Image processing device

Abstract

This image processing device comprises: a reception unit that receives, from a machine-tool camera, a captured image of a tool; an area computation unit that calculates a surplus area which is the area of the region, among regions corresponding to the tool, of a portion that is separated from the tool center by at least a prescribed distance; and an examination unit that, on the basis of the size of the surplus area, determines whether it is appropriate to continuously use the tool.

Description

Technical Field

[0001] The present invention relates to an inspection technique for tools in machine tools.

Background Art

[0002] Machine tools include devices for cutting a workpiece into a desired shape and devices for creating a workpiece by laminating metal powder or the like. Machine tools for cutting include a turning center that processes a workpiece by applying a cutting tool to a rotating workpiece, a machining center that processes a workpiece by applying a rotating tool to a workpiece, and a compound machining machine that combines these functions.

[0003] A tool is fixed to a tool holding part such as a spindle or a tool post. The machine tool processes the workpiece while moving the tool holding part while exchanging the tools according to a previously prepared machining program.

[0004] String-like chips scatter from the workpiece being processed, and these may wrap around the tool. A tool wrapped with chips needs to be exchanged with another tool of the same type. After the exchange, machining is continued with the new tool. After the work is completed, the operator removes the chips from the tool (see Patent Document 1).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] If only a small amount of chips are wrapped around the tool, it is often possible to continue using the tool. Small amounts of chips often detach naturally from the tool during spindle movement. Since tool replacement takes time, it is necessary to appropriately determine whether or not to replace the tool based on the amount of chips wrapped around it (hereinafter referred to as "amount of chips wrapped around the tool"). [Means for solving the problem]

[0007] An image processing apparatus in one aspect of the present invention includes a receiving unit that receives an image of a tool from a camera, an area calculation unit that calculates a surplus area, which is the area of ​​the region in the image corresponding to the tool that is located at or beyond a predetermined distance from the center of the tool, and an inspection unit that determines whether the tool is suitable for continued use based on the size of the surplus area.

[0008] An image processing apparatus in another aspect of the present invention includes a receiving unit that receives multiple captured images from a camera, where the camera and the tool move relative to each other with respect to the longitudinal direction of the tool; a calculation unit that calculates the number of differences between each of the multiple captured images, a first region including the region corresponding to the tool in the captured image, and a second region including the region corresponding to the tool in a reference image; and an inspection unit that determines whether the tool is suitable for continued use based on the number of differences in each of the multiple captured images. [Effects of the Invention]

[0009] According to the present invention, it becomes easier to appropriately determine whether or not tool replacement is necessary based on the amount of wrapping. [Brief explanation of the drawing]

[0010] [Figure 1] This is an external view of a machine tool. [Figure 2] This is a schematic diagram showing the positional relationship between the tool, camera, and lighting device in the tool recognition area. [Figure 3] This is a hardware configuration diagram of a machine tool and an image processing device. [Figure 4] This is a functional block diagram of an image processing device. [Figure 5]It is a schematic diagram showing the positional relationship between the tool and the imaging area. [Figure 6] It is a schematic diagram of the imaging image during the preliminary inspection. [Figure 7] It is a schematic diagram for explaining the method of calculating the number of black pixels of the reference tool during the preliminary inspection. [Figure 8] It is a schematic diagram of the imaging image during the winding inspection. [Figure 9] It is a schematic diagram for explaining the method of calculating the number of black pixels of the tool used during the winding inspection. [Figure 10] It is a screen diagram of the reference tool imaging screen. [Figure 11] It is a screen diagram of the tool used imaging screen. [Figure 12] It is a graph showing the relationship between the winding amount and the number of black pixels. [Figure 13] It is a graph showing the relationship between the winding amount and the differential number of pixels. [Figure 14] It is a flowchart showing the processing process of the winding inspection. [Figure 15] It is a flowchart showing the details of the image inspection in S26 of FIG. 14. [Figure 16] It is a schematic diagram of the imaging image during the preliminary inspection in the modification example. [Figure 17] It is a screen diagram of the inspection setting screen. [Figure 18] It is the first screen diagram of the tool used imaging screen in the modification example. [Figure 19] It is the second screen diagram of the tool used imaging screen in the modification example. [Figure 20] It is the third screen diagram of the tool used imaging screen in the modification example.

Embodiments for Carrying Out the Invention

[0011] FIG. 1 is an external view of the machine tool 100. The machine tool 100 in this embodiment is a multi-tasking machine that processes a workpiece placed within the machining area 200. The workpiece is fixed to the holding part 104 and is cut by a tool 102 attached to a spindle, which is another holding part. The holding part 104 that holds the workpiece is rotationally driven by a drive mechanism.

[0012] When the tool 102 is inserted into the tool recognition area 210, the lower lighting device 108 illuminates the tool 102, and the upper camera 106 captures an image of the tool 102. Based on the captured image at this time, tool registration, tool inspection, preliminary inspection, and winding inspection, which will be described later, are executed. The configuration of the tool recognition area 210 will be described in more detail in relation to FIG. 2 below.

[0013] The machine tool 100 includes a cover 202 that shields the exterior. The cover 202 includes a door 204. The user opens the door 204 to attach a workpiece to the machining area 200 and remove the workpiece from the machining area 200. The operation panel 206 receives various operations on the machine tool 100 from the operator.

[0014] The operation panel 206 is connected to an image processing device 110. The operator can remotely monitor the working status of the machine tool 100 by the image processing device 110. In this embodiment, the machine tool 100 main body and the image processing device 110 are connected via a wired cable. The image processing device 110 may be formed as an internal device within the machine tool 100, for example, within the operation panel 206.

