Abnormality factor identification device

Abstract

An abnormality factor identifying device (1) for identifying a factor in an abnormality occurring in a machine (2), the device (1) comprising: a sensor signal acquisition unit (38) configured to receive sensor signals associated with a physical state of the machine (2); an operating state determination unit (36) configured to determine operating states of the machine (2) based on information received from the machine (2); an abnormality level calculation unit (42) configured to calculate abnormality levels of the sensor signals for each operating state of the machine (2), the state being determined by the operating state determination unit (36); and a factor identification unit (44) configured to determine a factor in an abnormality in the machine (2) from historical data which is a series of the abnormality levels for each operating state, where: the sensor signal acquisition unit (38) receives information associated with the speed feedback on a spindle motor (62) for driving a spindle of the machine (2) or a value from an acceleration sensor installed on the spindle, the operating state determination unit (36) determines an operating state which is cutting or not cutting, and the factor identification unit (44) determines an abnormality in a spindle section when both an abnormality level during cutting and an abnormality level during non-cutting increase at approximately the same time, and identifies an abnormality in a tool when only an abnormality level increases during cutting.

Description

RELATED APPLICATION

[0001] This application claims priority over Japanese application JP 2018 - 033 031 A, filed on February 27, 2018. BACKGROUND OF THE INVENTION 1. Field of the Invention

[0002] The present invention relates to an abnormality factor identifying apparatus, and more particularly to an abnormality factor identifying apparatus that isolates an abnormality factor based on a symptom of a failure. 2. Description of related technology

[0003] To detect or predict an abnormality involving a failure in an industrial machine, such as a machine tool or a robot, a sensor that responds differently depending on the abnormality factor (e.g., a failure type or a failure location) is typically installed near a target location, and a detection value from the sensor is used to detect or predict an abnormality. However, it is difficult to install a sensor in a way that selectively responds only to a specific abnormality. Such a sensor may often respond to an abnormality associated with another factor. Therefore, there is a need to isolate an abnormality factor.

[0004] Conventional techniques are known for isolating an abnormality factor in a machine using detection values ​​from sensors. For example, Japanese Patent Laid-Open No. 2011-060076 A discloses a technique that determines the state of an abnormality based on signals from a number of sensors and internal information from a numerically designated device to identify the cause of an alarm sounding, and outputs an indication and a control signal. Japanese Patent Laid-Open No. JP H10-228304 A also discloses a technique that modifies the drive and mechanism model to improve the accuracy of abnormality detection for abnormality determination responsive to changes in the characteristics of a processing device.Furthermore, Japanese Patent Application Laid-Open No. JP H07-234987 A discloses a technique that, for ease of diagnosis of a failure in a numerically controlled device, displays suspected causes at the failure location and the like and changes the probability database of suspected causes for each occurrence of a failure.

[0005] An abnormality factor can be isolated by installing a sensor at each location of an industrial machine and identifying the abnormality factor based on the strength of the sensor response, as disclosed in Japanese Patent Application Laid-Open No. JP 2011-060076 A. However, it is desirable to install the smallest possible number of sensors to save costs and facilitate maintenance.

[0006] If details of an occurring phenomenon are known in advance for each abnormality factor, as disclosed in Japanese Patent Laid-Open No. JP H07-234987 A, the prior knowledge can be used to isolate an abnormality factor. However, generally speaking, a fault rarely occurs in an industrial machine, and it is often difficult to gather knowledge about a machine abnormality caused by a fault. Furthermore, sensor observation values ​​can often be significantly affected by the machine installation environment and individual differences. Any prepared prior knowledge often needs to be modified for use depending on the sensor installation environment and individual differences. Thus, it is desirable not to use prior knowledge about sensor observation values.

[0007] DE 20 2007 019 440 U1 describes a real-time preventive maintenance system for real-time preventive maintenance of an injection molding system. JP 2011 - 100 211 A describes a fault determination device that detects a fault even in a device in which many periodic changes occur and whose trends cannot be easily quantified and formulated. JP 2012 - 242 985 A describes a device for determining equipment anomalies, which is intended to enable operators to take appropriate measures by appropriately displaying the condition of the equipment upon detection of an anomaly. SUMMARY OF THE INVENTION

[0008] It is an object of the present invention to provide an abnormality factor identification device that isolates an abnormality factor based on a symptom of an abnormality. This object is achieved by an abnormality factor identification device according to claim 1.

