Monitoring system, monitoring method, and monitoring program

Abstract

To provide a monitoring system capable of more efficiently monitoring conditions of plural machines.SOLUTION: A monitoring system includes an abnormality value calculation unit that calculates an abnormality value based on condition data items of plural machines, a priority order determination unit that determines a priority order for the plural machines on the basis of the abnormality value calculated by the abnormality value calculation unit, and a display control unit that displays information concerning the plural machines according to the priority order determined by the priority order determination unit.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to a monitoring device, a monitoring method, and a monitoring program for monitoring the states of a plurality of machines.

Background Art

[0002] Conventionally, in a monitoring system for monitoring a plurality of machines, when analyzing the failure content at the time of alarm occurrence, it has been required to quickly grasp the failure content by using the actual operation data and history data of the machines.

[0003] In this regard, in Patent Document 1, a method has been proposed in which data related to machines of a manufacturer installed in a factory is continuously collected and stored at predetermined intervals in a unified manner on the monitoring device side and monitored.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] On the other hand, even when the monitoring device collects data related to a plurality of machines in a unified manner, it is unclear which machine should be preferentially dealt with.

[0006] The present disclosure is for solving the above problems, and an object thereof is to provide a monitoring device, a monitoring method, and a monitoring program capable of more efficiently monitoring the states of a plurality of machines.

Means for Solving the Problems

[0007] A monitoring device according to an example of the present disclosure includes an outlier calculation unit that calculates an outlier based on the state data of each of a plurality of machines, a priority determination unit that determines a priority for the plurality of machines based on the outlier calculated by the outlier calculation unit, and a display control unit that displays information about the plurality of machines according to the priority determined by the priority determination unit. According to this configuration, since the priority for the plurality of machines is determined based on the outlier and the information about the plurality of machines is displayed according to the determined priority, it is possible to efficiently monitor the states of the plurality of machines.

[0008] The state data includes a plurality of variable data. The outlier calculation unit calculates an outlier based on the Mahalanobis distance of the plurality of variable data. According to this configuration, since the priority for the plurality of machines is determined based on the outlier based on the Mahalanobis distance and the information about the plurality of machines is displayed according to the determined priority, it is possible to efficiently monitor the states of the plurality of machines.

[0009] The monitoring device further includes a contribution rate calculation unit that calculates the contribution rate of each variable data to the outlier, and an abnormality estimation unit that estimates an abnormality according to the calculated contribution rate. According to this configuration, since the contribution rate to the outlier is calculated and the abnormality is estimated according to the calculated contribution rate, it is possible to efficiently monitor the states of the plurality of machines.

[0010] The monitoring device further includes a maintenance proposal unit that guides information related to maintenance according to the estimated abnormality. According to this configuration, since the contribution rate to the outlier is calculated and the abnormality is estimated according to the calculated contribution rate, it is possible to efficiently monitor the states of the plurality of machines.

[0011] The priority determination unit determines the priority for the plurality of machines based on the calculated outlier and the information related to maintenance corresponding to each of the plurality of machines. According to this configuration, since the priority for the plurality of machines is determined based on the outlier and the information related to maintenance and the information about the plurality of machines is displayed according to the determined priority, it is possible to efficiently monitor the states of the plurality of machines.

[0012] The information related to maintenance includes at least one of maintenance history, maintenance personnel, secured information in maintenance parts, and maintenance area. According to this configuration, by including at least one of maintenance history, maintenance personnel, secured information in maintenance parts, and maintenance area as information related to maintenance, it is possible to efficiently monitor the states of a plurality of machines.

[0013] The priority determination unit calculates a difference value between an abnormal value and a reference threshold value, and determines priorities for a plurality of machines based on the calculated difference value. According to this configuration, priorities for a plurality of machines are determined based on the difference value between the abnormal value and the reference threshold value, and information regarding the plurality of machines is displayed according to the determined priorities, so it is possible to efficiently monitor the states of the plurality of machines.

[0014] The reference threshold value is provided so as to be settable for each of the plurality of machines. According to this configuration, since the threshold value is provided so as to be settable, it is possible to adjust according to the characteristics of each machine.

[0015] A monitoring method according to an example of the present disclosure includes a step of calculating an abnormal value based on state data of each of a plurality of machines, a step of determining priorities for the plurality of machines based on the calculated abnormal value, and a step of displaying information regarding the plurality of machines according to the determined priorities. According to this configuration, priorities for a plurality of machines are determined based on the abnormal value, and information regarding the plurality of machines is displayed according to the determined priorities, so it is possible to efficiently monitor the states of the plurality of machines.

