TW201227158A - Knife sharpening image inspection system of multi-axis tool grinder - Google Patents

Abstract

A knife sharpening image inspection system of a multi-axis tool grinder is disclosed, which is installed with a tool grinder, a machine vision device and a human-machine interface processing device. The tool grinder is installed with a controller. The machine vision device is assembled on the tool grinder and is installed with a fixture tool and an image capturing module. The image capturing module is combined with the fixture tool and is installed with a video camera, a lens and a light source module. The human-machine interface processing device is respectively connected to the tool grinder and the machine vision device and is installed with a computer. The computer is electrically connected to the video camera, and is installed with an image processing module and a machine coordinate processing module, so as to process images captured by the image capturing module, thereby providing an image inspection system which is convenient to operate, provides real-time monitoring, increases grinding precision and lowers cost.

Description

201227158 VI. Description of the Invention: - Technical Field of the Invention The present invention relates to an image detecting system, and more particularly to an image detecting system for detecting the grinding of a tool of a tool grinding machine. [Prior Art] In recent years, with the rapid development and prosperity of the industry, the cutting technology has also been increasingly improved. The geometry accuracy of the tool has been improved for the high precision of processing various mechanical parts and the requirements and requirements of Xiaoyi's production efficiency. It is one of the keys to the cutting quality of the shirt, and the quality of the tool depends on the knife grinding of the tool. It is also the key to determine the geometric accuracy and cutting performance of the tool. It can directly affect the tool's sexuality. Phase, tool life, cutting accuracy, cutting efficiency, cutting surface quality, etc.; however, 'the tool has precision problems before and after grinding. In the process of tool grinding, the grinding wheel will also cause grinding. The accuracy error of the tool • Therefore, after the tool is milled, the tool must be disassembled and installed to a tool to detect the J wind D in the detection, so that the grinding precision of the tool is connected, " Required, so the existing tool is grinding