[0009] An abnormality factor identification device according to the present invention solves the above problems by isolating an abnormality factor using a combination of information about machine operating states and sensor signals. The abnormality factor identification device of the present invention calculates operating abnormality levels based on sensor signals in several different machine operating states, creates historical data indicating the time series profiles of the abnormality levels, and stores the historical data in association with the machine operating states. The profiles of the abnormality levels in the multiple machine operating states are then analyzed to isolate an abnormality factor.

[0010] One aspect of the present invention is an abnormality factor identification device for identifying a factor in an abnormality occurring in a machine. The abnormality factor identification device includes a sensor signal acquisition unit that obtains sensor signals associated with the physical state of the machine, an operating state determination unit that determines operating states of the machine based on information obtained from the machine, an abnormality level calculation unit that calculates the abnormality levels of the sensor signals for each operating state of the machine determined by the operating state determination unit, and a factor identification unit that determines a factor in an abnormality in the machine from historical data that is a series of abnormality levels for each operating state.

[0011] The present invention achieves abnormality factor isolation with a higher degree of accuracy than conventional methods. In particular, the invention enables an abnormality factor to be isolated with a certain degree of accuracy, even in an environment with a small number of sensor readings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other objects and features of the present invention will be apparent from the embodiment described later with reference to the accompanying drawings, in which: Fig. 1 is a schematic hardware block diagram of an abnormality factor identifying apparatus according to a first embodiment; Fig. 2 is a schematic functional block diagram of the abnormality factor identifying apparatus according to the first embodiment; Fig. 3 illustrates an operating state determination table; Fig. 4 illustrates historical data on the abnormality levels of motor speed feedback values ​​for each machine operating state in case of tool wear; Fig. 5 illustrates historical data on the abnormality levels of motor speed feedback values ​​for each machine operating state in case of spindle fault; Fig. Figure 6 illustrates an abnormality factor identification table. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] An embodiment of the present invention will now be described with reference to the drawings.

[0014] Fig. Figure 1 is a schematic hardware block diagram illustrating a main part of an abnormality factor identification device according to an embodiment of the present invention. The abnormality factor identification device 1 can be implemented as a controller for machines, such as a robot and a machine tool. The abnormality factor identification device 1 can also be implemented as a computer, such as a personal computer installed next to a controller for machines, or a cell computer, a host computer, or a cloud server connected to the controller via a network. Fig. 1 illustrates the abnormality factor identification device 1 implemented as a controller for machines.

[0015] The abnormality factor identification device 1 of the present embodiment includes a CPU 11, which is a processor for controlling the entire abnormality factor identification device 1. The CPU 11 reads a system program from the ROM 12 via a bus 20 and controls the entire abnormality factor identification device 1 according to the system program. A RAM 13 temporarily stores temporary calculation data, display data, and various types of data input by an operator via an input unit (not shown).

[0016] A non-volatile memory 14 is backed up by, for example, a battery (not shown) and thus retains data even after the abnormality factor identifying device 1 is turned off.

[0017] The non-volatile memory 14 stores a control program read from an external device 72 via an interface 15, a control program input via a display / MDI unit 70, and various types of data obtained from each component of the abnormality factor identification device 1, a machine tool, a sensor, and the like (for example, various signals indicating the execution state of a command provided by a control program and the operating state of a machine tool, the positions, speeds, and voltage values ​​of a servo motor 50 and a spindle motor 62, detection values ​​of sensors such as a vibration sensor and a temperature sensor, processing conditions, tool and workpiece information).The control programs and various types of data stored in the non-volatile memory 14 can be loaded into the RAM 13 for execution or use. The ROM 12 stores a known analysis program and other various system programs preliminarily written therein.

