Abnormality detection device

Abstract

This abnormality detection device: causes a motor that drives a drive unit at a plurality of rotation speeds to run a detection operation on the basis of an instruction to diagnose the state of the drive unit; acquires, as information indicating the operating state of the drive unit, a control instruction for the motor driving the drive unit or a feedback signal from the motor driving the drive unit, during the detection operation; analyzes the control instruction for the motor driving the drive unit or the feedback signal from the motor; determines the state of the drive unit on the basis of the result of the analysis; and reports, on the basis of the determination result, that the state of the drive unit is different from that in normal time.

Description

Technical Field

[0001] The present invention relates to an abnormality detection device, and particularly to an abnormality detection device for detecting the biting of foreign matter into a drive unit of a machine tool.

Background Art

[0002] A machine tool cuts a workpiece with a tool attached to a spindle. During the cutting of the workpiece, chips, metal powder, etc. are generated. Also, during the cutting of the workpiece, depending on the machining content or due to tool wear or breakage, etc., the tool attached to the spindle is exchanged.

[0003] When exchanging a tool in a machine tool, chips, metal powder, etc. may get caught between the tapered surface and the shank. When chips, metal powder, etc. get caught between the tapered surface and the shank, the tool is inaccurately clamped with the relative position of the tool with respect to the spindle deviated from the original position. Then, when machining is started as it is and the spindle rotates at high speed, the cutting tool may break, chatter vibration may occur and the machining surface quality may deteriorate, or the accuracy of roundness and surface roughness may deteriorate.

[0004] To solve such problems, for example, there is a detection method based on a change in power value caused by the biting of chips, etc. (for example, Patent Document 1, etc.). Also, there is a method of acquiring waveform data of an externally attached detection sensor (for example, a vibration sensor attached to the spindle chuck part) and analyzing it by AI (deep learning) (for example, Patent Document 2, etc.).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] When minute chips, metal powder, etc. get caught between the tapered surface and the shank, the mounting state of the tool on the spindle is only slightly eccentric but hardly changes compared to the case where nothing is caught. Therefore, there is a problem that it is difficult to automatically detect such an abnormality with a simple tool mounting abnormality detection function. Although it is conceivable to provide a highly accurate sensor to detect the intrusion of minute foreign matter, this leads to an increase in equipment costs, and also greatly affects the inspection accuracy depending on the mounting position of the sensor and the location of the intruded foreign matter. In addition, since it is necessary to always analyze the vibration waveform, it also leads to an increase in calculation costs.

[0007] In addition, the types of abnormalities related to the spindle include not only the intrusion of chips, etc., but also abnormalities such as variations in the processed workpiece and wear of the tool itself. Therefore, there is also a possibility that the situation where foreign matter has been caught cannot be accurately detected. Furthermore, the same problem also occurs when minute chips, metal powder, etc. enter and do not come out between the guide surface of the feed axis and the drive unit, or when minute chips, metal powder, etc. are caught in the groove of the ball screw nut, etc., that is, when minute foreign matter enters the drive unit driven by the electric motor of the machine tool. Therefore, a technique for automatically and accurately detecting a slight abnormal state of the tool clamp is desired.

Means for Solving the Problem

[0008] The abnormality detection device according to one aspect of the present invention solves the above problems by observing the response of the spindle while causing the motor (spindle) to perform a detection operation of rotating at a plurality of rotational speeds and detecting the eccentricity of the tool based on the response.

[0009] And one aspect of the present invention is an abnormality detection device that detects foreign matter being bitten into a drive unit driven by a motor in a machine tool. Based on a command for diagnosing the state of the drive unit and a feedback signal of the motor, a control unit creates a control command for causing the motor that drives the drive unit to perform a detection operation at a plurality of rotational speeds, and during the detection operation, a drive unit information acquisition unit acquires, as information indicating the operating state of the drive unit, the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit based on the control command. Based on the frequency distribution of the result of frequency analysis of the control command for the motor driving the drive unit acquired by the drive unit information acquisition unit or the feedback signal of the motor driving the drive unit, and the frequency distribution of the result of frequency analysis of the control command for the motor driving the drive unit or the feedback signal of the motor driving the drive unit obtained in advance when the motor driving the drive unit is detected and operated normally, a drive unit state determination unit that determines the state of the drive unit; An abnormality detection device comprising: a notification unit that notifies that the state of the drive unit is different from the normal state based on a determination result by the drive unit state determination unit.

