JP2022143752A - Cutting work monitoring system - Google Patents

Abstract

To provide a cutting work monitoring system which can highly accurately analyze the state of at least one of a tool blade tip during cutting and a processing surface of a cutting object material in real time.SOLUTION: A cutting work monitoring system comprises: a camera 23 which is positioned with respect to a lathe tool 21 such that a tool blade tip in an imaging visual field becomes the same position and consecutively images the tool blade tip; a classification unit 33 which classifies the plurality of images captured by the camera 23 into any of a plurality of patterns on the basis of information reflected in each image; and an analysis unit 34 which analyzes the state of at least one of the tool blade tip and the processing surface of a cutting object material W from the image classified into the prescribed pattern among the plurality of patterns.SELECTED DRAWING: Figure 2

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a cutting monitoring system used, for example, to prevent troubles in cutting.

In lathe machining, it is generally necessary to quickly detect the occurrence of wear or chipping of the cutting edge of a tool, and to take measures such as replacing the tool. For this reason, conventionally, there has been known a method of photographing the cutting edge of a tool with a camera and examining the state of the cutting edge from the image. For example, in Patent Document 1, the cutting edge of a tool is photographed with a camera in a standby state before and after cutting, and the amount of wear is determined from a binary image. Further, in Patent Document 2, an infrared camera captures the cutting edge of a tool during cutting, and a neural network learns from it to determine abnormality.

JP-A-6-114694 JP-A-11-267949

In the method of Patent Literature 1, since the cutting edge of the tool is photographed with a camera in a standby state (stationary state) other than during cutting, there is a problem that it is not possible to immediately respond to troubles that occur during cutting. In the method of Patent Document 2, since the amount of edge wear is indirectly analogized from the temperature distribution, it is difficult to quantitatively evaluate the amount of wear, and much learning is required to improve the determination accuracy.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a cutting monitoring system capable of analyzing the state of at least one of the cutting edge of a tool during cutting and the machined surface of a work material in real time with high accuracy.

One aspect of the cutting monitoring system of the present invention is a camera that is positioned with respect to a turning tool so that the cutting edge of the tool is at the same position within an imaging field of view, and that continuously captures the cutting edge of the tool. a classifying unit that classifies a plurality of images into one of a plurality of patterns based on information reflected in each of the images; an analysis unit that analyzes the state of at least one of the machined surfaces of the work material.

In the present invention, the cutting edge of the tool during turning and the machined surface of the workpiece (hereinafter sometimes simply referred to as the cutting edge of the tool, etc.) are photographed continuously, that is, in real time, by a camera. In the present invention, "continuously photographing" means photographing at least 10 frames per second. In addition, in order to position and fix the camera with respect to the turning tool so that the cutting edge of the tool is at the same position within the field of view, for example, the camera may be attached via an arm or the like to a tool rest that supports the turning tool.
Then, the classification unit classifies each image into one of a plurality of patterns by comparing the obtained image information with, for example, the learning result of the storage unit. The analysis unit analyzes the state of at least one of the cutting edge of the tool and the machined surface of the work piece from each of the classified images.

Specifically, the images taken continuously by the camera include cases in which the cutting edge of the tool is hidden by chips, and in which the wear state is not visible due to a large amount of adhesion on the cutting edge. Therefore, from among a large number of continuously shot images, for example, the outline of the cutting edge (cutting edge ridgeline), the welding to the rake face, etc., or the images that show the machined surface of the work material are selected (classified) and image processed. Analyze the state of wear and chipping of the cutting edge, the state of welding, and the state of processing of the machined surface. Deep learning can be used for the above sorting, and since the determination is relatively simple, high determination accuracy can be obtained with a small amount of learning.

As described above, according to the present invention, the state of at least one of the cutting edge of the tool during cutting and the machined surface of the work can be analyzed in real time with high accuracy. In other words, the user or the like can grasp the state of the cutting edge of the tool during cutting in real time. As a result, for example, the practicability as an anomaly detection system or an in-process (during cutting) machining dimensional accuracy measurement system is enhanced.

In the above-described cutting monitoring system, the classification unit classifies the image showing a cutting edge ridgeline having a predetermined cutting length or longer into a first pattern among the plurality of patterns, and the analysis unit classifies the image into the first pattern. It is preferable to analyze the damage state of the cutting edge of the tool based on the shape of the cutting edge ridgeline of the images classified into the following.