[0018] The interface 15 is an interface for connecting the abnormality factor identification device 1 to the external device 72, such as an adapter. The abnormality factor identification device 1 reads programs and various parameters from the external device 72. The abnormality factor identification device 1 can also edit programs and various parameters and save them to the external memory via the external device 72. A programmable machine controller (PMC) 16 outputs signals to a machine tool and peripheral devices for the machine tool (for example, an actuator such as a robot hand for tool placement) via an I / O unit 17 and controls them according to a sequence program stored in the abnormality factor identification device 1.The PMC 16 also receives signals from various switches on the operation panel for the machine tool main body and from the peripheral devices, processes the signals as appropriate, and forwards the resulting signals to the CPU 11.

[0019] The display / MDI unit 70 is a manual data input device including a display and a keyboard, and an interface 18 receives a command and data from the keyboard of the display / MDI unit 70 and forwards them to the CPU 11. An interface 19 is connected to an operation panel 71 including a manual pulse generator used to manually drive each axis.

[0020] An axis control circuit 30 for controlling an axis provided in a machine tool receives a movement distance command from the CPU 1 and outputs the axis command to an auxiliary amplifier 40. The auxiliary amplifier 40 receives the command to drive the servo motor 50 that moves the machine tool axis. The servo motor 50 for the axis has a position and speed detector and controls the position and speed of the axis by passing position and speed feedback signals from the position and speed detector back to the axis control circuit 30.

[0021] The hardware block diagram from Fig. 1 shows the single axis control circuit 30, the single auxiliary amplifier 40, and the single servo motor 50. However, each of the numbers of provided axis control circuits 30, auxiliary amplifiers 40, and servo motors 50 is actually equal to the number of machine tool axes to be controlled.

[0022] A spindle control circuit 60 receives spindle speed commands and outputs a spindle speed signal to a spindle amplifier 61. The spindle amplifier 61 receives the spindle speed signal and rotates the spindle motor 62 of the machine tool at a predetermined rotation speed to drive the tool. The spindle motor 62 is connected to a position encoder 63. The position encoder 63 outputs feedback pulses in synchronization with the spindle rotation, and the feedback pulses are read by the CPU 11.

[0023] Fig. 2 is a schematic functional block diagram of the abnormality factor identifying apparatus 1 according to the first embodiment.

[0024] Each function block that is Fig. 2 is implemented when the CPU 11 included in the abnormality factor identifying device 1 of Fig. 1, executes each system program and controls the operation of each component of the abnormality factor identification device 1.

[0025] The abnormality factor identification device 1 in the present embodiment includes a control unit 34 that controls a machine 2 based on a control program read from the non-volatile memory 14, an operating state determination unit 36 ​​that determines the operating state of the machine 2 based on information obtained from the control unit 34 and the machine 2, a sensor signal acquisition unit 38 that receives a detection value from a sensor 3 for the machine as a sensor signal, an abnormality level calculation unit 42 that calculates operating abnormality levels of the machine 2 based on the machine operating state determined by the operating state determination unit 36 ​​and the sensor signal obtained by the sensor signal acquisition unit 38 from the sensor 3, and stores the calculated operating state abnormality levels in the non-volatile memory 14 as historical data,associated with the operating state of the machine 2, and a factor identification unit 44 that detects an abnormality in the machine 2 and identifies the abnormality factor based on the historical data on the operating abnormality levels of the machine stored in the non-volatile memory 14.

[0026] The control unit 34 is a functional unit that reads a control program block from the non-volatile memory 14 and controls the machine 2 based on the command from the block. The control unit 34 has typical functions for controlling each component of the machine 2. In one example, when the control program block issues a command to move an axis included in the machine 2, the control unit 34 outputs a movement distance for each control cycle to the servo motor 50 that drives the axis. In another example, when the control program block issues a command to move a peripheral device (not shown) attached to the machine 2, the control unit 34 outputs an operation command to the peripheral device. Furthermore, when the factor identification unit 44 detects an abnormality, the control unit 34 operates in a manner to deal with the abnormality.For example, the control unit 34 displays a warning on the display / MDI unit and terminates the current operation of the machine 2 based on the abnormality factor identified by the factor identification unit 44.

