Diagnosis device

Abstract

This diagnosis device comprises a first acquisition unit that acquires first state data indicating the state of a diagnosis subject, a normal diagnosis unit that diagnoses an abnormality in the diagnosis subject on the basis of the first state data acquired by the first acquisition unit, a second acquisition unit that acquires second state data different from the first state data on the basis of a diagnosis result obtained by the normal diagnosis unit, and an emergency diagnosis unit that diagnoses a case of an abnormality that has occurred in the diagnosis subject on the basis of the second state data acquired by the second acquisition unit.

Description

diagnostic equipment

[0001] The present disclosure relates to a diagnostic device for diagnosing an abnormality.

[0002] 2. Description of the Related Art There is known a technique for diagnosing signs of abnormalities occurring in industrial machinery by collecting and analyzing a large amount of physical quantity data such as current and vibration (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2020-12691

[0004] However, collecting and analyzing a large amount of physical quantity data increases data management costs. For example, the load of analyzing a large amount of physical quantity data increases. Furthermore, a large amount of physical quantity data that does not significantly contribute to the accuracy of abnormality diagnosis is accumulated. On the other hand, if the amount of collected data is small, there is a risk that abnormality diagnosis will not be performed with high accuracy. Therefore, there is a demand for a diagnostic device that can reduce the cost related to abnormality diagnosis and ensure the reliability of abnormality diagnosis.

[0005] The diagnostic device of the present disclosure includes a first acquisition unit that acquires first status data indicating the status of the object to be diagnosed, a continuous diagnostic unit that diagnoses an abnormality in the object to be diagnosed based on the first status data acquired by the first acquisition unit, a second acquisition unit that acquires second status data different from the first status data based on the diagnosis result by the continuous diagnostic unit, and an emergency diagnostic unit that diagnoses the cause of an abnormality that has occurred in the object to be diagnosed based on the second status data acquired by the second acquisition unit.

[0006] 1 is a diagram illustrating an example of a system including a diagnostic device. FIG. 2 is a block diagram illustrating an example of a hardware configuration of an industrial machine. FIG. 3 is a block diagram illustrating an example of a hardware configuration of a diagnostic device. FIG. 4 is a block diagram illustrating an example of functions of the diagnostic device. FIG. 5 is a diagram illustrating an example of a diagnostic result. FIG. 6 is an example of a display screen that displays information generated by a trigger generation unit. FIG. 7 is an example of a reception screen. FIG. 8 is a diagram illustrating an example of a diagnostic result displayed on a display device. FIG. 9 is a flowchart illustrating an example of a processing flow executed by the diagnostic device. FIG. 10 is a block diagram illustrating an example of functions of a diagnostic device. FIG. 11 is a diagram for explaining clustering. FIG. 12 is a diagram illustrating an example of a diagnostic result. FIG. 13 is an example of a display screen that displays information generated by a trigger generation unit.

[0007] Hereinafter, a diagnostic device according to an embodiment of the present disclosure will be described with reference to the drawings. In the following description, components having the same or similar functions will be denoted by the same reference numerals. Duplicate descriptions of those components may be omitted.

[0008] In this application, "based on XX" means "based on at least XX," and includes cases where it is based on other elements in addition to XX. Furthermore, "based on XX" is not limited to cases where XX is used directly, but also includes cases where it is based on XX that has been calculated or processed. "XX" is any element (for example, any information).

[0009] First Embodiment Fig. 1 is a diagram illustrating an example of a system including a diagnostic device. This system includes, for example, an industrial machine 1 and a diagnostic device 10. The industrial machine 1 is a machine that operates at an industrial site. The industrial machine 1 is, for example, a machine tool, an injection molding machine, a laser processing machine, a three-dimensional printer, or a robot. The industrial machine 1 is controlled by a control device 2.

[0010] The diagnostic device 10 is a device that diagnoses abnormalities in the industrial machine 1. The diagnostic device 10 is connected to the control device 2 by wire or wirelessly. The diagnostic device 10 may be implemented in the control device 2.

[0011] 2 is a block diagram showing an example of a hardware configuration of the industrial machine 1. The industrial machine 1 includes a control device 2, an input / output device 3, a servo amplifier 4, a servo motor 5, a spindle amplifier 6, a spindle motor 7, an auxiliary device 8, and a sensor 9.

[0012] The control device 2 is, for example, a numerical control device that controls the industrial machine 1. The control device 2 includes, for example, a hardware processor 201, a bus 202, a read-only memory (ROM) 203, a random access memory (RAM) 204, and a non-volatile memory 205.

[0013] The hardware processor 201 is a processor that controls the entire control device 2 in accordance with a system program. The hardware processor 201 reads the system program stored in the ROM 203 via the bus 202. The hardware processor 201 is, for example, a CPU (Central Processing Unit) or an electronic circuit.

[0014] The bus 202 is a communication path that connects the various pieces of hardware in the control device 2. The various pieces of hardware in the control device 2 exchange data via the bus 202.

[0015] The ROM 203 is a storage device that stores system programs, etc. The ROM 203 is a computer-readable storage medium.

[0016] The RAM 204 is a storage device that temporarily stores various data and functions as a work area for the hardware processor 201 to process various data.

[0017] The nonvolatile memory 205 is a storage device that retains data even when the power to the control device 2 is turned off. The nonvolatile memory 205 stores, for example, an operation program for the industrial machine 1. The nonvolatile memory 205 is a computer-readable storage medium. The nonvolatile memory 205 is, for example, a memory backed up by a battery or an SSD (Solid State Drive).

[0018] The control device 2 further includes a first interface 206, an axis control circuit 207, a spindle control circuit 208, a PLC (Programmable Logic Controller) 209, an I / O unit 210, a second interface 211, and a third interface 212.

[0019] The first interface 206 connects the bus 202 and the input / output device 3. The first interface 206 sends various data processed by the hardware processor 201 to the input / output device 3, for example.

[0020] The input / output device 3 receives various data via the first interface 206 and displays the various data on a display. The input / output device 3 also receives input of various data and sends the various data to, for example, the hardware processor 201 via the first interface 206.