[0016] A monitoring program according to an example of the present disclosure is a monitoring program that causes a computer to execute a monitoring method, the method including steps of calculating an abnormal value based on state data of each of a plurality of machines, determining a priority for the plurality of machines based on the calculated abnormal value, and displaying information about the plurality of machines according to the determined priority. According to this configuration, since the priority for the plurality of machines is determined based on the abnormal value and the information about the plurality of machines is displayed according to the determined priority, it is possible to efficiently monitor the states of the plurality of machines.

Effect of the Invention

[0017] According to the monitoring device, monitoring method, and monitoring program of the present disclosure, it is possible to more efficiently monitor the states of a plurality of machines.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Embodiments for Carrying Out the Invention

[0019] Embodiments of the present invention will be described in detail with reference to the drawings. For the same or corresponding parts in the drawings, the same reference numerals are given and their descriptions will not be repeated.

[0020] (Embodiment 1) (Overall Configuration) The configuration of the monitoring system 1 according to Embodiment 1 will be described. FIG. 1 is a diagram for explaining the configuration of the monitoring system 1 according to Embodiment 1. Referring to FIG. 1, the monitoring system 1 includes a plurality of devices 2A to 2N, data collection devices 10A to 10N (hereinafter also collectively referred to as the data collection device 10) provided corresponding to each of the devices 2A to 2N (hereinafter also collectively referred to as the device 2), and a monitoring device 100.

[0021] The apparatuses 2A to 2N are, for example, apparatuses for manufacturing something, assembly apparatuses, etc., and may be composed of one mechanism or a plurality of mechanisms. Note that, as an example, the apparatuses 2A to 2N do not necessarily have to be the same apparatuses and may be apparatuses of different types. The data collection apparatus 10 collects the state data of the apparatus 2. The state data may include all kinds of data related to the states of the respective mechanisms constituting the apparatus 2. Each mechanism may be composed of, for example, at least any one of apparatuses such as a conveyor, a robot arm, a servo motor, a cylinder (such as a molding machine), a suction pad, a cutter apparatus, and a sealing apparatus, or a part of such an apparatus. In addition to apparatuses involving some physical operation as described above, each mechanism may include apparatuses that perform internal processing such as an apparatus that detects some information by various sensors, an apparatus that acquires data from various sensors, an apparatus that detects some information from the acquired data, and an apparatus that processes the acquired data into information.

[0022] As a specific example, when the apparatus 2 is an injection molding machine as an example, the data collection apparatus 10 may collect state data from a temperature sensor that detects the temperature of a heater, a pressure sensor that detects injection pressure, a pressure sensor that detects resin pressure, a pressure sensor that detects the pressure of a pump, and a temperature sensor that detects the temperature of a mold. Note that the state data may be data indicating at least any one of torque, speed, acceleration, temperature, current, voltage, pneumatic pressure, pressure, flow rate, position, dimensions (height, length, width), and area. Such state data can be obtained by at least any one of known sensors and measuring devices such as cameras. For example, the flow rate can be obtained by a flow sensor. Also, the position, dimensions, and area can be obtained by an image sensor. Further, the state data may be data input to each mechanism such as an input command value and a control value when indicating the state of each mechanism. Note that the state data may be composed of data obtained from one or a plurality of measuring devices. Also, the state data may be the data obtained from the measuring device as it is, or may be data that can be obtained by applying some processing to the data obtained from the measuring device, such as position data obtained from image data. In this example, a configuration in which the data collection apparatus 10 is provided corresponding to one apparatus 2 will be described, but the present invention is not limited to this configuration, and a method may be adopted in which a plurality of apparatuses 2 are connected to the data collection apparatus 10 and state data is collected.

[0023] The data collection apparatuses 10A to 10N collect state data from the apparatuses 2A to 2N and output the collection results to the monitoring apparatus 100. The data collection apparatuses 10A to 10N collect state data from the apparatuses 2A to 2N, calculate abnormal values of each of the apparatuses 2A to 2N, and output the calculation results to the monitoring apparatus 100 as collection results.

[0024] The monitoring apparatus 100 aggregates the data transmitted from the data collection apparatuses 10A to 10N and displays, as an example, the results based on the states of the apparatuses 2A to 2N on a display apparatus.

[0025] FIG. 2 is a diagram for explaining the configuration of the data collection device 10 according to Embodiment 1. Referring to FIG. 2, the data collection device 10 typically has a structure according to a general-purpose computer architecture. Specifically, the data collection device 10 includes a processor 11 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a memory 12, a storage 13, and a communication interface 16. These components are connected to each other via a bus so as to be capable of data communication. The processor 11 realizes various processes according to the present embodiment by expanding and executing various programs stored in the storage 13 in the memory 12. The memory 12 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and stores programs read from the storage 13 and the like. The storage 13 is typically a non-volatile magnetic storage device such as a hard disk drive. The storage 13 stores a data collection program 14 and an outlier calculation program 15 that are executed by the processor 11. Various programs installed in the storage 13 are distributed in a state stored in a memory card or the like. The communication interface 16 mediates data transmission between the processor 11 and external devices (for example, device 2A and monitoring device 100). The communication interface 16 typically includes Ethernet (registered trademark), USB (Universal Serial Bus), and the like. Note that various programs stored in the storage 13 may be downloaded from a distribution server (not shown) or the like via the communication interface 16.

