Alarm generation system and alarm generation method

Abstract

To provide an alarm generation system and alarm generation method capable of announcing the risk of occurrence of an abnormality in the future.SOLUTION: An alarm generation system includes: an acquisition section for acquiring a measurement value obtained from a sensor; a learning section for generating a learning model by learning the measurement value acquired by the acquisition section; a prediction section for obtaining a prediction measurement value being the measurement value which may be obtained in the future after the present time with the use of the learning model generated by the learning section; and an alarm generation section for generating alarm when the prediction measurement value obtained by the prediction section satisfies an alarm generation condition.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an alarm generation system. [Background technology]

[0002] A paperless recorder is generally a device that records the measurement values ​​of various sensors as measurement data and displays the recorded measurement data. Such paperless recorders are equipped with a touch panel liquid crystal display device, and many of them are configured so that the display content of the measurement data displayed on the liquid crystal display device can be changed in response to user operations on the touch panel.

[0003] Furthermore, some recent paperless recorders are equipped with an alarm function that issues an alarm when a measurement value meets a predetermined condition (for example, when the measurement value exceeds a preset threshold). The alarm is issued, for example, by being displayed on a liquid crystal display device or being sent by email. Patent Document 1 listed below discloses a paperless recorder that displays information about the alarm generation condition with the highest level of importance among multiple alarm generation conditions. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-71837 Summary of the Invention [Problem to be solved by the invention]

[0005] However, it may be too late for a user to determine an abnormality based on the waveform displayed on the paperless recorder or an alarm notified by the paperless recorder. For example, in a product manufacturing process, if an operator waits until he or she discovers an abnormality in the waveform displayed on the paperless recorder or an alarm before dealing with the abnormality, the manufacturing process may deviate from a normal state, resulting in the production of defective products.

[0006] If the conditions for issuing an alarm by the paperless recorder were relaxed in order to prevent this situation from occurring, the accuracy of the alarm would decrease. For example, it is conceivable that an alarm could be issued even when no abnormality has occurred in the manufacturing process.

[0007] The present invention has been made in view of the above circumstances, and has an object to provide an alarm generation system that can notify that an abnormality may occur in the future. [Means for solving the problem]

[0008] In order to solve the above problem, an alarm generation system according to one aspect of the present invention comprises an acquisition unit that acquires measurement values ​​obtained from a sensor, a learning unit that generates a learning model by learning the measurement values ​​acquired by the acquisition unit, a prediction unit that uses the learning model generated by the learning unit to determine predicted measurement values, which are measurement values ​​that will be obtained in the future rather than at the present time, and an alarm generation unit that generates an alarm if the predicted measurement values ​​determined by the prediction unit satisfy an alarm generation condition.

[0009] Furthermore, an alarm generation system according to one aspect of the present invention includes a creation unit that creates information to notify that the alarm has been generated when the predicted measurement value obtained by the prediction unit satisfies the alarm generation condition.

[0010] The alarm generation system according to one aspect of the present invention also includes a display unit that displays at least one of the predicted measurement value obtained by the prediction unit and the time at which the alarm is predicted to occur.

[0011] In addition, in an alarm generation system according to one aspect of the present invention, the prediction unit further obtains information indicating the probability of the alarm occurring using the learning model generated by the learning unit, and the display unit further displays the information indicating the probability of the alarm occurring obtained by the prediction unit.

[0012] In addition, in an alarm generation system according to one aspect of the present invention, the alarm generation condition is at least one of the following: the predicted measurement value exceeds an upper limit value; the predicted measurement value is less than a lower limit value; the change value of the predicted measurement value exceeds an upper limit value of change; and the change value of the predicted measurement value is less than a lower limit value of change.

[0013] An alarm generation method according to one aspect of the present invention is performed by an alarm generation system, which includes the steps of acquiring measurement values ​​from a sensor, generating a learning model by learning the acquired measurement values, using the generated learning model to determine predicted measurement values, which are the measurement values ​​that will be obtained in the future rather than at the present time, and generating an alarm if the predicted measurement values ​​satisfy an alarm generation condition. [Effects of the Invention]

[0014] According to the present invention, it is possible to notify that there is a risk of an abnormality occurring in the future. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a block diagram showing the overall configuration of a recorder system according to an embodiment of the present invention. [Figure 2] 1 is a block diagram showing a configuration of a main part of an alarm generation system according to an embodiment of the present invention. [Figure 3]4A and 4B are diagrams for explaining an alarm recognition range in the embodiment of the present invention. [Figure 4] FIG. 4 is a flowchart illustrating an example of an operation of the recorder system according to the embodiment of the present invention. [Figure 5] FIG. 10 is a diagram showing a first display example of predicted measurement values ​​in the embodiment of the present invention. [Figure 6] FIG. 10 is a diagram showing a second display example of predicted measurement values ​​in the embodiment of the present invention. [Figure 7] FIG. 10 is a diagram showing a third example of display of predicted measurement values ​​in the embodiment of the present invention. [Figure 8] FIG. 10 is a diagram showing a fourth example of display of predicted measurement values ​​in the embodiment of the present invention. [Figure 9] FIG. 2 is a diagram showing a first display example of an alarm in the embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing a second example of an alarm display in the embodiment of the present invention. [Figure 11] FIG. 10 is a diagram showing a third example of an alarm display in the embodiment of the present invention. [Figure 12] FIG. 10 is a diagram showing a fourth example of an alarm display in the embodiment of the present invention. [Figure 13] 10A and 10B are diagrams illustrating an example of display of alarm detail information according to an embodiment of the present invention. [Figure 14] FIG. 10 is a block diagram showing the overall configuration of a recorder system according to a modified example of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] An alarm generation system and an alarm generation method according to an embodiment of the present invention will be described below with reference to the drawings. Note that the embodiment described below is an example in which the alarm generation system is applied to a recorder system. Here, the recorder system is a system that records measurement values ​​from various sensors as measurement data and displays the recorded measurement data.