[0021] The input / output device 3 is, for example, a touch panel. When the input / output device 3 is a touch panel, the input / output device 3 is, for example, a capacitive touch panel. The touch panel is not limited to a capacitive touch panel and may be a touch panel of another type. The input / output device 3 is installed in an operation panel (not shown) in which the control device 2 is housed.

[0022] The axis control circuit 207 is a circuit for controlling the servo motor 5. The axis control circuit 207 receives control commands from the hardware processor 201 and sends various commands to the servo amplifier 4 for driving the servo motor 5. The axis control circuit 207 sends, for example, a torque command for controlling the torque of the servo motor 5 to the servo amplifier 4.

[0023] The servo amplifier 4 receives a command from the axis control circuit 207 and supplies a current to the servo motor 5 .

[0024] The servo motors 5 are driven by receiving a current supply from the servo amplifier 4. The servo motors 5 are provided for each control axis of the industrial machine 1. If the industrial machine 1 is a machine tool having five axes, the servo motors 5 include, for example, an X-axis servo motor, a Y-axis servo motor, a Z-axis servo motor, an A-axis servo motor, and a C-axis servo motor. In this case, an axis control circuit 207 and a servo amplifier 4 are provided for each servo motor 5.

[0025] The servo motor 5 is connected to, for example, a ball screw that drives a tool post. When the servo motor 5 is driven, a structure of the industrial machine 1, such as the tool post, moves along a predetermined control axis.

[0026] The servo motor 5 has a built-in encoder (not shown) that detects the position and feed rate of the control axis. Position feedback information and speed feedback information indicating the position and feed rate of the control axis detected by the encoder are fed back to the axis control circuit 207. In this way, the axis control circuit 207 performs feedback control of each control axis.

[0027] The spindle control circuit 208 is a circuit for controlling the spindle motor 7. The spindle control circuit 208 receives a control command from the hardware processor 201 and sends a command to the spindle amplifier 6 to drive the spindle motor 7. The spindle control circuit 208 sends, for example, a spindle speed command to the spindle amplifier 6 to control the rotation speed of the spindle motor 7.

[0028] The spindle amplifier 6 receives a command from the spindle control circuit 208 and supplies a current to the spindle motor 7 .

[0029] The spindle motor 7 is driven by receiving a current supplied from the spindle amplifier 6. The spindle motor 7 is connected to the main shaft and rotates the main shaft.

[0030] The PLC 209 is a device that executes a ladder program to control the auxiliary device 8. The PLC 209 sends commands to the auxiliary device 8 via an I / O unit 210.

[0031] The I / O unit 210 is an interface that connects the PLC 209 and the auxiliary device 8. The I / O unit 210 sends commands received from the PLC 209 to the auxiliary device 8.

[0032] The auxiliary device 8 is installed in the industrial machine 1 and performs auxiliary operations in the industrial machine 1. The auxiliary device 8 operates based on commands received from the I / O unit 210. The auxiliary device 8 may be a device installed in the periphery of the industrial machine 1. The auxiliary device 8 is, for example, a tool changer, a cutting fluid injection device, or an opening / closing door drive device.

[0033] The second interface 211 connects the bus 202 and the sensor 9. The second interface 211 sends, for example, information acquired by the sensor 9 to the hardware processor 201 via the bus 202.

[0034] The sensors 9 are installed in various parts of the industrial machine 1 and detect various physical quantities. The sensors 9 are, for example, a temperature sensor, an acceleration sensor, an ammeter, and a liquid level meter.

[0035] The third interface 212 connects the bus 202 and the diagnostic device 10. The third interface 212 sends, for example, information processed by the hardware processor 201 to the diagnostic device 10 via the bus 202.

[0036] 3 is a block diagram showing an example of the hardware configuration of the diagnostic device 10. The diagnostic device 10 includes, for example, a hardware processor 101, a bus 102, a ROM 103, a RAM 104, a non-volatile memory 105, a first interface 106, and a second interface 107.

[0037] The hardware processor 101 is a processor that controls the entire diagnostic device 10 in accordance with a system program. The hardware processor 101 reads the system program stored in the ROM 103 via the bus 102. The hardware processor 101 is, for example, a CPU or an electronic circuit.

[0038] The bus 102 is a communication path that connects the various pieces of hardware in the diagnostic device 10. The various pieces of hardware in the diagnostic device 10 exchange data via the bus 102.

[0039] The ROM 103 is a storage device that stores system programs, etc. The ROM 103 is a computer-readable storage medium.

[0040] The RAM 104 is a storage device that temporarily stores various data and functions as a work area for the hardware processor 101 to process various data.

[0041] The nonvolatile memory 105 is a storage device that retains data even when the power to the diagnostic device 10 is turned off. The nonvolatile memory 105 is a computer-readable storage medium. The nonvolatile memory 105 is configured, for example, by a battery-backed memory or an SSD.

[0042] The first interface 106 connects the bus 102 and the input / output device 11. The first interface 106 sends various data processed by the hardware processor 101 to the input / output device 11, for example.

[0043] The input / output device 11 receives various data via the first interface 106 and displays the various data on a display. The input / output device 11 also receives input of various data and sends the various data to, for example, the hardware processor 101 via the first interface 106. The input / output device 11 is, for example, a touch panel.

[0044] The second interface 107 connects the bus 102 and the control device 2. The second interface 107 receives various data from the control device 2 and sends the data to the hardware processor 101, for example.

[0045] 4 is a block diagram showing an example of the functions of the diagnostic device 10. The diagnostic device 10 includes, for example, a first acquisition unit 111, a first data storage unit 112, a continuous diagnosis unit 113, a first history storage unit 114, a trigger generation unit 115, a result output unit 116, a reception unit 117, a second acquisition unit 118, a second data storage unit 119, an emergency diagnosis unit 120, and a second history storage unit 121.

[0046] The first acquisition unit 111, the constant diagnosis unit 113, the trigger generation unit 115, the result output unit 116, the reception unit 117, the second acquisition unit 118, and the emergency diagnosis unit 120 are realized, for example, by the hardware processor 101 performing arithmetic processing using the system program stored in the ROM 103 and various data stored in the non-volatile memory 105.