[0026] When using a computer having a structure according to a general-purpose computer architecture as described above, in addition to an application for providing the functions according to the present embodiment, an OS (Operating System) for providing basic functions of the computer may be installed. In this case, the program according to the present embodiment may execute processing by calling necessary modules among program modules provided as a part of the OS in a predetermined order and timing. That is, the program according to the present embodiment itself does not include the above-described modules, and processing may be executed in cooperation with the OS. Alternatively, part or all of the functions provided by the execution of the data collection program 14 and the outlier calculation program 15 may be implemented as a dedicated hardware circuit.

[0027] FIG. 3 is a diagram for explaining the configuration of the monitoring device 100 according to Embodiment 1. Referring to FIG. 3, the monitoring device 100 typically has a structure according to a general-purpose computer architecture. Specifically, the monitoring device 100 includes a processor 101 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a memory 102, a storage 103, a display controller 104, an input interface 105, and a communication interface 106. These components are connected to each other via a bus so as to be able to communicate with each other. The processor 101 realizes various processes according to the present embodiment by expanding and executing various programs stored in the storage 103 in the memory 102. The memory 102 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and stores programs and the like read from the storage 103. The storage 103 is typically a non-volatile magnetic storage device such as a hard disk drive. The storage 103 stores an analysis program 131 and an information collection program 132 that are executed by the processor 101. Various programs installed in the storage 103 are distributed in a state stored in a memory card or the like. The display controller 104 is connected to the display device 70, and outputs a signal for displaying various information to the display device 70 according to an internal command from the processor 101. The input interface 105 mediates data transmission between the processor 101 and an input device 75 such as a keyboard, a mouse, a touch panel, or a dedicated console. That is, the input interface 105 receives an operation command given by the user operating the input device 75. The communication interface 106 mediates data transmission between the processor 101 and an external device (for example, the data collection device 10). The communication interface 106 typically includes Ethernet (registered trademark), USB (Universal Serial Bus), and the like. Note that various programs stored in the storage 103 may be downloaded from a distribution server (not shown) or the like via the communication interface 106.

[0028] When using a computer having a structure that conforms to a general-purpose computer architecture as described above, in addition to an application for providing the functions according to the present embodiment, an OS (Operating System) for providing basic functions of the computer may be installed. In this case, the program according to the present embodiment may be one that calls necessary modules among program modules provided as part of the OS in a predetermined order and timing to execute processing. That is, the program itself according to the present embodiment does not include the above-described modules, and processing may be executed in cooperation with the OS. Alternatively, part or all of the functions provided by the execution of the analysis program 131 and the information collection program 132 may be implemented as a dedicated hardware circuit.

[0029] FIG. 4 is a diagram for explaining the functional blocks of the monitoring system according to Embodiment 1. Referring to FIG. 4, the data collection device 10A connected to the device 2A includes an abnormal value calculation unit 20 and a device data acquisition unit 22. The device data acquisition unit 22 is realized by the processor 11 executing the data collection program 14. The abnormal value calculation unit 20 is realized by the processor 11 executing the abnormal value calculation program 15.

[0030] The device data acquisition unit 22 acquires state data based on the state of the device 2A. The abnormal value calculation unit 20 calculates an abnormal value based on the state data acquired by the device data acquisition unit 22. The calculation of the abnormal value will be described later. The abnormal value calculated by the abnormal value calculation unit 20 is transmitted to the monitoring device 100 via the communication interface 16.

[0031] The monitoring device 100 includes an analysis unit 200 and an information acquisition unit 210. The analysis unit 200 is realized by the processor 11 executing the analysis program 131. The information acquisition unit 210 is realized by the processor 11 executing the information collection program 132.

[0032] The information acquisition unit 210 acquires the data transmitted from the data collection devices 10A to 10N respectively. The analysis unit 200 executes analysis processing of the data transmitted from the data collection devices 10A to 10N acquired by the information acquisition unit 210. The analysis unit 200 includes an information output unit 202 and a priority determination unit 204. The information output unit 202 outputs, for example, to display various information on the display device 70 via the display controller 104. The priority determination unit 204 determines the priority for the devices 2A to 2N based on the abnormal values calculated by the abnormal value calculation units 20 of the data collection devices 10A to 10N. The data collection devices 10A to 10N also transmit information (such as device names and date-time information) regarding the devices 2A to 2N together with the abnormal values to the monitoring device 100. The monitoring system 1 can efficiently monitor the states of a plurality of devices because it calculates the abnormal values of the devices 2A to 2N, the abnormal values are transmitted to the monitoring device 100, and the devices 2A to 2N are centrally monitored according to the abnormal values.