[0027] The operating state determination unit 364 is a functional unit that determines the operating state of the machine 2 based on the details of the control by the control unit 34 for the machine 2 and information obtained from the machine 2. For example, while the control unit 34 executes a rapid feed command, the operating state determination unit 36 ​​determines that the servo motor 50 provided in the machine 2 is driving. The operating state determination unit 36 ​​determines that the machine 2 is cutting while driving the servo motor 2 while the control unit 34 executes a cutting feed command. Furthermore, for example, when the operating state determination unit 36 ​​detects a signal from the machine 2 indicating that cutting feed is being performed, the operating state determination unit 36 ​​can determine that the machine 2 is cutting while driving the servo motor 50.Additionally, the operating state determination unit 36 ​​can detect an operating signal from a peripheral device provided in the machine 2 to determine that the peripheral device is operating. In this way, the operating state determination unit 36 ​​can comprehensively determine the operating state of the machine 2 based on the control information of the control unit 34, the information obtained from the machine 2, and an optional sensor signal obtained by the sensor signal detection unit 38 from the sensor 3. This enables the operating state of the machine 2 to be efficiently determined. The operating state determination unit 36 ​​can also determine multiple operating states of the machine 2 that may occur simultaneously, such as axle drive and acceleration, and axle drive and deceleration.

[0028] The operating state determination unit 36 ​​may also determine the operating state of the machine 2 using a machine operating state determination table, for example as shown in Fig. 3. The machine operating condition determination table from Fig. 3 associates the machine operating states with details of the control by the control unit 34 and information received from the machine. In the machine operating state table from Fig. 3, the symbol "-" can denote any object. The preliminary creation of the table associating the machine operating states with details of the control by the control unit 34 and information received from the machine allows the operating state determination unit 36 ​​to quickly determine the current operating state of the machine 2. In addition to the example in Fig. 3, for example, a function can be created in advance and used to determine the machine operating state, using details of the control by the control unit 34 (e.g., commands, coordinates) and information received from the machine as arguments. In some cases, a machine learning device may be used that receives details of the control by the control unit 34 (e.g., commands, coordinates) and information received from the machine and outputs the operating state of the machine 2. The operating state determination unit 36 ​​can be implemented in any way that allows the operating state of the current machine 2 to be determined accurately and quickly.

[0029] The sensor signal acquisition unit 38 is a functional unit that receives a detection value detected by the sensor 3 mounted on the machine 2 as a sensor signal. Examples of the sensor 3 from which the sensor signal acquisition unit 38 receives detection values ​​may include a position and speed detector and the position encoder 63 mounted on the servo motor 50 and the spindle motor 62, a temperature sensor that measures the temperature of the machine 2, an acceleration sensor that detects vibrations in the machine 2, and a noise sensor that detects noise generated by the machine 2. Although the sensor signal acquisition unit 38 may be configured to receive sensor signals from multiple sensors 3, the smallest possible number of sensors 3 may be desirably installed for cost savings and ease of maintenance.If the abnormality factor identification device 1 of the present invention receives sensor signals from several or even a single sensor 3, the abnormality factor isolation method implemented by the abnormality factor identification device 1 enables an abnormality factor to be isolated with reasonable accuracy. Even if a few sensors 3 provide the reduced accuracy of identifying the abnormality factor, the reduction is sufficiently compensated using the operating state information about the machine 2 determined by the operating state determination unit 36.

[0030] The sensor signals obtained by the sensor signal acquisition unit 38 may be instantaneous detection values ​​or time-series detection values ​​obtained sequentially in the same operating state of the machine 2. However, time-series detection values ​​are desirably obtained in the same operating state of the machine 2 because the abnormality level calculation unit 42 can use changes in the detection values ​​detected by the sensor 3 and calculate an abnormality level using a statistical method. The sensor signal acquisition unit 38 may obtain sensor signals during normal operation of the machine 2, or, for example, a predetermined test operation may be performed before the start of daily operation of the machine 2, and the sensor signals may be obtained during the test operation.