After the tool has to be removed and placed in -, 目, 丨MAA,.,, ^ Detecting machine for size inspection 1 so that the grinding and testing of existing tools must be separated, red and green, the soil is effective in the grinding process In the instant 仃,·,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, Improve it. 201227158 SUMMARY OF THE INVENTION Accordingly, the present invention has finally developed a present invention which can improve the existing defects in view of the lack of continuous testing and research to detect the lack of grinding precision of the tool. The invention mainly provides a multi-axis tool grinder tool grinding image detecting system, which can instantly detect the grinding precision of the tool through image processing and measuring method, providing a convenient operation, real-time monitoring and improving grinding precision and The target of the cost-reducing image detection system. Based on the above object, the main technical means of the present invention is to provide a multi-axis tool grinder tool grinding image detecting system, which is provided with a tool grinding machine, a machine vision device and a human machine interface processing device, wherein: the tool grinding machine is on the main shaft and works. a fixture for holding a tool is provided between the table, the tool grinding machine is provided with a controller for controlling the operation of each shaft and having a transmission interface; the machine vision device is detachably assembled on the tool grinding machine and provided with a clamping And an image capturing set, the clamping fixture is detachably coupled to a spindle of the tool grinding machine, the clamping fixture is provided with an extension seat toward the table; and the image capturing assembly is combined with the clamping fixture And a camera, a lens and a light source group. The camera is fixed on the extension and is provided with a transmission interface. The lens is combined with the camera and faces the worktable. The light source group provides the lens. a light source; and 201227158, the human-machine interface processing device is respectively connected to the tool grinder and the machine vision device and is provided with an electric 'The computer is electrically connected to the controller and the camera, and reminds the user of the operation process in the manner of the graphic teaching. The computer has an image processing module and a mechanical seat 4, and The image processing module is provided with a video computing program for transmitting the digital image obtained by the machine vision device to the computer through the transmission interface of the camera, and the mechanical coordinate processing module is The controller is electrically connected, and the mechanical coordinate signal generated by the movement of each axis of the tool grinder is captured through the transmission interface of the controller, and the captured mechanical seat signal is displayed on the screen of the computer and performed. Image detection. Further, the image capturing system performs image superimposition on the captured digital image to perform cutting, thereby obtaining a detected area of the tool to be tested, and performing binarization processing and morphological operation on the detected area. Further, the image capturing group finds the boundary of the tool contour to be measured by the Sober operator and the continuous Huo conversion to measure the straight line edge of the tool diameter, and uses the least square method to obtain the round fox of the tool to be tested. Center and radius. Preferably, the mechanical coordinate processing module calculates a geometric dimension of the tool to be tested by moving the center cross line on the continuous image. Preferably, the tool grinding machine is provided on each side of the main shaft with a nozzle oil pipe extending horizontally above the tool grinding table, 201227158, and both ends of the clamp/sigma are detachably coupled with the two injections. The catheter is combined. Preferably, the transmission interface of the controller is an Ethernet transmission interface, and the controller transmits and communicates signals with the mechanical coordinate processing module through the Tcp/|p communication protocol, and the camera The transmission interface is a pass-through interface for EEE 1394b. In the middle of the car, the Izumi fixture is provided at the middle section near the extension seat, so that the fixture can be conveniently installed on the tool grinding machine. Preferably, the side camera is a progressive scanning camera, and the lens is a object side telecentric lens having a small volume and a low image distortion rate. Preferably, the light source assembly is a front-illuminated light source group coupled to the extension base and located at the front end of the lens. The front-illuminated light source assembly is provided with an annular light source for front surface illumination detecting tool surface features. Preferably, the xenon source group is a back-illuminated light source set on a workbench, and the back-illuminated light source set is provided with a diffused backlight that produces a contrasting object contour. The above-mentioned technical means 'the multi-axis tool grinder tool grinding image detecting system of the present invention has at least the following advantages and effects: 1_The multi-axis tool grinding machine tool grinding image detecting system of the invention only needs to be treated when detecting the tool The tool is placed on the fixture of the tool grinder, and the tool can be easily detected through the detection mode of the man-machine interface processing device. The detection mode of the man-machine interface processing device can be divided into a mechanical coordinate detection mode and Image analysis mode, 201227158 The mechanical coordinate mode mainly uses the tool grinder to move the image pickup group, records the mechanical coordinate data of different positions of the tool through the controller, and obtains the tool to be tested through the operation of the mechanical coordinate processing module. The basic shape of the outer diameter, the helix angle, the chamfer, etc. = and the image analysis mode is to calculate the geometric shape of the tool to be tested through the image calculation program. 2. The multi-axis tool grinder tool grinding image detecting system of the invention can detect the geometrical dimensions of the tool on the line in real time without removing the tool and assembling it on a detecting machine for size detection, which can be conveniently and quickly Correcting and re-grinding the tool on the line not only greatly improves the grinding accuracy of the tool, but also reduces material waste and reduces processing costs. J Agriculture buys: · The multi-axis tool grinder tool grinding machine interface processing device of the present invention can teach the instruction to use the use of the process, so that the operator can easily learn the detection process. [Embodiment] In order to understand the technical features and practical effects of the present invention in detail, and in accordance with the contents of the specification, the detailed description of the preferred embodiment of the present invention will be described in detail. Figure: Two: Γ:]: Two grinding machine tool grinding image detection system is equipped with a grinding machine 10, a machine vision installation i 2 〇Λ _ interface processing device 30, wherein: - human machine tool grinding machine 1. Material - five-axis ^ grinder, the five-sleeve tool 7 201227158 grinder contains three linear axes (X, Y and z axes) and two rotating axes (c and A axes) 'The tool grinder 10 is on the main shaft 11 (on the z-axis The two sides of the direction are respectively provided with a fuel injection pipe 13 extending horizontally above the tool grinding machine 1 〇 table 12 (located on the XY axis plane), and the tool grinding machine 10 is provided with a tool for clamping the tool. The jig 14 is configured to be disposed between the main shaft 11 of the stencil tool grinder 10 and the table 12, wherein the tool 50 to be tested can be an end mill, a reamer or a drill bit. The tool grinder 10 is further provided with a controller 15 for controlling the linear shaft and the rotating shaft of the tool grinder 10, and the controller 15 is provided with an Ethernet transmission interface, preferably The controller 15 transmits and communicates signals through a TCP/IP protocol and has four ports. The working distance of the tool grinding machine is about 200 to 380 mm (mm), and the positioning accuracy is 4 micron (in m) 'reproducibility accuracy of 3 microns ("m); § myo machine vision device 20 0 Disassembled and assembled on the tool grinding machine 10 and provided with a clamping fixture 21 and an image capturing group 22, the two ends of the clamping fixture 21 are detachably coupled with the two injection conduits 13 of the tool grinding machine 1 In combination, the fixture 2 is further provided with an extension seat 23 in the direction of the table. Preferably, the fixture 21 is provided with a quick release device 24 near the middle portion of the extension seat 23, so that the fixture The jig 21 can be conveniently mounted on the tool grinder 1 , and the image capturing set 22 is combined with the jig 21 and is provided with a camera 25 , a lens 26 and a light source set 27 ' wherein the camera 21 It is fixed on the extension seat 23 of the fixture 21 and is provided with an EEE 139 transmission medium 201227158 surface. Preferably, the camera 25 is an electric coupling element camera (Charge-Coupled Device Camera; CCD Camera). 'Preferably' the camera 25 is a progressive scan CCD camera, which has the advantage that a complete picture can be captured at the same time 'no blurring due to object movement Image suitable for shooting in a dynamic environment; the lens 2 6 Combined with the camera 25 and facing the tool

