Apparatus, method, and program for grouping process data

Abstract

To perform a process such as specifying a cause of an anomaly or improving control by collectively analyzing such a plurality of facilities that are similar in use form, use facility, or business type or the like and are similar in the anomaly cause.SOLUTION: To provide a device including: a process data receiving unit configured to receive each of a plurality of process data including time-series data of values of one or more parameters indicating a state of each of a plurality of facilities; a data comparing unit configured to compare the time-series data of respective values of parameters between respective process data of the plurality of process data; a correlation degree calculating unit configured to calculate a degree of correlation between the process data by using a result of the comparison made by the data comparing unit; a grouping unit configured to group the plurality of process data by using the degree of the correlation between the process data; and an output unit configured to output at least one of a plurality of facility groups corresponding to the grouping of the plurality of process data.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an apparatus, a method, and a program for grouping process data.

Background Art

[0002] For example, an industrial plant is provided with various pieces of equipment responsible for the production process of a product. In recent years, cloud services by a cloud computing system have been provided for purposes such as monitoring the state of each piece of equipment in the plant. Such cloud services collect process data related to various pieces of equipment in one or more plants.

Summary of the Invention

[0003] In a first aspect of the present invention, an apparatus is provided. The apparatus may include a process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities. The apparatus may include a data comparison unit that compares the time-series data of the values of each parameter between each of the plurality of process data. The apparatus may include a correlation degree calculation unit that calculates a correlation degree between each of the plurality of process data using the result of the comparison by the data comparison unit. The apparatus may include a grouping unit that groups the plurality of process data using the correlation degree between each of the plurality of process data. The apparatus may include an output unit that outputs at least one of the groups of the plurality of facilities according to the grouping of the plurality of process data.

[0004] The grouping unit may determine the level of the group according to whether the minimum correlation degree among the correlation degrees between each of the process data within the group is included in any range of 2 or more.

[0005] The grouping unit may not include process data for which the correlation degree with any other process data among the plurality of process data is less than a predetermined lower limit value in any group.

[0006] The output unit may output information indicating equipment among the plurality of equipment for which the corresponding process data is not included in any of the groups.

[0007] The process data receiving unit may receive at least one of normal process data, which is process data when each piece of equipment is normal, or abnormal process data, which is process data when each piece of equipment is abnormal, for each of the plurality of equipment.

[0008] The grouping unit may separately group at least one normal process data and at least one abnormal process data among the plurality of process data.

[0009] The output unit may output a group of equipment in which the degree of correlation between the normal process data of each piece of equipment is equal to or greater than a predetermined first threshold value and the degree of correlation between the abnormal process data of each piece of equipment is equal to or greater than a predetermined second threshold value.

[0010] The output unit may output a group of equipment in which the degree of correlation between the normal process data of each piece of equipment is equal to or greater than a predetermined first threshold value and the degree of correlation between the abnormal process data of each piece of equipment is less than a predetermined second threshold value.

[0011] The grouping unit may further group the plurality of process data by using metadata associated with each of the plurality of process data.

[0012] In a second aspect of the present invention, a method is provided. The method may include receiving each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities. The method may include comparing the time-series data of the values of each parameter among the respective pieces of process data of the plurality of process data. The method may include calculating a degree of correlation between the respective pieces of process data using the result of the comparison. The method may include grouping the plurality of process data using the degree of correlation between the respective pieces of process data. The method may include outputting at least one of the groups of the plurality of facilities according to the grouping of the plurality of process data.

[0013] In a third aspect of the present invention, a program executed by a computer is provided. The program may cause the computer to function as a process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities. The program may cause the computer to function as a data comparison unit that compares the time-series data of the values of each parameter among the respective pieces of process data of the plurality of process data. The program may cause the computer to function as a correlation degree calculation unit that calculates a degree of correlation between the respective pieces of process data using the result of the comparison by the data comparison unit. The program may cause the computer to function as a grouping unit that groups the plurality of process data using the degree of correlation between the respective pieces of process data. The program may cause the computer to function as an output unit that outputs at least one of the groups of the plurality of facilities according to the grouping of the plurality of process data.

[0014] Note that the above summary of the invention does not enumerate all the features of the present invention. Also, sub-combinations of these feature groups can also be inventions.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out the Invention

[0016] Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution means of the invention.

