Control device and computer-readable recording medium

Abstract

The present invention provides a control device and a computer-readable recording medium, which can detect machining abnormalities based on more factors. The control device (1) controls a machine tool (100) capable of alarming and stopping based on abnormal machining load, and the control device (1) comprises: a camera unit (12) that captures chips generated as a result of machining a workpiece (W); a reference model determination unit (14) that predetermines a reference model for chips that are judged as machining abnormalities based on images of chips captured within a specified period before the alarm and stop in response to the occurrence of the alarm and stop; and a judgment unit (16) that determines that a machining abnormality has occurred when chips captured at a specified time in subsequent machining have a specified or higher similarity with the determined reference model of chips.

Description

Technical Field

[0001] The present invention relates to a control device and a computer-readable recording medium. Background Art

[0002] In the past, a machine tool that uses a tool to process a workpiece is known. In the machine tool, for example, the load of the tool or the shaft during processing is monitored as a processing load, thereby detecting an abnormality. On the other hand, even when the processing load is within the allowable range, an abnormality may occur during processing. Therefore, a grinding machine is proposed that photographs the chips of the workpiece generated during processing and uses the change in the chips to detect the wear state of the grinding stone (for example, refer to Patent Document 1).

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2019-42857 Summary of the invention

[0006] Problem that the invention aims to solve

[0007] In the grinding machine described in Patent Document 1, a camera is used to capture the chips collected in the chip collection device by the coolant. In addition, in the grinding machine described in Patent Document 1, it is determined whether the change amount of the chips at regular intervals included in the captured image data is above a threshold. Moreover, in the grinding machine described in Patent Document 1, when the change amount is below the threshold, the grinding stone is urged to be repaired or replaced. Thus, according to Patent Document 1, the wear state of the grinding stone can be grasped.

[0008] In addition, it is well known that in machine tools, machining abnormalities are also manifested in changes in chips generated by machining workpieces. Therefore, it is preferable to detect machining abnormalities based on more factors, for example, based on changes in chips that are flushed into a chip collector such as a coolant tank when coolant is used. In addition, it is more preferable to reduce the number of workpieces discarded due to machining abnormalities by detecting machining abnormalities earlier than alarming and stopping the machine tool due to abnormal machining load.

[0009] Solutions for solving problems

[0010] (1) The present disclosure relates to a control device that controls a machine tool capable of issuing an alarm and stopping based on an abnormality in a machining load, the control device comprising: a camera unit that captures images of chips generated as a result of machining a workpiece; a reference model determination unit that, in response to the occurrence of an alarm and a stop, predetermines a reference model for chips that are judged to be machining abnormalities based on images of chips captured within a specified period before the alarm and the stop; and a judgment unit that determines that a machining abnormality has occurred when chips captured at a specified timing in subsequent machining have a similarity of more than a specified degree with the determined reference model of the chips.

[0011] (2) In addition, the present disclosure relates to a recording medium having a program for causing a computer to operate as a control device that controls a machine tool capable of issuing an alarm and stopping based on an abnormality in a machining load, the program causing the computer to function as: an imaging unit that images chips generated as a result of machining a workpiece; a baseline model determination unit that, in response to the occurrence of an alarm and a stop, predetermines a baseline model for chips that are judged to be machining abnormalities based on images of chips captured within a specified period before the alarm and the stop; and a judgment unit that determines that a machining abnormality has occurred when chips captured at a specified timing in subsequent machining have a similarity of more than a specified degree with respect to the determined baseline model of chips.

[0012] Effects of the Invention

[0013] According to the present disclosure, it is possible to provide a control device capable of detecting machining abnormalities based on more factors and a recording medium having a program recorded thereon. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 1 is a block diagram showing a configuration of an operating system including a control device according to a first embodiment of the present disclosure.

[0015] Figure 2 It is a schematic diagram showing the arrangement position of the imaging unit of the control device according to the first embodiment.