[0047] The first data storage unit 112, the first history storage unit 114, the second data storage unit 119, and the second history storage unit 121 are realized, for example, by storing various information in the RAM 104 or the non-volatile memory 105.

[0048] The first acquisition unit 111 acquires first status data indicating the status of the diagnosis target. The diagnosis target is, for example, a device and a part that constitutes the industrial machine 1. The device and the part that constitutes the industrial machine 1 are, for example, a bearing, a servo motor 5, a spindle motor 7, a linear guide, a tool, and a spindle. The diagnosis target may also be a compressor, a motor, or the like of equipment installed in a factory.

[0049] The first acquisition unit 111 acquires the first state data at a predetermined cycle while the diagnosis target is in operation. The period during which the diagnosis target is in operation is, for example, a period during which the industrial machine 1 is operating based on an operation program.

[0050] The predetermined period is, for example, the control period of the diagnostic device 10. The first acquisition unit 111 may change the period for acquiring the first status data. For example, the first acquisition unit 111 may acquire the first status data based on information specifying the period received by the receiving unit 117, which will be described later. In other words, the first acquisition unit 111 may acquire the first status data at a period specified by the operator.

[0051] The first state data includes, for example, a torque command, and data indicating a current value, vibration, temperature, sound, elastic wave, speed, and rotation speed. The data includes signals. The first acquisition unit 111 acquires, for example, a torque command specifying the torque of the spindle motor 7.

[0052] The first acquisition unit 111 acquires first status data from the sensor 9 installed in the diagnosis target or from the control device 2 .

[0053] The first data storage unit 112 stores the first status data acquired by the first acquisition unit 111. The first data storage unit 112 stores the first status data in association with time information indicating the time when the first status data was acquired. In other words, the first status data stored in the first data storage unit 112 is time-series data. When the first acquisition unit 111 acquires a torque command specifying the torque of the spindle motor 7, the data stored in the first data storage unit 112 is time-series data of values ​​specifying the torque of the spindle motor 7.

[0054] The continuous diagnosis unit 113 diagnoses an abnormality of the diagnostic object based on the first status data stored in the first data storage unit 112. That is, the continuous diagnosis unit 113 diagnoses an abnormality of the diagnostic object based on the first status data acquired by the first acquisition unit 111.

[0055] The continuous diagnosis unit 113 diagnoses, for example, whether or not an abnormality has occurred in the object to be diagnosed. The continuous diagnosis unit 113 diagnoses the abnormality of the object to be diagnosed using a predetermined abnormality detection model.

[0056] The anomaly detection model is a model that diagnoses that an abnormality has occurred in the diagnosis object when the value of the first state data exceeds a preset threshold value, for example. Multiple threshold values ​​may be set in the anomaly detection model.

[0057] For example, the anomaly detection model may be set with a first threshold, a second threshold greater than the first threshold, and a third threshold greater than the second threshold, in which case the anomaly detection model calculates the degree of anomaly.

[0058] For example, when the value of the first status data is equal to or less than the first threshold, the abnormality level is "0." In this case, no abnormality has occurred in the diagnostic object. When the value of the first status data exceeds the first threshold and is equal to or less than the second threshold, the abnormality level is "1." In this case, an abnormality of low importance has occurred in the diagnostic object.

[0059] When the value of the first status data exceeds the second threshold value and is equal to or less than the third threshold value, the abnormality level is "2." In this case, an abnormality of medium importance has occurred in the diagnostic object. When the value of the first status data exceeds the third threshold value, the abnormality level is "3." In this case, an abnormality of high importance has occurred in the diagnostic object.

[0060] 5 is a diagram showing an example of the diagnosis result by the continuous diagnosis unit 113. In periods T1 and T3, the value of the first status data is equal to or less than the first threshold value. Therefore, the continuous diagnosis unit 113 determines that the diagnostic target is operating normally.

[0061] Furthermore, in period T2, the value of the first status data exceeds the first threshold value and is equal to or less than the second threshold value. In this case, the continuous diagnosis unit 113 determines that an abnormality with an abnormality level of "1" has occurred in the diagnostic object. Furthermore, in period T4, the value of the first status data exceeds the second threshold value. In this case, the continuous diagnosis unit 113 determines that an abnormality with an abnormality level of "2" has occurred in the diagnostic object.

[0062] The continuous diagnosis unit 113 may diagnose an abnormality in the diagnosis target using an anomaly detection model selected from a plurality of anomaly detection models that calculate the degree of anomaly. That is, the anomaly detection model is an anomaly detection model that most appropriately calculates the degree of anomaly occurring in the diagnosis target among the plurality of anomaly detection models.

[0063] For example, the difference between the degree of abnormality under normal conditions and the degree of abnormality under abnormal conditions calculated by the abnormality detection model used by the continuous diagnosis unit 113 is larger than the difference between the degree of abnormality under normal conditions and the degree of abnormality under abnormal conditions calculated by other abnormality detection models among the multiple abnormality detection models.

[0064] In addition, the abnormality detection model is selected from multiple abnormality detection models depending on the components that make up the object to be diagnosed, the structure of the industrial machine 1 in which the object to be diagnosed is installed, the setting state of the industrial machine 1, the operating program that operates the industrial machine 1, and the environment in which the object to be diagnosed is installed.

[0065] The setting state of the industrial machine 1 is, for example, the preload of the bearings. The setting state of the industrial machine 1 also includes the setting state of parameters set in the control device 2. The environment in which the diagnostic target is installed is, for example, the temperature in the factory where the industrial machine 1 is installed. Now, we return to the explanation of FIG. 4.

[0066] The first history storage unit 114 stores the diagnosis results by the continuous diagnosis unit 113. The diagnosis results are, for example, information indicating whether or not an abnormality has occurred in the diagnosis target. The diagnosis results may include information indicating the degree of abnormality. The diagnosis results may also include information indicating the time when the abnormality occurred.

[0067] The trigger generation unit 115 generates a trigger based on the diagnosis result stored in the first history storage unit 114. The trigger generation unit 115 generates a trigger in response to the first history storage unit 114 storing a diagnosis result indicating that an abnormality has occurred in the diagnosis target.