In this case, the analyzing section analyzes the images classified into the first pattern by the classifying section, so that the damage state and amount of damage such as wear and chipping of the cutting edge of the tool can be measured. Specifically, for example, the ridgeline (edge) of the cutting edge is detected by image processing such as a canny filter, and the change (increase) in the number of pixels of the edge is measured to analyze the damaged state of the cutting edge.

In the above-described cutting monitoring system, the classification unit classifies the image showing welding on the cutting edge of the tool into a second pattern among the plurality of patterns, and the analysis unit classifies the image into the second pattern. It is preferable to analyze the damage state of the cutting edge of the tool based on changes in the frequency of appearance of the images obtained.

In general, when the cutting edge of a tool is damaged, there is a tendency that welding tends to occur due to this damage. In other words, during cutting, welding to the cutting edge of the tool and its peeling off (falling off) are repeated randomly. The appearance frequency of welding to the image increases. That is, for example, when the continuous shooting speed (shooting interval) of the camera is constant, the number of images classified into the second pattern per unit time increases.
According to the above configuration of the present invention, it is possible to indirectly detect damage to the cutting edge even if the cutting edge of the tool is hidden or difficult to see due to welding. That is, the analysis unit can estimate the damage state of the cutting edge of the tool based on the change in the appearance frequency of the images classified into the second pattern by the classification unit.

In the above-described cutting monitoring system, the classification unit classifies the image showing the machined surface of the work material into a third pattern among the plurality of patterns, and the analysis unit classifies the image into the third pattern. It is preferable to analyze the machining state of the machined surface from the images classified into .

In this case, the analysis unit analyzes the images classified into the third pattern by the classification unit to determine the machining dimensional accuracy of the machined surface of the work material, the machined surface quality, the occurrence of burrs, the discharge of chips, and the like. can. That is, the "machined state of the machined surface of the work material" as used in the present invention means any one of machining dimensional accuracy, machined surface quality, burr generation state, and chip discharge state of the machined surface of the work material. Point above.
In particular, with the above-described configuration of the present invention, a user or the like can grasp the machining accuracy and quality of the machined surface immediately after cutting in real time.

In the cutting monitoring system described above, it is preferable that the classification unit performs image classification by deep learning.

In this case, the accuracy of classification determination by the classifier is stably enhanced by deep learning.

According to the cutting monitoring system of one aspect of the present invention, the state of at least one of the cutting edge of the tool during cutting and the machined surface of the work can be analyzed in real time with high accuracy.

FIG. 1 is a side view showing an example of a turning apparatus according to this embodiment. FIG. 2 is a functional block diagram showing an example of the cutting monitoring system of this embodiment. FIG. 3 shows an example of images classified into the first pattern by the classification unit. FIG. 4 shows an example of images classified into the second pattern by the classification unit. FIG. 5 shows an example of images classified into the third pattern by the classification unit. FIG. 6 shows an example of analysis (image processing) of images classified into the first pattern. FIG. 7 shows an example of analysis (image processing) of images classified into the first pattern. FIG. 8 is a diagram showing an example of changes in appearance frequency of images classified into the second pattern. FIG. 9 is a flow chart showing an example of processing of the cutting monitoring device of this embodiment.

A cutting monitoring system 10 according to one embodiment of the present invention will be described with reference to the drawings. The cutting monitoring system 10 of this embodiment includes a turning device 20 and a cutting monitoring device 30 .

As shown in FIGS. 1 and 2, the turning device 20 is a machine tool such as an NC lathe. The turning device 20 is a device for turning a work material W such as metal. That is, the cutting monitoring system 10 is used for turning (lathe processing) by a machine tool such as an NC lathe. Turning refers to cutting using a turning tool such as a turning tool.

The turning device 20 includes a turning tool 21, a tool post 22, a camera 23, an arm 24, and a chuck (not shown). That is, the cutting monitoring system 10 includes the camera 23 .

As shown in FIG. 1, the turning tool 21 is, for example, an indexable cutting tool in which a cutting insert 26 is detachably attached to the tip of a holder 25, or the like. That is, the turning tool 21 has a holder 25 and a cutting insert 26 . The turning tool 21 is not limited to this configuration, and may be, for example, a solid type cutting tool in which the cutting edge of the tool is formed integrally with a holder.