[0016] Figure 3 This is a flowchart showing the operation of the control device according to the first embodiment.

[0017] Figure 4 This is a flowchart showing the operation of the control device according to the first embodiment.

[0018] Figure 5 This is a schematic diagram showing the shape of chips used when a reference model determination unit of a control device according to a second embodiment of the present disclosure determines a reference model.

[0019] Description of Reference Numerals

[0020] 1: control device; 11: alarm and stop execution unit; 12: imaging unit; 14: reference model determination unit; 16: determination unit; 100: machine tool; W: workpiece. DETAILED DESCRIPTION

[0021] Below, refer to Figures 1 to 5 The control device 1 and the program according to each embodiment of the present disclosure will be described.

[0022] First, an overview of a control device 1 according to each embodiment and a machine tool 100 controlled by the control device 1 will be described.

[0023] The machine tool 100 is a system for machining a workpiece W using a tool 101 (cutter). In the machine tool 100, for example, due to the deterioration of the tool 101, the load (hereinafter also referred to as machining load) of the machining workpiece W increases, wherein the deterioration of the tool 101 is a machining abnormality. Therefore, in the machine tool 100, the damage of the tool 101 or the damage of the device is suppressed by monitoring the machining load. Specifically, when each load exceeding a predetermined value is detected, the machine tool 100 issues an alarm and stops.

[0024] In addition to issuing an alarm and stopping, the control device 1 also uses the change in chips generated by machining the workpiece W to determine machining abnormalities. For example, the control device 1 uses the coolant flushed into the coolant tank 102 (see Figure 2 ) to judge machining abnormality. In addition, since there is a deviation in the timing of alarm and stop, it is possible that the alarm and stop are issued before the abnormality caused by the change of chips is judged. Therefore, the control device 1 optimizes the conditions for judging machining abnormality to achieve the judgment of machining abnormality before the alarm and stop. In addition, "chips" are interpreted in a broad sense, not limited to chips generated by cutting, and widely include chips generated by removal processing other than cutting (such as grinding).

[0025] [First embodiment]

[0026] Next, refer to Figures 1 to 4 A control device 1 and a program according to a first embodiment of the present disclosure will be described.

[0027] The control device 1 is a device capable of controlling the machining operation of the machine tool 100. For example, the control device 1 is a device capable of controlling the machine tool 100 to issue an alarm and stop the machine tool 100 based on an abnormality in the machining load of the machining device. Figure 1As shown, the control device 1 includes an alarm and stop execution unit 11, an imaging unit 12, an image storage unit 13, a reference model determination unit 14, a reference model storage unit 15, a determination unit 16, and a signal output unit 17.

[0028] The alarm and stop execution unit 11 is realized by, for example, the operation of a CPU. The alarm and stop execution unit 11 determines the alarm and stop of the machine tool 100 based on the machining load of the machine tool 100. The alarm and stop execution unit 11 detects, for example, a load exceeding a prescribed value of the tool 101 or an axis (not shown) using a sensor (not shown). The alarm and stop execution unit 11 puts the machine tool 100 into the alarm and stop state in response to the detection of a load exceeding a prescribed value of the tool 101 or an axis.

[0029] The imaging unit 12 is, for example, an imaging device such as a camera. The imaging unit 12 captures the chips generated as a result of machining the workpiece W. The imaging unit 12 captures, for example, the chips that are flushed into the coolant tank 102 by the coolant in the machining device. Figure 2 As shown, the imaging unit 12 is arranged just above the flow path of the coolant flowing to the coolant tank 102 .

[0030] The image storage unit 13 is a secondary storage medium such as a hard disk, for example. The image storage unit 13 stores images (moving images) captured by the imaging unit 12. The image storage unit 13 also stores the time of capturing images together with the captured images.