[0068] The trigger is information or a signal that triggers the second acquisition unit 118 to acquire second status data that is different from the first status data. The information generated by the trigger generation unit 115 is, for example, information for prompting the operator to perform a diagnostic operation. The information prompting the operator to perform a diagnostic operation is displayed on a display device, for example.

[0069] 6 is an example of a display screen that displays information generated by the trigger generation unit 115. For example, the display screen displays a string of characters saying, "An abnormality has occurred. Please perform a diagnostic operation." Also, an "OK" button is displayed below this string of characters.

[0070] The operator executes a diagnostic operation when the information generated by the trigger generation unit 115 is displayed on the display screen. For example, if the first status data is a torque command for the spindle motor 7 and the constant diagnosis unit 113 diagnoses that an abnormality has occurred in the diagnostic target, the operator executes a diagnostic operation for the spindle.

[0071] The diagnostic operation is, for example, measuring the runout of the spindle. The runout of the spindle is measured, for example, by measuring the distance between a tool holder attached to the spindle and an eddy current displacement sensor while rotating the spindle. The runout of the spindle may also be measured by applying a dial gauge to the tool holder attached to the spindle.

[0072] The diagnostic operation may be measurement of vibrations of the diagnostic object. The vibrations of the diagnostic object may be, for example, vibrations generated when the diagnostic object is subjected to a frequency sweep operation or vibrations generated when the diagnostic object is excited. That is, the second state data may be vibration data acquired when the diagnostic object is subjected to a frequency sweep operation or vibration data acquired when the diagnostic object is excited.

[0073] The frequency sweep operation is a process of vibrating a motor such as the servo motor 5 or the spindle motor 7 by means of an input signal input to the motor. The frequency sweep operation is, for example, a process of gradually increasing the frequency of the input signal to the motor. The object to be diagnosed is vibrated by, for example, applying an impact to the object to be diagnosed by an impulse hammer or the like.

[0074] The result output unit 116 outputs the diagnosis result by the continuous diagnosis unit 113. In response to the diagnosis result indicating that the diagnosis target is operating normally being stored in the first history storage unit 114, the result output unit 116 causes the diagnosis result indicating that the diagnosis target is operating normally to be displayed on, for example, a display device.

[0075] Meanwhile, in response to the first history storage unit 114 storing a diagnostic result indicating that an abnormality has occurred in the diagnostic object, the result output unit 116 displays the diagnostic result indicating that an abnormality has occurred in the diagnostic object, for example, on a display device. The display device is, for example, the input / output device 11. The result output unit 116 may output an electronic file in which the diagnostic result is recorded to, for example, an external server (not shown). Now, we return to the description of FIG. 4.

[0076] The receiving unit 117 receives the input of the results of the diagnostic operation by the operator. For example, the receiving unit 117 displays a reception screen on the display device and receives the input of the results of the diagnostic operation from the reception screen.

[0077] 7 is an example of a reception screen. The reception screen includes, for example, an area for receiving input of a measurement value of spindle runout and an area for receiving input of a measurement value of spindle vibration. When the operator inputs the measurement values ​​into these areas, the reception unit 117 receives input of the results of the diagnostic operation. Now, we return to the description of FIG. 4.

[0078] The second acquisition unit 118 acquires second status data different from the first status data based on the diagnosis result by the continuous diagnosis unit 113. The second status data is, for example, information indicating the result of a diagnostic operation by an operator accepted by the acceptance unit 117. In other words, when a trigger is generated based on the diagnosis result by the continuous diagnosis unit 113, the second acquisition unit 118 acquires information indicating the result of the diagnostic operation performed based on the trigger.

[0079] The second acquisition unit 118 acquires, for example, information indicating spindle runout and information indicating spindle vibration. The second status data is not limited to information accepted by the acceptance unit 117. The second status data may be data detected by the sensor 9. In this case, the second acquisition unit 118 starts acquiring the second status data at a predetermined cycle in response to the generation of a trigger by the trigger generation unit 115.

[0080] The data detected by the sensor 9 may be, for example, data indicating a torque command, a current value, a vibration, a temperature, a sound, an elastic wave, a speed, and a rotation speed. The data may include signals. The second state data may be data obtained from the control device 2.

[0081] For example, the second acquisition unit 118 may acquire information indicating the electrical resistance between the workpiece and the tool during cutting from the sensor 9. It is known that the electrical resistance between the tool and the workpiece decreases as tool wear progresses. Therefore, by the second acquisition unit 118 acquiring information indicating the electrical resistance between the tool and the workpiece, the emergency diagnosis unit 120 (described later) can diagnose tool wear based on the information indicating this electrical resistance.

[0082] Furthermore, the second acquisition unit 118 may acquire, for example, the temperature of the bearing from the sensor 9. It is known that the temperature of the bearing rises when the bearing is damaged. Therefore, by the second acquisition unit 118 acquiring the temperature of the bearing, the emergency diagnosis unit 120 (described later) can diagnose damage to the bearing based on this temperature.

[0083] The second data storage unit 119 stores the second status data acquired by the second acquisition unit 118. That is, the second data storage unit 119 stores the information accepted by the acceptance unit 117.

[0084] Furthermore, the second data storage unit 119 stores data detected by the sensor 9. When the second status data is data detected by the sensor 9, the second data storage unit 119 stores the second status data in association with time information indicating the time when the second status data was acquired. In other words, the second status data stored in the second data storage unit 119 may be time-series data.

[0085] The emergency diagnosis unit 120 diagnoses the cause of the abnormality that has occurred in the diagnosis target based on the second status data acquired by the second acquisition unit 118. That is, the emergency diagnosis unit 120 diagnoses the cause of the abnormality that has occurred in the diagnosis target based on the second status data stored in the second data storage unit 119.

[0086] The emergency diagnosis unit 120 diagnoses the cause of an abnormality that has occurred in the object to be diagnosed using a predetermined diagnosis model. The cause of the abnormality is, for example, the location where the abnormality has occurred and the state of the abnormality.

