
the image analysis model is used for collecting images of the surface of the workpiece after cutting processing and carrying out workpiece surface image H based on the rotation speed of the main shaft 3 Collecting a workpiece surface image H 3 Splicing to form workpiece appearance image information H 2 Workpiece exterior image information H by learning model 2 Is used for the analysis of (a),acquiring workpiece processing quality data H 1 According to the processing quality data H of the workpiece 1 Performing virtual modelsBIs corrected by the correction of (a);
feedback assembly for processing quality data H according to workpiece 1 Calculating the motion trail and the motion speed of the numerical control lathe to form lathe motion dataPAccording to lathe movement dataPAnd processing the workpiece.
2. The machine vision-based numerically controlled lathe work assist system of claim 1, wherein the light assembly comprisesCIs arranged in the numerical control lathe in an up-down mode, and the light componentCThe included angle is 30-110 degrees, and the machine vision acquisition assemblyQLight assembly located at upper and lowerCOn the extension line of the middle angle of the included angle, acquiring bar images towards the axis of the main shaftM。
3. The machine vision-based numerically controlled lathe work assist system of claim 2, wherein the machine vision acquisition assemblyQAcquiring an image of the outer surface of the barMBy multiple bar imagesMImage pulling is carried out, arc surface images generated by shooting are pulled into plane images, and the images shot by multiple angles are used as image pulling basic proportion dataDCalculating image pulling base proportion data based on pixel area rangeD：
；
Wherein sn is the pixel area of the feature of the nth reference image, and the feature of the reference image is the image of the bar stockMThe area of the characteristic pixel point collected in the middle part is Sn which is the area of the characteristic pixel point of the nth pulling image, and the pulling image characteristic is positioned in the bar imageMAnd the area of the characteristic pixel points collected by the edge.
4. A machine vision based numerically controlled lathe work assist system as in claim 3, whereinIn that, a virtual modelBVirtual model is carried out according to spindle rotating speed and cutter feeding positionBI.e. virtual model is made in dependence on tool feed depthBIs used for simulating the cutting position of a bar material and is an image of the bar materialMAnd carrying out characteristic simulation on the outer surface of the bar according to the characteristic information, simulating the protrusion, the pit and the shape of the outer surface of the bar, and calculating the tool setting position based on the protrusion, the pit and the shape of the outer surface of the bar.
5. The machine vision-based numerically controlled lathe work assist system of claim 4, wherein the machine vision acquisition assemblyQIn the process of workpiece rotation, image acquisition is carried out through an optical flow method, and a machine vision acquisition assemblyQShooting and collecting surface image H of workpiece 3 Machine vision acquisition assembly based on spindle rotation speed calculationQShooting interval, namely calculating the time of one rotation of the workpiece through the rotation speed of the main shaft:in which, in the process,rfor the rotation time of the main shaft,Tfor the rotation speed of the main shaft, the machine vision acquisition assembly is calculated through the time of one rotation of the workpieceQShooting interval.
6. The machine vision-based numerically controlled lathe machining assist system of claim 5, wherein the workpiece surface image H 3 Image traction is carried out, an arc image is drawn into a plane image, and a workpiece surface image H after traction is carried out 3 Analyzing the surface features and marking the coordinates of the surface featuresx n ，y n ) Wherein, the method comprises the steps of, wherein,x n is the firstnOf individual surface featuresxThe coordinates of the two points of the coordinate system,y n is the firstnOf individual surface featuresyCoordinates of adjacent workpiece surface images H 3 Calculating the motion position of the surface feature, namely motion feature coordinatesx n +L，y n +L）。
7. According to the weightsThe machine vision-based numerically controlled lathe machining auxiliary system as set forth in claim 6, wherein the machine vision-based numerically controlled lathe machining auxiliary system is characterized in that the machine vision-based numerically controlled lathe machining auxiliary system is based on surface feature coordinatesx n ，y n ) Performing workpiece surface image H 3 Form the complete workpiece appearance image information H 2 By means of the workpiece-appearance image information H 2 Performing virtual modelsBIs corrected according to the surface characteristic coordinatesx n ，y n ) Synchronizing to a virtual modelBIn the whole workpiece appearance image information H 2 Analysis of the learning model is carried out to obtain the workpiece appearance image information H 2 Surface features of different positions in the workpiece are obtained, and then the processing quality data H of the workpiece is obtained 1 。
8. The machine vision-based numerically controlled lathe machining auxiliary system according to claim 7, wherein the surface feature axis size is calculated, the influence range of the surface feature is obtained, and the size marking is performed according to the position of the end face of the workpiece, namely, the surface feature coordinates [ ]x n ，y n ) Move to different motion characteristic coordinatesx n +L，y n +L) When the surface characteristic coordinates are obtainedx n ， y n ) Collecting surface characteristic coordinatesx n ，y n ) Is used to calculate the surface feature coverage.
9. The machine vision-based numerically controlled lathe work assist system of claim 8, wherein the light assembly comprisesCReflective belts with different reflective states are formed on the surface of a workpiece, and machine vision acquisition assemblyQAt the completion of the workpiece surface image H 3 After the collection of the surface, the reflective strip is extracted, the fluctuation state of the reflective strip is obtained, the fluctuation position of the pixel point of the reflective strip is extracted, the convex and concave positions of the surface of the workpiece are obtained, and the bending state of the reflective strip is related to the processing quality of the workpiece.