[0015] The tool storage unit 130 stores a plurality of tools 102. A tool 102 is acquired from the plurality of tools 102 stored in the tool storage unit 130 by a tool changer (described later) and is mounted on the spindle. As shown in FIG. 1, the Y-axis and Z-axis are set in the horizontal direction, and the X-axis is set in the vertical direction. The Z-axis direction corresponds to the axial direction of the spindle and the workpiece.

[0016] FIG. 2 is a schematic diagram showing the positional relationship among the tool 102, the camera 106, and the lighting device 108 in the tool recognition area 210. The tool 102 includes a cutting edge 112 used for machining the workpiece and a shank 114 fixed to a holder 118 of the spindle 116. The spindle 116 is configured to be rotatable and movable while holding the tool 102. The spindle 116 can also rotate the tool it holds.

[0017] Camera 106 is equipped with an image sensor such as a CMOS (Complementary Metal Oxide Semiconductor) or a CCD (Charge-Coupled Device). Camera 106 images the tool 102 attached to the spindle 116 from above (in the X-axis direction). Camera 106 is connected to an image processing device 110, and the captured images are transmitted to the image processing device 110. Camera 106 is fixed in the tool recognition area 210. By rotating the tool 102 with the spindle 116 as its axis, the tool 102 can be imaged from multiple directions. In addition, by moving the tool 102 horizontally (in the YZ direction) with the spindle 116, multiple locations on the tool 102 can be imaged.

[0018] An illumination device 108 is fixed below the camera 106, facing it. The illumination device 108 illuminates the tool 102 from below. Through transmitted illumination by the illumination device 108, the camera 106 can acquire a high-contrast image that makes it easy to determine the contour position of the tool 102.

[0019] When a user registers a new tool 102 (hereinafter referred to as "tool registration"), they set the control panel 206 to tool registration mode and attach the new tool 102 to the spindle 116. Next, they enter an arbitrary tool ID. The spindle 116 moves and rotates the tool 102, and the fixed camera 106 automatically images the tool 102 from various positions and directions. From the numerous images obtained by the camera 106, the tool shape is recognized, and the tool ID and tool shape are registered in association. With this control method, the tool shape can be automatically registered and associated with the tool ID for each tool 102. The tool shape is formed as two-dimensional or three-dimensional data. A "preliminary inspection," which is a prerequisite for the wrap-around inspection described later, is also performed during tool registration, but the details will be described later.

[0020] Furthermore, when inspecting the tool 102 during or after machining, the spindle 116 moves the tool 102 into the tool recognition area 210. Similar to the initial registration, the spindle 116 moves and rotates the tool 102, and the camera 106 automatically images the tool 102 from various positions and directions. The tool shape is recognized from the numerous images obtained by the camera 106. Hereinafter, such inspections performed as needed during machining will be referred to as "tool inspections." The operator determines the degree of wear and the presence or absence of defects in the tool 102 by comparing the tool shape data at the time of tool registration with the tool shape data at the time of tool inspection.

[0021] The camera 106 in this embodiment has a resolution of approximately 1 million pixels (1224 x 1024). The imaging area is approximately 300 mm x 300 mm. The camera 106 can acquire up to 80 images per second.

[0022] In this embodiment, the machine tool 100 performs a "chip wrapping inspection" in addition to a tool inspection to determine defects in the tool 102. This inspection checks the amount of chips wrapped around the tool 102. The following description will focus on the chip wrapping inspection.

[0023] Figure 3 is a hardware configuration diagram of the machine tool 100 and the image processing device 110. The machine tool 100 includes an operation control device 120, a machining control device 122, a machining device 124, a tool changing unit 126, and a tool storage unit 130. The machining control device 122, which functions as a numerical control device, transmits control signals to the machining device 124 according to the machining program. The machining device 124 moves the spindle 116 to machine the workpiece according to instructions from the machining control device 122.

[0024] The operation control device 120 includes an operation panel 206 and controls the machining control unit 122. The tool storage unit 130 stores tools. The tool changing unit 126 corresponds to a so-called ATC (Automatic Tool Changer). The tool changing unit 126 retrieves a tool from the tool storage unit 130 and replaces the tool in the spindle 116 with the retrieved tool, according to the exchange instruction from the machining control unit 122.

[0025] The image processing device 110 primarily performs image processing such as tool shape recognition. As described above, the image processing device 110 may be configured as part of the operation control device 120. The image processing device 110 may be a general-purpose laptop PC (Personal Computer) or tablet computer.

[0026] Figure 4 is a functional block diagram of the image processing device 110. Each component of the image processing apparatus 110 is realized by hardware including a CPU (Central Processing Unit) and various computer processors, memory and storage devices, and wired or wireless communication lines connecting them, as well as software stored in the storage devices that supplies processing instructions to the arithmetic units. The computer program may consist of device drivers, an operating system, various application programs located at a higher layer, and libraries that provide common functions to these programs. The blocks described below represent functional units, not hardware units.

[0027] Furthermore, the operation control device 120 and the processing control device 122 may also be implemented on a separate operating system from the image processing device 110, including hardware such as a processor or other arithmetic unit, memory or storage device, and wired or wireless communication lines connecting them, as well as software or programs stored in the storage device that supply processing instructions to the arithmetic unit.