The holder 25 has a columnar shape extending in one direction. In the example shown in FIG. 1, one direction in which the holder 25 extends is inclined with respect to the horizontal plane H at an angle θ. The angle θ is, for example, 30°. A rear end portion of the holder 25 is supported by the tool post 22 . The turning tool 21 and the tool post 22 are integrally fixed.

The cutting insert 26 is made of cemented carbide, for example. The cutting insert 26 has, for example, a polygonal plate shape such as a rectangular plate shape, or a disk shape. In this embodiment, the cutting insert 26 has, for example, a rhombic plate shape.
As shown in FIG. 3, the cutting insert 26 has a rake face 26a, a flank face (not shown), and a cutting edge 26b arranged on the ridge between the rake face 26a and the flank face. In this embodiment, at least a portion of the cutting insert 26, specifically the portion including at least the rake face 26a and the cutting edge 26b, may be simply referred to as the "tool cutting edge" or "cutting edge."

The rake face 26a is arranged on at least one of a pair of plate faces of the cutting insert 26 facing in the plate thickness direction. As shown in FIG. 1, the rake face 26a is arranged on one plate face facing the upper side of the cutting insert 26, that is, on the upper face. In the example shown in FIG. 1, the rake face 26a is inclined with respect to the horizontal plane H at substantially the same angle as the angle .theta.

As shown in FIG. 5, the rake face 26a of this embodiment has a feature point 26c. The feature point 26c forms part of the pattern provided on the rake face 26a. The characteristic point 26c is provided on the rake face 26a for the purpose of, for example, smoothly discharging the chips C, improving the appearance design, and improving the distinguishability. In this embodiment, the characteristic point 26c is, for example, a projecting chip breaker or the like.

As shown in FIG. 1, the cutting edge 26b is arranged at the tip of the turning tool 21. As shown in FIG. When the cutting edge 26b is brought into contact with the work W rotating around the central axis O, the work W is turned, and a machined surface Wa as shown in FIG. 5 is formed. .

In this embodiment, as shown in FIG. 3, the cutting edge 26b is substantially V-shaped when the upper surface of the cutting insert 26, that is, the rake surface 26a is viewed from the front. Specifically, this cutting edge 26b has one corner edge extending in a curved shape and a pair of linear edges connected to both ends of this corner edge and extending in a straight line.

As shown in FIG. 1, the tool rest 22 supports a turning tool 21 . The tool post 22 moves the turning tool 21 with respect to the workpiece W at least in the direction in which the horizontal plane expands, that is, along the plane direction of the horizontal plane. Note that the tool post 22 may move the turning tool 21 with respect to the work W in the vertical direction.

The camera 23 is arranged above the turning tool 21 and the workpiece W. As shown in FIG. The camera 23 is, for example, a global shutter camera. The camera 23 continuously photographs the cutting edge of the tool. In this embodiment, "continuously photographing" means photographing at least 10 frames per second. Specifically, in this embodiment, the camera 23 continuously captures the cutting edge of the tool at a speed of 30 frames or more per second, for example. During cutting, the camera 23 photographs the cutting surface Wa of the workpiece W as well as the cutting edge of the tool.

In this embodiment, the camera 23 photographs the cutting edge of the tool from a direction perpendicular to the rake face 26a. Specifically, the camera 23 captures an image of the cutting edge of the tool from a direction inclined by a predetermined angle with respect to the vertical direction. This predetermined angle is substantially the same as the angle at which the rake face 26a is inclined with respect to the horizontal plane H (corresponding to the angle θ). The distance between the camera 23 and the cutting edge of the tool is, for example, 300 mm or more.

Camera 23 is fixed to tool post 22 via arm 24 . Therefore, the camera 23 can move along with the movement of the tool post 22 . The camera 23 is positioned with respect to the turning tool 21 so that the cutting edge of the tool within the field of view is at the same position, as shown in FIGS. 3 to 5, for example.

As shown in FIG. 1, arm 24 connects camera 23 and tool post 22 . The arm 24 has a front end connected to the camera 23 and a rear end connected to the tool post 22 . The arm 24 has at least two or more shaft portions 24a, at least one or more joint portions 24b connecting the ends of the adjacent shaft portions 24a, and the rear end portion of the arm 24 and the tool rest 22. and a fixed base 24c.