[0033] FIG. 5 is a diagram for explaining the state data acquired by the device data acquisition unit 22 according to Embodiment 1. Referring to FIG. 5, in this example, the device data acquisition unit 22 acquires data of a plurality of variables (parameters) as state data from the device 2A. Specifically, the device data acquisition unit 22 acquires the actual value per unit time. It also acquires the standard value per unit time. For example, when the device 2A is an injection molding machine, the device data acquisition unit 22 acquires, as state data, data such as the temperature of the heater, injection pressure, resin pressure, pump pressure, mold temperature, etc. The abnormal value calculation unit 20 calculates the degree of deviation between the actual value and the standard value as an abnormal value. For example, the standard value per unit time may be obtained by performing a simulation of the values of a plurality of variables when operating the injection molding machine according to the production plan using a virtual model of the injection molding machine, and taking the values of the plurality of variables in the injection molding operation obtained by the simulation as the standard values.

[0034] FIG. 6 is a diagram for explaining the calculation process of the outlier calculation unit 20 according to Embodiment 1. Referring to FIG. 6, in this example, as an example, data of three variables P1 to P3 will be described. For the variables P1 to P3, a three-dimensional space of three axes is set, and a data group indicating a normal range as a learned model and data indicating an abnormal state are shown. The black point cloud data indicates the data group indicating the normal range. The data group indicating the normal range is composed of standard values. On the other hand, the hatched data indicates data away from the normal range. The distance from the center point of the data group indicating the normal range becomes the outlier value. That is, the larger the distance, the higher the outlier value. In this example, the three-dimensional space of the three variables P1 to P3 is described, but it is of course possible to expand it to a multi-dimensional space according to the number of variables.

[0035] FIG. 7 is another diagram for explaining outliers in the outlier calculation unit 20 according to Embodiment 1. Referring to FIG. 7(A), the data change from point to point is shown. In this example, the two-dimensional case is shown, where the change is Δx with respect to the x-axis and Δy with respect to the y-axis. In the two-dimensional case, the change in the distance of Δx and Δy is calculated as the outlier value. Referring to FIG. 7(B), the data change from the distribution to the point is shown. In the three-dimensional case, the change in the distance from the center of the distribution to the point is calculated as the outlier value. Note that in this example, as an example, the case where the change in distance is calculated as the outlier value is described, but it is not limited to this, and the speed of the change in distance, that is, the magnitude of the change rate per unit time, may be calculated as the outlier value. As an example of the algorithm for calculating the outlier value, an outlier detection algorithm such as outlier detection based on the Mahalanobis distance, LOF (Local Outlier Factor), or IsolationForest may be used.

[0036] FIG. 8 is a diagram for explaining the processing of the monitoring device 100 according to Embodiment 1. Referring to FIG. 8, the monitoring device 100 acquires information (step S2). Specifically, the information acquisition unit 210 acquires the data collected by the data collection devices 10A to 10N regarding the devices 2A to 2N. Next, the monitoring device 100 executes an analysis process on the collected data (step S4). Specifically, the analysis unit 200 executes an analysis process based on the acquired data. In this regard, the priority determination unit 204 determines the priorities for a plurality of machines based on the abnormal values calculated by the abnormal value calculation unit 20. Next, the monitoring device 100 displays the data regarding the devices 2A to 2N in the order of priority as an analysis result (step S6). Specifically, the information output unit 202 displays the information regarding the plurality of machines according to the determined priorities. Then, the process ends (END).

[0037] FIG. 9 is a diagram for explaining an example of a monitoring screen displayed on the display device 70 according to Embodiment 1. Referring to FIG. 9, the data regarding a plurality of devices are displayed in a list. Specifically, the data regarding the devices assigned to the identification numbers (IDs) 1 to 14 are displayed. As the data, the date and time when the data was acquired, the device information such as the device name, and the abnormal value are respectively displayed in association with each other.