[0087] The emergency diagnosis unit 120 diagnoses, for example, that an abnormality has occurred in a bearing, a motor, or a tool as the cause of the abnormality. The emergency diagnosis unit 120 also diagnoses, for example, that wear, chipping, or breakage has occurred. The emergency diagnosis unit 120 also diagnoses that a part has reached the end of its life.

[0088] The diagnostic model is, for example, a model that indicates a correlation between the second status data and the cause of an abnormality that has occurred in the diagnostic target. The diagnostic model is generated by machine learning using the second status data and information indicating the cause of the abnormality as training data.

[0089] For example, if the measured value of the spindle runout is equal to or greater than α1 [mm] and less than α2 [mm] and vibrations in a specific frequency band appear as the spindle rotates, the diagnostic model outputs information indicating that damage has occurred in the spindle bearing. That is, the emergency diagnostic unit 120 diagnoses that damage has occurred in the spindle bearing. Here, the vibrations in the specific frequency band are, for example, vibrations that include sideband waves of a wave that indicates the rotation frequency of the spindle.

[0090] For example, if the measured spindle runout value is α2 [mm] or more and vibrations in a specific frequency band appear as the spindle rotates, the diagnostic model outputs information indicating that a foreign object has become caught between the spindle and the tool holder. That is, the emergency diagnosis unit 120 diagnoses that a foreign object has become caught between the spindle and the tool holder. Here, the vibrations in the specific frequency band are, for example, vibrations that indicate the rotation frequency of the spindle.

[0091] When the second status data includes multiple types of data, the emergency diagnosis unit 120 may diagnose the cause of the abnormality that has occurred in the diagnosis target based on the correlation between the multiple types of data. For example, if there is a correlation between the rotation speed of the servo motor 5 under normal conditions and the frequency component of vibration of the servo motor 5 under normal conditions, the correlation between the rotation speed of the servo motor 5 and the frequency component of vibration under abnormal conditions will be different from the correlation under normal conditions. Therefore, the emergency diagnosis unit 120 diagnoses the cause of the abnormality in the diagnosis target based on the fact that the correlation between the rotation speed of the servo motor 5 and the frequency component of vibration is different from the correlation between the rotation speed of the servo motor 5 and the frequency component of vibration under normal conditions.

[0092] The second history storage unit 121 stores a history of cause information indicating the cause of an abnormality in the diagnostic object diagnosed by the emergency diagnosis unit 120. The cause information is stored in association with the second status data and the acquisition time of the second status data.

[0093] The emergency diagnosis unit 120 may diagnose the cause of an abnormality that has occurred in the diagnosis target based on the cause information recorded in the second history storage unit 121. That is, the emergency diagnosis unit 120 determines whether or not the past second status data stored in the second history storage unit 121 matches the second status data stored in the second data storage unit 119. If these match each other, the emergency diagnosis unit 120 diagnoses that an abnormality indicated by the cause information stored in the second history storage unit 121 in association with the second status data has occurred in the diagnosis target.

[0094] It should be noted that the past second status data stored in the second history storage unit 121 and the second status data stored in the second data storage unit 119 do not necessarily need to strictly match. In other words, if the past second status data and the newly acquired second status data are similar to a predetermined degree, the emergency diagnosis unit 120 may diagnose that an abnormality indicated by the cause information stored in association with the second status data has occurred in the diagnosis target.

[0095] The result output unit 116 outputs the diagnosis result by the emergency diagnosis unit 120. When the diagnosis result indicating the cause of the abnormality is stored in the second history storage unit 121, the result output unit 116 displays the diagnosis result on, for example, a display device.

[0096] 8 is a diagram showing an example of a diagnosis result displayed on the display device. For example, in response to a diagnosis result indicating that an abnormality has occurred in the spindle bearing being stored in the second history storage unit 121, the result output unit 116 displays a character string indicating the diagnosis result, "High possibility of abnormality in the spindle bearing," on the display screen. The result output unit 116 may display the diagnosis result by the emergency diagnosis unit 120 together with the diagnosis result by the regular diagnosis unit 113 on the display device. The result output unit 116 may output an electronic file in which the diagnosis result is recorded to, for example, an external server (not shown).

[0097] 9 is a flowchart showing an example of the flow of processing executed by the diagnostic device 10. In the diagnostic device 10, first, the first acquisition unit 111 acquires first state data (step SA1).

[0098] Next, the first data storage unit 112 stores the first status data acquired by the first acquisition unit 111 (step SA2).

[0099] Next, the continuous diagnosis unit 113 diagnoses an abnormality in the object to be diagnosed based on the first state data stored in the first data storage unit 112 (step SA3).

[0100] If no abnormality has occurred in the diagnostic target (No in step SA4), the first acquisition unit 111 continues to acquire the first status data (step SA1).

[0101] If an abnormality has occurred in the object to be diagnosed (Yes in step SA4), the first history storage unit 114 stores the diagnosis result by the continuous diagnosis unit 113 (step SA5).

[0102] When the diagnosis result is stored in the first history storage unit 114, the trigger generation unit 115 generates a trigger, and the result output unit 116 outputs the diagnosis result (step SA6).

[0103] When the trigger generating unit 115 generates a trigger, a diagnostic operation is performed by the operator, and the receiving unit 117 receives an input of the result of the diagnostic operation (step SA7).

[0104] Next, the second acquisition unit 118 acquires second status data (step SA8), where the second status data is information indicating the results of the diagnostic operation received by the reception unit 117.

[0105] Next, the second data storage unit 119 stores the second status data acquired by the second acquisition unit 118 (step SA9).

[0106] Next, the emergency diagnosis unit 120 diagnoses the cause of the abnormality that has occurred in the object to be diagnosed based on the second state data stored in the second data storage unit 119 (step SA10).

[0107] Next, the second history storage unit 121 stores information indicating the cause of the abnormality diagnosed by the emergency diagnosis unit 120 (step SA11).

[0108] Finally, the result output unit 116 outputs information indicating the cause of the abnormality stored in the second history storage unit 121 (step SA12), and the process ends.