[0017] [Embodiment] <Recorder System> Fig. 1 is a block diagram showing the overall configuration of a recorder system according to an embodiment of the present invention. As shown in Fig. 1, recorder system 1 includes sensors 20-1 to 20-n (n is an integer satisfying n>0) communicatively connected via a network NW, a recorder R, and a terminal device 30. Recorder system 1 also includes sensors 20-n+1 to 20-o (o is an integer satisfying o≧n) directly connected to recorder R. Network NW includes, for example, the Internet, a wide area network (WAN), a local area network (LAN), a provider device, a wireless base station, etc.

[0018] The sensors 20-1 to 20-o are, for example, pressure sensors, pH sensors, vibration sensors, temperature sensors, flow rate sensors, corrosion sensors, strain sensors, noise sensors, gas sensors, voltage sensors, current sensors, level sensors, etc. The sensors 20-1 to 20-n acquire measured values ​​of the measurement objects and transmit the acquired measured values ​​together with identification information (sensor ID) as measurement information to the recorder R. The sensors 20-n+1 to 20-o acquire measured values ​​of the measurement objects and output information indicating the acquired measured values ​​to the recorder R.

[0019] The recorder R records measurement information transmitted from the sensors 20-1 to 20-n via the network NW and displays the recorded measurement information. The rear of the recorder R can also be connected to modules (such as voltage, current, PID, pulse, digital IO, and analog IO). By directly wiring the sensors 20-n+1 to 20-o, the recorder R records information indicating the measurement values ​​output by the sensors 20-n+1 to 20-o and displays the recorded measurement information. The recorder R is equipped with an alarm generation system 10. The alarm generation system 10 calculates predicted measurement values, which are measurement values ​​likely to be obtained in the future, and generates information to notify the user U that an alarm has occurred if the calculated predicted measurement values ​​satisfy the alarm generation conditions. The alarm generation system 10 also displays at least one of the calculated predicted measurement values ​​and the predicted time at which the alarm will occur. The predicted time at which the alarm will occur is based on the predicted measurement values. Details of the alarm generation system 10 will be described later.

[0020] The terminal device 30 is a terminal that receives information notified from the alarm generation system 10 (for example, information sent by email to notify that an alarm has occurred) and notifies the user U. The terminal device 30 is, for example, a portable notebook or tablet computer, a PDA (Personal Digital Assistant), or a smartphone. The terminal device 30 may also be a stationary device.

[0021] Alarm generation system 2 is a block diagram showing the main configuration of an alarm generation system according to an embodiment of the present invention. As shown in Fig. 2, the alarm generation system 10 includes an acquisition unit 11, a learning unit 12, a prediction unit 13, an alarm generation unit 14, a creation unit 15, a storage unit 16, a first communication unit 17-1, a second communication unit 17-2, and a display unit 18.

[0022] The first communication unit 17-1 communicates with external devices such as sensors 20-1 to 20-n connected to the network NW to send and receive data. The first communication unit 17-1 is, for example, connected to the network NW by wire. The first communication unit 17-1 may also be connected to the network NW by wireless. The first communication unit 17-1 receives measurement information output by each of the sensors 20-1 to 20-n. The measurement information includes identification information (sensor ID) of each of the sensors 20-1 to 20-n and information indicating the measurement value.

[0023] The acquisition unit 11 acquires the measurement information received by the first communication unit 17-1. The acquisition unit 11 acquires date and time information when the measurement information was acquired from a clock (not shown) provided in the alarm generation system 10. The acquisition unit 11 associates the measurement information (information indicating a sensor ID and a measurement value) with the acquired date and time information, and stores them in measurement value information 16a of the storage unit 16. The acquisition unit 11 also acquires information indicating the measurement values ​​output by sensors 20-n+1 to 20-o. The acquisition unit 11 acquires date and time information when the information indicating the measurement values ​​was acquired from a clock (not shown) provided in the alarm generation system 10. The acquisition unit 11 associates the information indicating the measurement value, the sensor ID of the sensor that output the information indicating the measurement value, and the acquired date and time information, and stores them in measurement value information 16a of the storage unit 16.

[0024] The learning unit 12 uses the measurement value information 16a in the storage unit 16 to learn the relationship between multiple measurement values ​​and the date and time information at which the measurement values ​​are obtained for each sensor ID. The learning unit 12 may learn the relationship for each sensor ID every time new measurement information and date and time information are stored in the measurement value information 16a, or may learn the relationship for each sensor ID at a predetermined interval such as one minute, one hour, or one day. The learning unit 12 stores the learning model obtained by learning in the learning model 16b in the storage unit 16 in association with the sensor ID.

[0025] For example, the learning unit 12 uses AI (Artificial Intelligence) technology to learn the relationship between multiple measurement values ​​and the date and time information when the measurement values ​​are obtained for each sensor ID. Examples of AI technology include machine learning and reinforcement learning. The learning unit 12 may change the learning cycle based on the algorithm used for learning and the usage situation. Furthermore, the learning unit 12 may use a time series analysis method such as a Kalman filter or an ARIMA model based on the relationship between multiple measurement values ​​and the date and time information when the measurement values ​​are obtained. The following describes an example in which a learning model is created by performing machine learning. The learning unit 12 stores the created learning model in learning model 16b of the storage unit 16.