[0028] The image processing device 110 includes a user interface processing unit 140, a data processing unit 142, a communication unit 300, and a data storage unit 144. The user interface processing unit 140 accepts operations from the operator and is responsible for processing related to the user interface, such as displaying images and outputting sound. The communication unit 300 is responsible for communication with the operation control device 120. The data processing unit 142 executes various processes based on the data acquired by the user interface processing unit 140 and the data stored in the data storage unit 144. The data processing unit 142 also functions as an interface for the user interface processing unit 140, the communication unit 300, and the data storage unit 144. The data storage unit 144 stores various programs and setting data.

[0029] The user interface processing unit 140 includes an input unit 146 and an output unit 148. The input unit 146 receives input from the user via hardware devices such as a touch panel, mouse, or keyboard. The output unit 148 provides the user with various information via image display or audio output. The output unit 148 includes the display unit 138. The display unit 138 displays various images on the screen.

[0030] The communication unit 300 includes a receiving unit 304 that receives data from the operation control device 120, and a transmitting unit 306 that transmits data and commands to the operation control device 120.

[0031] The data processing unit 142 includes an area calculation unit 150, an inspection unit 152, a tool change instruction unit 154, and an imaging processing unit 156. The imaging processing unit 156 controls the camera 106 to image the tool 102. The machining control unit 122 moves the spindle 116 directly below the camera 106, and the imaging processing unit 156 images the tool 102. The imaging processing unit 156 can also instruct the machining control unit 122 on the direction of movement of the spindle 116. The inspection unit 152 binarizes the captured image into white pixels and black pixels according to the brightness of each pixel in the captured image. The inspection unit 152 controls tool registration, tool inspection, preliminary inspection, and chip wrapping inspection. The area calculation unit 150 calculates the "excess area," described later, as the amount of chip wrapping around the tool 102 from the captured images obtained during the preliminary inspection and chip wrapping inspection. The inspection unit 152 determines whether the tool can be used again based on the excess area. When the inspection unit 152 determines that the continued use of tool 102 is inappropriate (hereinafter also referred to as "abnormality determination"), the tool change instruction unit 154 instructs the machining control unit 122 to change the tool via the operation control device 120. The machining control unit 122 instructs the tool change unit 126 to change the tool that has been determined to be abnormal.

[0032] Figure 5 is a schematic diagram showing the positional relationship between the tool 102 and the imaging area 170. The imaging area 170 is located directly below the light-receiving surface of the camera 106. The camera 106 images objects within the range of the imaging area 170. The machining control unit 122 inserts the tool 102 into the imaging area 170 by moving the spindle 116. Since the imaging area 170 is smaller than the tool 102, it is not possible to image the entire tool 102 at once.

[0033] If the lens of the camera 106 is enlarged to increase the imaging area 170, it will lead to an increase in the cost of the camera 106. Also, if a large camera 106 is installed in the tool recognition area 210, the space of the machining area 200 will be reduced, which is undesirable. For this reason, in this embodiment, a relatively small camera 106 is used to image the tool 102 in multiple stages, and a method is adopted in which the overall shape of the tool 102 is recognized based on the multiple captured images. Hereafter, an image captured by camera 106 of a portion of tool 102 will be referred to as a "partial image".

[0034] During preliminary inspection and wrap-around inspection, the machining control unit 122 moves the tool 102 (spindle 116) at a constant speed in the positive Z-axis direction, that is, along the longitudinal direction of the tool 102. Here, the longitudinal direction refers to the axial direction of the tool 102. In Figure 5, the longitudinal direction of the tool 102 coincides with the Z-axis direction. Also, in this embodiment, the direction of the tool length of the tool 102 coincides with the longitudinal direction. The imaging processing unit 156 constantly monitors the imaging area 170. The live view image in the imaging area 170 is transmitted from the camera 106 to the image processing device 110.

[0035] Figure 6 is a schematic diagram of the images captured during the preliminary examination. The inspection unit 152 performs a wrap-around inspection on the tool 102 during or after machining at a predetermined timing. The timing of the wrap-around inspection is arbitrary, but in this embodiment, it is explained that the wrap-around inspection is performed when the continuous use time of a certain tool 102A exceeds a predetermined time, for example, 3 minutes. In other words, if tool 102A is replaced with another tool 102B when the continuous use time of tool 102A is 3 minutes or less, the wrap-around inspection of tool 102A is not performed. If an abnormality is determined in the wrap-around inspection of tool 102A, machining is continued after replacing tool 102A with a spare tool 102A of the same type.

[0036] Furthermore, after the tool registration is complete, the inspection unit 152 performs a preliminary inspection, which is a prerequisite for the wrap-around inspection. The contents of the preliminary inspection and the wrap-around inspection are basically the same, but the details will be described later. The inspection unit 152 calculates the amount of wrap-around by comparing the results of the preliminary inspection and the results of the wrap-around inspection, and makes an abnormal / normal determination based on the amount of wrap-around.

[0037] Hereafter, the tool 102 at the time of tool registration, in other words, the tool 102 in a state where no chips are wrapped around it at all, will be called the "reference tool". Also, the tool 102 that is actually used to machine the workpiece after tool registration is complete, in other words, the tool 102 that may have chips wrapped around it, will be called the "tool in use". Figure 6 shows an image taken during a preliminary inspection of a tool 102A1 (one of the A-type tools 102). Hereafter, the X coordinate value of the center line of tool 102A1 will be "X1", and the radius of tool 102A1 will be "R". Therefore, the X coordinate value X2 of the contour line of tool 102A will be "X1 + R".