[0109] 10 is a block diagram showing an example of functions of a diagnostic device 10 according to a second embodiment. The following mainly describes functions that are different from those in the first embodiment, and descriptions of functions that are the same as those in the first embodiment may be omitted.

[0110] The diagnostic device 10 of this embodiment differs from the diagnostic device 10 of the first embodiment mainly in that the continuous diagnostic unit 113 includes a first diagnostic unit 113A and a second diagnostic unit 113B.

[0111] The continuous diagnosis unit 113 includes a first diagnosis unit 113A and a second diagnosis unit 113B. The first diagnosis unit 113A diagnoses whether or not an abnormality has occurred in the diagnosis target based on the first state data. The first diagnosis unit 113A diagnoses whether or not an abnormality has occurred in the diagnosis target using a predetermined abnormality detection model.

[0112] The anomaly detection model is, for example, a model that diagnoses that an anomaly has occurred when the value of the first status data exceeds a preset threshold value.

[0113] The second diagnosis unit 113B diagnoses the type of abnormality that has occurred in the diagnosis target based on the first status data. The second diagnosis unit 113B diagnoses the type of abnormality by clustering the first status data.

[0114] Fig. 11 is a diagram for explaining clustering. Each black circle shown in Fig. 11 represents analysis data obtained by analyzing the first status data. The analysis data is, for example, multidimensional data obtained by frequency analysis of the first status data.

[0115] The second diagnostic unit 113B groups the analytical data using a clustering method such as the k-means method, for example, and divides the analytical data into a first group G1, a second group G2, and a third group G3.

[0116] Each group is labeled with information indicating an abnormality. For example, if analytical data of the first status data acquired when a known abnormality occurs is included in a certain group, the group is estimated to be a collection of analytical data of the first status data acquired when the known abnormality occurred. In other words, the group is labeled with information indicating the known abnormality.

[0117] Assume that the analytical data D1 is data obtained by analyzing the first status data acquired when the diagnostic object is operating normally. In this case, it is presumed that the other analytical data included in the first group are data obtained by analyzing the first status data acquired when the diagnostic object is operating normally. Therefore, the first group is labeled with information indicating that the diagnostic object is normal.

[0118] Assume that analytical data D2 is data obtained by analyzing the first status data acquired when the diagnostic object is operating in a worn state. In this case, it is presumed that the other analytical data included in the second group are data obtained by analyzing the first status data acquired when the diagnostic object is operating in a worn state. Therefore, the second group is labeled with information indicating that the diagnostic object is worn.

[0119] Assume that analytical data D3 is data obtained by analyzing the first status data acquired when the diagnostic object is operating in a damaged state. In this case, it is estimated that the other analytical data included in the third group are data obtained by analyzing the first status data acquired when the diagnostic object is operating in a damaged state. Therefore, the third group is labeled with information indicating that the diagnostic object is damaged.

[0120] The second diagnostic unit 113B determines to which group the analytical data obtained by analyzing the first status data belongs. For example, if the analytical data belongs to the first group G1, the second diagnostic unit 113B diagnoses that the diagnostic target is operating normally.

[0121] If the analysis data belongs to the second group G2, the second diagnostic unit 113B diagnoses that the diagnostic object is operating in a worn state, i.e., the second diagnostic unit 113B diagnoses that the type of abnormality that has occurred in the diagnostic object is wear.

[0122] If the analysis data belongs to the third group G3, the second diagnostic unit 113B diagnoses that the diagnostic object is operating in a damaged state, i.e., the second diagnostic unit 113B diagnoses that the type of abnormality that has occurred in the diagnostic object is damage.

[0123] If the analytical data does not belong to any group, the second diagnosis unit 113B diagnoses that an unknown abnormality has occurred in the diagnosis target.

[0124] 12 is a diagram showing an example of a diagnosis result by the continuous diagnosis unit 113. The first diagnosis unit 113A determines that the diagnosis target is operating normally when the value of the first status data is equal to or less than a predetermined threshold value. Furthermore, the first diagnosis unit 113A diagnoses that an abnormality has occurred in the diagnosis target when the value of the first status data exceeds the predetermined threshold value. In other words, the first diagnosis unit 113A diagnoses that an abnormality has occurred in the diagnosis target during periods T2 and T4.

[0125] The second diagnostic unit 113B diagnoses the type of abnormality that has occurred in the diagnostic object based on the analysis data obtained by analyzing the first state data. For example, the second diagnostic unit 113B diagnoses that the diagnostic object is worn out during time period T2. The second diagnostic unit 113B also diagnoses that the diagnostic object is damaged during time period T4.

[0126] The first history storage unit 114 stores the diagnosis results by the continuous diagnosis unit 113. The trigger generation unit 115 generates a trigger based on the diagnosis results stored in the first history storage unit 114. The trigger generation unit 115 generates a trigger in response to the first history storage unit 114 storing a diagnosis result indicating that an abnormality has occurred in the diagnosis target.

[0127] 13 is an example of a display screen that displays information generated by the trigger generation unit 115. For example, the display screen displays a string of characters that reads, "An unknown abnormality has occurred. Please perform a diagnostic operation." Also, an "OK" button is displayed below this string of characters.

[0128] When the information generated by the trigger generating unit 115 is displayed on the display screen, the operator executes a diagnostic operation.

[0129] The result output unit 116 outputs the diagnosis result obtained by the continuous diagnosis unit 113. The functions of the reception unit 117, the second acquisition unit 118, the second data storage unit 119, the emergency diagnosis unit 120, and the second history storage unit 121 are the same as those in the first embodiment.

[0130] The receiving unit 117 may receive information specifying the type of first status data. In this case, the operator can specify the type of first status data to be used for diagnosis in the continuous diagnosis unit 113. The receiving unit 117 may also receive information specifying an anomaly detection model. In this case, a plurality of anomaly detection models may be stored in a storage unit (not shown) in advance. The first diagnosis unit 113A may diagnose an anomaly in the diagnosis target using the specified anomaly detection model.

[0131] The second acquisition unit 118 may acquire the diagnosis result by the continuous diagnosis unit 113. That is, the second acquisition unit 118 may acquire the diagnosis result stored in the first history storage unit 114. In this case, the emergency diagnosis unit 120 diagnoses the cause of the abnormality that has occurred in the diagnosis target based on the diagnosis result by the continuous diagnosis unit 113 and the second state data.