The table 1 2 ' of the grinding machine 10 is preferably a lens-side telecentric lens having a small volume and a low image distortion rate (Te|ecentrjc)

The light source group 27 is configured to provide the lens 26 as a light source, so that the lens 26 can capture a digital image of the tool 50 to be tested. Preferably, the light source group 27 can be associated with the extension seat 23. Preferably, the front-illuminated light source group is provided with an annular light source 271, and the annular light source is 271, which is combined with the lens-based light source group or the back-illuminated light source group located on the table 12. The 271 series can detect the surface characteristics of the tool 5 正面 front light, and it is tested by red, green and blue light source. The image of the metal surface illuminated by red light is more obvious. Therefore, the ring-shaped red light-emitting diode can be used. (LED) light source, preferably, the δ Xuan back-illuminated light source group is provided with a diffused backlight board 272 which can generate a contrasting object wheel line, which is used for object size detection, so the backlight illumination mode is used to detect the tool 5Q. The diameter, the radius of the arc, and the angle may be used as a red light-emitting diode (LED) light-emitting plate 272; and 'the human-machine interface processing device 30 is respectively associated with the tool grinder 忉201227158 and the machine vision assembly 20 Connected and provided with a computer 31, which is connected to the controller 15 of the tool and the camera 25 of the machine vision device, and the camera 25 of the machine vision device. The user operation flow is shaken in a graphical teaching manner, and the image processing module 32 and a mechanical coordinate unit _ ^ . , the Wang Wang group 33, the scene & image processing mode The group 32 is provided with an image computing shoe 9 private 321 in which the digital image taken by the machine vision device 2 is transmitted to the image processing mode of the computer 31 via the transmission interface ❿ (iEEE 1394b) of the camera 25. In the group π, 'there are more than 4 unnecessary noises and defects in the original image in the sentence, or the special wind in the original image is not awkward. So you must enter: Step analysis and processing of the image Therefore, the image processing module 321 can process the original image to obtain the more detailed image information of the tool to be tested 50; wherein the figure can be as shown in Figure 3; The digital images captured by the capture group 22 are superimposed and then cut. dJ is wrong to obtain the area to be tested 50 - the area to be detected (Region of | nterest · " wrest, RCM), so that the image operation spear type 3 2 1 only need to be for this part of the hook, the sundial The image processing is performed in the area of the under-detection of the U-knife, which not only improves the image transfer, but also reduces the efficiency of the image operation program 321 and reduces the amount of calculation of the image calculation program 321 The detected area (R〇|) is binarized and morphologically operated; wherein the binarization processing is one of the most important methods in the division of the jersey, and 丄π is performed in the image segmentation. The image is segmented before the analysis - + βρ Υ J shows the image segmentation, mainly as shown in Figure 4. A picture is divided into two UJ 1U pixels from the pixels in the image (MxN pixels, such as 1296x966). The ethnic group, with a gray-scale threshold value I0 201227158 distinguishes the target object from the background 'to achieve the purpose of image segmentation, using the histogram to obtain the critical value (τ0) ' and the critical threshold (Γ. The image is binarized as a reference, wherein when the gray level 像素 of the pixel in the image is greater than the critical value (〇 〇), the gray level 该 of the point becomes 255, and vice versa, when the gray level of the image is less than the critical value ( Γ0), the grayscale value becomes 〇, where the image grayscale value function is as shown in equation (1): /(〇,〇) /(],〇) /(〇,1) /(U)