[0038] Corresponding to ID1, date and time information, a device ("ABC Industrial Head Office Factory Electric Injection Molding Machine A"), and an abnormal value ("7.4") are associated and displayed. Corresponding to ID2, date and time information, a device ("ABC Industrial Motomachi Factory Electric Injection Molding Machine A"), and an abnormal value ("7.4") are associated and displayed. Corresponding to ID3, date and time information, a device ("ABC Industrial Motomachi Factory Electric Injection Molding Machine B"), and an abnormal value ("7.0") are associated and displayed. Corresponding to ID4, date and time information, a device ("ABC Industrial Head Office Factory Electric Injection Molding Machine A"), and an abnormal value ("7.0") are associated and displayed. Corresponding to ID5, date and time information, a device ("DEF Manufacturing Kyoto Factory Hydraulic Injection Molding Machine D"), and an abnormal value ("6.8") are associated and displayed. Corresponding to ID6, date and time information, a device ("ABC Industrial Head Office Factory Electric Injection Molding Machine A"), and an abnormal value ("6.6") are associated and displayed. Corresponding to ID7, date and time information, a device ("DEF Manufacturing Kyoto Factory Hydraulic Injection Molding Machine D"), and an abnormal value ("6.3") are associated and displayed. Corresponding to ID8, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), and an abnormal value ("6.3") are associated and displayed. Corresponding to ID9, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), and an abnormal value ("3.8") are associated and displayed. Corresponding to ID10, date and time information, a device ("ABC Industrial Head Office Factory Electric Injection Molding Machine A"), and an abnormal value ("3.6") are associated and displayed. Corresponding to ID11, date and time information, a device ("ABC Industrial Head Office Factory Electric Injection Molding Machine A"), and an abnormal value ("3.6") are associated and displayed. Corresponding to ID12, date and time information, a device ("ABC Industrial Motomachi Factory Electric Injection Molding Machine A"), and an abnormal value ("3.6") are associated and displayed. Corresponding to ID13, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), and an abnormal value ("3.4") are associated and displayed. Corresponding to ID14, date and time information, a device ("ABC Industrial Head Office Factory Electric Injection Molding Machine A"), and an abnormal value ("3.2") are associated and displayed.

[0039] In this example, regarding various injection molding machines which are a plurality of machines, based on the calculated abnormal values, priorities for the injection molding machines which are the plurality of machines are determined, and a case is shown where information regarding the injection molding machines is displayed according to the determined priorities. Specifically, a case is shown where information regarding the devices is displayed in descending order of the abnormal values. Thereby, it is possible to grasp at a glance which machine has a large abnormal value. Thereby, it is possible to efficiently monitor the states of the plurality of machines.

[0040] (Embodiment 2) FIG. 10 is a diagram for explaining the functional blocks of the monitoring system according to Embodiment 2. Referring to FIG. 10, the monitoring system according to Embodiment 2 is different in that the monitoring device 100 is replaced with a monitoring device 100A as compared with the monitoring system described in FIG. 4. The monitoring device 100A is different in that the analysis unit 200 is replaced with an analysis unit 200A as compared with the monitoring device 100. The analysis unit 200A further includes a contribution rate calculation unit 206, an abnormality estimation unit 208, and a maintenance proposal unit 209 as compared with the analysis unit 200. The contribution rate calculation unit 206 calculates the contribution rates of a plurality of variables related to the cause of the abnormal value regarding the abnormal value. For example, the contribution rate calculation unit 206 calculates the contribution rates of a plurality of variables to the abnormal value based on the direction from the center of the group of data groups indicating the normal range of the data described in FIG. 6. The abnormality estimation unit 208 estimates the cause of the abnormality according to the calculated contribution rates of the plurality of variables. The maintenance proposal unit 209 presents information regarding maintenance according to the estimated cause of the abnormality.

[0041] For example, the contribution rate calculation unit 206 may calculate the contribution rates of a plurality of variables related to the cause of the abnormal value regarding the information regarding the injection molding machine with the highest priority. Alternatively, the contribution rate calculation unit 206 may receive a selection input from the user and calculate the contribution rates of a plurality of variables related to the cause of the abnormal value regarding the information regarding the injection molding machine corresponding to the received selection input.

[0042] FIG. 11 is a diagram for explaining the contribution rates of a plurality of variables calculated by the contribution rate calculation unit 206 according to Embodiment 2. Referring to FIG. 11, in this example, a plurality of contribution rates related to the factors of the outlier are shown for the outlier. Specifically, as an example, the contribution rates of a plurality of variables such as variable PA (heater temperature), variable PB (injection pressure), variable PC (resin pressure), variable PD (pump pressure), variable PE (mold temperature), etc. are shown.

[0043] The abnormality estimation unit 208 estimates the cause of the abnormality according to the calculated contribution rates of the plurality of variables. For example, as an example, the abnormality estimation unit 208 extracts the variable with a high contribution rate value among variables PA to PE. The abnormality estimation unit 208 extracts, as an example, variable PA (heater temperature). The abnormality estimation unit 208 estimates the abnormality according to the extracted variable PA. Specifically, the abnormality estimation unit 208 determines that the causal relationship between variable PA (heater temperature) and the outlier value is strong. That is, the abnormality estimation unit 208 estimates that there is an abnormal cause in the heater based on variable PA. The maintenance proposal unit 209 presents information related to maintenance according to the estimated cause of the abnormality.