[0132] The second acquisition unit 118 may determine the type of second condition data to acquire depending on the diagnosis result by the continuous diagnosis unit 113. For example, the second acquisition unit 118 may acquire either information indicating spindle runout or information indicating spindle vibration depending on whether the diagnosis result is wear or damage.

[0133] As described above, the diagnostic device 10 includes a first acquisition unit 111 that acquires first status data indicating the status of the object to be diagnosed, a continuous diagnosis unit 113 that diagnoses an abnormality in the object to be diagnosed based on the first status data acquired by the first acquisition unit 111, a second acquisition unit 118 that acquires second status data different from the first status data based on the diagnosis result by the continuous diagnosis unit 113, and an emergency diagnosis unit 120 that diagnoses the cause of an abnormality that has occurred in the object to be diagnosed based on the second status data acquired by the second acquisition unit 118.

[0134] Therefore, the diagnostic device 10 can diagnose the object to be diagnosed based on the first state data that can be acquired at any time while the object to be diagnosed is operating. In other words, when diagnosing the object to be diagnosed, the diagnostic device 10 does not affect the operation of the object to be diagnosed.

[0135] Furthermore, the second acquisition unit 118 acquires the second status data only when the continuous diagnosis unit 113 determines that the second status data is necessary. In other words, the second acquisition unit 118 acquires the second status data at an appropriate timing. Therefore, the diagnostic device 10 can reduce the cost associated with abnormality diagnosis.

[0136] Furthermore, the diagnostic device 10 diagnoses the diagnostic object based on not only the first status data but also the second status data, thereby ensuring the reliability of the diagnostic results.

[0137] Furthermore, the continuous diagnosis unit 113 diagnoses an abnormality in the diagnosis target using an anomaly detection model selected from a plurality of anomaly detection models that calculate an abnormality degree, and the difference between the abnormality degree in the normal state and the abnormal state calculated by the anomaly detection model is greater than the difference between the abnormality degree in the normal state and the abnormal state calculated by each of the other anomaly detection models among the plurality of anomaly detection models. Therefore, the continuous diagnosis unit 113 can appropriately diagnose an abnormality in the diagnosis target.

[0138] Furthermore, the anomaly detection model is selected from a plurality of anomaly detection models depending on the components constituting the diagnosis target, the structure of the industrial machine 1 in which the diagnosis target is installed, the settings of the industrial machine 1, the operating program for operating the industrial machine 1, and the environment in which the diagnosis target is installed. In other words, the anomaly detection model is an optimal model for detecting anomalies. This allows the continuous diagnosis unit 113 to appropriately diagnose anomalies in the diagnosis target.

[0139] The diagnostic device 10 further includes a receiving unit 117 that receives at least one of information specifying the type of first status data and information specifying the type of anomaly detection model. Therefore, the diagnostic device 10 can appropriately diagnose the cause of an abnormality that has occurred in the diagnostic object, based on the first status data and the anomaly detection model that are suitable for the diagnostic object.

[0140] Furthermore, the first acquiring unit 111 changes the cycle for acquiring the first status data, so that the operator can set the cycle in accordance with the processing capacity of the diagnostic device 10.

[0141] The second state data is vibration data acquired when the diagnosis target is subjected to a frequency sweep operation or vibration data acquired when the diagnosis target is vibrated. Therefore, the diagnostic device 10 can diagnose the cause of an abnormality that has occurred in the diagnosis target based on the vibration data.

[0142] Furthermore, the emergency diagnosis unit 120 analyzes the frequency components of the second state data to diagnose the cause of the abnormality. Therefore, the abnormality diagnosis unit can accurately diagnose the cause of the abnormality that has occurred in the object to be diagnosed.

[0143] The second status data includes multiple types of data, and the emergency diagnosis unit 120 diagnoses the cause of the abnormality that has occurred in the diagnostic object based on the correlation between the multiple types of data. Therefore, the emergency diagnosis unit 120 can accurately diagnose the cause of the abnormality that has occurred in the diagnostic object.

[0144] The diagnostic device 10 further includes a history storage unit that records a history of cause information indicating the cause of an abnormality diagnosed by the emergency diagnostic unit 120, and the emergency diagnostic unit 120 diagnoses the cause based on the cause information recorded in the history storage unit. Therefore, the emergency diagnostic unit 120 diagnoses the cause of an abnormality that has occurred in the diagnostic target based on the history of past abnormalities. As a result, the diagnostic device 10 can reduce the processing load related to diagnosing an abnormality. The history storage unit is, for example, the second history storage unit 121.

[0145] The continuous diagnosis unit 113 includes a first diagnosis unit 113A and a second diagnosis unit 113B, where the first diagnosis unit 113A diagnoses whether an abnormality has occurred in the object to be diagnosed, and the second diagnosis unit 113B diagnoses the type of abnormality that has occurred in the object to be diagnosed. In this case, the emergency diagnosis unit 120 can select second status data to be used for diagnosing the cause of the abnormality, depending on the type of abnormality diagnosed by the second diagnosis unit 113B.

[0146] Although the present disclosure has been described in detail, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible to these embodiments without departing from the gist of the present disclosure or the gist of the present disclosure derived from the content of the claims and their equivalents. Furthermore, these embodiments can also be implemented in combination.