Effects of the Invention

[0010] According to one aspect of the present invention, it becomes possible to detect the biting of foreign matter into the spindle with high accuracy without incurring the introduction cost of a high-precision sensor or the like.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a schematic hardware configuration diagram showing the main part of an abnormality detection device according to an embodiment of the present invention. The abnormality detection device 1 of the present invention can be implemented, for example, as a control device for controlling a machine tool, and can also be implemented in a personal computer installed together with the control device for controlling the machine tool, or an edge computer, fog computer, cloud server, etc. connected to the control device via a wired / wireless network. In this embodiment, an example of the abnormality detection device implemented as a control device for controlling a machine tool is shown.

[0013] The CPU 11 included in the abnormality detection device 1 of the present invention is a processor that controls the entire abnormality detection device 1. The CPU 11 reads out the system program stored in the ROM 12 via the bus 22 and controls the entire abnormality detection device 1 according to the system program. Temporary calculation data, display data, and various data input from the outside are temporarily stored in the RAM 13.

[0014] The non-volatile memory 14 is composed of, for example, a memory backed up by a battery (not shown) or an SSD (Solid State Drive), etc., and the storage state is maintained even when the power of the abnormality detection device 1 is turned off. In the non-volatile memory 14, data read from the external device 72 via the interface 15, processing programs, data and processing programs input via the input device 71, various data acquired from the machine tool, etc. are stored. The data and processing programs stored in the non-volatile memory 14 may be expanded to the RAM 13 at the time of execution / use. Also, various system programs such as known analysis programs are written in advance in the ROM 12.

[0015] The interface 15 is an interface for connecting the CPU 11 of the abnormality detection device 1 and an external device 72 such as a USB device. From the external device 72 side, for example, a processing program and various parameters used for controlling the machine tool can be read. Also, the processing program and various parameters edited in the abnormality detection device 1 can be stored in the external storage means via the external device 72.

[0016] The programmable logic controller (PLC) 16 outputs and controls signals to the machine tool and peripheral devices of the machine tool (for example, tool changers, actuators such as robots, sensors attached to the machine tool, etc.) via the I / O unit 17 using the sequence program built into the abnormality detection device 1. Further, it receives signals from various switches on the operation panel and peripheral devices provided on the main body of the industrial machine, performs necessary signal processing on the signals, and then passes them to the CPU 11.

[0017] To the display device 70, each data read into the memory, data obtained as a result of executing a machining program, a system program, etc. are output and displayed via the interface 18. Further, the input device 71 composed of a keyboard, a pointing device, etc. passes commands, data, etc. based on operations by the operator to the CPU 11 via the interface 19.

[0018] The axis control circuit 30 for controlling the axes provided in the machine tool receives a control command amount for moving the drive unit along the axis from the CPU 11 and outputs this command to the servo amplifier 40. The servo amplifier 40 receives this command and drives the servo motor 50 that moves the drive unit provided in the machine tool along the axis. The servo motor 50 of the axis incorporates a position / velocity detector, and feeds back the position / velocity feedback signal from this position / velocity detector to the axis control circuit 30 to perform position / velocity feedback control. In the hardware configuration diagram of FIG. 1, only one each of the axis control circuit 30, the servo amplifier 40, and the servo motor 50 is shown, but actually, they are prepared in the number corresponding to the number of axes provided in the machine tool to be controlled. For example, when controlling a general machine tool, three sets of axis control circuits 30, servo amplifiers 40, and servo motors 50 for relatively moving the spindle to which the tool is attached and the workpiece in the three linear axes (X-axis, Y-axis, Z-axis) directions are prepared.

[0019] The spindle control circuit 60 receives a spindle rotation command and outputs a spindle speed signal to the spindle amplifier 61. The spindle amplifier 61 receives this spindle speed signal and rotates the spindle motor 62 of the machine tool at the commanded rotational speed to drive the tool. A position coder 63 is coupled to the spindle motor 62, and the position coder 63 outputs feedback pulses in synchronization with the rotation of the spindle, and the feedback pulses are read by the CPU 11.