[0017] FIG. 1 shows a computing system 10 according to the present embodiment together with facilities 100-1 to N. The computing system 10 according to the present embodiment groups process data received from each control device 130 according to the degree of correlation, using a grouping device 150 connected to one or more control devices 130 that each control one or more facilities 100. Thereby, the grouping device 150 can classify process data from each of a plurality of facilities 100 that are controlled by the same or different control devices 130 and may even be different operators in some cases into groups. Further, the grouping device 150 may classify the facilities 100 having similar operation characteristics into groups based on the grouping of the process data. As a result, for example, a group processing device 160 connected to the grouping device 150 can perform optimization of control and the like for each group of process data having similar operation characteristics or each group of facilities 100.

[0018] Each of one or more facilities 100-1 to N (also shown as "facility 100") is provided in a plant or the like. Such a plant may be, for example, an industrial plant such as a chemical or metal plant, a plant that manages and controls the wellhead and its surroundings of a gas field or oil field, a plant that manages and controls power generation such as hydraulic, thermal, or nuclear power, a plant that manages and controls environmental power generation such as solar or wind power, a plant that manages and controls water supply and sewerage or a dam, or the like. Further, the facility 100 may be provided in a building, various factories, or transportation facilities. Such a facility 100 may have one or more process devices, one or more power generation devices, and one or more other devices. The plurality of facilities 100 may be installed in the same plant or the like, or may be an aggregate of facilities installed in a plurality of plants or the like that may have different operators. Note that the facility 100 may be an aggregate of devices provided throughout the plant.

[0019] Each of the one or more facilities 100 includes one or more sensors 110 (such as sensor 110-1, sensor 110-K, etc.) for measuring the state of the facility 100, and one or more devices 120 (such as device 120-1, device 120-L, etc.) to be controlled by the facility 100. Each sensor 110 is provided at each location within the facility 100 and measures the state of the facility 100 at that location. Each sensor 110 may be attached to the device 120 or may be built into the device 120. Also, each sensor 110 may be a field device having a function of measuring a state. Such a field device may be, for example, a sensor device such as a pressure gauge, a flow meter, or a temperature sensor, an imaging device such as a camera or video for photographing the situation of a plant or the like or an object, an acoustic device such as a microphone or a speaker for collecting abnormal sounds or the like of a plant or the like or for emitting an alarm sound or the like, a position detection device for outputting the position information of the devices included in the facility 100, or other devices.

[0020] Each device 120 is provided at each location within the facility 100 and is controlled by the control device 130. Each device 120 may be a process device, a power generation device, or any other device, or may be a part of such a device. Also, each device 120 may be a field device that operates under external control. Such a field device may be, for example, a valve device such as a flow control valve or an on-off valve, an actuator device such as a fan or a motor, or other devices.

[0021] Each of the one or more control devices 130 may be installed at a site where one or more facilities 100 to be controlled are installed. The control device 130 may be a computer for process control, or may be a distributed control system (DCS) which is a distributed processing system for process control. Each control device 130 is connected to one or more sensors 110 that the facility 100 to be controlled has, and receives measurement data from each sensor 110. Each control device 130 uses a predetermined control program, control algorithm, or control model using machine learning, etc., to generate control data for controlling each device 120 that the facility 100 to be controlled has according to the measurement data. Then, each control device 130 transmits the control data to each device 120 to cause it to perform a desired operation.

[0022] Each control device 130 transmits process data indicating such a process control state to the grouping device 150 via the network 140. The process data may include measurement data received by the control device 130 from at least one sensor 110, may include target values of measurement data received from at least one sensor 110, or may include at least a part of the control data generated by the control device 130. Such process data includes time-series data of values of one or more parameters indicating the state of the facility 100 (temperature measured by a certain sensor 110, control value supplied to a certain device 120, etc.). The control device 130 may always transmit the process data to the grouping device 150. Alternatively, the control device 130 may transmit the process data for a specified period to the grouping device 150 according to an instruction from the administrator of the control device 130.

[0023] Here, at some sites, monitoring devices other than the control device 130 may collect process data. In this case, instead of the control device 130, the device that collects the process data may transmit the process data to the grouping device 150.

[0024] Network 140 connects between one or more control devices 130, grouping devices 150, and group processing devices 160. Network 140 may be a wide area network such as the Internet or a WAN. Network 140 may be a wireless communication network including, for example, a mobile communication network such as 4G (fourth generation) or 5G (fifth generation), or alternatively, network 140 may be a wired communication network including a wired Internet or the like.