[0026] The prediction unit 13 uses the learning model stored in the learning model 16b to predict, for each sensor ID, time information indicating a time in the future from the current time and a predicted measurement value, which is a measurement value that will be obtained at that time. For example, the prediction unit 13 obtains results such as a predicted measurement value one point ahead and a predicted measurement value two points ahead. The time distance between the first and second points depends on the learning data. If the interval between one point in the learning data is one second, the interval between one point in the predicted value will also be one second, and if the interval between one point in the learning data is one minute, the interval between one point in the predicted value will also be one minute. The prediction unit 13 associates the predicted measurement value and time information with the sensor ID and stores them in predicted measurement value information 16c of the storage unit 16.

[0027] The alarm generating unit 14 determines whether any of the predicted measurement values ​​satisfies the alarm generation condition based on the predicted measurement value for each sensor ID and time information stored in the predicted measurement value information 16c in the storage unit 16. Specifically, the alarm generating unit 14 determines whether any of the predicted measurement values ​​satisfies the alarm generation condition within the alarm recognition range, which is the time range for determining whether any of the predicted measurement values ​​satisfies the alarm generation condition.

[0028] Any time range can be set as the alarm recognition range. For example, it is possible to set a time range based on the current time point or a time range based on a future time point. The alarm generation condition is, for example, at least one of the following: the predicted measurement value exceeds an upper limit value; the predicted measurement value falls below a lower limit value; the change in the predicted measurement value exceeds an upper change limit value; or the change in the predicted measurement value falls below a lower change limit value.

[0029] Fig. 3 is a diagram illustrating an alarm recognition range in an embodiment of the present invention. In Fig. 3, a solid line indicates a measurement value obtained in the past (past measurement value), and a dashed line indicates a predicted measurement value that will be obtained in the future. In the example shown in Fig. 3, the alarm recognition range is shown as "30 minutes from the present time" and "60 minutes from the present time." Here, it is assumed that the alarm generation condition is set to be that the predicted measurement value exceeds an upper limit value.

[0030] 3, when the alarm recognition range is set to "30 minutes from the present time," there are no predicted measurement values ​​within that time range that exceed the alarm upper limit, and therefore the alarm generating unit 14 determines that no alarm generation conditions are met. On the other hand, when the alarm recognition range is set to "60 minutes from the present time," there are predicted measurement values ​​within that time range that exceed the alarm upper limit, and therefore the alarm generating unit 14 determines that some alarm generation conditions are met.

[0031] The alarm generating unit 14 determines whether or not any of the predicted measurement values ​​for each sensor ID stored in the predicted measurement value information 16c in the storage unit 16 satisfies the alarm generation condition within the alarm recognition range. The alarm generating unit 14 generates an alarm if at least one of the predicted measurement values ​​for each sensor ID satisfies the alarm generation condition within the alarm recognition range. The alarm generating unit 14 outputs alarm display information to the display unit 18, which is information for displaying the predicted measurement value and the time when the alarm is predicted to occur.

[0032] Furthermore, the alarm generating unit 14 acquires sensor installation location information indicating the location where the sensor stored in association with the sensor ID is installed from the sensor installation information 16d in the storage unit 16. Here, the sensor installation location information is set in advance by the user. For example, the name of the place corresponding to the location can be used as the sensor installation location information. The alarm generating unit 14 calculates the occurrence time indicating the time from the current time to the time when the alarm is predicted to occur. The alarm generating unit 14 outputs alarm detail information, which is information for displaying details of the alarm, to the display unit 18. The alarm detail information includes the sensor installation location information, the alarm occurrence condition, and the occurrence time.

[0033] When alarm generating unit 14 determines that the predicted measurement value satisfies the alarm generation condition, creation unit 15 creates notification information for notifying that an alarm has occurred. Creation unit 15 outputs the created notification information to second communication unit 17-2. For example, creation unit 15 creates an email containing information for notifying that an alarm has occurred, addressed to a preset notification destination (for example, terminal device 30). Creation unit 15 outputs the created email to second communication unit 17-2.

[0034] The storage unit 16 stores the above-mentioned measurement value information 16a, learning model 16b, predicted measurement value information 16c, and sensor installation information 16d. The measurement value information 16a, learning model 16b, predicted measurement value information 16c, and sensor installation information 16d may be stored on the cloud or a PC. The storage unit 16 is realized by a hard disk drive (HDD), flash memory, random access memory (RAM), read only memory (ROM), etc.

[0035] The second communication unit 17-2 communicates with an external device such as a terminal device 30 connected to the network NW to transmit and receive data. Specifically, the second communication unit 17-2 is configured by a wireless device that performs wireless communication using a wireless communication technology such as WiFi (registered trademark) or LTE. The second communication unit 17-2 acquires the notification information output by the creation unit 15 and transmits the acquired notification information to the terminal device 30. The notification information includes information for notifying that an alarm has occurred. Here, the information for notifying that an alarm has occurred includes, for example, information on the channel on which the alarm occurred, the alarm level, the alarm type, the time of occurrence, etc.