[0020] FIG. 2 schematically shows, as a block diagram, the functions provided by the abnormality detection device 1 according to an embodiment of the present invention. Each function provided by the abnormality detection device 1 according to the present embodiment is realized by the CPU 11 provided in the abnormality detection device 1 shown in FIG. 1 executing a system program and controlling the operations of the respective parts of the abnormality detection device 1. The abnormality detection device 1 according to the present embodiment focuses on the spindle as a drive unit driven by an electric motor of a machine tool, and has a function of detecting minute changes occurring in the spindle by causing the spindle to perform operations for detection at a plurality of rotational speeds and analyzing the results.

[0021] The abnormality detection device 1 of the present embodiment includes a control unit 110, a drive unit information acquisition unit 120, a drive unit state determination unit 130, and a notification unit 140. Further, in the RAM 13 to the non-volatile memory 14 of the abnormality detection device 1, an NC program 210 acquired from the input device 71, the external device 72, etc. is stored in advance. Furthermore, in the RAM 13 to the non-volatile memory 14 of the abnormality detection device 1, there are provided a drive unit information storage unit 220 which is an area for storing information related to the operating state of the spindle as the drive unit, and a normal-time drive unit information storage unit 230 in which information related to the operating state of the spindle acquired when the spindle as the drive unit is operating normally is stored in advance.

[0022] The control unit 110 executes the system program read by the CPU 11 of the abnormality detection device 1 shown in FIG. 1 from the ROM 12, and is mainly realized by performing arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11, and control processing of each part of the machine tool 2 using the axis control circuit 30, the spindle control circuit 60, and the PLC 16. The control unit 110 analyzes the NC program 210 and creates command data for controlling the machine tool 2 equipped with the servo motor 50 and the spindle motor 62 and the peripheral devices of the machine tool 2. Then, based on the created command data, the control unit 110 controls each part of the machine tool 2 and the peripheral devices. For example, the control unit 110 generates data related to the movement of the axis based on a command to move the drive unit along each axis of the machine tool 2 and outputs it to the servo motor 50. Also, for example, the control unit 110 generates data related to the rotation of the spindle based on a command to rotate the spindle of the machine tool 2 and outputs it to the spindle motor 62. Further, for example, the control unit 110 generates a predetermined signal for operating the peripheral device based on a command to operate the peripheral device of the machine tool 2 and outputs it to the PLC 16. On the other hand, the control unit 110 acquires the states (such as the current value, position, speed, acceleration, torque, etc. of the motor) of the servo motor 50 and the spindle motor 62 as feedback values and uses them for each control process.

[0023] The control unit 110 switches to a diagnostic mode for diagnosing the state of the spindle based on a command from the NC program 210 or a command from an operator received from an operation panel or an input device 71 (not shown). When switching to the diagnostic mode, the control unit 110 creates command data for causing the spindle to perform a detection operation at a plurality of rotational speeds, and controls the rotational operation of the spindle based on the command data. The detection operation rotates the spindle at at least a plurality of predetermined rotational speeds. The detection operation may be a so-called sweep operation in which the rotational speed of the spindle is continuously changed as illustrated in FIG. 3, or when it is desired to detect the state of the spindle with higher accuracy, as illustrated in FIG. 4, it may be an operation in which the speed is maintained for a predetermined time at a plurality of predetermined rotational speeds. The time for maintaining this speed varies depending on the material and shape of the spindle and the tool, etc., but it may be a time sufficient for an increase in vibration due to resonance to occur (for example, 300 to 500 msec).

[0024] The drive unit information acquisition unit 120 executes a system program read by the CPU 11 provided in the abnormality detection device 1 shown in FIG. 1 from the ROM 12, and mainly realizes arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11, and control processing of each part of the machine tool 2 using the axis control circuit 30, the spindle control circuit 60, and the PLC 16. When the machine tool 2 is performing a detection operation by the control unit 110, the drive unit information acquisition unit 120 acquires information related to the operating state of the spindle motor 62. The information related to the operating state of the spindle motor 62 acquired by the drive unit information acquisition unit 120 may be, for example, a torque command for the spindle motor 62, or may also be the current value or voltage value of the spindle motor 62, or further may be information such as the position and speed fed back from the spindle motor 62. These information can be acquired without attaching a special sensor or the like to the spindle motor 62, and the influence of the vibration generated in the spindle motor 62 appears. The drive unit information acquisition unit 120 acquires these information from the control unit 110, and stores the information related to the operating state of the acquired spindle motor 62 in the drive unit information storage unit 220 as time-series data.