[0038] After registering tool 102A1, inspection unit 152 performs a preliminary inspection on tool 102A1. Imaging processing unit 156 instructs operation control device 120 to move the spindle 116 linearly in the Z-axis direction. After detecting the tip of the blade portion 112 in the imaging area 170 (live view image), imaging processing unit 156 instructs camera 106 to acquire an image (partial image). Upon receiving the instruction, camera 106 acquires the first partial image and stores it in memory. In Figure 6, the first partial image is acquired at a predetermined starting position P1. The starting position P1 is defined, for example, when the Z distance between the tip of tool 102A1 and the center point of the image reaches a predetermined value.

[0039] After acquiring a partial image at the starting position P1, the machining control unit 122 slowly moves the spindle 116 (tool 102A1) linearly in the positive Z-axis direction. The imaging processing unit 156 continuously acquires partial images in conjunction with the movement of the tool 102A1. The final partial image is acquired at a predetermined ending position P2. The group of partial images obtained from the starting position P1 to the ending position P2 yields an image containing the contour of a part of the cutting edge 112.

[0040] The area calculation unit 150 sets the inspection area Q as part of the imaging range, based on the multiple partial images obtained. The X coordinates of the inspection area correspond to the range of X1 to X3 and Z coordinates Z1 to Z2. The positions of Z1 and Z2 are arbitrary, but it is desirable that Z2 be set to a position that does not include the shank portion 114. The position of X3 is set to an arbitrary position such that X3 > X2 = X1 + R.

[0041] If the camera 106 is wide-angle, the entire inspection area Q may be captured in a single image. If the imaging area 170 is smaller than the camera 106, as in this embodiment, the tool 102 can be imaged multiple times by moving the spindle 116, and the imaging processing unit 156 can synthesize an image corresponding to the inspection area Q from the multiple partial images.

[0042] In preliminary and wrap-around inspections, all or part of the area corresponding to the tool 102 is the target of imaging. In Figure 6, the "area corresponding to the tool 102" may be the entire area of ​​the cutting edge 112 and the shank 114, or it may be at least the area that includes the inspection area Q.

[0043] Figure 7 is a schematic diagram illustrating the method for calculating the number of black pixels in a reference tool during preliminary inspection. The area calculation unit 150 binarizes each pixel of the captured image corresponding to the inspection area Q based on its brightness. In this embodiment, each pixel of the captured image is either a black pixel (black pixel) or a white pixel (white pixel). In the case of a reference tool, the black pixels are the pixels corresponding to the position of the tool 102 (hereinafter referred to as "tool pixels").

[0044] Hereafter, the coordinates (x,z) of pixels in the captured image corresponding to the inspection area Q will be referred to as pixel coordinates. Furthermore, x and z here will be called the X pixel coordinate and the Z pixel coordinate, respectively.

[0045] Let x1 be the X-pixel coordinate corresponding to the central axis of tool 102A1. Assume that there are n black pixels with X-pixel coordinate = x1. In other words, there are n black pixels corresponding to the positions of X-coordinate X1 (central axis) and Z-coordinate Z1 to Z2. The number of black pixels with X-pixel coordinate = x1 + 1 is also n. When the X-pixel coordinate is greater than X2 (=X1 + R), in other words, outside the contour line of tool 102A1, the number of black pixels is 0. This is because there are no objects that appear in the captured image outside of tool 102A1 (see also Figure 6).

[0046] Hereinafter, the number of black pixels detected at the x-pixel coordinate x of the inspection area Q will be denoted as "C(x)". In Figure 7, C(x) = n for X1 ≤ x ≤ X2, and C(x) = 0 for x > X2. In reality, various image noises are generated when imaging the tool 102A1, so C(x) > 0 even for x > X2, but the measurement results including noise will be discussed later in relation to Figures 12 and 13.

[0047] Figure 8 is a schematic diagram of images captured during the entanglement inspection. As explained in relation to Figures 6 and 7, black pixels are identified from the inspection area Q of the tool 102A1. As described above, the inspection unit 152 performs a wrap-around inspection on the tool 102A1 at a predetermined timing.

[0048] Figure 8 shows an image captured during a wrap-around inspection of tool 102A1. Chips 180 are attached to tool 102A1. Even during the wrap-around inspection, the imaging processing unit 156 instructs the operation control device 120 to move tool 102A1 linearly in the Z-axis direction. After detecting the tip of the blade portion 112 in the imaging area 170 (live view image), the imaging processing unit 156 instructs the camera 106 to acquire an image (partial image). Upon receiving the instruction, the camera 106 acquires the first partial image and stores it in memory.

[0049] The machining control unit 122 moves the tool 102A1 in a straight line in the positive Z-axis direction. The imaging processing unit 156 continuously acquires partial images in conjunction with the movement of the tool 102A1. The area calculation unit 150 sets the inspection area Q of the tool 102A in the range of X1 to X3 and Z1 to Z2. The inspection area Q during preliminary inspection and the inspection area Q during wrap-around inspection are the same range.

[0050] In the entanglement inspection, the captured image includes not only the tool 102A1 but also the chips 180. The area calculation unit 150 binarizes the captured image and classifies it into black pixels and white pixels. At this time, most of the black pixels correspond to the tool 102A1, but some correspond to the chips 180.