10. According to claimThe machine vision-based numerically controlled lathe machining assist system according to 9, wherein lathe movement data is performed based on workpiece machining quality informationPFirstly, counting the movement speed of the previous lathe tool and the rotation speed of the main shaft, and calculating lathe movement data according to the movement speed of the previous lathe tool and the rotation speed of the main shaftP：
；
FFor the data of the movement of the tool of the lathe,Kfor the movement speed of the previous cutting tool,g1g2 is the fluctuation range of the outer contour pixel points of the standard cutting position;
；
Bis the motion data of the main shaft of the lathe,Ythe motion speed of the previous main shaft.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410290316.2A CN117884955B (en) | 2024-03-14 | 2024-03-14 | Numerical control lathe processing auxiliary system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410290316.2A CN117884955B (en) | 2024-03-14 | 2024-03-14 | Numerical control lathe processing auxiliary system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117884955A true CN117884955A (en) | 2024-04-16 |
| CN117884955B CN117884955B (en) | 2024-06-07 |
Family
ID=90646023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410290316.2A Active CN117884955B (en) | 2024-03-14 | 2024-03-14 | Numerical control lathe processing auxiliary system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117884955B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102825504A (en) * | 2012-09-18 | 2012-12-19 | 重庆科技学院 | State detection method for main shaft of numerically-controlled machine tool |
| CN108115232A (en) * | 2016-11-26 | 2018-06-05 | 阿杰·查米莱斯股份有限公司 | For the method for the mechanical processing and inspection of workpiece |
| CN108620950A (en) * | 2018-05-08 | 2018-10-09 | 华中科技大学无锡研究院 | A kind of turning cutting tool drilling monitoring method and system |
| CN213196754U (en) * | 2020-02-21 | 2021-05-14 | 宁波三韩合金材料有限公司 | Numerical control machine tool cutter state monitoring device based on vibration signal and image acquisition |
| CN115003452A (en) * | 2020-01-15 | 2022-09-02 | Dmg森精机株式会社 | Image processing apparatus, machine tool, and image processing method |
| CN115984576A (en) * | 2022-11-14 | 2023-04-18 | 浙江中泽精密科技有限公司 | Nondestructive burr removing method and system for square aluminum shell of new energy battery |
| US11629817B1 (en) * | 2021-12-14 | 2023-04-18 | Andong National University Industry-Academic Cooperation Foundation | Device and method for preventing worker safety accident during machining |
-
2024
- 2024-03-14 CN CN202410290316.2A patent/CN117884955B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102825504A (en) * | 2012-09-18 | 2012-12-19 | 重庆科技学院 | State detection method for main shaft of numerically-controlled machine tool |
| CN108115232A (en) * | 2016-11-26 | 2018-06-05 | 阿杰·查米莱斯股份有限公司 | For the method for the mechanical processing and inspection of workpiece |
| CN108620950A (en) * | 2018-05-08 | 2018-10-09 | 华中科技大学无锡研究院 | A kind of turning cutting tool drilling monitoring method and system |
| CN115003452A (en) * | 2020-01-15 | 2022-09-02 | Dmg森精机株式会社 | Image processing apparatus, machine tool, and image processing method |
| CN213196754U (en) * | 2020-02-21 | 2021-05-14 | 宁波三韩合金材料有限公司 | Numerical control machine tool cutter state monitoring device based on vibration signal and image acquisition |
| US11629817B1 (en) * | 2021-12-14 | 2023-04-18 | Andong National University Industry-Academic Cooperation Foundation | Device and method for preventing worker safety accident during machining |
| CN115984576A (en) * | 2022-11-14 | 2023-04-18 | 浙江中泽精密科技有限公司 | Nondestructive burr removing method and system for square aluminum shell of new energy battery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117884955B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111007073B (en) | Method and system for online detection of part defects in additive manufacturing process | |
| CN109822398B (en) | Numerical control machine tool broken cutter detection system and method based on deep learning | |
| CN111230593B (en) | Milling cutter abrasion loss visual measurement method based on dynamic image sequence | |
| CN110153567A (en) | A kind of laser cutting system based on image recognition | |
| US4998005A (en) | Machine vision system | |
| CN110376963B (en) | Closed-loop control precision machining method and system based on in-situ detection | |
| CN113146172B (en) | Multi-vision-based detection and assembly system and method | |
| CN108062072A (en) | A kind of dual camera image collecting device and the flat-bottom milling cutter of image mosaic abrasion online test method | |
| CN115035120B (en) | Machine tool control method and system based on Internet of things | |
| JP2002189510A (en) | Working relevant information preparation device and numerical controller equipped with the same device | |
| CN114279357B (en) | Die casting burr size measurement method and system based on machine vision | |
| CN112264839A (en) | Cutting tool abrasion in-situ measuring device and method for manufacturing Internet of things | |
| CN115972093B (en) | Workpiece surface measuring method and device and wing wallboard soft mold polishing method | |
| CN104436593A (en) | Intelligent processing system and method for feather pieces of shuttlecock | |
| JP2023090683A (en) | Finishing automation system and method thereof | |
| CN114406007A (en) | Seamless steel pipe tracking production system one by one | |
| CN109345500B (en) | Machine vision-based method for calculating position of tool nose point of machine tool cutter | |
| CN117884955B (en) | Numerical control lathe processing auxiliary system based on machine vision | |
| CN110097526B (en) | Workpiece image generating device | |
| CN117408970A (en) | Semantic segmentation-based method for polishing surface defects of medium plate by robot | |
| CN115056074B (en) | Steel pipe tip clout processingequipment based on machine vision | |
| CN115770988A (en) | Intelligent welding robot teaching method based on point cloud environment understanding | |
| CN107976201A (en) | A kind of method that machining path is automatically generated based on face battle array 3D cameras | |
| CN109900722B (en) | Method and system for acquiring glass cambered surface image and application | |
| CN110059374B (en) | Milling force modeling method based on cutter bounce and abrasion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |