Diagnostic device and computer-readable recording medium

Abstract

The diagnosis device according to the present disclosure comprises: a data acquisition unit that acquires data indicating a predetermined state pertaining to industrial machine; a diagnosis unit that calculates an abnormality degree of the state on the basis of a separation degree of the data acquired by the data acquisition unit from a distribution of the data acquired in a reference state; a change degree calculation unit that calculates a degree of change in abnormality as a change degree; a first alert generation unit that compares the abnormality degree to an abnormality degree threshold value and determines whether or not a predetermined notification is required; a second alert generation unit that compares the change degree to a change degree threshold value and determines whether or not the predetermined notification is required; and a notification unit that outputs the predetermined notification on the basis of the results of the determinations by the first alert generation unit and the second alert generation unit.

Description

Technical Field

[0001] The present invention relates to a diagnostic apparatus and a computer-readable recording medium.

Background Art

[0002] In manufacturing sites such as factories, diagnosis of the operating conditions of industrial machines such as machine tools and robots, and diagnosis of whether products are good or defective are carried out. Conventionally, such tasks that require such diagnosis have been performed manually by workers with experience, either visually or while referring to the values detected by sensors. However, in manual work, there is a problem that the accuracy of diagnosis fluctuates due to differences in judgment criteria based on differences in the experience of each worker and lack of concentration due to changes in physical condition. Therefore, in many manufacturing sites, devices for automatic diagnosis based on data detected by sensors and the like are introduced for various diagnostic tasks.

[0003] A device for diagnosing the operating conditions of industrial machines calculates the degree of abnormality based on, for example, the degree of deviation from the normal state of values (such as sensor data) representing the state of the machine. Then, the calculated degree of abnormality is presented to the user. In this method, the user needs to monitor the change in the value of the degree of abnormality. Therefore, it is desirable to automatically issue a warning based on the calculated value of the degree of abnormality. For example, a method of setting a threshold value for the degree of abnormality and notifying the user of the occurrence of an abnormality when the degree of abnormality exceeds the threshold value is generally used (such as Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When diagnosing a condition using thresholds, environmental changes can cause the degree of anomaly to drift, making it impossible to accurately diagnose the condition. To address this, it is necessary to allow a certain margin in the anomaly threshold to match the environment. Therefore, simply comparing with a threshold may result in low sensitivity in detecting anomalies.

[0006] Furthermore, the interpretation of the degree of abnormality may differ depending on whether the abnormality mode changes gradually (e.g., wear mode) or abruptly (e.g., tool breakage mode). Thus, simply comparing with a threshold value may not always be sufficient as a diagnostic method. Therefore, there is a need for state detection technology that takes into account not only sudden changes but also gradual changes. [Means for solving the problem]

[0007] The diagnostic device according to the present invention solves the above problem by detecting abnormalities while considering not only the degree of abnormality but also the degree of change in said abnormality.

[0008] Furthermore, one aspect of the present disclosure is a diagnostic device for diagnosing a predetermined state relating to an industrial machine, comprising: a data acquisition unit that acquires data indicating a predetermined state relating to the industrial machine; a diagnostic unit that calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state; a degree of change calculation unit that calculates the degree of change of the degree of abnormality as a degree of change; a first alert generation unit that compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary; a second alert generation unit that compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary; and a notification unit that outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit.

[0009] Another aspect of the present disclosure is a computer-readable recording medium that records a program causing a computer to perform a process for diagnosing a predetermined state relating to an industrial machine, the recording medium recording a program causing a computer to operate as follows: a data acquisition unit that acquires data indicating a predetermined state relating to the industrial machine; a diagnostic unit that calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state; a degree of change calculation unit that calculates the degree of change of the degree of abnormality as a degree of change; a first alert generation unit that compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary; a second alert generation unit that compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary; and a notification unit that outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit. [Effects of the Invention]

[0010] One aspect of this disclosure makes it possible to flexibly detect anomalies in both anomaly modes in which the degree of anomaly changes gradually and anomaly modes in which the degree of anomaly changes suddenly. [Brief explanation of the drawing]

[0011] [Figure 1] This is a schematic hardware configuration diagram of a diagnostic device according to one embodiment of the present invention. [Figure 2] This block diagram shows the schematic functions of a diagnostic device according to the first embodiment of the present invention. [Figure 3] This figure shows an example of an anomaly threshold table. [Figure 4] This figure shows an example of a change threshold table. [Figure 5] This graph shows the temporal progression of abnormalities related to the torque command of the main shaft motor. [Figure 6] This graph shows the temporal progression of abnormalities related to the torque command of the feed axis motor. [Figure 7] This block diagram shows the general functions of the diagnostic device according to the second embodiment. [Figure 8] This block diagram shows the schematic functions of a diagnostic device according to a modification of the second embodiment. [Figure 9] This figure shows an example of a threshold setting screen. [Figure 10] This block diagram shows the schematic functions of a diagnostic device according to another embodiment of the present invention. [Figure 11] This figure shows an example of a conditional expression table. [Modes for carrying out the invention]

[0012] Embodiments of the present invention will be described below with reference to the drawings. Figure 1 is a schematic hardware configuration diagram showing the main components of a diagnostic device according to one embodiment of the present invention. The diagnostic device 1 of the present invention can be implemented, for example, as a control device that controls an industrial machine 4 based on a control program. The diagnostic device 1 of the present invention can also be implemented on a personal computer attached to the control device that controls the industrial machine 4 based on a control program, or on a personal computer, cell computer, fog computer 6, or cloud server 7 connected to the control device via a wired / wireless network. In this embodiment, an example is shown in which the diagnostic device 1 is implemented on a personal computer connected to the control device of the industrial machine 4 via a network.

[0013] The CPU 11 in the diagnostic device 1 of the present invention is a processor that controls the diagnostic device 1 as a whole. The CPU 11 reads a system program stored in the ROM 12 via the bus 22 and controls the entire diagnostic device 1 according to the system program. The RAM 13 temporarily stores temporary calculation data, display data, and various data input from external sources.

[0014] The non-volatile memory 14 is composed of, for example, a memory backed up by a battery not shown in the figure, an SSD (Solid State Drive), etc., and retains its stored state even when the power of the diagnostic device 1 is turned off. The non-volatile memory 14 stores data and programs read from an external device 72 via an interface 15, data and programs input via an input device 71, data acquired from an industrial machine 4, etc. The data and programs stored in the non-volatile memory 14 may be expanded to the RAM 13 during execution / use. Also, various system programs such as known analysis programs are pre-written in the ROM 12.

[0015] The interface 15 is an interface for connecting the CPU 11 of the diagnostic device 1 and an external device 72 such as a USB device. From the external device 72 side, for example, a program related to the functions of the diagnostic device 1, various data related to service provision, etc. can be read. Also, programs and various data edited within the diagnostic device 1 can be stored in external storage means via the external device 72.

[0016] To the display device 70, data read onto the memory, data obtained as a result of executing programs and system programs, etc. are output and displayed via an interface 18. Also, an input device 71 composed of a keyboard, a pointing device, etc. passes commands, data, etc. based on operations by an operator to the CPU 11 via an interface 19.

[0017] The interface 20 is an interface for connecting the CPU 11 of the diagnostic device 1 and a network 5. The network 5 may be a WAN (Wide Area Network) composed of a dedicated line, etc., or a wide area network such as the Internet. Industrial machines 4 such as machine tools and robots installed in factories, fog computers 6, cloud servers 7, etc. are connected to the network 5. These devices exchange data with each other via the network 5 and the diagnostic device 1.

[0018] Figure 2 is a schematic block diagram showing the functions of the diagnostic device 1 according to the first embodiment of the present invention. Each function of the diagnostic device 1 according to this embodiment is realized by the CPU 11 of the diagnostic device 1 shown in Figure 1 executing a system program and controlling the operation of each part of the diagnostic device 1.

[0019] The diagnostic device 1 of this embodiment includes a data acquisition unit 100, a diagnostic unit 110, a first alert generation unit 120, a change degree calculation unit 130, a second alert generation unit 140, and a notification unit 150. Furthermore, the RAM 13 to non-volatile memory 14 of the diagnostic device 1 are pre-configured with a data storage unit 180, which is an area for storing data acquired by the data acquisition unit 100; an abnormality degree storage unit 190, which is an area for storing the abnormality degree calculated by the diagnostic unit 110; and an alert information storage unit 200, which is an area where information related to alerts is pre-stored.

[0020] The data acquisition unit 100 acquires data indicating a predetermined state related to the industrial machine 4 and stores it in the data storage unit 180. The data acquired by the data acquisition unit 100 may be, for example, sensor signals detected by sensors during the operation of the industrial machine 4. The sensor signals may be, for example, current values, voltage values, position, speed, acceleration related to the drive of a motor attached to the industrial machine 4, temperature detected by a temperature sensor, humidity detected by a humidity sensor, vibration detected by a vibration sensor, pressure detected by a pressure sensor, sound detected by a sound sensor, light detected by a light sensor, or images detected by a vision sensor. The data acquired by the data acquisition unit 100 may be data indicating the operating state of the industrial machine 4, or inspection data acquired by inspecting products manufactured by the industrial machine 4. It may also be other data indicating the environmental state of the manufacturing site where the industrial machine 4 is installed.

[0021] The data acquisition unit 100 may acquire data from industrial machinery 4, fog computers 6, cloud servers 7, etc., via a wired or wireless network 5. Alternatively, data stored in memory such as CompactFlash (registered trademark) may be acquired via external equipment 72. Furthermore, operators may manually input data from input devices 71.

[0022] The diagnostic unit 110 calculates the degree of abnormality of the data acquired by the data acquisition unit 100. The diagnostic unit 110 stores, for example, at least one reference data in a predetermined standard state. It may then calculate the degree of deviation as the degree of abnormality, indicating how much the distribution deviates from the distribution of that reference data. As a method for calculating the degree of deviation, for example, it may be simply calculated based on how much the distribution of the acquired data deviates from the distribution of the reference data. Alternatively, the distribution of the reference data may be considered as a cluster, and the degree of deviation from the cluster may be calculated using a known method such as the k-means method. The diagnostic unit 110 should then calculate the degree of abnormality so that the larger the degree of deviation, the larger the value. The diagnostic unit 110 stores the calculated degree of abnormality in the abnormality storage unit 190, along with the time when the data that formed the basis for calculating the degree of abnormality was detected.

[0023] The first alert generation unit 120 determines whether a predetermined notification is necessary based on the degree of anomaly related to predetermined data calculated by the diagnostic unit 110. The first alert generation unit 120 may, for example, compare the degree of anomaly calculated by the diagnostic unit 110 with a predetermined anomaly threshold and determine that a predetermined notification is necessary if it exceeds the anomaly threshold. The predetermined notification may be, for example, a warning notification related to predetermined data. It is also possible to use the degree of anomaly calculated from the data directly, but in that case, the result of the judgment may become inaccurate due to noise in the data. To avoid this, a predetermined statistical quantity (for example, mean, median, 95th percentile, etc.) may be calculated based on multiple degrees of anomaly calculated at regular time intervals, and this statistical quantity may be treated as the degree of anomaly at that time.

[0024] Anomaly thresholds may be predetermined for each data type. Furthermore, multiple anomaly thresholds may be associated with a single data type. Additionally, thresholds may dynamically change based on predetermined data values ​​or anomaly levels. The relationship between data types and anomaly thresholds may be pre-associated and stored in, for example, the alert information storage unit 200. Figure 3 shows an example where the relationship between data types and anomaly thresholds is defined in an anomaly threshold table. As illustrated in Figure 3, the anomaly threshold table stores at least one anomaly threshold data entry for each data type, associated with a predetermined notification. In the example in Figure 3, for example, two anomaly thresholds, AThrx1 and AThrx2, are defined for the X-axis motor torque command data, each associated with the notifications "An anomaly has occurred in the X-axis motor" and "A serious problem has occurred in the X-axis motor," respectively. Furthermore, for the spindle motor torque command data, a function f is defined that calculates an abnormality threshold using the abnormality Ax of the X-axis motor torque command, the abnormality Ay of the Y-axis motor torque command, and the abnormality Az of the Z-axis motor torque command as arguments, and a notification of "an abnormality has occurred in the spindle" is associated with this. The first alert generation unit 120 refers to this table to identify the abnormality threshold corresponding to each type of data. Then, by comparing the abnormality of each data with the identified abnormality threshold, it determines the necessity of a predetermined notification.

[0025] The degree of change calculation unit 130 calculates a degree of change that indicates the degree of change in the abnormality calculated by the diagnostic unit 110. The degree of change calculation unit 130 may calculate the degree of change based on, for example, the difference between the abnormality calculated by the diagnostic unit 110 and the abnormality calculated by the diagnostic unit 110 in the previous instance (for example, the one time before). Alternatively, the degree of change may be calculated based on, for example, a predetermined statistic calculated from the abnormality of the most recent n times calculated by the diagnostic unit 110. Furthermore, the degree of change D may be calculated using, for example, the following equation 1. In equation 1, A is the abnormality to be used for the calculation of the degree of change, μ is the average value of the abnormality for the most recent m times (m is an integer, for example, 50), and σ is the standard deviation of the abnormality for the most recent m times.

[0026]

number

[0027] The degree of change calculated by the degree of change calculation unit 130 is an index that shows how much the anomaly calculated from the data acquired at the time of calculation has changed from the anomaly calculated previously, as illustrated above. The degree of change may be calculated using a calculation method other than the one described above, as long as it can be treated as such an index. When calculating the degree of change, it is also possible to directly use the anomaly calculated from the data, but in that case, a suddenly large degree of change may be calculated due to noise in the data. To avoid this, a predetermined statistic (e.g., mean, median, nth percentile, e.g., 95th percentile) may be calculated based on multiple anomaly values ​​calculated at regular time intervals, and this statistic may be treated as the anomaly value at that time before calculating the degree of change.

[0028] The second alert generation unit 140 determines whether a predetermined notification is necessary based on the degree of change in the abnormality of predetermined data calculated by the degree of change calculation unit 130. The second alert generation unit 140 may, for example, compare the degree of change calculated by the degree of change calculation unit 130 with a predetermined degree of change threshold and determine that a predetermined notification is necessary if it exceeds the degree of change threshold. The predetermined notification may be, for example, a warning notification related to predetermined data. The degree of change threshold may be predetermined for each type of data, or it may change dynamically based on predetermined conditions.

[0029] The change threshold may be predetermined for each data type. Alternatively, multiple change thresholds may be associated with a single data type. Furthermore, the threshold may dynamically change based on a predetermined data value or degree of change. The relationship between data type and change threshold may be pre-associated and stored in, for example, the alert information storage unit 200. Figure 4 shows an example where the relationship between data type and change threshold is defined in a change threshold table. As illustrated in Figure 4, the change threshold table stores at least one change threshold data set for each data type, associating the change threshold with a predetermined notification. In the example in Figure 4, for example, two change thresholds, VThx1 and VThx2, are defined for the degree of abnormality in the torque command data of the X-axis motor, each associated with the notifications "An abnormality has occurred in the X-axis motor" and "A serious problem has occurred in the X-axis motor," respectively. Furthermore, for the torque command data of the spindle motor, a function g is defined that calculates an abnormality threshold using the degree of change in the abnormality of the torque command of the X-axis motor Vx, the degree of change in the abnormality of the torque command of the Y-axis motor Vy, and the degree of change in the abnormality of the torque command of the Z-axis motor Vz as arguments, and a notification of "an abnormality has occurred in the coolant" is associated with this. The second alert generation unit 140 refers to this table and identifies the degree of change threshold corresponding to each type of data. Then, by comparing the degree of change in the abnormality of each data with the identified degree of change threshold, it determines the necessity of the predetermined notification.

[0030] The notification unit 150 determines whether a predetermined notification is necessary based on the results of the determinations made by the first alert generation unit 120 and the second alert generation unit 140. Based on this determination, it outputs a predetermined notification. The notification unit 150 may determine the content of the predetermined notification by referring, for example, to abnormality threshold data or change threshold data stored in the alert information storage unit 200. The destination of the predetermined notification by the notification unit 150 may be, for example, the display of a message on the display device 70. Alternatively, it may send a message via the network 5 to the industrial machine 4 that detected the abnormality, or to the higher-level fog computer 6 or cloud server 7. Furthermore, the notification unit 150 may record that a notification has been made in a log storage area (not shown) of the diagnostic device 1. At this time, the notification unit 150 may be configured to receive and log whether the user has confirmed the notification. In this configuration, the notification unit 150 may periodically re-notify notifications that have not been confirmed by the user.

[0031] The notification unit 150 may also notify the current time, the value of the data that caused the anomaly, the degree of anomaly calculated from the data, and the degree of change in the degree of anomaly along with the notification content. In addition, it may also notify the data that caused the anomaly, the recent trend of the degree of anomaly, and various information related to other data acquired at the same time.

[0032] The following describes an example of a diagnostic process for determining the operating status of the industrial machine 4 using the diagnostic device 1 equipped with the above configuration. Figure 5 is a graph showing the temporal progression of the abnormality level related to the torque command of the spindle motor when cutting a workpiece with a tool attached to the spindle. In the example in Figure 5, the torque command of the spindle motor detected when machining with a new tool is used as reference data, and the abnormality level of the detected value is calculated. Coolant is supplied via a center-through system to remove chips generated during machining and to cool the tool and workpiece. Generally, tool wear progresses as the workpiece is machined. Therefore, as observed at the point indicated by the white arrow A in Figure 5, the abnormality level calculated from the spindle motor torque command increases as machining progresses. Also, if the coolant jetting stops intermittently during machining, as observed at the point indicated by the white circle B, the abnormality level calculated from the spindle motor torque command suddenly decreases and then returns to its original value. When a diagnosis is performed by the diagnostic device 1 according to this embodiment based on such data, for example, a predetermined threshold AThrs can be set for the abnormality level calculated from the spindle motor torque command, and a diagnosis can be made that the tool wear has reached its limit when the abnormality level exceeds that threshold. On the other hand, a predetermined threshold VThs can be set for the degree of change in the abnormality calculated from the torque command of the spindle motor, and when the degree of change in the abnormality exceeds this threshold, it is possible to detect that an abnormality has occurred in the center-through coolant.

[0033] Figure 6 is a graph showing the temporal progression of the abnormality level related to the torque command of the feed axis motor when cutting a workpiece with a tool attached to the spindle. In the example in Figure 6, the torque command detected when a new feed axis motor was installed was used as reference data, and the abnormality level of the detected value was calculated. In addition, AThrx1 and AThrx2 are set as abnormality thresholds for the torque command of the feed axis motor. In the example in Figure 6, the abnormality level increased for approximately two months (period P) until the feed axis motor failed, and then the abnormality level fluctuated up and down until it finally failed. If the abnormality threshold AThrx1 is set by focusing only on the abnormality level, the abnormality level calculated in period P until the failure will cross the abnormality threshold AThrx1 many times, resulting in an unnecessary number of notifications. In contrast, if a predetermined change threshold is set for the degree of change in the abnormality level, and abnormality detection is performed based on the degree of change, it becomes possible to output notifications only when a large change occurs in the abnormality level. In this way, it is common for minor abnormalities to occur intermittently and repeatedly before finally leading to failure. In such cases, by notifying based on the point of change in the anomaly level observed over the long term, rather than the anomaly level itself, it becomes possible to provide notifications at an appropriate frequency.

[0034] The diagnostic device 1 according to this embodiment, which has the above configuration, focuses not only on the degree of abnormality but also on the degree of change in the degree of abnormality, and uses both to diagnose the condition of the industrial machine 4. With this configuration, it is possible to flexibly detect abnormalities in both abnormal modes in which the degree of abnormality changes gradually and abnormal modes in which the degree of abnormality changes suddenly.

[0035] Figure 7 is a schematic block diagram showing the functions of the diagnostic device 1 according to the second embodiment of the present invention. Each function of the diagnostic device 1 according to this embodiment is realized by the CPU 11 of the diagnostic device 1 shown in Figure 1 executing a system program and controlling the operation of each part of the diagnostic device 1.

[0036] The diagnostic device 1 of this embodiment is an improved version of the diagnostic device 1 of the first embodiment, with the addition of a user interface unit 160 for setting conditions. The user interface unit 160 displays a screen on the display device 70 for editing the abnormality threshold table and the change threshold table stored in the alert information storage unit. The user can set the abnormality threshold and change threshold by referring to the tables displayed on the screen.

[0037] The diagnostic device 1 according to this embodiment, having the above configuration, allows for the free setting of abnormality thresholds and change thresholds for each data point. Depending on the installation environment and equipment of the industrial machine 4, the values ​​of abnormality and change that should be judged as abnormal may change. In such cases, the user can set appropriate thresholds according to the installation environment and equipment of the industrial machine 4.

[0038] As a modification of the diagnostic device 1 according to the second embodiment, instead of directly setting the abnormality threshold and change threshold, it is conceivable to configure the device so that the abnormality threshold and change threshold can be set indirectly based on values ​​such as the abnormality level detected in the past and the notification frequency. Figure 8 shows a schematic block diagram of the functions of the diagnostic device 1 according to this modification. The diagnostic device 1 of this modification is the diagnostic device 1 according to the second embodiment with the addition of a parameter adjustment unit 210 that adjusts each threshold based on user input.

[0039] In this modified version, the user interface unit 160 displays time-series data of previously detected anomalies on the display device 70. It then accepts notification timing input by the user while referring to the displayed time-series data. Figure 9 shows an example of the threshold setting screen displayed by the user interface unit 160 in this modified version. As illustrated in Figure 9, the user interface unit 160 displays previously detected anomalies related to the specified data type as time-series data. The user can specify when to send a notification using a pointing device or the like while viewing this display. Other values, such as the acceptable over-detection frequency, can also be specified using a keyboard or the like.

[0040] The parameter adjustment unit 210 calculates appropriate anomaly thresholds and change thresholds based on the notification timing, acceptable over-detection frequency, and time-series data of the displayed anomaly, which are received by the user interface unit 160. The calculated anomaly thresholds and change thresholds are then set in the alert information storage unit 200. The parameter adjustment unit 210 may be configured to calculate the anomaly thresholds and change thresholds by, for example, solving an optimization problem. In this case, the parameter set includes the anomaly threshold and change threshold, the number of data samples m used to calculate the mean value μ and standard deviation σ of the anomaly in equation 1, and the parameters used by the change calculation unit 130 to calculate statistics. The unit then calculates the timing at which notifications occur in the time-series data of anomalies detected in the past, when the values ​​of the predetermined parameter set are applied. The unit then searches for the parameter set values ​​that maximize the evaluation values, such as how well the calculated notification timing matches the timing specified by the user, and whether the frequency of notifications falls within the acceptable over-detection frequency. The parameter set values ​​that maximize the evaluation values ​​are then set as the appropriate anomaly threshold, change threshold, and other parameter values.

[0041] By using the diagnostic device 1 based on this modified version, users can set abnormality thresholds and change thresholds by specifying values ​​that are easy to understand intuitively.

[0042] Although embodiments of the present invention have been described above, the present invention is not limited to the examples of embodiments described above, and can be implemented in various forms by making appropriate modifications. For example, in the embodiment described above, the first alert generation unit 120 and the second alert generation unit 140 are configured to determine whether to notify an alert based on the degree of abnormality and the degree of change, respectively. However, a configuration may be provided that makes the determination based on the values ​​of both the degree of abnormality and the degree of change. Figure 10 shows a schematic block diagram illustrating the functions of a diagnostic device 1 according to another embodiment. In addition to the first alert generation unit 120 and the second alert generation unit 140, the diagnostic device 1 according to this embodiment further includes a third alert generation unit 170.

[0043] The data acquisition unit 100, diagnostic unit 110, first alert generation unit 120, change degree calculation unit 130, second alert generation unit 140, and notification unit 150 of the diagnostic device 1 according to this embodiment are the same as the functions of the diagnostic device 1 according to the first embodiment. The third alert generation unit 170 in this embodiment determines whether a predetermined notification is necessary based on the degree of abnormality related to predetermined data calculated by the diagnostic unit 110 and the degree of change in the degree of abnormality related to predetermined data calculated by the degree of change calculation unit 130. The third alert generation unit 170 may, for example, calculate a predetermined conditional expression using the degree of abnormality and the degree of change as parameters, and determine that a predetermined notification is necessary when the predetermined conditional expression is satisfied. The predetermined notification may, for example, be a warning notification related to predetermined data.