[0044] For example, the abnormality estimation unit 208 may estimate the cause of the abnormality according to the calculated contribution rates of the plurality of variables with respect to the information related to the injection molding machine with the highest priority. Alternatively, the abnormality estimation unit 208 may receive a selection input from the user and estimate the cause of the abnormality according to the contribution rates of the plurality of variables related to the factors of the calculated outlier value with respect to the information related to the injection molding machine corresponding to the received selection input.

[0045] FIG. 12 is a diagram for explaining the presentation of maintenance-related information in the maintenance proposal unit 209 according to Embodiment 2. Referring to FIG. 12(A), the maintenance proposal unit 209 presents maintenance-related information together with a guide message "Replacement of part XXX is necessary". Referring to FIG. 12(B), the maintenance proposal unit 209 presents maintenance-related information together with a guide message "Maintenance is necessary for part YYY". For example, when the abnormality estimation unit 208 estimates that there is an abnormality cause in the heater, the maintenance proposal unit 209 may present information regarding replacement of the heater, or may present information regarding maintenance of heater parts.

[0046] As described above, the monitoring system according to Embodiment 2 can easily grasp the state of the machine corresponding to the abnormal value by calculating the contribution rates of a plurality of variables with respect to the abnormal value, and can efficiently monitor the states of a plurality of machines. Further, the monitoring system according to Embodiment 2 can estimate the cause of the abnormality by calculating the contribution rate, and can efficiently monitor the states of a plurality of machines.

[0047] (Embodiment 3) FIG. 13 is a diagram for explaining an example of a monitoring screen displayed on the display device 70 according to Embodiment 3. Referring to FIG. 13, data regarding a plurality of devices are displayed in a list. Specifically, data regarding the devices respectively assigned identification numbers (IDs) 1 to 14 are displayed. As the data, the date and time when the data was acquired, device information, abnormal values, and maintenance history are respectively associated and displayed. The maintenance history is history data of the previous maintenance. The maintenance history may be information input by an administrator who manages the monitoring device 100, or may be information transmitted from the data collection device 10A as information registered in the data collection device 10A.

[0048] In this example, the priority determination unit 204 determines the priorities for a plurality of machines based on the calculated abnormal values and the maintenance-related information corresponding to the plurality of machines respectively. For example, the maintenance-related information may include at least one of maintenance history, maintenance personnel, securing information in maintenance parts, and maintenance area.

[0049] Specifically, corresponding to ID1, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("7.4"), and a maintenance history are associated and displayed. Corresponding to ID2, date and time information, a device ("ABC Industry Motomachi Factory Electric Injection Molding Machine A"), an abnormal value ("7.4"), and a maintenance history are associated and displayed. Corresponding to ID3, date and time information, a device ("ABC Industry Motomachi Factory Electric Injection Molding Machine B"), an abnormal value ("7.0"), and a maintenance history are associated and displayed. Corresponding to ID4, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("7.0"), and a maintenance history are associated and displayed. Corresponding to ID5, date and time information, a device ("DEF Manufacturing Kyoto Factory Hydraulic Injection Molding Machine D"), an abnormal value ("6.8"), and a maintenance history are associated and displayed. Corresponding to ID6, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("6.6"), and a maintenance history are associated and displayed. Corresponding to ID7, date and time information, a device ("DEF Manufacturing Kyoto Factory Hydraulic Injection Molding Machine D"), an abnormal value ("6.3"), and a maintenance history are associated and displayed. Corresponding to ID8, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), an abnormal value ("6.3"), and a maintenance history are associated and displayed. Corresponding to ID9, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), an abnormal value ("3.8"), and a maintenance history are associated and displayed. Corresponding to ID10, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("3.6"), and a maintenance history are associated and displayed. Corresponding to ID11, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("3.6"), and a maintenance history are associated and displayed. Corresponding to ID12, date and time information, a device ("ABC Industry Motomachi Factory Electric Injection Molding Machine A"), an abnormal value ("3.6"), and a maintenance history are associated and displayed.Corresponding to ID13, date and time information, a device ("Hybrid Injection Molding Machine C, Kyoto Factory, DEF Manufacturing Company"), an abnormal value ("3.4"), and a maintenance history are associated and displayed. Corresponding to ID14, date and time information, a device ("Electric Injection Molding Machine A, Head Office Factory, ABC Industries"), an abnormal value ("3.2"), and a maintenance history are associated and displayed.