[0031] The reference model determination unit 14 is implemented, for example, by the CPU operating. In response to the occurrence of an alarm and stop, the reference model determination unit 14 predetermines a reference model for chips used to determine the machining abnormality based on the image of the chips captured within a specified period before the alarm and stop. The reference model determination unit 14 operates, for example, with the alarm and stop execution unit 11 executing the alarm and stop of the machine tool 100 as a trigger. In the present embodiment, the reference model determination unit 14 determines the average value of the size of the chips contained in the image of the chips captured within a specified period before the alarm and stop as the reference model. That is, the reference model determination unit 14 determines the size of the chips generated within a specified period before the alarm and stop as the reference model for determining the occurrence of an abnormality. Here, as the size of the chips, for example, the reference model determination unit 14 calculates the average value of the pixel amount of each chip for a plurality of chips contained in the image of the chips as the size of the chips.

[0032] In addition, the reference model determination unit 14 corrects the already determined reference model based on the image of the chips captured within the prescribed period before the new alarm and stop occurs in response to the occurrence of a new alarm and stop. For example, the reference model determination unit 14 corrects the already determined reference model using the occurrence of a new alarm and stop as a trigger for an alarm and stop that has occurred more than once. That is, in the case where the detection of machining abnormalities using the already determined reference model by the judgment unit 16 described later cannot be detected, the reference model determination unit 14 corrects the already determined reference model using the newly occurring alarm and stop as a trigger. For example, when a new alarm and stop occurs, the reference model determination unit 14 determines the correction model used to correct the reference model using the image of the chips captured within the prescribed period before the new alarm and stop occurs. For example, the reference model determination unit 14 corrects the already determined reference model by taking the average value of the size of the already determined reference model and the correction model as the new reference model.

[0033] The reference model storage unit 15 is, for example, a secondary storage medium such as a hard disk. The reference model storage unit 15 stores the reference model determined by the reference model determination unit 14. The reference model storage unit 15 stores, for example, a determined reference model of the size of chips.

[0034] The judgment unit 16 is implemented, for example, by operating a CPU. When the chips captured at a specified timing in subsequent processing have a similarity greater than a specified value with respect to the determined reference model, the judgment unit 16 judges that a processing abnormality has occurred. For example, the judgment unit 16 calculates the average value of the size of the chips contained in each image repeatedly captured by the camera unit 12 at a specified timing during the processing of the workpiece W. The judgment unit 16 compares the calculated average value of the size of the chips with the size of the chips of the determined reference model to calculate the similarity. When the calculated similarity is greater than a specified value, the judgment unit 16 judges that a processing abnormality has occurred. Here, as the size of the chips, the judgment unit 16, for example, calculates the average value of the pixel amount of each chip as the size of the chips for multiple chips contained in the image of the chips, similarly to the reference model determination unit 14.

[0035] The signal output unit 17 is implemented by, for example, a CPU. When the determination unit 16 determines that a processing abnormality exists, the signal output unit 17 outputs a signal indicating that a processing abnormality has occurred. The signal output unit 17 displays, for example, a signal indicating that a processing abnormality has occurred as a display image on a display device such as a monitor (not shown).

[0036] Next, refer to Figure 3 The flowchart of FIG. 1 illustrates the flow of operations of the control device 1 according to the present embodiment.

[0037] First, the imaging unit 12 starts imaging chips generated by machining the workpiece W (step S1). The imaging unit 12 stores the captured images in the image storage unit 13 in association with the imaging time. Next, the machine tool 100 starts machining the workpiece W (step S2).

[0038] Next, the determination unit 16 determines whether the determination of the baseline model has been executed by the baseline model determination unit 14 (step S3). The determination unit 16 determines, for example, whether the baseline model is stored in the baseline model storage unit 15. If the determination of the baseline model has been executed (step S3: "Yes"), the process proceeds to step S4. On the other hand, if the determination of the baseline model has not been executed (step S3: "No"), that is, if the alarm and stop have not occurred once, the process proceeds to step S7.

[0039] In step S4, the determination unit 16 calculates the average value of the size of the chips included in the image captured by the imaging unit 12. For example, the determination unit 16 calculates the average value of the number of pixels of the plurality of chips as the average value of the size of the chips. Then, the determination unit 16 calculates the similarity between the calculated average value and the size of the already determined reference model.