[0031] The sensor signal acquisition unit 38 receives sensor signals for each operating state of the machine 2 and can store the obtained signals in the non-volatile memory 14 as reference sensor signals associated with the operating state based on an operating command from an operator via the display / MDI unit 70. The reference sensor signals stored in the non-volatile memory 14 are used by the abnormality level calculation unit 42 as references for calculating an operating abnormality level of the machine 2. Thus, the reference sensor signals are desirably obtained when the machine 2 is operating normally. The non-volatile memory 14 can store data sufficient for the abnormality level calculation unit 42 to statistically process the sensor signals associated with the same operating state.The installation and operating environments for the machine 2 can influence the detection values ​​detected by the sensor 3. To solve this problem, the machine 2 can actually operate as a test in an early phase after the machine is installed in an environment for actual operation. During the test, reference data can be obtained from the sensor signals in multiple operating states, and the obtained reference sensor signals can be stored in the non-volatile memory 14 in association with the respective operating state.

[0032] The abnormality level calculation unit 42 is a functional unit that calculates operating abnormality levels of the engine 2 for each operating state determined by the operating state determination unit 36 ​​based on the sensor signals obtained by the sensor signal acquisition unit 38, and stores the historical data of the calculated operating abnormality levels of the engine 2 for each operating state in the nonvolatile memory 14. For example, the abnormality level calculation unit 42 may use a predetermined function to calculate deviation levels of the obtained sensor signal data from the reference sensor signal data (set) for each operating state stored in the nonvolatile memory 14, and use the calculated levels as abnormality levels.In this case, for example, known techniques such as a common outlier test, the K-Nearest Neighbor algorithm, and the MT system can be used. The historical data stored by the abnormality level calculation unit 42 in the non-volatile memory 14 indicates the time series of the calculated abnormality levels. For example, each of the operating abnormality levels of the machine 2 for each operating state included in the historical data may include the information indicating the calculation order of the abnormality levels and also the detection times of the sensor signals based on which the abnormality levels are calculated.

[0033] The factor identification unit 44 is a functional unit that detects an abnormality in the machine 2 and identifies the abnormality factor based on the historical data on the operating abnormality levels of the machine 2 stored in the non-volatile memory 14. The factor identification unit 44 analyzes the time series profile of the abnormality levels of the historical data for each operating state of the machine 2 and isolates an abnormality factor (the abnormality location, the abnormality type) based on the resulting profile of the abnormality levels for each operating state. For example, the factor identification unit 44 can determine the rate of change in the abnormality levels of the historical data for each of the multiple operating states of the machine 2 and isolate an abnormality factor based on the abnormality level values ​​and the rate of change of the abnormality levels for each operating state.

[0034] Fig. 4 and Fig. 5 each illustrates an example of the historical data of the abnormality levels of engine speed feedback values ​​during the operation of the machine 2, for the corresponding operating state of the machine 2, which are stored in the non-volatile memory 14. In Fig. 4 and Fig. 5, th1 and th2 each denote a threshold value of abnormality levels for determining that the operation of the machine 2 in the corresponding operating state indicates an abnormality symptom. For ease of illustration, Fig. 4 and Fig. 5 stores the historical data of abnormality levels associated with the operating states of the machine 2 that drive the axis (not cutting) and that drive the axis (cutting). However, the non-volatile memory 14 actually stores the historical data of abnormality levels associated with many operating states.

[0035] In the example shown in Fig. As shown in Figure 4, the operating state of machine 2, which drives the axis (non-cutting), indicates no significant changes in the abnormality levels. In contrast, the operating state of machine 2, which drives the axis (cutting), indicates an abnormality symptom (exceeding the threshold th2) in the abnormality levels, and the abnormality level slowly increased over four days until an abnormality factor was isolated. Such a case follows the identification of an abnormality, such as wear, occurring in a tool.

[0036] In the example shown in Fig. As shown in Figure 5, both abnormality levels in the axis driving (non-cutting) and axis driving (cutting) operating states of machine 2 indicate abnormality symptoms (exceeding the thresholds th1 and th2), and the abnormality level increases sharply over four days before the isolation of an abnormality factor. Such a case follows the identification of an abnormality, such as a failure occurring in the spindle mechanism (for example, a bearing for the spindle motor 62).

[0037] Such an abnormality associated with the spindle can also be identified based on sensor signals detected by an acceleration sensor (spindle vibrations), a temperature sensor (spindle temperature), and a noise sensor (spindle vibrations and unusual noise).