[0051] Figure 9 is a schematic diagram illustrating the method for calculating the number of black pixels of the tool used during wrap-around inspection. Pixels corresponding to the location of chip 180 are called "chip pixels". For X1≦x≦X2, C(x)=n. This is the same as the reference tool. Black pixels detected in the range X1≦x≦X2 are tool pixels. On the other hand, even for x>X2, in other words, a small number of black pixels are detected outside the contour line of tool 102A1. These are chip pixels corresponding to chip 180. Hereafter, tool pixels detected outside X2 will be called "excess pixels". Most of the excess pixels are chip pixels, but a small number of objects other than chips or noise may also be included. The excess pixel group 190 shown in Figure 9 represents the set of excess pixels. The total number of excess pixels is called the "excess area".

[0052] The area calculation unit 150 calculates the surplus area S1 of the tool 102A1 (reference tool) during the preliminary inspection and the surplus area S2 of the tool 102A1 (tool used) during the wrap-around inspection. The greater the amount of chips 180 wrapped around the tool 102A1, the larger the surplus area S2 becomes. Ideally, as shown in Figure 7, the surplus area S1 of the reference tool is "0".

[0053] A threshold T1 is set in advance. The inspection unit 152 determines tool 102A1 to be "abnormal" when S2 (excess area of ​​the tool used) - S1 (excess area of ​​the reference tool) > threshold T1. In this case, tool 102A1 needs to be replaced with another tool 102A2 of the same type.

[0054] More specifically, first, an image is acquired of the reference tool, targeting the inspection area Q. The area calculation unit 150 acquires the brightness value of each pixel (x, z) included in the image. The area calculation unit 150 counts the number of black pixels whose brightness value is below a predetermined threshold. Next, an image is acquired of the tool being used, targeting the inspection area Q, in the same manner. The area calculation unit 150 acquires the brightness value of each pixel (x, z) included in the image. The area calculation unit 150 counts the number of black pixels whose brightness value is below a predetermined threshold. The inspection unit 152 compares the black pixels of the tool being used with the black pixels of the reference tool coordinate by coordinate and counts the number of differing pixels. The difference at this time corresponds to "S2-S1". Hereinafter, the difference between the excess area S2 and the excess area S1 will be called the "difference in pixel count D" or "difference value D". When the difference value D is greater than or equal to the threshold T1, the amount of wrapping is considered to be very large, and the tool 102A1 is judged to be abnormal (unusable).

[0055] Figure 10 is a screen view of the reference tool imaging screen 230. The imaging processing unit 156 images the tool 102, and the display unit 138 displays the image. The reference tool imaging screen 230 is an image of the reference tool 102 that is free of chips, for example, an image of the reference tool during a preliminary inspection. As described above, the area calculation unit 150 calculates the excess area based on the image. The display unit 138 may display the excess area S1 on the reference tool imaging screen 230.

[0056] Figure 11 is a screen view of the tool imaging screen 220. The tool imaging screen 220 is an image of the tool 102 around which the chips 180 are wrapped. When the tool is imaged during the wrapping inspection, the tool imaging screen 220 is displayed. The area calculation unit 150 also calculates the excess area S2 for the tool. The display unit 138 may display the excess area S2 on the tool imaging screen 220. The display unit 138 of the image processing device 110 can also display the reference tool imaging screen 230 and the tool imaging screen 220 in parallel. In this case, the display unit 138 displays the excess area S1 of the reference tool and the excess area S2 of the tool, as well as the difference value D between them. The operator can freely set the threshold T1 while comparing the reference tool imaging screen 230 (reference tool) and the tool imaging screen 220 corresponding to various wrapping amounts. The input unit 146 receives the input of the threshold T1 and sets it as an internal parameter of the inspection unit 152. Once the threshold T1 is set, the inspection unit 152 determines whether the tool can be used continuously based on the threshold T1.

[0057] Figure 12 is a graph showing the relationship between the amount of wrapping and the number of black pixels. The horizontal axis represents the tool radial direction (X-axis direction), and the vertical axis represents the number of black pixels for each X-pixel coordinate. The black pixels include both tool pixels corresponding to tool 102 and chip pixels corresponding to chip 180. Graph 231 shows the number of black pixels for tool 102A1 with almost no chip wrapped around it. Graph 232 shows the number of black pixels for tool 102A1 with some chip wrapped around it but still usable. Graph 234 shows the number of black pixels for tool 102A1 with a large amount of chip wrapped around it and therefore needs to be replaced. The graphs in Figure 12 correspond to the schematic diagrams shown in Figures 7 and 9.

[0058] As shown in Figure 12, the number of black pixels decreases sharply when the distance from the tool center exceeds R (tool diameter). In the case of Graph 234, the number of black pixels remains even when the distance from the tool center exceeds R. This is because a large number of chip pixels are detected outside the tool contour. Furthermore, even with tool 102A1, which has no chips wrapped around it as shown in the reference tool imaging screen 230, a small number of excess pixels are detected. This is because noise is generated due to fluctuations in imaging conditions and binarization of the image. Therefore, a small number of excess pixels as noise are also detected in Graph 231. Even with a reference tool, the excess area S1 is not actually zero.

[0059] Figure 13 is a graph showing the relationship between the amount of wrapping and the number of difference pixels. Figure 13 shows the difference in black pixels D (number of difference pixels) between tool 102A1 as the reference tool and tool 102A1 as the tool used, corresponding to graphs 231, 232, and 234 in Figure 12. The larger the amount of wrapping, the more excess pixels are detected around the tool diameter R, especially outside the tool diameter R.

[0060] Figure 14 is a flowchart showing the processing steps for the entanglement inspection. At the timing of the wrap-around inspection, the machining control unit 122 moves the spindle 116 to the tool recognition area 210 (S24). After inserting the spindle 116 into the tool recognition area 210, the machining control unit 122 notifies the operation control device 120 that it is ready.