[0147] The following are supplementary notes related to embodiments of the present disclosure. Supplementary note [1] A diagnostic device comprising: a first acquisition unit that acquires first state data indicating a state of a diagnostic object; a continuous diagnostic unit that diagnoses an abnormality of the diagnostic object based on the first state data acquired by the first acquisition unit; a second acquisition unit that acquires second state data different from the first state data based on a diagnosis result by the continuous diagnostic unit; and an emergency diagnostic unit that diagnoses a cause of the abnormality that has occurred in the diagnostic object based on the second state data acquired by the second acquisition unit. Supplementary note [2] The diagnostic device according to supplementary note [1], wherein the continuous diagnostic unit diagnoses an abnormality of the diagnostic object using an anomaly detection model selected from a plurality of anomaly detection models that calculate an anomaly degree, and a difference between the anomaly degree in a normal state and the anomaly degree in an abnormal state calculated by the anomaly detection model is larger than a difference between the anomaly degree in a normal state and the anomaly degree in an abnormal state calculated by each of the other anomaly detection models among the plurality of anomaly detection models. Supplementary Note [3] The diagnostic device according to Supplementary Note [2], wherein the anomaly detection model is selected from the plurality of anomaly detection models depending on the components constituting the diagnostic object, the structure of the industrial machine on which the diagnostic object is installed, the setting state of the industrial machine, the operating program for operating the industrial machine, and the environment in which the diagnostic object is installed. Supplementary Note [4] The diagnostic device according to Supplementary Note [2] or [3], further comprising a reception unit that receives at least one of information specifying a type of the first status data and information specifying a type of the anomaly detection model. Supplementary Note [5] The diagnostic device according to any of Supplements [1] to [4], wherein the first acquisition unit changes a cycle for acquiring the first status data. Supplementary Note [6] The diagnostic device according to any of Supplements [1] to [5], wherein the second status data is vibration data acquired when the diagnostic object is subjected to a frequency sweep operation or vibration data acquired when the diagnostic object is vibrated. Supplementary Note [7] The diagnostic device according to any of Supplements [1] to [6], wherein the emergency diagnosis unit diagnoses the cause of the anomaly by analyzing frequency components of the second status data.Supplementary Note [8] The diagnostic device according to any one of Supplements [1] to [7], wherein the second status data includes multiple types of data, and the emergency diagnosis unit diagnoses the cause of the abnormality that has occurred in the diagnostic object based on a correlation between the multiple types of data. Supplementary Note [9] The diagnostic device according to any one of Supplements [1] to [8], further comprising a history storage unit that records a history of cause information indicating the cause of the abnormality diagnosed by the emergency diagnosis unit, and the emergency diagnosis unit diagnoses the cause based on the cause information recorded in the history storage unit. Supplementary Note

[10] The diagnostic device according to any one of Supplements [1] to [9], wherein the continuous diagnosis unit includes a first diagnosis unit and a second diagnosis unit, and the first diagnosis unit diagnoses whether an abnormality has occurred in the diagnostic object, and the second diagnosis unit diagnoses the type of the abnormality that has occurred in the diagnostic object.

[0148] REFERENCE SIGNS LIST 1 Industrial machine 2 Control device 201 Hardware processor 202 Bus 203 ROM 204 RAM 205 Non-volatile memory 206 First interface 207 Axis control circuit 208 Spindle control circuit 209 PLC 210 I / O unit 211 Second interface 212 Third interface 4 Servo amplifier 5 Servo motor 6 Spindle amplifier 7 Spindle motor 8 Auxiliary equipment 9 Sensor 10 Diagnostic device 101 Hardware processor 102 Bus 103 ROM 104 RAM 105 Non-volatile memory 106 First interface 107 Second interface 111 First acquisition unit 112 First data storage unit 113 Continuous diagnosis unit 113A First diagnosis unit 113B Second diagnosis unit 114 First history storage unit 115 Trigger generation unit 116 Result output unit 117 Reception unit 118 Second acquisition unit 119 Second data storage unit 120 Emergency diagnosis unit 121 Second history storage unit 11 Input / output device

Claims

1. a first acquisition unit that acquires first status data indicating a status of a diagnostic object; a continuous diagnosis unit that diagnoses an abnormality in the diagnostic object based on the first state data acquired by the first acquisition unit; a second acquisition unit that acquires second status data different from the first status data based on a diagnosis result by the continuous diagnosis unit; an emergency diagnosis unit that diagnoses a cause of the abnormality that has occurred in the diagnosis object based on the second state data acquired by the second acquisition unit; A diagnostic device comprising:

2. the continuous diagnosis unit diagnoses the abnormality of the diagnosis target using an abnormality detection model selected from a plurality of abnormality detection models that calculate an abnormality degree; 2. The diagnostic device according to claim 1, wherein the difference between the degree of abnormality in normal times and the degree of abnormality in abnormal times calculated by the anomaly detection model is larger than the differences between the degree of abnormality in normal times and the degree of abnormality in abnormal times calculated by each of the other anomaly detection models among the plurality of anomaly detection models.

3. 3. The diagnostic device according to claim 2, wherein the anomaly detection model is selected from the plurality of anomaly detection models depending on the components constituting the object to be diagnosed, the structure of the industrial machine in which the object to be diagnosed is installed, the setting state of the industrial machine, the operating program for operating the industrial machine, and the environment in which the object to be diagnosed is installed.

4. The diagnostic device according to claim 2 , further comprising a receiving unit that receives at least one of information specifying a type of the first state data and information specifying a type of the anomaly detection model.

5. 4. The diagnostic device according to claim 1, wherein the first acquisition unit changes a cycle for acquiring the first status data.

6. The diagnostic device according to any one of claims 1 to 3, wherein the second state data is vibration data acquired when the diagnostic object is subjected to a frequency sweep operation, or vibration data acquired when the diagnostic object is vibrated.

7. 4. The diagnostic device according to claim 1, wherein the emergency diagnostic unit diagnoses the cause of the abnormality by analyzing frequency components of the second status data.

8. the second status data includes a plurality of types of data, 4. The diagnostic device according to claim 1, wherein the emergency diagnostic unit diagnoses the cause of the abnormality that has occurred in the diagnostic object based on the correlation between the plurality of types of data.

9. a history storage unit that records a history of cause information indicating the cause of the abnormality diagnosed by the emergency diagnosis unit, 4. The diagnostic device according to claim 1, wherein the emergency diagnostic unit diagnoses the cause based on the cause information recorded in the history storage unit.

10. the continuous diagnostic unit includes a first diagnostic unit and a second diagnostic unit; the first diagnostic unit diagnoses whether or not the abnormality has occurred in the diagnostic object; 4. The diagnostic device according to claim 1, wherein the second diagnostic unit diagnoses the type of the abnormality that has occurred in the diagnostic object.