[0038] Additionally, abnormality factors can be identified based on different machine operating states. For example, if the machine 2 is a machine tool, a spindle or a table support may have an abnormality factor if the abnormality level suddenly increases in the operating state driving the axis (start of cutting) and the abnormality level does not increase much in other operating states. If the machine 2 is a robot, a deceleration for a joint of the robot is very likely to have an abnormality factor if the abnormality level calculated in the operating state of raising a robot arm (axis driving: in the direction opposite to gravity) increases slowly day by day and the abnormality level calculated in the operating state of lowering the robot arm (axis driving: in the direction of gravity) increases sharply.In this way, an abnormality factor can be identified based on changes in the abnormality levels in different operating states of the machine 2.

[0039] For the simplest identification of an abnormality factor, the factor identification unit 44 may perform the identification processing performed in the Fig. 4 and Fig. 5, based on, for example, a table or a rule provided by the manufacturer of the machine 2. In this case, an abnormality factor identification table, for example in Fig.6, created and stored in the non-volatile memory 14. The factor identification unit 44 can use the abnormality factor identification table to determine the abnormality location and type. The profile of the historical data on the abnormality levels for each operating state of the machine 2 is defined by not directly using the sensor signals, but by referring to the abnormality levels, which are round parameters. Thus, machines 2 of the same type provide similar profiles, and an abnormality factor identification table provided by the manufacturer can be used directly without any problems.In some cases, after the machine 2 is installed at an operation site, a parameter (e.g., a threshold value) for a rule contained in an abnormality factor identification table may be modified based on sensor signals obtained for each operation state. This modification can adapt the parameters to the characteristics of the machine 2 installed at the site and the installation environment.

[0040] Additionally, the factor identification unit 44 may include a machine learning device that can be used to identify the abnormality location and the abnormality type based on the historical data of abnormality levels. In this case, the machine learning device may be caused to perform, for example, machine learning based on the abnormality factors in the abnormalities of the machine 2 (or a machine of the same type) that have occurred (and been treated) in the past and the historical data of the abnormality levels stored at these times in the non-volatile memory 14. Based on the learning results, an abnormality factor can be identified by causing the machine learning device to identify the abnormality location and the abnormality type based on the historical data of the abnormality levels.Although adding a machine learning device involves difficulties due to a costly learning process, machine learning is advantageous due to its flexible adaptation to characteristics of the machine 2 and the installation environment.

[0041] Furthermore, the manufacturer of machine 2 can prepare a general-purpose learning model by having a machine of the same type perform machine learning. After machine 2 is installed in a factory for operation, etc., the machine 2 can be caused to perform additional machine learning using the general-purpose learning model to create a derivative model. Using the derivative model can reduce the learning cost to some extent.

[0042] Although an embodiment of the present invention has been described, the present invention is not limited to the above embodiment and may be modified to other aspects as appropriate.

Claims

[1] Abnormality factor identification device (1) for identifying a factor in an abnormality occurring in a machine (2), wherein the device (1) comprises: a sensor signal acquisition unit (38) designed to receive sensor signals associated with a physical state of the machine (2); an operating state determination unit (36) designed to determine operating states of the machine (2) based on information received from the machine (2); an abnormality level calculation unit (42) designed to calculate abnormality levels of the sensor signals for each operating state of the machine (2), wherein the state is determined by the operating state determination unit (36); and a factor identification unit (44) designed to determine a factor in an abnormality in the machine (2) from historical data which are a series of abnormality levels for each operating state, where: the sensor signal acquisition unit (38) receives information associated with the speed feedback on a spindle motor (62) for driving a spindle of the machine (2) or a value from an accelerometer installed on the spindle, the operating state determination unit (36) determines an operating state which is cutting or not cutting, and The factor identification unit (44) determines an abnormality in a spindle section if both an abnormality level during cutting and an abnormality level during non-cutting increase at approximately the same time, and identifies an abnormality in a tool if only one abnormality level increases during cutting. [2] Abnormality factor identification device (1) according to claim 1, wherein the abnormality level calculation unit (42) calculates the abnormality levels of the sensor signals for each operating state using sensor signals stored under a normal condition.

Images