[0036] The display unit 18 may be, for example, a liquid crystal display device equipped with a touch panel. It acquires measurement values ​​and date and time information from the measurement value information 16a in the storage unit 16 and displays a trend chart showing the relationship between the acquired measurement values ​​and the date and time information. Alternatively, it acquires predicted measurement values ​​and time information from the predicted measurement value information 16c in the storage unit 16 in addition to the relationship between the measurement values ​​and the date and time information and displays a trend chart showing the relationship between the acquired predicted measurement values ​​and the time information. The display unit 18 also acquires alarm display information, which is information for displaying the predicted measurement values ​​output by the alarm generating unit 14 and the time when an alarm is predicted to occur, and displays either or both of the predicted measurement values ​​and the time when an alarm is predicted to occur based on the acquired alarm display information. Here, a case where the display unit 18 displays both the predicted measurement values ​​and the time when an alarm is predicted to occur will be described. The display unit 18 also displays details of the alarm. Display examples of the trend chart, the predicted measurement values ​​and the alarm, and the alarm details will be described later.

[0037] The above-described acquisition unit 11, learning unit 12, prediction unit 13, alarm generation unit 14, and creation unit 15 are realized, for example, by a hardware processor such as a CPU (Central Processing Unit) executing a program (software) stored in the storage unit 16. Some or all of these functional units may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by a combination of software and hardware. The program may be stored in advance in a storage device (a storage device with a non-transitory storage medium) such as an HDD or flash memory, or may be stored in a removable storage medium (a non-transitory storage medium) such as a DVD or CD-ROM, and installed by inserting the storage medium into a drive device.

[0038] <Recording system operation> Fig. 4 is a flow diagram showing an example of the operation of the recorder system according to the embodiment of the present invention. The following mainly describes the operation of the alarm generation system 10 provided in the recorder system 1. The flow chart shown in Fig. 4 is executed repeatedly at regular time intervals, for example.

[0039] (Step S11) In the alarm generation system 10, the first communication unit 17-1 receives measurement information (information including a sensor ID and a measurement value) transmitted by the sensors 20-1 to 20-n. The acquisition unit 11 acquires the measurement information received by the first communication unit 17-1. The acquisition unit 11 also acquires information indicating the measurement values ​​output by the sensors 20-n+1 to 20-o. (Step S12) In the alarm generation system 10, the acquisition unit 11 acquires date and time information when measurement information was acquired from a clock included in the alarm generation system 10. The acquisition unit 11 associates the measurement information (information including a sensor ID and a measurement value) with the acquired date and time information, and stores them in measurement value information 16a of the storage unit 16. The acquisition unit 11 acquires date and time information when information indicating a measurement value was acquired from a clock included in the alarm generation system 10. The acquisition unit 11 associates the information indicating the measurement value, the sensor ID of the sensor that output the information indicating the measurement value, and the acquired date and time information, and stores them in measurement value information 16a of the storage unit 16.

[0040] (Step S13) In the alarm generation system 10, the learning unit 12 uses the measurement value information 16a in the storage unit 16 to learn the relationship between a plurality of measurement values ​​and the date and time information at which the measurement values ​​are obtained for each sensor ID. (Step S14) In the alarm generation system 10, the learning unit 12 associates the learning model obtained by learning with the sensor ID and stores it in the learning model 16b of the storage unit 16. For example, the "learning model" includes a predicted value, a gradient, and a noise parameter.

[0041] (Step S15) In the alarm generation system 10, the prediction unit 13 calculates a predicted measurement value and time information for each sensor ID using a learning model stored in the learning model 16b. (Step S16) In the alarm generation system 10, the prediction unit 13 stores the predicted measurement value and time information in the predicted measurement value information 16c of the storage unit 16 in association with the sensor ID.

[0042] (Step S17) In the alarm generation system 10, the alarm generation unit 14 determines whether any of the predicted measurement values ​​satisfies the alarm generation condition based on the predicted measurement value and time information for each sensor ID stored in the predicted measurement value information 16c in the storage unit 16. If none of the predicted measurement values ​​satisfies the alarm generation condition (if step S17 is "NO"), the process ends. (Step S18) In the alarm generation system 10, the alarm generation unit 14 generates an alarm when the predicted measurement values ​​satisfy the alarm generation condition (when "YES" in step S17).

[0043] (Step S19) In the alarm generation system 10, the creation unit 15 creates notification information. Then, the creation unit 15 outputs the created notification information to the second communication unit 17-2. The second communication unit 17-2 acquires the notification information output by the creation unit 15 and transmits the acquired notification information to the terminal device 30.

[0044] The terminal device 30 receives the notification information transmitted by the alarm generation system 10. Then, the terminal device 30 acquires the received notification information and displays information included in the acquired notification information for notifying that an alarm has occurred.

[0045] <Example of predicted measurement value display> FIG. 5 is a diagram showing a first example of a display of predicted measurement values ​​in an embodiment of the present invention. In FIG. 5, the horizontal axis represents time, and the vertical axis represents measurement values. The display unit 18 displays the past measurement value in channel A001 and the predicted measurement value in channel A002, thereby overlaying the past measurement value and the predicted measurement value in the past area. That is, in the example shown in FIG. 5, the past measurement value and the predicted measurement value are displayed as different channel information. The display unit 18 displays channels A001 and A002 in different colors; for example, the predicted measurement value is displayed in a lighter color than the past measurement value. The display unit 18 displays that the value of the past measurement value indicated by the arrow labeled A01 is −0.790, and the value of the predicted measurement value indicated by the arrow labeled A02 is 1.000.