The shaft portion 24a is, for example, a shaft, a pipe, or the like.
By operating a knob (not shown) or the like, the joint portion 24b has a lock mode in which the ends of the shaft portions 24a are fixed so as not to be rotatable, and a free mode in which the ends of the shaft portions 24a are rotatably connected. , can be switched. The provision of the joint portion 24b allows the arm 24 to be deformed. By changing the shape of the arm 24, the position of the camera 23 can be adjusted so as to directly face the cutting edge of the turning tool 21, regardless of the tool shape or type of the turning tool 21, for example. During cutting, the joint portion 24b is in lock mode.

The fixed table 24c fixes the arm 24 to the tool rest 22 by, for example, magnetic force. Therefore, the mounting position of the arm 24 can be adjusted with respect to the tool rest 22 . That is, in the present embodiment, the position of the camera 23 can also be adjusted so as to face the cutting edge of the tool by adjusting the attachment position of the fixed table 24c to the tool post 22. FIG.

Although not shown, the chuck detachably holds the material W to be cut. The chuck rotates the work W around its central axis O. As shown in FIG.

Although not shown, the turning device 20 may include a backlight for emphasizing the contours of the cutting edge 26b and the machining surface Wa, and a front light for illuminating the rake face 26a. Thereby, the shutter speed of the camera 23 may be increased.

As shown in FIG. 2 , the cutting monitoring device 30 includes an image acquisition section 31 , a storage section 32 , a classification section 33 , an analysis section 34 and a display section 35 . That is, the cutting monitoring system 10 includes a classification section 33 and an analysis section 34 .

The image acquisition unit 31 acquires an image captured by the camera 23, that is, image data. The image acquisition unit 31 causes the storage unit 32 to store the acquired image information. Note that the cutting monitoring device 30 may associate the acquired image information with the tool ID, the device ID, the user ID, etc., and store them in the storage unit 32, for example.

The storage unit 32 stores various information used by the cutting monitoring device 30 . The storage unit 32 stores the acquired image information. The storage unit 32 stores, for example, teacher data and learning results of deep learning used by the classification unit 33 to classify images.

The classification unit 33 executes image classification by deep learning, for example, based on the learning results stored in the storage unit 32 . That is, the classification unit 33 classifies a plurality of images captured by the camera 23 into one of a plurality of patterns based on information captured in each image. In this embodiment, the plurality of patterns includes a first pattern (cutting edge ridgeline), a second pattern (welding), and a third pattern (machined surface of the work material).

Specifically, as shown in FIG. 3, the classification unit 33 classifies an image in which a cutting edge ridge line of a cutting edge 26b having a predetermined cutting edge length or longer is captured in the imaging field into a first pattern among the plurality of patterns. In the example shown in FIG. 3, the cutting edge 26b is not in contact with the workpiece W, and the entire ridgeline of the cutting edge is clearly captured within the imaging field.

Further, as shown in FIG. 4, the classification unit 33 classifies the image in which the welding TA appears on the cutting edge of the tool into the second pattern among the plurality of patterns. In the example shown in FIG. 4, at least a portion of the rake face 26a and at least a portion of the cutting edge 26b are hidden by the welding TA attached to the cutting edge of the tool.

Further, as shown in FIG. 5, the classification unit 33 classifies the image showing the processing surface Wa of the workpiece W into the third pattern among the plurality of patterns. In the example shown in FIG. 5, the surface and contour of the machined surface Wa immediately after being cut by the cutting edge 26b are clearly shown.
Each image shown in FIGS. 3 to 5 is an image of the cutting edge of the tool taken when turning the plate-like work material W, as shown in FIG. At this time, the material of the work material W was stainless steel, the number of revolutions of the work material W was 100 times per minute, and the cutting was performed in a dry environment.