[0050] In this example, for various injection molding machines which are multiple machines, based on the calculated abnormal value and the maintenance history, a priority order for the injection molding machines which are multiple machines is determined, and information regarding the injection molding machines is displayed according to the determined priority order. Specifically, it shows the case where information regarding the devices is displayed in the order of the abnormal values and the priority order of the dates of the maintenance history. For example, when the abnormal values are the same, the data with the newer date of the maintenance history is determined to have a higher priority. For example, compared with the data in Figure 9, the data of ID4 has a higher priority than the data of ID3 with a newer date of the maintenance history. Similarly, the data of ID11 with a newer date of the maintenance history has a higher priority than the rank of the data of ID10. Thereby, it is possible to grasp at a glance which machine has a high abnormal value. Thereby, it is possible to efficiently monitor the states of multiple machines.

[0051] In this example, the priority determination unit 204 has been described as determining the priority using the maintenance history as the calculated abnormal value and the information related to maintenance corresponding to each of the plurality of machines. However, the present invention is not limited to this. For example, the information of the maintenance staff may be used. For example, when priorities are provided for the maintenance staff, when the abnormal values are the same, the data associated with the maintenance staff with a higher priority may be determined in descending order. Alternatively, the availability information of the maintenance parts may be used. For example, when the information on the availability of the parts is registered in advance as the availability information of the maintenance parts, when the abnormal values are the same, the data associated with the availability of the maintenance parts may be determined in descending order. Alternatively, the information of the maintenance area may be used. For example, when priorities are provided for the maintenance area, when the abnormal values are the same, the data associated with the maintenance area with a higher priority may be determined in descending order. Thereby, it is possible to grasp at a glance which machine has a high abnormal value in consideration of the information related to maintenance. Thereby, it is possible to efficiently monitor the states of a plurality of machines.

[0052] (Embodiment 4) FIG. 14 is a diagram for explaining an example of a monitoring screen displayed on the display device 70 according to Embodiment 4. Referring to FIG. 14, data related to a plurality of devices are listed. Specifically, data related to the devices respectively assigned identification numbers (IDs) 1 to 14 are displayed. As the data, the date and time when the data was acquired, device information, abnormal value, threshold value, and difference are respectively associated and displayed. In this example, the priority determination unit 204 calculates a difference value between the calculated abnormal value and a reference threshold value, and determines the priority for a plurality of machines based on the calculated difference value. For example, in this example, the priorities are determined in descending order of the value of the difference from the threshold value.

[0053] Specifically, corresponding to ID1, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("7.4"), a threshold value ("6.0"), and a difference ("1.4") are associated and displayed. Corresponding to ID2, date and time information, a device ("ABC Industry Motomachi Factory Electric Injection Molding Machine A"), an abnormal value ("7.4"), a threshold value ("6.0"), and a difference ("1.4") are associated and displayed. Corresponding to ID3, date and time information, a device ("ABC Industry Motomachi Factory Electric Injection Molding Machine B"), an abnormal value ("7.0"), a threshold value ("6.0"), and a difference ("1.0") are associated and displayed. Corresponding to ID4, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("7.0"), a threshold value ("6.0"), and a difference ("1.0") are associated and displayed. Corresponding to ID9, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), an abnormal value ("3.8"), a threshold value ("2.9"), and a difference ("0.9") are associated and displayed. Corresponding to ID5, date and time information, a device ("DEF Manufacturing Kyoto Factory Hydraulic Injection Molding Machine D"), an abnormal value ("6.8"), a threshold value ("6.0"), and a difference ("0.8") are associated and displayed. Corresponding to ID10, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("3.6"), a threshold value ("2.9"), and a difference ("0.7") are associated and displayed. Corresponding to ID6, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("6.6"), a threshold value ("6.0"), and a difference ("0.6") are associated and displayed. Corresponding to ID11, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine B"), an abnormal value ("3.6"), a threshold value ("3.1"), and a difference ("0.5") are associated and displayed. Corresponding to ID12, date and time information, a device ("ABC Industry Motomachi Factory Electric Injection Molding Machine A"), an abnormal value ("3.6"), a threshold value ("3.2"), and a difference ("0.4") are associated and displayed.Corresponding to ID13, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), an abnormal value ("3.4"), a threshold value ("3.0"), and a difference ("0.4") are associated and displayed. Corresponding to ID7, date and time information, a device ("DEF Manufacturing Kyoto Factory Hydraulic Injection Molding Machine D"), an abnormal value ("6.3"), a threshold value ("6.0"), and a difference ("0.3") are associated and displayed. Corresponding to ID8, date and time information, a device ("DEF Manufacturing Kyoto Factory Hybrid Injection Molding Machine C"), an abnormal value ("6.3"), a threshold value ("6.0"), and a difference ("0.3") are associated and displayed. Corresponding to ID14, date and time information, a device ("ABC Industry Head Office Factory Electric Injection Molding Machine A"), an abnormal value ("3.2"), a threshold value ("3.0"), and a difference ("0.2") are associated and displayed.