[0044] The predetermined conditional expressions may be defined in advance for each type of data. Furthermore, multiple predetermined conditional expressions may be associated with a single type of data. Additionally, a threshold that dynamically changes based on the predetermined conditional expression may be used. The relationship between the data type and the predetermined conditional expression may be stored in advance in the alert information storage unit 200, for example. Figure 11 shows an example where the relationship between the data type and the predetermined conditional expression is defined in a conditional expression table. As illustrated in Figure 11, the conditional expression table stores at least one conditional expression data for each data type, associating a conditional expression with a predetermined notification. In the example in Figure 11, for example, for spindle motor temperature data, a conditional expression is defined that is true when the result calculated by a function h with the spindle motor temperature abnormality degree Ast, the spindle motor temperature change degree Vst, the spindle motor torque command abnormality degree As, and the spindle motor torque command change degree Vs as arguments exceeds the threshold CThs, and the notification "An abnormality has occurred in the spindle motor" is associated with it. The third alert generation unit 170 refers to this table to identify the predetermined conditional expression corresponding to each type of data. Then, using the degree of anomaly and change of each data point, the system evaluates whether a predetermined conditional expression is met and determines the necessity of the prescribed notification.

[0045] A diagnostic device 1 according to another embodiment having the above configuration diagnoses the state of the industrial machine 4 by determining a complex conditional expression using the degree of abnormality and the degree of change in the degree of abnormality. This configuration makes it possible to flexibly detect abnormal modes that can be detected under more complex conditions. [Explanation of Symbols]

[0046] 1. Diagnostic device 4. Industrial Machinery 5 Network 6. Fog Computer 7 Cloud Server 11 CPU 12 ROM 13 RAM 14 Non-volatile memory 15,18,19,20 Interface 22 buses 70 Display device 71 Input device 72 External equipment 100 Data acquisition unit 110 Diagnostic Department 120 First Alert Generation Unit 130 Change Calculation Unit 140 Second Alert Generation Unit 150 Notification Department 160 User Interface Section 170 Third Alert Generation Unit 180 Data Storage Unit 190 Abnormality storage unit 200 Alert Information Storage Unit 210 Parameter adjustment section

Claims

1. A diagnostic device for diagnosing a predetermined condition related to industrial machinery, A data acquisition unit that acquires data indicating a predetermined state related to the industrial machine, A diagnostic unit calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state, A change degree calculation unit that calculates the degree of change of the aforementioned abnormality as the degree of change, A first alert generation unit compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary, A second alert generation unit compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary, A notification unit that outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit, The system includes a user interface unit for setting the abnormality threshold and the change threshold, The user interface unit displays the degree of abnormality calculated by the diagnostic unit in chronological order, and accepts input for the timing of notification based on the displayed content. The system includes a parameter adjustment unit that automatically adjusts at least one of the abnormality threshold and the change threshold based on the received notification timing and the abnormality level. Diagnostic equipment.

2. A diagnostic device for diagnosing a predetermined condition relating to an industrial machine, A data acquisition unit that acquires data indicating a predetermined state related to the industrial machine, A diagnostic unit calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state, A change degree calculation unit that calculates the degree of change of the aforementioned abnormality as the degree of change, A first alert generation unit compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary, A second alert generation unit compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary, A notification unit that outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit, The system includes a user interface unit for setting the abnormality threshold and the change threshold, The user interface unit displays the degree of abnormality calculated by the diagnostic unit in a time series, accepts input for the acceptable frequency of false positives, The system includes a parameter adjustment unit that automatically adjusts at least one of the abnormality threshold and the change threshold based on the accepted input frequency of overdetection and the degree of abnormality. Diagnostic equipment.