The classification of images by the classification unit 33 is performed, for example, by the following method.
First, a plurality of images are captured by the camera 23 in test cutting performed before the main cutting of the work material W. As shown in FIG. A plurality of images acquired in this way are divided into a first pattern (cutting edge ridgeline) in which the cutting edge 26b is not in contact with the work material W and the cutting edge ridge line is clearly visible, and a first pattern (cutting edge ridge line) in which the cutting edge 26b is in contact with the work material W. A second pattern (welding) in which the welded TA is placed on the rake face 26a although it is not there, and a third pattern (machined surface of the work material) that captures the moment when the cutting edge 26b contacts the work material W. , and stored (teaching data), and this classification method is learned by deep learning. That is, machine learning for estimating the classification of the first to third patterns is performed based on the teacher data in the storage unit 32, and the learning result is fed back to the storage unit 32, thereby improving the determination accuracy of the image classification. .
Note that this classification is just an example, and the appropriate classification method differs depending on the cutting conditions, the type and shape of the work material W, and the like.
For the classification (selection) of the image data described above, automatic image recognition software such as HALCON (manufactured by Links Co., Ltd.) can be used.

The analysis unit 34 analyzes the state of at least one of the cutting edge of the tool and the processing surface Wa of the workpiece W from the images classified into a predetermined pattern among the plurality of patterns. For example, an image processing program or the like can be used as the analysis unit 34 .

Specifically, the analysis unit 34 analyzes the damage state of the cutting edge of the tool based on the shape of the cutting edge ridgeline of the cutting edge 26b in the image classified into the first pattern (hereinafter, sometimes referred to as the first analysis). be). In this embodiment, the analysis unit 34 detects the cutting edge ridge (edge) of the cutting edge 26b by, for example, image processing such as a canny filter, and measures the change (increase) in the number of pixels of the edge to determine the damage of the cutting edge. Analyze the state.

6 and 7 show an example of image processing of the cutting edge ridgeline of the cutting edge 26b by the analysis unit 34. FIG. The image (original image) in FIG. 7 was taken after the image in FIG. 6 during a predetermined cutting process. In FIG. 7, as compared to FIG. 6, the ridge of the cutting edge is formed with a convex portion due to welding TA and a concave portion due to chipping CP. That is, by comparing the number of edge pixels, the damage state of the cutting edge can be estimated.
In this manner, the analysis unit 34 analyzes the damage state of the cutting edge of the tool. Note that the above analysis is merely an example, and other analysis methods may be used to analyze the first pattern.

The analysis unit 34 also analyzes the damage state of the cutting edge of the tool based on changes in the appearance frequency of the images classified into the second pattern (hereinafter sometimes referred to as second analysis).
FIG. 8 shows an example of changes in appearance frequency of images classified into the second pattern. A hatched portion in the graph of FIG. 8 indicates that the classification unit 33 classified the image into the second pattern (welding).

Specifically, during cutting, welding to the cutting edge of the tool and its peeling off (falling off) are randomly repeated. Therefore, the frequency of occurrence of welding increases. From this, it is presumed that damage to the cutting edge occurred near the symbol P on the horizontal axis (cutting time) in FIG.
In this manner, the analysis unit 34 analyzes the damage state of the cutting edge of the tool. Note that the above analysis is merely an example, and other analysis methods may be used to analyze the second pattern.

Further, the analysis unit 34 analyzes the processing state of the processing surface Wa of the work material W from the images classified into the third pattern (hereinafter sometimes referred to as third analysis). In this embodiment, the "machined state of the machined surface Wa of the work material W" refers to the machined dimensional accuracy of the machined surface Wa of the work material W, machined surface quality, burr generation state, and chip discharge state. Any one or more of

In FIG. 5, the analysis unit 34 determines the machining dimensional accuracy by measuring, for example, the distance L between the feature point 26c on the rake face 26a and the machining surface Wa by image processing. That is, in this embodiment, for example, even if the camera 23 is shaken (displaced from the origin position) due to vibration or the like during cutting, the machining dimensions can be measured with high accuracy. Further, the analysis unit 34 determines the quality of the machined surface Wa, for example, by measuring the dimensions of the uneven shape appearing on the surface or contour of the machined surface Wa. Further, the analysis unit 34 may analyze, for example, the presence or absence of burrs on the machined surface Wa, the length and curling state of the chips C, the discharge direction of the chips C, and the like.
In this manner, the analysis unit 34 analyzes the machining state of the machining surface Wa of the workpiece W. As shown in FIG. Note that the above analysis is merely an example, and other analysis methods may be used to analyze the third pattern.

The display unit 35 displays various information of the cutting monitoring system 10 . The display unit 35 displays, for example, the analysis result of the analysis unit 34 described above.