[0046] FIG. 6 is a diagram showing a second example of displaying predicted measurement values ​​in an embodiment of the present invention. In FIG. 6, the horizontal axis represents time, and the vertical axis represents measurement values. The display unit 18 displays past measurement values ​​and predicted measurement values ​​on channel A001. The display unit 18 displays the predicted measurement values ​​without overlapping the past measurement values ​​by drawing the predicted measurement values ​​as an extension of the past measurement values. In the example shown in FIG. 6, the predicted measurement values ​​are drawn in a different color, such as a lighter color, than the past measurement values. The display unit 18 displays that the value of the past measurement value indicated by the arrow labeled A01 is -0.790.

[0047] Fig. 7 is a diagram showing a third example of display of predicted measurement values ​​in an embodiment of the present invention. In Fig. 7, the horizontal axis represents time and the vertical axis represents measurement values. As in the example shown in Fig. 6, the display unit 18 displays past measurement values ​​and predicted measurement values ​​in channel A001, and plots the predicted measurement values ​​by extending them into the past measurement values. However, in the example shown in Fig. 7, the past measurement values ​​are plotted as solid lines and the predicted measurement values ​​are plotted as dashed lines. The display unit 18 displays that the value of the past measurement value indicated by the arrow labeled A01 is -0.790.

[0048] FIG. 8 is a diagram showing a fourth example of display of predicted measurement values ​​in an embodiment of the present invention. In FIG. 8, the horizontal axis represents time, and the vertical axis represents measurement values. As in the examples shown in FIGS. 6 and 7, the display unit 18 displays past measurement values ​​and predicted measurement values ​​in channel A001, and plots the predicted measurement values ​​by extending them into the past measurement values. However, in the example shown in FIG. 8, a dividing line SL is drawn between the past measurement values ​​and the predicted measurement values, and the background colors are different. Here, the dividing line SL may be omitted. The display unit 18 displays that the value of the predicted measurement value indicated by the arrow labeled A01 is -0.790.

[0049] <Alarm display example> 9 is a diagram showing a first example of an alarm display in an embodiment of the present invention. In this example, the display unit 18 displays the alarm ALM, the current value (latest measurement value) in channel A001, and the current value in channel A002. The display unit 18 displays the current values ​​numerically (digitally). In the example shown in FIG. 9, the current value in channel A001 is displayed in the upper row UR, and the current value in channel A002 is displayed in the lower row LR.

[0050] When the current value of at least one channel satisfies the alarm generation condition, the display unit 18 turns on the alarm ALM and displays the current value of the channel for which the alarm generation condition is satisfied in a color different from that when the current value does not satisfy the alarm generation condition. For example, when the current value of at least one channel satisfies the alarm generation condition, the display unit 18 turns on the alarm ALM in red and displays the current value of the channel for which the alarm generation condition is satisfied in red (a color different from black, which is the color when the current value does not satisfy the alarm generation condition).

[0051] The display unit 18 also displays an alarm display section ALMD for a channel for which the alarm generation condition is satisfied, which displays information indicating the cause of the alarm. In the example shown in Fig. 9, the alarm display section ALMD is displayed in the upper row UR where the current value for channel A001 is displayed. An "L" displayed in the alarm display section ALMD indicates that the cause of the alarm is that the current value has fallen below the alarm lower limit, and an "H" indicates that the cause of the alarm is that the current value has exceeded the alarm upper limit. If the cause of the alarm is that the current value has fallen below the alarm lower limit, the background of the "L" displayed in the alarm display section ALMD is displayed in red, for example, as shown in Fig. 9.

[0052] Furthermore, when a future measurement value satisfies the alarm generation condition, the display unit 18 also lights up the alarm ALM and displays the current value of the channel for which the alarm generation condition is satisfied in a color different from that when the current value does not satisfy the alarm generation condition. However, when a future measurement value satisfies the alarm generation condition, the display unit 18 lights up and displays the current value in a color (e.g., yellow) different from the color (e.g., red) when the current value satisfies the alarm generation condition.

[0053] Furthermore, when the future measurement value satisfies the alarm generation condition, the display unit 18 displays the alarm display section ALMD on the channel for which the alarm generation condition is satisfied. Then, the display unit 18 displays the background of "L" or "H" displayed in the alarm display section ALMD in yellow, for example, depending on the cause of the alarm.

[0054] Fig. 10 is a diagram showing a second example of alarm display in an embodiment of the present invention. In this example, the display unit 18 displays the alarm ALM, the current value in channel A001, and the current value in channel A002, similar to the example shown in Fig. 9. However, the display unit 18 displays the current values ​​as a bar graph. In the example shown in Fig. 10, the current value in channel A001 is displayed on the left side LS, and the current value in channel A002 is displayed on the right side RS.

[0055] 9, when the current value of at least one channel satisfies the alarm generation condition, the display unit 18 lights up the alarm ALM in red, for example, and displays the current value of the channel for which the alarm generation condition is satisfied in red, for example. Also, like the example shown in Fig. 9, the display unit 18 displays an alarm display unit ALMD for displaying information indicating the cause of the alarm on the channel for which the alarm generation condition is satisfied, and displays the background of "L" or "H" in red, for example.

[0056] 9, when a future measurement value satisfies the alarm generation condition, the display unit 18 lights up the alarm ALM in yellow, for example, and displays the current value of the channel for which the alarm generation condition is satisfied in yellow, for example. Also, like the example shown in FIG. 9, the display unit 18 displays an alarm display unit ALMD for displaying information indicating the cause of the alarm on the channel for which the alarm generation condition is satisfied, and displays the background of "L" or "H" in yellow, for example.