[0040] Next, the determination unit 16 determines whether the calculated average value of the size is abnormal (step S5). For example, when the calculated similarity is greater than a predetermined value, the determination unit 16 determines that there is a processing abnormality. When the determination unit 16 determines that there is an abnormality (step S5: "Yes"), the process proceeds to step S6. On the other hand, when the determination unit 16 determines that there is no abnormality (step S5: "No"), the process proceeds to step S7.

[0041] In step S6, the signal output unit 17 outputs a signal indicating that a machining abnormality has occurred. The signal output unit 17 displays a display indicating that a machining abnormality has occurred on a display device, for example. In addition, the alarm and stop execution unit 11 stops the machining operation of the machine tool 100. Thus, the processing of this flow ends.

[0042] In step S7, the alarm and stop execution unit 11 determines whether an alarm and stop have occurred in the machine tool 100. If an alarm and stop have occurred (step S7: "Yes"), the process proceeds to step S8. On the other hand, if an alarm and stop have not occurred (step S7: "No"), the process returns to step S10.

[0043] In step S8, the reference model determination unit 14 determines whether the occurrence of the alarm and stop is the first time. For example, when the reference model storage unit 15 does not store a reference model, the reference model determination unit 14 determines that the occurrence of the alarm and stop is the first time. When the occurrence of the alarm and stop is the first time (step S8: "Yes"), the process proceeds to step S9. On the other hand, when the occurrence of the alarm and stop is not the first time (step S8: "No"), the process proceeds to step S10.

[0044] In step S9 , the reference model determination unit 14 determines the average value of the sizes of the chips in a predetermined period before the alarm is issued and the operation is stopped as the reference model. This flow ends.

[0045] In step S10, the reference model determination unit 14 uses the average value of the size of the chips within a specified period before the alarm is issued and the machine stops to correct the already determined reference model. The reference model determination unit 14 corrects the existing reference model by, for example, using the average value of the existing reference model and the newly calculated correction model as a new reference model. Thus, the processing of this flow ends.

[0046] Next, the procedure of this embodiment is described.

[0047] Each configuration included in the control device 1 can be realized by hardware, software, or a combination thereof. Here, realization by software means realization by a computer reading and executing a program.

[0048] Various types of non-transitory computer readable media (Non-transitory Computer Readable Medium) can be used to store the program and provide the program to the computer. Non-transitory computer readable media include recording media (Tangible Storage Medium: physical recording media) with various types of entities. Examples of non-transitory computer readable media include magnetic recording media (such as floppy disks, magnetic tapes, hard disk drives), magneto-optical recording media (such as magneto-optical disks), CD-ROM (Read Only Memory: Read Only Memory), CD-R, CD-R / W, semiconductor memory (such as mask ROM, PROM (Programmable ROM: Programmable Read Only Memory), EPROM (Erasable PROM: Erasable Programmable Read Only Memory), Flash ROM, RAM (Random Access Memory: Random Access Memory)). In addition, the display program can also be provided to the computer through various types of transient computer readable media (Transitory Computer Readable Medium). Examples of transient computer readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer readable media can provide the program to a computer via a wired communication path such as electric wires and optical fibers, or via a wireless communication path.

[0049] As described above, according to the control device 1 and the program according to the first embodiment, the following effects are achieved.

[0050] (1) A control device 1 controls a machine tool 100 capable of issuing an alarm and stopping based on an abnormality in a machining load, the control device 1 comprising: an imaging unit 12 for capturing images of chips generated as a result of machining a workpiece W; a reference model determination unit 14 for predetermining a reference model of chips used to determine machining abnormalities based on images of chips captured within a specified period before the alarm and the stop, in response to the occurrence of an alarm and the stop; and a judgment unit 16 for determining that a machining abnormality has occurred when chips captured in subsequent machining have a similarity greater than a specified degree with respect to the determined reference model of chips.