/(Μ-1,0) /(HI) where X and y represent spatial coordinates, and the f-value of any point (x, 乂) represents the grayscale value of the image at that point; the morphological operation contains expansion (Dilation ), Erosion, Disconnect (0penjng), and Close (c|〇sing)

The method obtains a digital image corresponding to the actual appearance contour and size of the tool 5 by means of two-dimensional image calculation, and can be operated by a Sober operator (s〇be丨〇perat) as shown in equation (2) 〇r) Find the intensity of the grayscale value function gradient of the image: 2 2 Sfk y) 5f(x,y) V .dx • -do _ dx dy (2) where 匕 is the operator that calculates the horizontal gradient, Gy is Calculate the operator of the vertical gradient. Therefore, by appropriately selecting the values in the mask 匕 and Gy, the grayscale values of the vertical and vertical changes can be expressed, that is, 201227158 realizes the edge description of the tool 50 to be tested, and the image can be parsed. The part with high contrast and the outline or feature of the object, so that the original image passes

After the operation of the Gx and Gy horizontal vertical gradient operators, significant edge results can be obtained. Furthermore, the line segments can be detected by a Hough Transform, which includes two main forms, one of which The system is expressed by the slope, and the other is expressed by the angle and the distance. The representation is as shown in equations (3) and (4): y = mx + b (3) R = xcos0 + >&gt ;sin0 (4) where m is the slope, and its computational advantage is that even if there is a break in the line segment or the interference of the noise still does not affect the line segment, the line can also be represented by two parameters R and Θ, and the line is straight to the original The vertical distance of the point, where 0 is the intersection angle of the vertical line of the line and the χ axis, can be used to solve the problem that the value of m is infinite; therefore, it is utilized. Hessau Yunzhenzi (S〇be| 〇perat〇r) and the Hough Transform (Hough Transform) can be found as shown in Figure 5 = 50 rounds of temple boundaries for tool 5 〇 diameter or edge straight line Measure 'and can use the Least Square Method (this method is not explained in the prior art), as shown in Figure 6, to find the center and radius of the arc of the tool 50 to be tested; After the operation of the image calculation program 321 , the image taken by the 201227158 machine vision device 20 can be processed and transmitted through the distance of the image point to the point, the distance from the point to the line, the parallel distance between the two points, and The formula of the central angle intersecting the two lines and the formula of the tool 50 as shown in Fig. 7 (including the outer diameter of the tool to be tested, the radius of the semicircle, the chamfer, the axial relief angle, the axis The mechanical coordinate processing module 33 is electrically connected to the controller 15 of the tool grinder 1 ' the mechanical coordinate processing module 33 is transmitted through the transmission interface of the controller 15 (Ethe_) and take the second to the tool grinder. The mechanical coordinates generated by the movement of each axis (X, Y'X, q A axis). The ceremony number is displayed on the screen 311 of the computer on the screen 311 of the computer. The camera 25 continuously captures the image on the screen 31 of the computer 31, and a continuous cross line is placed on the continuous image. By moving the center + Fengqi's ancient ten-line method, you can calculate the geometry of the tool to be tested 5Q as shown in Figure 8 (including the outer diameter, chamfer, and chamfer width of the tool to be tested (height). , the drill tip angle, the helix angle and the axial distance (gap) gap angle, etc. == The difference between the two mechanical coordinate processing module 33 and the image processing module 33 is that the mechanical coordinate processing module: Image monitoring, and the image processing module 32 has the form of early-image capture and motion image overlay. 13 [S] 201227158 By the above technical means, the tool grinder tool grinding image detecting system of the present invention detects the tool At 50 o'clock, the image processing module 32 and the mechanical coordinate processing module 33 of the human interface processing device 30 are first corrected, and the Scaling Factor of the system is obtained as shown in FIG. 9 to make the corrected image. Processing module 32 and The tool coordinate processing module 33 can accurately detect the geometric value of the tool 50 to be tested, which is shown in Tables 1 to 8, which is the outer diameter of the point-to-point distance of the mechanical coordinate processing module of the tool tool of the present invention. Test result error percentage No. Measurement value average value error 1 1.009 1.008 1.001 -0.007 -0.50% 2 1.009 0.998 -0.010 3 1.008 1.008 0.000 4 1.007 1.003 -0.005 5 1.007 1.005 -0.003 Table 1, mechanical coordinates of the invention Comparison table between the processing module and a tool microscope (outer diameter of the point-to-point distance). Note: Unit: mm (mm)