[0057] FIG. 11 is a diagram showing a third example of an alarm display in an embodiment of the present invention. In this example, the display unit 18 displays an alarm ALM and the current value of each channel. In the example shown in FIG. 11, the display unit 18 displays an overview of the current values ​​of each channel in the form of a table. In the example shown in FIG. 11, the current value of each channel is displayed in one of a total of 30 fields, six vertically and five horizontally. In the example shown in FIG. 11, the current value of channel A001 is displayed in the field where R05 and C03 intersect, and the current value of channel A002 is displayed in the field where R05 and C04 intersect.

[0058] 9 and 10, when the current value of at least one channel satisfies the alarm generation condition, the display unit 18 lights up the alarm ALM, for example, in red, and displays the background color of the channel for which the alarm generation condition is satisfied, for example, in red. Also, when the future measurement value of at least one channel satisfies the alarm generation condition, the display unit 18 lights up the alarm ALM, for example, in yellow, and displays the background color of the channel for which the alarm generation condition is satisfied, for example, in yellow. By providing an overview display, the user can confirm at a glance whether the current value or future measurement value for each channel satisfies the alarm generation condition.

[0059] Fig. 12 is a diagram showing a fourth example of an alarm display in an embodiment of the present invention. In Fig. 12, the horizontal axis represents time and the vertical axis represents measurement values. The display unit 18 displays the alarm ALM, and also displays past measurement values ​​in the form of a trend chart on channel A001, and displays predicted measurement values ​​in the form of a trend chart on channel A002, similar to the example shown in Fig. 5. The display unit 18 displays channels A001 and A002 in different colors.

[0060] 12, the display unit 18 displays that the value of the predicted measurement value indicated by the arrow labeled A01 is 0.523, and the value of the past measurement value indicated by the arrow labeled A02 is -0.825. Because the value of the predicted measurement value indicated by the arrow labeled A01 satisfies the alarm generation condition, the display unit 18 turns on the alarm ALM and displays the predicted measurement value in a color different from when the alarm generation condition is met. For example, when the predicted measurement value meets the alarm generation condition, the display unit 18 turns on the alarm ALM in yellow and displays the predicted measurement value in a color different from the red color used when the predicted measurement value meets the alarm generation condition, such as yellow.

[0061] 9 and 10, the display unit 18 displays an alarm display section ALMD that displays information indicating the cause of the alarm on a channel for which the alarm generation condition is satisfied. When the current value satisfies the alarm generation condition, the display unit 18 displays the background of "L" or "H" in the alarm display section ALMD in red, for example, and when a future measurement value satisfies the alarm generation condition, the display unit 18 displays the background of "L" or "H" in the alarm display section ALMD in yellow, for example.

[0062] <Example of alarm detail information display> 13 is a diagram showing an example of display of alarm detail information in an embodiment of the present invention. The alarm detail information displays information indicating whether the alarm is on or off, information indicating the sensor installation position, information indicating the alarm occurrence conditions, and information indicating the occurrence time in association with each other.

[0063] In the example shown in FIG. 13, the display unit 18 displays the alarm "ON", the sensor installation location "Factory A - constant temperature bath 00453", the alarm generation condition "exceeds the upper limit", and the generation time "15 minutes later", in association with each other. The display unit 18 displays the alarm "ON", the sensor installation location "Factory C - constant temperature bath 02450", the alarm generation condition "exceeds the upper limit of the rate of change", and the generation time "3 minutes later", in association with each other. The display unit 18 displays the alarm "ON", the sensor installation location "Factory A - constant temperature bath 00245", the alarm generation condition "exceeds the upper limit", and the generation time "10 minutes later", in association with each other. The display unit 18 displays the alarm "ON", the sensor installation location "Factory B - constant temperature bath 11945", the alarm generation condition "below the lower limit", and the generation time "35 minutes later", in association with each other.

[0064] As described above, the alarm generation system 10 according to this embodiment includes an acquisition unit 11 that acquires measurement values ​​obtained from sensors 20-1 to 20-n, a learning unit 12 that generates a learning model by learning the measurement values ​​acquired by the acquisition unit 11, a prediction unit 13 that uses the learning model generated by the learning unit 12 to determine predicted measurement values, which are measurement values ​​that will be obtained in the future from the present time, and an alarm generation unit 14 that generates an alarm when the predicted measurement values ​​determined by the prediction unit 13 satisfy the alarm generation conditions.

[0065] With this configuration, it is possible to determine measurement values ​​that will be obtained in the future from the present time in the alarm generation system 10. Also, with this configuration, it is possible to generate an alarm in the alarm generation system 10 when the predicted measurement values ​​satisfy the alarm generation conditions. This makes it possible to notify that there is a risk of an abnormality occurring in the future.

[0066] Furthermore, the alarm generation system 10 according to this embodiment includes a creation unit 15 that creates information indicating that an alarm has occurred when the predicted measurement value obtained by the prediction unit 13 satisfies the alarm generation condition. With this configuration, the alarm generation system 10 can create information such as an email to indicate that an alarm has occurred. By sending information to notify the created alarm, the alarm generation system 10 can notify a user located in a remote location that an alarm has occurred, thereby notifying the user that there is a risk of danger.

[0067] Furthermore, the alarm generation system 10 according to this embodiment includes a display unit that displays at least one of the predicted measurement value obtained by the prediction unit 13 and the time when the alarm is predicted to occur. With this configuration, the alarm generation system 10 can display at least one of the predicted measurement value and the time when the alarm is predicted to occur, thereby notifying the user in advance that there is a risk of danger. Also, with this configuration, the alarm generation system 10 can notify the user of the time when the alarm will occur.