[0061] The inspection unit 152 performs an image inspection of the tool 102 (S26). The image inspection determines whether the tool can be used again. Details of the image inspection will be explained in relation to Figure 15 below.

[0062] If the image inspection result is judged to be abnormal (Y in S28), the display unit 138 notifies the operator that a large amount or large chips are wrapped around the tool being used (S30). Subsequently, the imaging processing unit 156 instructs the machining control unit 122 to change the tool via the operation control device 120 (S32). The tool change unit 126 exchanges the tool being used (tool 102A1 with a large amount of chips wrapped around it) with a spare tool of the same type 102A2 stored in the tool storage unit 130.

[0063] If the image inspection result is determined to be normal (N in S28), processing in S30 and S32 is skipped.

[0064] Figure 15 is a flowchart showing the details of the image examination in S26 of Figure 14. The imaging processing unit 156 images the tool 102 and acquires an image corresponding to the inspection area Q (S40). The area calculation unit 150 calculates the surplus area S2 of the tool being used and calculates the difference value D between the surplus area S1 acquired in advance during the preliminary inspection and the surplus area S2 (S42). The inspection unit 152 determines that there is an abnormality if the difference value D is greater than the threshold T1 (Y in S44) (S46). If the difference value D is less than or equal to the threshold T1 (N in S44), the inspection unit 152 determines that the tool is normal (can be used again) (S48). As described above, tool replacement is performed when an abnormality is determined.

[0065] [Summary] The machine tool 100 and the image processing device 110 have been described above based on the embodiments. Chips wrapped around tool 102 can potentially damage the workpiece. On the other hand, replacing tool 102 even when only a small amount of chips are wrapped around it would reduce machining efficiency. According to this embodiment, the image processing device 110 can recognize the amount of chips wrapped around tool 102 using image recognition and automatically determine whether the tool can be used continuously. This control method makes it possible to achieve both machining efficiency and safety in the machine tool 100.

[0066] Furthermore, the operator can intuitively set an appropriate threshold T1 by referring to the surplus area S1, S2 or difference value D along with the captured image of the tool 102 on the reference tool imaging screen 230 and the tool in use imaging screen 220.

[0067] It should be noted that the present invention is not limited to the embodiments and modifications described above, and the components can be modified and implemented without departing from the spirit of the invention. Various inventions may be formed by appropriately combining the multiple components disclosed in the embodiments and modifications described above. In addition, some components may be deleted from all the components shown in the embodiments and modifications described above.

[0068] [Differentiation] In this embodiment, the inspection unit 152 is described as determining that the tool 102A1 is abnormal when the difference value D (=S2-S1) > threshold T1. As a modification, the inspection unit 152 may calculate the difference value D2 = S2 / S1. An arbitrary threshold T2 may be set, and the inspection unit 152 may determine that the tool 102A1 is abnormal when D2 > T2.

[0069] The image processing device 110 periodically performs tool inspections to determine whether there are any defects in the tool 102. The image processing device 110 may also instruct the machine tool 100 to perform a entanglement inspection during the tool inspection. The inspection unit 152 of the image processing device 110 may perform an entanglement inspection when it detects any abnormality during machining. For example, an acceleration sensor may be built into the spindle 116, and the camera 106 periodically notifies the image processing device 110 of the acceleration. The inspection unit 152 of the image processing device 110 may perform an entanglement inspection when the acceleration of the camera 106 exceeds a predetermined threshold, as this may indicate that interference with the tool 102 may have occurred. A sound-collecting microphone may be installed in the machining area, and the image processing device 110 may perform an entanglement inspection when an abnormal sound (such as a sound above a predetermined volume or a sound in a predetermined frequency band) is generated.

[0070] A tangle inspection may be performed when replacing tool 102A1 with another tool 102B after machining with tool 102A1. For example, suppose tool 102A2, which is the same type of tool as tool 102A1, is stored in the tool storage unit 130. When replacing tool 102A1 with tool 102B, a tangle inspection is performed on tool 102A1. If tool 102A1 is found to be abnormal, the tool exchange unit 126 exchanges tool 102A1 for tool 102B, and then the operation control device 120 sets the status data of tool 102A1 to "unavailable". The next time tool 102A1 is needed, the tool exchange unit 126 selects tool 102A2 of the same type instead of the unavailable tool 102A1. If chips tangle around tool 102A2 and it is found to be abnormal, tool 102A2 is also set to "unavailable". After completing a series of machining operations, the operator removes chips from the tool 102, which is marked as "unavailable" in the tool storage unit 130. After this, the operator may change the status of tools 102A1 and 102A2 from "unavailable" to "available" using the image processing device 110 or the operation control device 120.

[0071] In this embodiment, the tool diameter R is set as the boundary line, and the area calculation unit 150 detects black pixels located outside the boundary line (tool diameter R) as surplus pixels. The boundary line between surplus pixels and tool pixels is not limited to the tool diameter R, but may be arbitrarily set by the operator.

[0072] In this embodiment, the camera 106 is fixed, and the spindle 116 is moved close to the camera 106 to image the tool 102. As a modification, a movable camera 106 may be used. The data processing unit 142 includes a camera control unit (not shown), and the camera control unit may move the camera 106 close to the tool 102 during tool inspection to image the tool 102.