FIG. 9 is a flowchart showing an example of processing of the cutting monitoring device 30. As shown in FIG.
As shown in FIG. 9, first, the image acquisition unit 31 acquires image information output from the camera 23 (step S1).
Next, the classification unit 33 classifies each image into first to third patterns based on the learning results stored in the storage unit 32 (step S2). That is, the classification unit 33 classifies each image into one of the first to third patterns by comparing the acquired image information with the learning result.

Next, the analysis unit 34 analyzes the state of at least one of the cutting edge of the tool and the machined surface Wa of the workpiece W from the images classified into the first to third patterns (step S3). Specifically, the analysis unit 34 performs the above-described first analysis on the images classified into the first pattern (cutting edge ridge). The analysis unit 34 also performs the above-described second analysis on the images classified into the second pattern (welding). The analysis unit 34 also performs the above-described third analysis on the images classified into the third pattern (machined surface of the work material).
Next, the display unit 35 displays the analysis result output from the analysis unit 34 (step S4). After the process of step S4, the cutting monitoring device 30 terminates the above example process.

In the cutting monitoring system 10 of the present embodiment described above, the camera 23 continuously monitors the cutting edge of the tool during turning and the machined surface Wa of the work material W (hereinafter sometimes simply referred to as the cutting edge of the tool, etc.). , i.e., in real time. Further, the camera 23 is positioned and fixed with respect to the turning tool 21 so that the cutting edge of the tool within the imaging field of view is at the same position.
Then, the classification unit 33 classifies each image into one of a plurality of patterns by comparing the obtained image information with the learning result of the storage unit 32 . The analysis unit 34 analyzes the state of at least one of the cutting edge of the tool and the machined surface Wa of the workpiece W from each image after classification.

Specifically, the images captured continuously by the camera 23 include those in which the cutting edge of the tool is hidden by chips C and those in which a large amount of fused TA adheres to the cutting edge and the state of wear cannot be seen. there is Therefore, in this embodiment, out of a large number of consecutively shot images, the outline of the cutting edge 26b (cutting edge ridgeline), the welding TA to the rake surface 26a, or the processed surface Wa of the workpiece W can be seen. After selection (classification), image processing is performed to analyze the state of wear and chipping of the cutting edge 26b, the state of the welding TA, and the processing state of the processing surface Wa. Deep learning can be used for the above sorting, and since the determination is relatively simple, high determination accuracy can be obtained with a small amount of learning.

As described above, according to the present embodiment, the state of at least one of the cutting edge of the tool during cutting and the processing surface Wa of the work W can be analyzed in real time with high accuracy. In other words, the user or the like can grasp the state of the cutting edge of the tool during cutting in real time. As a result, for example, the practicability as an anomaly detection system or an in-process (during cutting) machining dimensional accuracy measurement system is enhanced.

Further, in the present embodiment, the classification unit 33 classifies an image in which a cutting edge ridge line having a predetermined cutting length or more is captured within the imaging field of view into the first pattern among the plurality of patterns, and the analysis unit 34 classifies the image into the first pattern. The damage state of the cutting edge of the tool is analyzed based on the shape of the cutting edge ridgeline of the image classified into .
In this case, the image classified by the classification unit 33 into the first pattern is analyzed by the analysis unit 34, whereby the damage state and amount of damage such as wear and chipping of the cutting edge of the tool can be measured.

Further, in the present embodiment, the classification unit 33 classifies the image of the welding TA on the cutting edge of the tool into the second pattern among the plurality of patterns, and the analysis unit 34 classifies the images classified into the second pattern. The damage state of the cutting edge of the tool is analyzed based on the change in appearance frequency.
In general, when the cutting edge of a tool is damaged, there is a tendency for adhesion TA to easily occur due to this damage. That is, when the cutting edge is damaged, the welded TA strongly adheres to the damaged portion and is difficult to remove, so the appearance frequency of the welded TA on the image increases. That is, for example, when the continuous shooting speed (shooting interval) of the camera 23 is constant, the number of images classified into the second pattern per unit time increases.
According to this embodiment, it is possible to indirectly detect damage to the cutting edge even if the cutting edge of the tool is hidden by the welding TA and cannot be seen or is difficult to see. In other words, the damage state of the cutting edge of the tool can be estimated by the analysis unit 34 based on the change in the appearance frequency of the images classified into the second pattern by the classification unit 33 .