A comparison table between the test results of the mechanical coordinate processing module 33 of the grinder tool image inspection system and the test results of a tool microscope (OLYMPUS STM6). 14 201227158 Tool microscope measurement result No. Measurement value average 佶1 1.009 1.008 2 1.009 3 1.008 4 1.007 5 1.007 Table 2 Mechanical coordinate processing module measurement value ------- __ Error 0.998 -0.010 1.005 - 0.003 1.010 0.002 1.003 -0.005 1.014 0.006 -0.20% error percentage outer diameter). Note · · Unit: metric ((7) called tool microscope measurement results

Measurement value 1.009 2 1.008 1.008 4 5 1.007 1.007 Table 3. The mechanical coordinate processing module of the present invention and the outer diameter of one. Note · Zhuo position: mm ((7) is called mechanical coordinate processing module point-to-point parallel distance outer diameter detection 0.998 1.002 1.009 0.995 1.011 error percentage error -0.010 -0.006 0.001 -0.013 0.003 -0.50% tool microscope test results comparison table (point to point Parallel distance

Comparison table with microscopic test results (two straight intersecting angles 39.57 Table 4, mechanical coordinate processing module of the present invention and chamfering) Note: unit degree 201227158 tool microscope measurement result mechanical coordinate processing module two straight line intersection central angle detection The wrong dust, :, 丨 丨 error percentage No. Measured value average measured value error 1 119.89 120.63 032~~~ 2 121.09 120.94 0.63 3 120.29 120.31 120.56 0.25 0.34% 4 119.73 121.11 0.80 ~ 5 120.53 120.31 0.00 drill tip · corner). Note: Unit ceggrree ------- Tool Microscope Measurement Results Mechanical Coordinate Processing Module Helical Mu Detection No. Measured Value Average Measured Value Error 1 34.89 35.38 0.49 A 2 34.89 34.93 0.04 3 34.90 34.89 35.18 0.29 ~ 4 34.89 34.80 -0.09 5 Main C · Upper 34.88 35.16 0.27 Error percentage 0-57% L The mechanical coordinate of the invention is different from the age of the _ Wang 贱 fiber side wire ( ··罝你H^r^rack TM f Note · ·Single degree tool microscope measurement result Mechanical coordinate processing module Two straight line intersecting angle of the gap detection No. Measured value average measurement error 1 4.52 4.94 5.20 0.26 _2 4.99 5.24 0.30 3 5.20 5.42 0.48 4 5.34 5.62 0.68 5 4.65 5.57 0.63 谟% difference 9 •51% Note·Unit degree 16 201227158