[0073] When the surplus area is large, for example, when S2 (surplus area of ​​the tool used) - S1 (surplus area of ​​the reference tool) > threshold T3, the transmitting unit 306 may transmit a control signal to the operation control device 120 instructing it to move the spindle 116 to a predetermined position within the machining area 200 and to rotate the spindle 116 at high speed there. The rotation speed is arbitrary, but it should be set in the range of approximately 500 to 2000 rpm. When the operation control device 120 receives this control signal, it causes the machining control unit 122 to execute the above control. After a predetermined number of rotations, the inspection unit 152 may re-execute the entanglement inspection. The rotational motion of the spindle 116 may remove the chips 180 from the tool 102. When the surplus area is small in the second entanglement inspection, for example, when S2 - S1 ≤ T3, the inspection unit 152 may determine that the tool 102 can be used continuously.

[0074] The output unit 148 may include a notification unit (not shown). The notification unit may notify the operator of a message such as "There is a possibility that chips are wrapped around the tool" when S1-S2>T1 is met in the entanglement inspection. The notification method may be either audio or text, or both.

[0075] The following describes modified methods for detecting chip entanglement with the tool 102 and breakage of the tool 102.

[0076] Figure 16 is a schematic diagram of the image captured during the preliminary inspection in a modified example. In the modified example, the inspection unit 152 performs a wrap-around inspection on the tool 102 during or after machining at a predetermined timing. The inspection unit 152 also performs a preliminary inspection when the tool is registered.

[0077] Figure 16 is an image taken during a preliminary inspection of a tool 102A2 (one of the A-type tools 102). In Figure 16, the X coordinate of the center line of tool 102A2 is denoted as "X1".

[0078] After registering tool 102A2, the inspection unit 152 performs a preliminary inspection on tool 102A2. During the preliminary inspection, the imaging processing unit 156 moves the main spindle 116 linearly in the Z-axis direction, that is, in the longitudinal direction of tool 102. Here, the difference in coordinate values ​​between the center line of the imaging area and the center line of tool 102A2 is defined as "XP". The difference value XP can be arbitrarily set by the user using the method described later.

[0079] The machining control unit 122 adjusts the spindle 116 in the X-axis direction according to the difference value XP, and then moves it in the Z-axis direction based on the movement value ZP. The movement value ZP can also be arbitrarily set by the user using the method described later. The imaging processing unit 156 continuously acquires partial images in conjunction with the movement of the tool 102A2. That is, multiple partial images are captured during the process of moving the tool 102 in its longitudinal direction. Hereinafter, the partial images obtained during the preliminary inspection will be referred to as "reference images".

[0080] In this way, during the preliminary inspection, multiple partial images are acquired as reference images for the inspection area Q defined by the difference value XP and the movement value ZP. During the preliminary inspection, no chip entanglement with the tool 102 or breakage of the tool 102 occurred.

[0081] During the entanglement inspection, multiple partial images are acquired for the same inspection area Q as during the preliminary inspection. During the entanglement inspection, multiple partial images are captured as tool 102 is moved in its longitudinal direction. Hereinafter, partial images taken during the entanglement inspection will be referred to as "verification images". During the entanglement inspection, there is a possibility that chips may be entangled around tool 102.

[0082] Figure 17 is a screenshot of the inspection settings screen 310. The user can set the inspection target, inspection range, and detection sensitivity on the inspection settings screen 310 before the preliminary inspection. The inspection settings screen 310 is displayed on the display unit 138. The inspection settings screen 310 includes an inspection selection area 313, a range setting area 314, and a detection sensitivity setting area 316. In the inspection selection area 313, the user sets whether or not to include "breakage inspection" and "wrapping inspection" as inspection items. In Figure 17, only the wrapping inspection is selected. Breakage inspection will be described later.

[0083] In the range setting area 314, the user defines the inspection area Q by setting the difference value XP and the movement value ZP. In the detection sensitivity setting area 316, the user selects the inspection sensitivity from "high," "medium," or "low." In this modified example, the inspection unit 152 compares the reference image and the verification image and determines the size of the chip wrapping based on the difference in the number of black pixels contained in each.

[0084] The inspection sensitivity is set, for example, to T1 for "high" (number of pixels as the threshold), T2 (>T1) for "medium" (number of pixels), and T3 (>T2) for "low" (number of pixels). In the modified example, instead of the area calculation unit 152, the "calculation unit" performs wrap-around detection by calculating the number of difference points (described later) instead of the excess area. That is, the functional block diagram of the image processing device 110 in the modified example is the same as the functional block diagram explained in Figure 4, but with the "area calculation unit" changed to a "calculation unit". The calculation unit compares the reference image and the verification image at the same imaging position and calculates the number of difference points, which is the difference in the number of pixels between the second region, which is a black pixel in the reference image, and the first region, which is a black pixel in the verification image. The black pixels here are identified by the same method as explained in relation to Figure 7.

[0085] The first region may contain not only the tool itself but also chips wrapped around the tool 102. On the other hand, since no chips are wrapped around the tool 102 during the preliminary inspection, the second region corresponds only to the tool 102. The inspection unit 152 determines whether the tool 102 is normal (ready for continued use) based on the difference in the number of black pixels between the first and second regions. Ideally, if no chips are wrapped around the tool, the first and second regions will be a perfect match, and the difference in the number of points will be zero. In other words, the first and second regions are regions corresponding to the tool 102 that should ideally be the same, and when chips or other debris are wrapped around the tool 102, the first region becomes larger than the second region.