Further, in the present embodiment, the classification unit 33 classifies the image showing the processing surface Wa of the work material W into the third pattern among the plurality of patterns, and the analysis unit 34 classifies the image into the third pattern. The machined state of the machined surface Wa is analyzed from the obtained image.
In this case, the image classified by the classification unit 33 into the third pattern is analyzed by the analysis unit 34 to determine the machining dimensional accuracy of the machined surface Wa of the work material W, the machined surface quality, the occurrence of burrs, and the amount of chips C. Ejection status can be determined.
In particular, in this embodiment, the user or the like can grasp the machining accuracy and quality of the machined surface Wa immediately after cutting in real time, so that, for example, when a problem occurs in the machining state, it can be quickly dealt with.

Further, in this embodiment, the classification unit 33 executes image classification by deep learning.
In this case, the classification determination accuracy of the classification unit 33 is stably enhanced by deep learning.

Further, in this embodiment, the camera 23 photographs the cutting edge of the tool from a direction perpendicular to the rake face 26a, that is, from a direction directly facing the rake face 26a.
In this case, the camera 23 can easily focus on the cutting edge of the tool, and the effects of the present embodiment described above can be obtained more stably.

Further, in this embodiment, the distance between the camera 23 and the cutting edge of the tool is 300 mm or more.
When the above distance is 300 mm or more, for example, when replacing the cutting insert 26 with a new one or indexing the cutting edge 26b (changing the corner used), that is, when replacing the cutting edge, the camera 23 will not work. It is difficult to get in the way of Moreover, even if the chips C extend or scatter during cutting, they are less likely to come into contact with the camera 23, so that effective images can be obtained stably.

It should be noted that the present invention is not limited to the above-described embodiments, and, for example, as described below, changes in configuration can be made without departing from the gist of the present invention.

In the above-described embodiment, an example was given in which the camera 23 is fixed to the tool post 22 via the arm 24 that can be switched between the lock mode and the free mode, but the present invention is not limited to this. That is, the camera 23 may be fixed to the tool post 22 via a non-deformable rigid member or the like. Alternatively, the camera 23 may be fixed directly to the tool rest 22 . Note that the camera 23 only needs to be positioned with respect to the turning tool 21 so that the cutting edge of the tool within the imaging field of view is at the same position. and may be fixed.

In addition, without departing from the gist of the present invention, each configuration described in the above-described embodiment and modifications may be combined, and addition, omission, replacement, and other changes of configuration are possible. Moreover, the present invention is not limited by the embodiments described above, but only by the claims.

According to the cutting monitoring system of the present invention, the state of at least one of the cutting edge of the tool during cutting and the machined surface of the work can be analyzed in real time with high accuracy. Therefore, it has industrial applicability.

DESCRIPTION OF SYMBOLS 10... Cutting monitoring system, 21... Turning tool, 23... Camera, 33... Classification part, 34... Analysis part, TA... Welding, W... Work material, Wa... Machining surface

Claims (5)

a camera that is positioned with respect to the turning tool so that the cutting edge of the tool is at the same position within the imaging field of view, and that continuously captures the cutting edge of the tool;
a classification unit that classifies a plurality of images captured by the camera into one of a plurality of patterns based on information captured in each of the images;
an analysis unit that analyzes the state of at least one of the cutting edge of the tool and the machined surface of the work material from the images classified into a predetermined pattern among the plurality of patterns;
Cutting monitoring system. The classification unit classifies the image in which the cutting edge ridgeline having a predetermined cutting length or more is shown as a first pattern among the plurality of patterns,
The analysis unit analyzes the damage state of the tool cutting edge based on the shape of the cutting edge ridge line in the image classified into the first pattern.
The cutting monitoring system according to claim 1. The classification unit classifies the image showing the welding on the cutting edge of the tool into a second pattern among the plurality of patterns,
The analysis unit analyzes the damage state of the cutting edge of the tool based on changes in the appearance frequency of the images classified into the second pattern.
3. The cutting monitoring system according to claim 1 or 2. The classification unit classifies the image showing the processing surface of the work material into a third pattern among the plurality of patterns,
The analysis unit analyzes the processing state of the processing surface from the images classified into the third pattern.
The cutting monitoring system according to any one of claims 1 to 3. The classification unit performs image classification by deep learning,
The cutting monitoring system according to any one of claims 1 to 4.

Images