Tool microscope measurement results

No. 4 Measured value 14.51 14.26 14.52 14.53 14.85 Mechanical coordinate mode Check the clearance angle of the two straight intersecting angles - _ Measured error percentage average 14.53 Measured value 15.40 15.19 15.04 ___J5134_ 15.13 Error 0.87 0.66 0.51 0.81 0.60 4.72% Table 8, The mechanical coordinate processing module of the present invention - the remaining angle of the angle note: the unit light ee ~ money mirror inspection of the fruit of the fruit (the two lines intersect and the detection result obtained by the image processing module 32 is compared with Tables 9 to 16: Measuring device measurement results eight (eight), xu clothing ^ ^ I u rr] small image processing module. Point-to-point clamp outside detection error percentage No. measurement value average value 硎 value error 1 1.007 1.007 1.005 -0.002 -0.22% 2 1.008 1.005 -0.002 3 1.006 1.006 -0.001 4 1.007 1.004 -0.003 5 1.008 1005 -0.002 Table 9, Benfaqing processing module and __ quantity; record of occupational testing wire Table (outer diameter of the point distance) Note: Unit: mm (mm) 17 201227158 Measurement device measurement results Image processing module point to line distance 隹 outer diameter detection error percentage No. measurement value average value Measured value Error 1 1.007 1.012 0.005 2 1.008 1.012 0.005 3 Γ 1.006 1.007 1.010 Γ 0.003 0.38% 4 1.007 1.010 0.003 5 1.008 1.011 0.004 Table 10, comparison table of the detection results of the image processing module and a measuring device of the present invention (point-to-straight distance) Outer diameter). Note: Unit: mm (mmj

Measuring device measurement result Image processing module Point-to-point axis parallel distance outer diameter detection error percentage No. Measurement value average measurement value error 1 1.007 1.007 1.009 0.002 0.42% 2 1.008 1.013 0.006 3 1.006 1.009 0.002 4 1.007 1.013 0.006 5 1.008 1.013 0.006 Table 11. Comparison table between the detection results of the image processing module and a measuring device of the present invention (outer diameter of the parallel distance of the point-to-point axis). Note: unit: mm (mm) I8 2〇l227l58

Average value 40.30 Measuring device measurement result Image processing module Two-line intersection angle detection chamfer detection measurement value 40.64 40.75 40.38 40.26 40.92 Error percentage error 0.34 0.45 0.08 -0.04 0.62 0.72% 12 'The image processing module of the present invention A comparison table of the detection results of a measuring device (the chamfer of the intersection angle of the two straight lines). Note: Unit competition

^---|——-- ---- Measurement device measurement results Image processing module two straight phase wins S check Pan I's dust S detection error percentage No. ----_ 1 --- 2 Value average value error 120.91 121.02 120.56 -0.46 -0.06% 120.62 -0.40 3 120.91 121.19 0.17 4 121.13 121.34 0.32 __5 121.12 121.04 0.02 Table 13. Comparison of the detection results of the image processing module and a measuring device of the present invention Table (drill tip and angle of the intersection of two straight lines). Note: When you are in the factory

Measuring device measurement results Image processing module Two linear phase $ class angle of the gap detection error percentage No. Measurement value average value error 1 5.10 5.33 0.25 2 5.02 5.35 0.27 3 5.12 5.08 5.23 0.15 4.68% 4 5.15 5.28 0.20 5 5.02 5.41 0.33 Table 14. Comparison table between the detection results of the image processing module and the measuring device of the present invention (the angle of the intersection of the two lines intersecting each other). Note: Unit 19 201227158 Measuring device measurement results Image processing module The angle of the gap between the two straight intersecting angles Error percentage No. The measured value average measured value error 1 15.57 15.58 15.75 0.17 1.00% 2 15.63 15.59 '0.01 3 15.52 15.80 0.22 4 15.50 15.82 0.24 5 15.68 15.72 0.14 Table 15. Comparison table of the detection results of the image processing module and a measuring device of the present invention (the clearance angle of the intersecting angle between the two lines). Note: unit ctegree measuring device measurement result image processing module minimum flat method arc radius detection error percentage No. measurement value average measurement value error 1 2.010 1.996 -0.013 2 2.009 1.991 -0.018 3 2.009 2.009 1.985 -0.024 -0.96% 4 2.007 1.995 -0.014 5 2.009 1.981 -0.028 Table 16. Comparison table (arc radius) of the detection results of the image processing module and a measuring device of the present invention. Note: Unit: mm (mm) By the above technical means, the tool grinder tool grinding of the present invention