[0025] The drive unit state determination unit 130 is realized by executing the system program read by the CPU 11 provided in the abnormality detection device 1 shown in FIG. 1 from the ROM 12, mainly by performing arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11. The drive unit state determination unit 130 analyzes the information related to the operating state of the spindle motor 62 stored in the drive unit information storage unit 220. The drive unit state determination unit 130 performs, for example, frequency analysis or statistical analysis on the information related to the operating state of the spindle motor 62 stored in the drive unit information storage unit 220, which is time-series data. When performing frequency analysis, the drive unit state determination unit 130 may use a known analysis method such as Fourier transform. When performing statistical analysis, known statistical quantities such as mean, variance, standard deviation, skewness, and kurtosis may be calculated and analyzed for the values measured when the spindle is rotated at each rotational speed. The drive unit state determination unit 130 analyzes whether the operating state of the spindle motor 62 is normal based on the information related to the operating state of the spindle motor 62 analyzed in this way and the information stored in the normal drive unit information storage unit 230.

[0026] The drive unit state determination unit 130 may also analyze whether the operating state of the spindle motor 62 is normal based on, for example, the similarity between the information related to the operating state of the spindle obtained when the spindle is operating normally and the information related to the operating state of the spindle motor 62 acquired by the drive unit information acquisition unit 120. The drive unit state determination unit 130 can determine that the state of the spindle is normal when the similarity is equal to or greater than a predetermined threshold. When determining the normality / abnormality of the operating state of the spindle motor 62 based on the information related to the operating state of the spindle, the normal drive unit information storage unit 230 stores in advance the information related to the operating state of the spindle motor 62 (frequency distribution, various statistical quantities, etc.) obtained when the spindle is operating normally.

[0027] Fig. 5 shows an example of the frequency distribution of information (torque command) related to the operating state of the spindle motor 62 during normal operation. Fig. 6 shows an example of the frequency distribution of information (torque command) related to the operating state of the spindle motor 62 when minute chips or the like are caught. As shown in Fig. 6, when the spindle motor 62 is operated with minute chips or the like caught, the resonance point changes, and the main frequency components of the information related to its operating state are different from those during normal operation. Therefore, the similarity of the frequency distributions may be determined to be similar when, for example, for a predetermined number of frequencies with large components, the sum of the squared differences in amplitude at each frequency is less than or equal to a predetermined threshold. Also, the similarity may be calculated using an algorithm for calculating the similarity of general frequency distributions, and a determination of similarity may be made based on the calculated value.

[0028] Fig. 7 shows an example in which statistics such as the average value are calculated for each rotational speed for information (torque command) related to the operating state detected when the spindle motor 62 is operated stepwise at a plurality of rotational speeds during normal (normal A and B) and abnormal (with chips) times. As shown in Fig. 7, during normal operation, the statistics at each rotational speed take similar values and change trends. However, during abnormal operation, it has been experimentally observed that different values or change trends from those during normal operation are taken. For example, focusing on the variance value or the standard deviation, a peak (the part indicated by the white arrow in the figure) that is not seen during normal operation appears during abnormal operation. It is difficult to detect the catching of minute chips simply by operating the drive unit. However, by operating stepwise at a plurality of rotational speeds, calculating the statistics at each rotational speed, and comparing them with the statistics at each rotational speed during normal operation, it becomes possible to easily detect an abnormality (catching of chips).

[0029] At this time, the normal driving unit information storage unit 230 may store a plurality of typical samples of information related to the operating state of the spindle motor 62 obtained when the main spindle is operating normally. Further, the normal driving unit information storage unit 230 may store information related to the operating state of each spindle motor 62 when different tools are attached. Even during normal operation, the information related to the operating state of the spindle motor 62 may vary depending on the environment, deposits on the main spindle or tool, the type of tool, etc. However, by storing samples of information related to several operating states in advance, if information related to an operating state similar to any of the samples is obtained, the driving unit state determination unit 130 can determine that the state of the main spindle is normal.