[0068] Furthermore, according to the alarm generation system 10 of this embodiment, the prediction unit 13 uses the learning model generated by the learning unit 12 to further obtain information indicating the probability of an alarm occurring, and the display unit 18 further displays the information indicating the probability of an alarm occurring obtained by the prediction unit 13. With this configuration, the alarm generation system 10 can display the probability of an alarm occurring, and can therefore notify the user in advance of the probability of a danger occurring.

[0069] Furthermore, according to the alarm generation system 10 of this embodiment, the alarm generation condition is at least one of the following: the predicted measurement value exceeds an upper limit; the predicted measurement value is less than a lower limit; the change in the predicted measurement value exceeds an upper change limit; and the change in the predicted measurement value is less than a lower change limit. By configuring in this manner, the alarm generation system 10 can determine whether to generate an alarm based on at least one of the following: the predicted measurement value exceeds an upper limit; the predicted measurement value is less than a lower limit; the change in the predicted measurement value exceeds an upper change limit; and the change in the predicted measurement value is less than a lower change limit.

[0070] Although the embodiments of the present invention have been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like are also included within the scope of the gist of the present invention. For example, in the above-described embodiment, the alarm generation system 10 transmits notification information to one terminal device 30, but this is not limiting. For example, the alarm generation system 10 may transmit notification information to multiple terminal devices 30.

[0071] In the above-described embodiment, the alarm generation system 10 acquires the date and time information when the measurement information transmitted by each of the sensors 20-1 to 20-n was acquired, but this is not limiting. For example, each of the sensors 20-1 to 20-n may acquire date and time information when it measured the detection target, and transmit the measurement information including the acquired date and time information to the alarm generation system 10.

[0072] In the above-described embodiment, examples of displaying predicted measurement values ​​have been described, such as displaying past measurement values ​​and predicted measurement values ​​as different channel information and drawing predicted measurement values ​​by extending past measurement values, but the present invention is not limited to these examples. For example, the display unit 18 may display predicted measurement values ​​by blinking. Furthermore, the display unit 18 may display predicted measurement values ​​in a light color as an animation by drawing lines that gradually become darker.

[0073] In the above-described embodiment, the alarm detail information is displayed by associating sensor installation location information, alarm occurrence conditions, and alarm occurrence times. However, this is not a limitation. For example, when displaying the alarm detail information, the display unit 18 may display the alarm occurrence probability in addition to the sensor installation location information, alarm occurrence conditions, and alarm occurrence times. In this case, the prediction unit 13 predicts the alarm occurrence probability when predicting, for each sensor ID, predicted measurement values, which are one or more measurement values ​​that will be obtained in the future from the present time, and time information indicating the time when the predicted measurement values ​​will be obtained. The prediction unit 13 creates alarm display information, which is information for displaying the relationship between the predicted measurement values, the occurrence probabilities of the predicted measurement values, and the time information, on the display unit 18, and outputs the created alarm display information.

[0074] In the above-described embodiment, the creation unit 15 creates an email addressed to a predetermined notification destination, including information for notifying that an alarm has occurred. However, this is not limiting. For example, the creation unit 15 may create an email addressed to a predetermined notification destination, including information indicating the time of occurrence in addition to information for notifying that an alarm has occurred. Furthermore, the creation unit 15 may create an email addressed to a predetermined notification destination, including information for notifying that an alarm has occurred, information indicating the time of occurrence, and information indicating the probability of the alarm occurring.

[0075] In the above-described embodiment, the recorder system 1 includes the alarm generation system 10 and the sensors 20-1 to 20-n, but the present invention is not limited to this example. For example, the display unit 18 included in the alarm generation system 10 may be configured as a device separate from the alarm generation system 10.

[0076] Furthermore, when the display unit 18 included in the alarm generation system 10 is configured as a device separate from the alarm generation system 10, the alarm generation system 10 that does not include the display unit 18 may be configured on the cloud. In this case, communication with the alarm generation system 10 that does not include the display unit 18 may be performed by a gateway, or may be performed by each of the sensors 20-1 to 20-n. Furthermore, in this case, the display unit 18 may be replaced by a terminal device such as a personal computer or a smartphone.

[0077] In the above-described embodiment, an example has been described in which the alarm generating system 10 is provided in the recorder R. However, some of the functions of the alarm generating system 10 may be realized by a device separate from the recorder R. FIG. 14 is a block diagram showing the overall configuration of a recorder system according to a modified example of the present invention. As shown in FIG. 14, the recorder system 1 according to this modified example is connected to a network NW and includes a server device 40 that realizes some of the functions of the alarm generating system 10. The server device 40 is connected to the recorder R (alarm generating system 10) so as to be able to communicate with it.

[0078] The server device 40 may be configured to realize, for example, the functions of the learning unit 12 of the alarm generation system 10 and a memory unit (part of the memory unit 16) that stores the learning model 16b. When configured in this way, the learning unit 12 realized by the server device 40 acquires multiple pieces of measurement value information from the alarm generation system 10, and learns, based on the acquired multiple pieces of measurement value information, the relationship between the multiple measurement values ​​and the date and time information at which the measurement values ​​were obtained for each sensor ID.