[0086] The user touches the setting button 318 to activate the entered setting. At this time, the imaging processing unit 156 and the inspection unit 152 save the setting to the data storage unit 144. To cancel, the user touches the cancel button 320.

[0087] The fracture inspection method will be described later, but first, we will explain the method of checking for entanglement with specific examples.

[0088] Figure 18 is a first screenshot of the imaging screen of the tools used in a modified example. In Figure 18, verification images P1 to P4 have been acquired. Reference images V1 to V4 (not shown) have been acquired in advance at the same imaging positions as verification images P1 to P4. The calculation unit compares the second region in reference image V1 with the first region in verification image P1. More specifically, the inspection unit 152 defines the black pixel region in verification image P1 that is below a predetermined threshold brightness as the first region, and the black pixel region in reference image V1 that is below a threshold brightness as the second region, and calculates the difference in the number of pixels between the first and second regions D1.

[0089] When chip winding occurs at the tip of the tool 102, the difference score D1 increases. When no winding occurs, even considering the influence of image noise and the like, the difference score D1 becomes a small value. In FIG. 18, since D1 < T1, regardless of whether the detection sensitivity is high, medium, or low, the inspection unit 152 does not detect winding for the verification image P1. In FIG. 18, since almost no chip winding occurs at the tip of the tool 102, the first region in the verification image P1 almost completely corresponds to the second region in the reference image V1.

[0090] The difference score D4 between the verification image P4 and the reference image V4 is greater than the threshold value T1 and less than the threshold value T3. Therefore, when the verification sensitivity is set to "high (T1)", the inspection unit 152 determines that the tool 102 is not suitable for continued use because chips are wound around the tool 102. On the other hand, when the verification sensitivity is set to "medium (T2)" or "low (T3)", the inspection unit 152 determines that the tool 102 can be continued to be used. The inspection unit 152 sequentially compares the difference score D with the threshold value for the verification images P1 to P4, and determines that the tool 102 cannot be used when a difference value exceeding the threshold value is detected for any of the verification images.

[0091] By setting the detection sensitivity, the user can freely set the judgment criteria for the continued use of the tool 102.

[0092] FIG. 19 is a second screen diagram of the imaging screen of the tool in use in the modified example. In FIG. 19, since the movement value ZP is set larger than that at the time of inspection shown in FIG. 18, the verification images P1 to P9 and the reference images V1 to V9 (not shown) are acquired. The difference score D4 of the number of pixels between the first region of the verification image P4 and the second region of the reference image V4 is greater than the threshold value T2 and less than the threshold value T3. Therefore, when the detection sensitivity is set to "high (T1)" or "medium (T2)", the inspection unit 152 determines that the tool 102 cannot be continued to be used. When the detection sensitivity is set to "low (T3)", the inspection unit 152 determines that the tool 102 can be continued to be used.

[0093] Figure 20 is a third screen view of the tool imaging screen in the modified example. In Figure 20, the movement value ZP is set to be larger than that during the inspection shown in Figure 18, so verification images P1 to P9 and reference images V1 to V9 (not shown) are acquired. The difference in the number of pixels D5 between the first region of verification image P5 and the second region of reference image V5 is greater than the threshold T3. Therefore, regardless of whether the detection sensitivity is set to "high (T1)", "medium (T2)", or "low (T3)", the inspection unit 152 determines that the tool 102 cannot be used further based on the verification image P5.

[0094] In this way, the inspection unit 152 subtracts the number of black pixels in the second region of the reference image from the number of black pixels in the first region of the verification image, and if the difference point D is greater than a threshold, it determines that the amount of chips wrapped around the tool 102 is too large to be suitable for continued use.

[0095] On the other hand, when a defect occurs in the tool 102, the number of black pixels in the first region of the verification image becomes less than the number of black pixels in the second region of the reference image. When fracture detection is selected in the inspection setting screen 310, the inspection unit 152 subtracts the number of black pixels in the first region of the verification image from the number of black pixels in the second region of the reference image and compares the resulting difference number E with a threshold. If the difference number E is greater than the threshold, the inspection unit 152 determines that the tool 102 is fractured to the point where it is unsuitable for continued use. The threshold for fracture inspection also changes according to the setting in the detection sensitivity setting area 316 in the inspection setting screen 310.

[0096] As described above, in the modified example, the inspection unit 152 compares the reference image, which is the image captured at the time of tool registration, with the verification image, which is the image captured at the time of entanglement inspection and breakage inspection, and determines whether or not chip entanglement or breakage of the tool 102 has occurred based on the difference in the number of pixels in the first and second regions. The inspection unit 152 determines whether or not the tool 102 can be used further based on the detection sensitivity setting value set by the user.

Claims

1. A receiving unit that receives an image of a tool from a camera, The area calculation unit calculates the excess area, which is the area of ​​the portion of the region corresponding to the tool that is located at a predetermined distance or more from the tool's central axis, in the aforementioned captured image. The system includes an inspection unit that determines whether the tool is suitable for continued use based on the surplus area, The receiving unit receives a plurality of captured images corresponding to each part of the tool by moving the camera and the tool relative to each other with respect to the longitudinal direction of the tool. The area calculation unit calculates the excess area for each of the plurality of captured images, The inspection unit is an image processing device that determines whether the entire tool is suitable for continued use based on the excess area calculated for each of the multiple captured images.

2. The image processing apparatus according to Claim 1, wherein the area calculation unit determines whether the tool is suitable for continued use based on the difference between a first surplus area calculated based on an image of a reference tool and a second surplus area calculated based on an image of the tool being used.

Images