[0030] The drive unit state determination unit 130 may, for example, perform machine learning on information (such as frequency distribution and statistical quantities) related to the operating state of the main shaft obtained when the main shaft is operating normally, and based on the learning model obtained through this machine learning and the information (such as frequency distribution and statistical quantities) related to the operating state of the spindle motor 62 acquired by the drive unit information acquisition unit 120, analyze whether the operating state of the spindle motor 62 is normal. In this case, the normal drive unit information storage unit 230 stores in advance a learning model obtained by learning information related to the operating state of the spindle motor 62 acquired when the main shaft is operating normally. The learning model may be, for example, a cluster set or an autoencoder obtained by performing unsupervised learning on information related to the normal operating state of the spindle motor 62. Also, the learning model may be, for example, a neural network or a support vector machine obtained by performing supervised learning using information related to the normal operating state of the spindle motor 62 and information related to the abnormal operating state of the spindle motor 62. For example, when using a cluster set, if the distance between the cluster set stored in the normal drive unit information storage unit 230 and the information related to the operating state of the spindle motor 62 acquired by the drive unit information acquisition unit 120 falls within a predetermined threshold value, the drive unit state determination unit 130 can determine that the state of the main shaft is normal. Similarly, when using an autoencoder, a neural network, or a support vector machine, the calculated value is compared with a predetermined threshold value, and it is possible to determine whether it is normal based on the degree of deviation.

[0031] The notification unit 140 is realized by the CPU 11 of the abnormality detection device 1 shown in FIG. 1 executing the system program read from the ROM 12, mainly including arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11, and input / output processing using the interface 18 and the like. When the driving unit state determination unit 130 does not determine that the state of the main shaft is normal, that is, when it determines that the state of the main shaft is abnormal, the notification unit 140 gives a predetermined notification to each unit. When it is not determined that the state of the main shaft is normal, the notification unit 140 may, for example, display on the display device 70 that a foreign object has been caught in the main shaft, or issue an alarm indicating that a foreign object has been caught in the main shaft, or output a machine stop signal to the control unit 110, or further transmit a message indicating that a foreign object has been caught in the main shaft to a higher-level management device (such as a fog computer or a cloud server) via a network (not shown).

[0032] With the abnormality detection device 1 according to the present embodiment having the above configuration, by analyzing information related to the operating state of the spindle motor 62, it is possible to detect with high accuracy even when a minute foreign object has been caught in the main shaft. In the diagnosis mode for diagnosing an abnormality of the main shaft, a detection operation of rotating the main shaft at a plurality of predetermined rotational speeds is performed. By maintaining the rotation for a predetermined time at the plurality of rotational speeds, it is possible to easily detect a deviation of the resonance point and a change in the statistic. Further, by analyzing the difference from the normal state based on the frequency distribution of the information related to the operating state and the change in the statistic at each rotational speed, it is possible to detect minute changes that are difficult to detect by simply analyzing the time-series data as it is.

[0033] As described above, an embodiment of the present invention has been described. However, the present invention is not limited only to the examples of the above-described embodiments, and can be implemented in various modes by making appropriate changes. For example, in the above-described embodiment, by analyzing information related to the operating state of the spindle motor 62 that drives the spindle, a difference from the normal state is detected, and a minute change such as minute foreign matter biting into the spindle is detected. However, the same detection method may be applied to information related to the operating state of the servo motor 50 that drives the feed shaft that moves the spindle or the ball screw nut. Thereby, when minute chips, metal powder, etc. enter between the guide surface of the feed shaft that moves the spindle and the drive unit and do not come out, or when minute chips, metal powder, etc. bite into the groove of the ball screw nut that moves the spindle, etc., it is also possible to detect minute changes even when minute foreign matter enters the drive unit driven by the electric motor of the machine tool.

Explanation of Signs

[0034] 1 Abnormality detection device 2 Machine tool 11 CPU 12 ROM 13 RAM 14 Non-volatile memory 15, 18, 19 Interface 16 PLC 17 I / O unit 22 Bus 30 Axis control circuit 40 Servo amplifier 50 Servo motor 60 Spindle control circuit 61 Spindle amplifier 62 Spindle motor 63 Position coder 70 Display device 71 Input device 72 External device 110 Control unit 120 Drive unit information acquisition unit 130 Drive unit state determination unit 140 Notification unit 210 NC program 220 Drive unit information storage unit 230 Normal-time drive unit information storage unit