[0051] In addition, there is a program for causing a computer to operate as a control device 1, which controls a machine tool 100 capable of issuing an alarm and stopping based on an abnormality in a machining load, and the program is used to cause the computer to function as the following units: a camera unit 12, which captures chips generated as a result of machining a workpiece W; a reference model determination unit 14, which, in response to the occurrence of an alarm and a stop, predetermines a reference model for chips used to determine that a machining abnormality has occurred based on images of chips captured within a specified period before the alarm and the stop; and a judgment unit 16, which determines that a machining abnormality has occurred when chips captured in subsequent machining have a similarity of more than a specified degree with respect to the determined reference model of chips.

[0052] Thus, in addition to the machining load, machining abnormalities can be detected based on more factors. Therefore, the possibility of detecting machining abnormalities before an alarm is issued and the machine stops is increased. If machining abnormalities can be detected earlier, it is preferred in that damage to the tool 101 or the machine tool 100 can be suppressed. For example, by suppressing the flow of fragments of the tool 101 or the workpiece W caused by the abnormal machining load into the coolant tank 102, the failure of the pump or chip conveyor of the coolant tank 102 can be suppressed in advance. In addition, the number of discarded workpieces W can be reduced by detecting machining abnormalities in advance.

[0053] (2) In response to the occurrence of a new alarm and stop, the reference model determination unit 14 corrects the already determined reference model based on the image of the chips captured within a predetermined period before the new alarm and stop. As a result, the accuracy of detecting machining abnormalities before the alarm and stop is improved. Therefore, the reliability of the control device 1 and the machine tool 100 controlled by the control device 1 can be improved.

[0054] [Second embodiment]

[0055] Next, refer to Figure 5 A control device 1 and a program according to a second embodiment of the present disclosure will be described. In the description of the second embodiment, the same components as those in the above-described embodiment are denoted by the same reference numerals, and the description thereof will be omitted or simplified.

[0056] The control device 1 of the second embodiment is different from the first embodiment in that the reference model determination unit 14 determines the average value of the shapes of the chips contained in the images of the chips captured within a predetermined period before the alarm is issued and the control device 1 stops as the reference model. Figure 5The determined reference model is corrected by using the overlapped portion of the shape of the chips related to the determined reference model and the shape of the chips of the correction model obtained by stopping due to the occurrence of a new alarm as the reference model. In addition, the control device 1 of the second embodiment is different from the first embodiment in that the judgment unit 16 obtains the shape of the chips based on the image captured by the camera unit 12 during the processing of the workpiece W. In addition, the control device 1 of the second embodiment is different from the first embodiment in that when the similarity between the shape of the acquired chips and the shape of the chips shown in the reference model is greater than a specified value, the judgment unit 16 determines that a processing abnormality has occurred.

[0057] As described above, according to the control device 1 and the program according to the second embodiment, the following effects are achieved.

[0058] The reference model determination unit 14 determines the shape of the chips as the reference model. In addition, when the similarity between the shape of the acquired chips and the shape of the chips shown in the reference model is greater than a predetermined value, the determination unit 16 determines that a machining abnormality has occurred. Thus, it is possible to determine that a machining abnormality has occurred based on other viewpoints. Since the method of determining a machining abnormality can be increased, a more general control device 1 and program can be provided.

[0059] [Third Embodiment]

[0060] Next, a control device 1 and a program according to a third embodiment of the present disclosure will be described. In the description of the third embodiment, the same components as those in the above-described embodiment are denoted by the same reference numerals, and the description thereof will be omitted or simplified.