[0054] In this example, for various injection molding machines which are multiple machines, based on the value of the difference between the calculated abnormal value and the threshold value, the priority order for the injection molding machines which are multiple machines is determined, and the information regarding the injection molding machines is displayed according to the determined priority order. Specifically, it shows the case where the information regarding the device is displayed in the order of the magnitude of the value of the difference between the abnormal value and the threshold value. Thereby, based on the difference value between the abnormal value and the threshold value, it is possible to grasp at a glance which machine has a high abnormal value. Thereby, it is possible to efficiently monitor the states of multiple machines. In this example, the threshold value may be provided so that it can be changed by the user or administrator, etc. That is, the threshold value may be set and changed for each machine. Thereby, it is possible to efficiently monitor the states of multiple machines by setting the threshold value according to the state of each machine.

[0055] Also, in this example, a method of quickly grasping which machine has a high abnormal value based on the difference value between the abnormal value and the threshold value has been described. However, the method is not limited to this. For example, speed information indicating that the abnormal value is about to reach the threshold value may be used. Specifically, the date information when the abnormal value reaches the threshold value may be estimated, and based on the earliest date information, the priority for the injection molding machines provided as a plurality of machines may be determined, and information regarding the injection molding machines may be displayed according to the determined priority. Thereby, it becomes possible to efficiently monitor the states of a plurality of machines.

[0056] In the configuration of the above monitoring system, the configurations of the data collection devices 10A to 10N and the monitoring device 100 have been described separately. However, the configuration is not limited to this, and it is also possible to combine the monitoring device 100 and the data collection devices 10A to 10N into one device. Further, a configuration may be adopted in which a part of the functions of the data collection device 10, for example, the function of the abnormal value calculation unit, is provided in the monitoring device 100.

[0057] Although the embodiments of the present invention have been described, it should be considered that the embodiments disclosed this time are illustrative in all respects and not restrictive. The scope of the present invention is indicated by the claims, and it is intended that all modifications within the meaning and scope equivalent to the claims are included.

Explanation of Reference Numerals

[0058] 1 Monitoring system, 2A to 2N devices, 10A to 10N data collection devices, 11, 101 processors, 12, 102 memories, 13, 103 storages, 14 data collection program, 15 outlier calculation program, 16, 106 communication interfaces, 20 outlier calculation unit, 22 device data acquisition unit, 70 display device, 75 input device, 100, 100A monitoring devices, 104 display controller, 105 input interface, 131 analysis program, 132 information collection program, 200, 200A analysis unit, 202 information output unit, 204 priority determination unit, 206 contribution rate calculation unit, 208 anomaly estimation unit, 209 maintenance proposal unit, 210 information acquisition unit.

Claims

1. An abnormality value calculation unit that calculates an abnormality value based on the state data of each of a plurality of machines; A priority determination unit that determines a priority for the plurality of machines based on the abnormality value calculated by the abnormality value calculation unit; A monitoring device comprising a display control unit that displays information regarding the plurality of machines according to the priority determined by the priority determination unit.

2. The state data includes a plurality of variable data, The abnormality value calculation unit calculates an abnormality value based on the Mahalanobis distance of the plurality of variable data. The monitoring device according to claim 1.

3. A contribution rate calculation unit that calculates a contribution rate of each variable data to the abnormality value; The monitoring device according to claim 2, further comprising an abnormality estimation unit that estimates an abnormality according to the calculated contribution rate.

4. The monitoring device according to claim 3, further comprising a maintenance proposal unit that guides information regarding maintenance according to the estimated abnormality.

5. The priority determination unit determines the priority for the plurality of machines based on the calculated abnormality value and information related to maintenance corresponding to each of the plurality of machines. The monitoring device according to claim 1.

6. The information related to maintenance includes at least one of maintenance history, maintenance personnel, information on securing maintenance parts, and maintenance area. The monitoring device according to claim 5.

7. The priority determination unit calculates a difference value between the abnormality value and a reference threshold value, and determines the priority for the plurality of machines based on the calculated difference value. The monitoring device according to claim 1.

8. The reference threshold value is provided so as to be settable for each of the plurality of machines. The monitoring device according to claim 7.

9. A step of calculating an abnormality value based on the state data of each of a plurality of machines; A step of determining a priority for the plurality of machines based on the calculated abnormality value; A monitoring method comprising a step of displaying information regarding the plurality of machines according to the determined priority.

10. A monitoring program for causing a computer to execute a monitoring method, A step of calculating an abnormality value based on the state data of each of a plurality of machines; A step of determining a priority for the plurality of machines based on the calculated abnormality value; A monitoring program that executes a step of displaying information regarding the plurality of machines according to the determined priority.

Images