Claims

1. An abnormality detection device for detecting that a foreign object has been bitten into a drive unit driven by a motor in a machine tool, a control unit that creates a control command for causing the motor that drives the drive unit to perform a detection operation at a plurality of rotational speeds based on a command for diagnosing the state of the drive unit and a feedback signal of the motor, a drive unit information acquisition unit that acquires, as information indicating the operation state of the drive unit, the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit based on the control command during the detection operation, a drive unit state determination unit that determines the state of the drive unit based on the similarity between the frequency distribution of the result of frequency-analyzing the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit acquired by the drive unit information acquisition unit and the frequency distribution of the result of frequency-analyzing the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit acquired in advance when the motor that drives the drive unit is caused to perform a detection operation normally, a notification unit that notifies that the state of the drive unit is different from the normal state based on the determination result by the drive unit state determination unit, An abnormality detection device comprising the above.

2. An abnormality detection device for detecting that a foreign object has been bitten into a drive unit driven by a motor in a machine tool, a control unit that creates a control command for causing the motor that drives the drive unit to perform a detection operation at a plurality of rotational speeds based on a command for diagnosing the state of the drive unit and a feedback signal of the motor, a drive unit information acquisition unit that acquires, as information indicating the operation state of the drive unit, the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit based on the control command during the detection operation, a drive unit state determination unit that analyzes the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit acquired by the drive unit information acquisition unit and determines the state of the drive unit based on the result of the analysis, a notification unit that notifies that the state of the drive unit is different from the normal state based on the determination result by the drive unit state determination unit, Comprising the above, A learning model obtained by performing machine learning on data obtained by frequency analysis of a control command for a motor that drives the drive unit or a feedback signal of the motor that drives the drive unit, which was acquired in advance when the motor that drives the drive unit was detected and operated normally, is stored in advance. The drive unit state determination unit determines the state of the drive unit based on the learning model and the result of frequency analysis of a control command for the motor that drives the drive unit or a feedback signal of the motor that drives the drive unit, which is acquired by the drive unit information acquisition unit. An abnormality detection device.

3. An abnormality detection device for detecting that a foreign object has been bitten into a drive unit driven by a motor in a machine tool, a control unit that creates a control command for detecting and operating the motor that drives the drive unit at a plurality of rotational speeds based on a command for diagnosing the state of the drive unit and a feedback signal of the motor; a drive unit information acquisition unit that acquires, as information indicating the operating state of the drive unit, a control command for the motor that drives the drive unit or a feedback signal of the motor that drives the drive unit based on the control command during the detection operation; a drive unit state determination unit that determines the state of the drive unit based on the similarity of the value and change tendency between the result of calculating the statistic at each rotational speed for the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit acquired by the drive unit information acquisition unit, and the result of calculating the statistic at each rotational speed for the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit, which was acquired in advance when the motor that drives the drive unit was detected and operated normally; a notification unit that notifies that the state of the drive unit is different from the normal state based on the determination result by the drive unit state determination unit; An abnormality detection device comprising the above.

4. An abnormality detection device for detecting that a foreign object has been bitten into a drive unit driven by a motor in a machine tool, a control unit that creates a control command for detecting and operating the motor that drives the drive unit at a plurality of rotational speeds based on a command for diagnosing the state of the drive unit and a feedback signal of the motor; A drive unit information acquisition unit that acquires, as information indicating the operating state of the drive unit, the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit based on the control command during the detection operation; A drive unit state determination unit that analyzes the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit acquired by the drive unit information acquisition unit, and determines the state of the drive unit based on the result of the analysis; A notification unit that notifies that the state of the drive unit is different from the normal state based on the determination result by the drive unit state determination unit; Comprising: Data obtained by machine learning of the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit, which were acquired in advance when the motor that drives the drive unit was detected during normal operation, and the statistical quantities at each rotational speed are calculated, and a learning model is stored in advance; The drive unit state determination unit determines the state of the drive unit based on the learning model and the result of calculating the statistical quantities at each rotational speed for the control command for the motor that drives the drive unit or the feedback signal of the motor that drives the drive unit acquired by the drive unit information acquisition unit; An abnormality detection device.

5. The control unit controls to maintain each rotational speed for a predetermined time determined in advance during the detection operation. The abnormality detection device according to any one of claims 1 to 4.

Images