[0061] The control device 1 according to the third embodiment is different from the first embodiment in that the reference model determination unit 14 determines the transition (rate of change) of the size of the chips contained in the image of the chips captured within the predetermined period traced back from the alarm and the stop as the reference model. In addition, the control device 1 according to the third embodiment is different from the first embodiment in that the reference model determination unit 14 corrects the already determined reference model by taking the average value of the transition of the size of the chips related to the already determined reference model and the transition of the size of the chips of the correction model obtained due to the occurrence of a new alarm and the stop as the new reference model. In addition, the control device 1 according to the third embodiment is different from the first embodiment in that the judgment unit 16 obtains the transition of the size of the chips within the predetermined period based on the image captured by the imaging unit 12 during the machining of the workpiece W. In addition, the control device 1 according to the third embodiment is different from the first embodiment in that when the similarity between the acquired transition of the size of the chips and the transition of the size of the chips shown in the reference model is greater than a predetermined value, the judgment unit 16 judges that a machining abnormality has occurred.

[0062] As described above, according to the control device 1 and the program according to the third embodiment, the following effects are achieved.

[0063] The reference model determination unit 14 determines the change in the amount of change in the size of the chips as the reference model. In addition, when the similarity between the change in the amount of change in the size of the chips obtained and the change in the amount of change in the size of the chips shown in the reference model is greater than a predetermined value, the determination unit 16 determines that a machining abnormality has occurred. Thus, it is possible to determine that a machining abnormality has occurred from other viewpoints. Since the method for determining a machining abnormality can be increased, a more general control device 1 and program can be provided.

[0064] [Fourth Embodiment]

[0065] Next, a control device 1 and a program according to a fourth embodiment of the present disclosure will be described. In the description of the fourth embodiment, the same components as those of the above-described embodiment are denoted by the same reference numerals, and the description thereof will be omitted or simplified.

[0066] The control device 1 involved in the fourth embodiment is different from the first to third embodiments in that the reference model determination unit 14 also calibrates the determined reference model based on the image of the chips captured within a specified period before the other machine tools 100 issue an alarm and stop. That is, the difference from the first to third embodiments is that the reference model determination unit 14 uses the reference models of the multiple machine tools 100 before the alarm and stop to determine the common reference model of the multiple machine tools 100. For example, the reference model determination unit 14 repeatedly calibrates the reference model of one machine tool 100 using the reference models of other machine tools 100, as the reference model determination unit 14 involved in the first to third embodiments described above, thereby determining the common reference model.

[0067] As described above, according to the control device 1 and the program according to the fourth embodiment, the following effects are achieved.

[0068] (3) The reference model determination unit 14 also corrects the determined reference model based on images of chips captured within a predetermined period before the other machine tools 100 generate an alarm and stop. Thus, if a reference model is determined for one machine, the reference model can also be used for the machine tools 100 that have not generated an alarm and stopped. Therefore, the operation of the plurality of machine tools 100 can be made more stable.

[0069] [Fifth Embodiment]

[0070] Next, a control device 1 and a program according to a fifth embodiment of the present disclosure will be described. In the description of the fifth embodiment, the same components as those in the above-described embodiment are denoted by the same reference numerals, and the description thereof will be omitted or simplified.

[0071] The control device 1 involved in the fifth embodiment is different from the first to fourth embodiments in that the reference model determination unit 14 determines a new reference model based on the image of the chips captured within a prescribed period before the new alarm and stop in response to the occurrence of the new alarm and stop. In addition, the control device 1 involved in the fifth embodiment is different from the first to fourth embodiments in that the judgment unit 16 corrects the similarity used to judge that a machining abnormality has occurred in a manner that includes the new reference model.

[0072] As described above, according to the control device 1 and the program according to the fifth embodiment, the following effects are achieved.

[0073] (4) In response to the occurrence of a new alarm and stop, the reference model determination unit 14 determines a new reference model based on the image of the chips captured within a specified period before the new alarm and stop, and the judgment unit 16 corrects the similarity used to judge the occurrence of a machining abnormality in a manner including the new reference model. Thus, the similarity used to judge the occurrence of a machining abnormality can be optimized. Therefore, the possibility of detecting the occurrence of a machining abnormality before the alarm and stop is increased.