The image detecting system can quickly and conveniently assemble the machine vision device 20 onto the tool grinder 10 without damaging the structure of the tool grinder 10, and can pass through the integrated software and hardware. The interactive processing and verification mode of the image processing module 32 and the mechanical coordinate processing module 33 of the human interface processing device 30 can instantly detect the size of the tool 50 to be tested on the line, and can monitor the tool 50 at any time. Grinding accuracy not only reduces the cost of failure during the grinding process, but also allows the operator to follow the steps to complete the 5G inspection of the tool by means of easy-to-understand graphical teaching, thus effectively improving the complicated operation of the existing tool testing equipment. The process, in turn, the application of digital image processing technology can greatly reduce the error in human operation, and thus effectively provide a multi-axis tool grinding tool grinding image detection system that can be easily operated, monitored, improved in grinding precision and reduced in cost. The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any one of ordinary skill in the art may be utilized without departing from the scope of the present invention. Equivalent embodiments of the present invention may be made without departing from the technical scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a schematic view showing the structure configuration of a multi-axis tool grinder tool grinding image detecting system of the present invention. Fig. 2 is a block diagram showing the operation of the multi-axis tool grinder tool grinding image detecting system of the present invention. Figure 3 is a schematic illustration of the operation of the present invention for cutting a detected area of a tool digital image. Figure 4 is a schematic illustration of a digital image of a tantalum array of the present invention. Fig. 5 is a flow chart showing the detection of the edge line of the contour boundary of the tool to be tested by the Sober operator and the Huo-style conversion. Fig. 6 is a flow chart showing the detection of the center and radius of the arc of the tool to be tested by the Sober operator and the least squares method. S ] 201227158 Figure 7 is a schematic diagram of the geometrical dimensions of the tool to be tested after the operation of the image processing module. FIG. 8 is a schematic diagram of the geometric size of the tool to be tested after the operation of the mechanical coordinate processing module of the present invention. Figure 9 is a block diagram showing the correction of the present invention prior to tool inspection.

[Explanation of main component symbols] 10 Tool grinding machine 11 Spindle 12 Workbench 13 Fuel injection pipe 14 Clamp 15 Controller 20 Machine vision device 21 Fixture 22 Image capture group 23 Extension seat 24 Quick release device 25 Camera 26 Lens 27 Light source group 271 Ring light source 272 diffusion backlight 30 human interface processing device 31 computer 311 screen 32 image processing module 321 image calculation program 33 mechanical coordinate processing module 50 tool 22

Claims (1)