3. A diagnostic device for diagnosing a predetermined condition relating to an industrial machine, A data acquisition unit that acquires data indicating a predetermined state related to the industrial machine, A diagnostic unit calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state, A change degree calculation unit that calculates the degree of change of the aforementioned abnormality as the degree of change, A first alert generation unit compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary, A second alert generation unit compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary, A notification unit that outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit, The system includes a user interface unit for setting the abnormality threshold and the change threshold, The user interface unit displays the degree of abnormality calculated by the diagnostic unit in chronological order, and accepts input for the timing of notification and the acceptable frequency of false positives based on the displayed content. The system includes a parameter adjustment unit that automatically adjusts at least one of the abnormality threshold and the change threshold based on the received notification timing, the acceptable frequency of false positives, and the degree of abnormality. Diagnostic equipment.

4. A statistical measure of the degree of anomaly is calculated at regular time intervals, and the calculated statistical measure is treated as the degree of anomaly. A diagnostic device according to any one of claims 1 to 3.

5. The degree of change calculation unit calculates the degree of change based on the difference between it and the degree of anomaly calculated immediately before, A diagnostic device according to any one of claims 1 to 3.

6. The degree of change calculation unit calculates the degree of change based on a statistical value of at least one most recently calculated degree of anomaly. A diagnostic device according to any one of claims 1 to 3.

7. For each of the predetermined notifications, a management system is in place to determine whether or not the user has confirmed it. A diagnostic device according to any one of claims 1 to 3.

8. A computer-readable recording medium that stores a program that causes a computer to perform a process to diagnose a predetermined condition related to industrial machinery, A data acquisition unit that acquires data indicating a predetermined state related to the industrial machine. A diagnostic unit calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state. A change degree calculation unit that calculates the degree of change of the aforementioned abnormality as the degree of change. A first alert generation unit compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary. A second alert generation unit compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary. A notification unit outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit. A user interface unit for setting the abnormality threshold and the change threshold, The user interface unit displays the degree of abnormality calculated by the diagnostic unit in chronological order, and accepts input for the timing of notification based on the displayed content. A computer-readable recording medium containing a program that causes a computer to operate as a parameter adjustment unit that automatically adjusts at least one of an abnormality threshold and a change threshold based on the received input notification timing and the abnormality level.

9. A computer-readable recording medium that stores a program causing a computer to perform a process for diagnosing a predetermined state of an industrial machine, A data acquisition unit that acquires data indicating a predetermined state related to the industrial machine. A diagnostic unit calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state. A change degree calculation unit that calculates the degree of change of the aforementioned abnormality as the degree of change. A first alert generation unit compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary. A second alert generation unit compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary. A notification unit outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit. A user interface unit for setting the abnormality threshold and the change threshold, The user interface unit displays the degree of abnormality calculated by the diagnostic unit in a time series, accepts input for the acceptable frequency of false positives, A computer-readable recording medium containing a program that causes a computer to operate as a parameter adjustment unit that automatically adjusts at least one of an abnormality threshold and a change threshold based on an acceptable frequency of false detections and the degree of abnormality.

10. A computer-readable recording medium that stores a program causing a computer to perform a process for diagnosing a predetermined state of an industrial machine, A data acquisition unit that acquires data indicating a predetermined state related to the industrial machine. A diagnostic unit calculates the degree of abnormality of the state based on the degree of deviation of the data acquired by the data acquisition unit from the distribution of the data acquired in a reference state. A change degree calculation unit that calculates the degree of change of the aforementioned abnormality as the degree of change. A first alert generation unit compares the degree of abnormality with an abnormality threshold and determines whether a predetermined notification is necessary. A second alert generation unit compares the degree of change with a degree of change threshold and determines whether a predetermined notification is necessary. A notification unit outputs a predetermined notification based on the results of the determinations made by the first alert generation unit and the second alert generation unit. A user interface unit for setting the abnormality threshold and the change threshold, The user interface unit displays the degree of abnormality calculated by the diagnostic unit in chronological order, and accepts input for the timing of notification and the acceptable frequency of false positives based on the displayed content. A computer-readable recording medium that records a program causing a computer to operate as a parameter adjustment unit that automatically adjusts at least one of an abnormality threshold and a change threshold based on the received notification timing, the acceptable frequency of false positives, and the degree of abnormality.

Images