[0074] As mentioned above, each preferred embodiment of the control device and the program of the present disclosure has been described, but the present disclosure is not limited to the above-mentioned embodiments, and appropriate changes can be made.

[0075] For example, in the above-mentioned embodiment, the camera unit 12 may also be configured to be movable within the machine tool 100. The camera unit 12 may also be configured to be movable by an automatic conveying device (not shown) including a robot. The camera unit 12 may also be configured to adjust the resolution, shooting interval, position, posture, etc. according to the processing program being executed. That is, the camera unit 12 may also optimize the position so that more chips can be photographed. In addition, the shooting conditions of the camera unit 12 may also be optimized by machine learning. In particular, the shooting conditions of the camera unit 12 may also be optimized in association with the timing of alarms in the machine tool 100 or peripheral equipment.

[0076] In the above embodiment, when the determination unit 16 determines that the similarity is lower than the value determined as abnormal but higher than a predetermined value, the imaging unit 12 may capture the chips at a shorter timing. This can improve the detection accuracy of the occurrence of machining abnormality, thereby improving the reliability of the control device 1.

[0077] In addition, in the above-mentioned embodiment, the reference model determination unit 14 may also determine the reference model based on the deviation of the size of the chips contained in the captured image. When the deviation of the size of the chips contained in the image captured during processing is greater than a predetermined similarity with the reference model, the determination unit 16 determines that a processing abnormality has occurred.

[0078] In addition, the above-mentioned embodiments may be combined arbitrarily as long as they are practicable. For example, the determination unit 16 may use two or more reference models to determine the occurrence of machining abnormalities. This can improve the accuracy of abnormality detection.

[0079] Furthermore, in each of the above-described embodiments, the control device may be configured in any of a form integrated with the machine tool and a form independent of the machine tool.

Claims

1. A control device for controlling a machine tool that can issue an alarm and stop based on an abnormality in a machining load, the control device comprising: A camera unit that captures chips generated as a result of machining the workpiece; a reference model determination unit that, in response to the occurrence of the alarm and stop, predetermines a reference model for chips judged as machining abnormalities based on images of chips captured during a prescribed period before the alarm and stop and until the alarm and stop, if the alarm and stop is the first time, and corrects the determined reference model of the chips if the alarm and stop is not the first time; and The determination unit determines that machining abnormality has occurred when chips imaged at a predetermined timing in subsequent machining have a predetermined degree of similarity or more with respect to the determined or corrected reference model of the chips.

2. The control device according to claim 1, characterized in that: In response to occurrence of a new alarm and stop, the reference model determination unit corrects the determined reference model based on images of chips captured within a predetermined period before the new alarm and stop is issued and until the new alarm and stop is issued.

3. The control device according to claim 1, characterized in that: The reference model determination unit determines a new reference model in response to occurrence of a new alarm and stop based on images of chips captured within a predetermined period before and until a new alarm and stop is issued, The determination unit corrects the similarity used to determine that a machining abnormality has occurred so as to include a new reference model.

4. The control device according to claim 2, characterized in that: The reference model determination unit further corrects the determined reference model based on images of chips captured within a predetermined period before the other machine tools are stopped due to an alarm and until the time when the other machine tools are stopped due to an alarm.

5. A computer-readable recording medium having a program recorded thereon for causing a computer to execute a control process for controlling a machine tool capable of generating an alarm and stopping based on an abnormality in a machining load, the program causing the computer to execute the following process: Camera processing, photographing the chips produced as a result of machining the workpiece; A reference model determination process for, in response to the occurrence of the alarm and stop, predetermining a reference model for chips judged as machining abnormalities based on images of chips captured during a prescribed period before the alarm and stop and until the alarm and stop, if the alarm and stop is the first time, and correcting the determined reference model of the chips if the alarm and stop is not the first time; and The determination process determines that a machining abnormality has occurred when the chips photographed at a predetermined timing in subsequent machining have a predetermined or greater similarity with the determined or corrected reference model of the chips.

Images