201227158 VII. Patent application scope: 1_ A multi-axis tool grinding machine tool grinding image detection system, which comprises a tool grinding machine, a machine vision device and a human machine interface processing device, wherein: the tool grinding machine is provided between the main shaft and the work table. a fixture for holding a tool, the tool grinding machine is provided with a controller for controlling each shaft and having a transmission interface; the machine vision device is detachably assembled on the tool grinding machine and is provided with a clamp and an image a drawing set, the clamping fixture is detachably coupled with a spindle of the tool grinding machine, wherein the clamping fixture is provided with an extension seat toward the table, and the image capturing assembly is combined with the clamping fixture and a camera is provided a lens and a light source group, the camera is fixed on the 戎 extension and is provided with a transmission interface, the lens is combined with the camera and faces the worktable, the light source group provides the lens and a light source; The human interface processing device is respectively connected to the tool grinder and the machine view device and is provided with a computer, and the computer The controller and the camera are electrically connected and remind the user to operate in a graphical manner. The computer is provided with an image processing module and a mechanical center; the image processing module The image computing program for transmitting the digital image obtained by the device viewing device to the computer for image processing is transmitted through the transmission interface of the camera, and the mechanical coordinate processing module is associated with the controller. Electrical connection, and 23 201227158 Through the transmission interface of the controller, the mechanical coordinate signal generated by the movement of each axis of the tool grinding machine is captured, and the captured mechanical seat signal is not displayed on the screen of the computer and the image is performed. Detection. 2. The multi-axis tool grinder tool grinding image detecting system according to claim 1, wherein the image capturing system performs image superimposition on the captured digital image to perform cutting, thereby obtaining a detected area of the tool to be tested. Binary processing and morphological operations are performed on the detected region. 3- Multi-axis tool grinder tool grinding image detection system as described in claim 2, wherein the image capturing group finds the boundary of the tool profile to be tested for tool diameter or edge through the Sober operator and the Hawker transformation The measurement of the straight line is performed, and the center and radius of the rounded corner of the tool to be tested are obtained by the least square method. 4: The multi-axis tool grinder tool grinding image spur system according to the claim 3, wherein the mechanical coordinate processing module is drawn on the continuous image by a central cross line 'transparent by moving the center cross line The geometry of the tool to be tested. 5 multi-axis tool grinder tool grinding image loosening system described in item 4, wherein the far-reaching tool grinding machine is respectively provided on both sides of the main shaft: the front side, the flat-spreading oil sprayed on the tool grinding table The catheter, and the two ends of the distal fixture are detachably combined with the two injection conduits. The multi-axis tool grinder tool described in Chang 5 is used to detect the image of the interface. The transmission interface of the controller is a transmission interface of Ethernet 24 201227158, B - and the remote controller communicates with the machine through the TCP/IP protocol. The 4 h chess group coordinates the transmission and communication of the signal, and the camera's interface is the transmission interface of the ""丨EEE i394b. ° month to find the multi-axis tool grinder tool grinding image detection system described in the sixth, complex ±, "T the clamp is located near the middle of the extension seat, and there is a demolition device, making the central fixture convenient The ground is installed on the tool grinder. Into, 8_, for example, the multi-axis tool grinder tool grinding image m described in $7, wherein the camera system is a progressive scanning camera, and the head is - volume Small object-side telecentric lens with low image distortion rate. The multi-axis tool grinder tool grinding image as described in Item 8 is first combined with the extension seat and: = front-illuminated light source group at the front end of the lens, the front-illuminated light source group is provided with an annular light source capable of frontal illumination to detect the surface features of the tool. 〇. The multi-axis tool grinding machine tool grinding image described in Item 8 is First, the s Xuan source group is a back-illuminated light source group located on the workbench, and the back-illuminated light source group is provided with a diffused backlight panel of the object rim line. Strong "', as described in claim 1 Multi-wheel tool grinder tool grinding image detection system The image capturing group uses the Sober operator and the Huo-style conversion to find the boundary of the contour of the blade to be tested for the tool diameter or the edge line _, and uses the least square method to determine the center of the arc of the tool to be tested and radius. 25 201227158 12, as claimed in the claim, the multi-axis tool grinder tool grinds the image of the system, wherein the mechanical coordinate processing module is connected to the continuous image in the straight line to the cross line, by moving the center cross line, The geometry of the tool to be tested out of the nose. 13. If the request item is described, the multi-axis tool grinder tool grinding image is 'system'. The tool grinding machine is respectively provided on both sides of the main shaft: a spray that is horizontally extended above the work surface of the tool grinder An oil conduit, and both ends of the fixture are detachably coupled to the two fuel injection conduits. The multi-axis tool grinder tool grinding image inspection system described in Item 1 wherein the transmission interface of the controller is an Ethernet transmission interface and the controller communicates with the machine through the TC p /丨p communication protocol. The coordinate processing module transmits and communicates signals, and the transmission interface of the camera is an EEE 1394b transmission interface. 1 5. The multi-axis tool grinder tool grinding image detecting system described in claim ' wherein the clamping device is provided with a quick-release device at a middle portion adjacent to the extension seat, so that the clamping device can be conveniently installed On the work odor grinder. 1 6 The multi-axis tool grinder tool grinding image detecting system according to claim 1, wherein the camera is a progressive scanning camera, and the lens is a object-side telecentric lens with a small volume and low image distortion rate. . The multi-axis tool grinder tool grinding image detecting system according to claim 1, wherein the light source group is combined with the extension seat, true js] 26 201227158 a front-illuminated light source group located at the front end of the lens, The front-illuminated light source set is provided with an annular light source that can frontally illuminate the surface features of the tool. The multi-axis tool grinder tool grinding image detecting system according to claim 1, wherein the light source group is a back-illuminated light source group located on the worktable, and the back-illuminated light source group is provided with a contrast A diffused backlight of a strong object outline. Eight, schema: (such as the next page) 27