[0079] Alternatively, the server device 40 may be configured to implement the functions of a memory that stores the prediction unit 13 and predicted measurement value information 16c, in addition to the functions of the learning unit 12 and the learning model 16b of the alarm generation system 10. In this configuration, the prediction unit 13 implemented in the server device 40 uses the learning model stored in the learning model 16b to predict, for each sensor ID, predicted measurement values, which are one or more measurement values ​​that will be obtained after a predetermined period, i.e., in the future from the present time, and the occurrence times, which are the times when the predicted measurement values ​​will be obtained. The server device 40 then transmits the predicted results to the alarm generation system 10.

[0080] Alternatively, the server device 40 may be configured to realize the functions of the alarm generation unit 14 in addition to the functions of the learning unit 12, the prediction unit 13, and the storage unit that stores the learning model 16b and the predicted measurement value information 16c of the alarm generation system 10. In the case of this configuration, the server device 40 transmits to the alarm generation system 10 the determination result as to whether or not there is anything that satisfies the alarm generation condition.

[0081] Furthermore, when displaying the trend charts (trend charts of past measurement values ​​and predicted measurement values) exemplified in FIGS. 5 to 8, the display unit 18 may display them as follows. The display unit 18 may display a line indicating either or both of the upper limit value and the lower limit value of the predicted measurement value, and may change the color of the displayed line when the predicted measurement value exceeds either the upper limit value or the lower limit value of the predicted measurement value. The display unit 18 may display predicted measurement values ​​that satisfy the alarm generation conditions in a different color from predicted measurement values ​​that do not satisfy the alarm generation conditions, or may blink the display of predicted measurement values ​​that satisfy the alarm generation conditions. The display unit 18 may display a mark indicating that an alarm has occurred at the location of the predicted measurement value that satisfies the alarm occurrence condition. The display unit 18 may use a different background color for predicted measurement values ​​that satisfy the alarm generation condition from the background color for predicted measurement values ​​that do not satisfy the alarm generation condition.

[0082] In the above-described alarm generation system 10, when it is determined that a predicted measurement value satisfies an alarm generation condition, the learning unit 12 may update the learning model based on the determination result of whether or not the measurement value corresponding to the predicted measurement value satisfies the alarm generation condition. Furthermore, the learning unit 12 may update the learning model based on the determination result of whether or not the predicted measurement value satisfies the alarm generation condition and the determination result of whether or not the measurement value corresponding to the predicted measurement value satisfies the alarm generation condition.

[0083] Alternatively, a computer program for implementing the functions of the alarm generation system 10 described above may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read and executed by a computer system. Note that the term "computer system" may also include hardware such as an OS and peripheral devices. Furthermore, the term "computer-readable recording medium" refers to a flexible disk, a magneto-optical disk, a writeable nonvolatile memory such as a ROM or flash memory, a portable medium such as a DVD (Digital Versatile Disc), or a storage device such as a hard disk built into a computer system.

[0084] Furthermore, the term "computer-readable recording medium" also includes those that retain a program for a certain period of time, such as volatile memory (e.g., DRAM (Dynamic Random Access Memory)) within a computer system that serves as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by transmission waves in the transmission medium. Here, the "transmission medium" that transmits the program refers to a medium that has the function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may also be a program for implementing some of the functions described above, or may be a so-called differential file (differential program) that can implement the functions described above in combination with a program already stored in the computer system. [Explanation of symbols]

[0085] 1... Recording system, 10... Alarm generation system, 11... Acquisition unit, 12... Learning unit, 13... Prediction unit, 14... Alarm generation unit, 15... Creation unit, 16... Storage unit, 16a... Measurement value information, 16b... Learning model, 16c... Predicted measurement value information, 16d... Sensor installation information, 17-1... First communication unit, 17-2... Second communication unit, 18... Display unit, 20-1 to 20-n... Sensors

Claims

1. an acquisition unit that acquires a measurement value output from the sensor; a learning unit that generates a learning model by learning the relationship between the measurement values ​​acquired by the acquisition unit and date and time information at which the measurement values ​​were acquired; a prediction unit that uses the learning model generated by the learning unit to calculate predicted measurement values, which are measurement values ​​of the sensor that will be obtained in the future from the present time; an alarm generating unit that generates an alarm when the predicted measurement value obtained by the prediction unit satisfies an alarm generating condition within an alarm recognition range, which is a time range based on the current time or a certain time in the future; a display unit that displays the alarm generated by the alarm generating unit and the measurement value acquired by the acquiring unit; Equipped with the display unit changes the display mode of the alarm between when the latest measurement value satisfies the alarm generation condition and when the predicted measurement value satisfies the alarm generation condition. Alarm generation system.

2. An alarm generation system as described in claim 1, further comprising a creation unit that creates information to notify that the alarm has occurred when the predicted measurement value obtained by the prediction unit satisfies the alarm generation condition.

3. The prediction unit further obtains information indicating a probability that the alarm will occur using the learning model generated by the learning unit, 3. The alarm generation system according to claim 1, wherein the display unit further displays information indicating the probability of the alarm occurring determined by the prediction unit.

4. A step of acquiring a measurement value output from a sensor; generating a learning model by learning the relationship between the acquired measurement values ​​and date and time information at which the measurement values ​​were obtained; A step of using the generated learning model to obtain predicted measurement values, which are measurement values ​​of the sensor that will be obtained in the future from the present time; generating an alarm if the predicted measurement value satisfies an alarm generation condition within an alarm recognition range, which is a time range based on the current time or a future time point; Displaying the generated alarm and the acquired measurement values; and the display step includes changing a display mode of the alarm when the latest measurement value satisfies the alarm generation condition and a display mode of the alarm when the predicted measurement value satisfies the alarm generation condition. Alarm generation method.

Images