[0025] The grouping device 150 is connected to the network 140. The grouping device 150 may be a computer such as a server computer, a general-purpose computer, a workstation, or a PC (personal computer), or may be a computer system to which a plurality of computers are connected. Such a computer system is also a computer in a broad sense. Further, the grouping device 150 may be implemented by one or more executable virtual computer environments within the computer. Alternatively, the grouping device 150 may be a dedicated computer designed for grouping process data, or may be dedicated hardware realized by a dedicated circuit. The grouping device 150 may be a cloud server that provides cloud services such as cloud computing services or cloud storage services to a plurality of different operators, or may be one server computer included in a server group that provides cloud services.

[0026] The grouping device 150 receives each of a plurality of process data indicating the respective time-series states of the plurality of facilities 100-1 to N via the network 140. The grouping device 150 groups the plurality of process data using the degree of correlation between the process data. Then, the grouping device 150 outputs one or more groups obtained by grouping the plurality of process data. The grouping device 150 may output group information regarding a group of the plurality of facilities 100 corresponding to the grouping of the plurality of process data.

[0027] The group processing device 160 is connected to the grouping device 150. The group processing device 160 may be a computer or a computer system as exemplified for the grouping device 150. The group processing device 160 analyzes the operations of the facilities 100 for each group of facilities 100 having similar operation characteristics, and optimizes the control of the facilities 100 by presenting, to the control device 130 or the user of the control device 130, the values of control parameters that can optimize the control. The group processing device 160 may provide an analysis tool for analyzing the operations of the facilities 100 for each group to the user of the group processing device 160.

[0028] FIG. 2 shows the grouping device 150 according to the present embodiment. The grouping device 150 includes a process data receiving unit 200, a process data storage unit 210, a data comparison unit 220, a correlation degree calculation unit 240, a grouping unit 250, a group storage unit 260, and an output unit 270.

[0029] The process data receiving unit 200 receives a plurality of process data indicating the states of one or more facilities 100 from one or more control devices 130. The process data receiving unit 200 stores each received process data in the process data storage unit 210.

[0030] The process data storage unit 210 is connected to the process data receiving unit 200 and stores a plurality of process data received by the process data receiving unit 200. The process data storage unit 210 may be realized using an external storage device such as a hard disk drive (HDD) or a solid state drive (SSD), or a memory such as a DRAM. Alternatively, the process data storage unit 210 may be provided outside the grouping device 150 and may be cloud storage or the like. The process data storage unit 210 may store each process data as a data file, for example.

[0031] The data comparison unit 220 is connected to the process data reception unit 200 and the process data storage unit 210. The data comparison unit 220 compares the time-series data of the values of each parameter among the respective process data of the plurality of process data received by the process data reception unit 200. In the present embodiment, the data comparison unit 220 compares the newly received new process data stored in the process data storage unit 210 with each process data already stored in the process data storage unit 210, thereby sequentially updating the comparison results among the plurality of process data (online update process). Instead of this, the data comparison unit 220 may collectively perform the comparison of the process data for all combinations of the process data stored in the process data storage unit 210 up to a certain point (batch process).

[0032] The correlation degree calculation unit 240 is connected to the data comparison unit 220. The correlation degree calculation unit 240 calculates the correlation degree between each process data using the result of the comparison by the data comparison unit 220. Here, the process data includes time-series data of parameter values for each of the plurality of parameters. Even if two different facilities 100 have corresponding or similar parameters, due to various circumstances such as different models of the connected control device 130, different ports of the connection destination for the control device 130, different operators or administrators, and different names or tags assigned to the parameters, the correspondence relationship is unclear. Therefore, the correlation degree calculation unit 240 comprehensively calculates how correlated the time-series data of the parameters are between the process data using the result of the comparison by the data comparison unit 220, and calculates the correlation degree between the process data. The correlation degree calculation unit 240 may store the calculated correlation degree in association with each pair of the plurality of process data stored in the process data storage unit 210 in the process data storage unit 210. In the present embodiment, the correlation degree calculation unit 240 calculates the correlation degree between the new process data and each process data already stored in the process data storage unit 210, and stores it in the process data storage unit 210.

[0033] The grouping unit 250 is connected to the correlation degree calculation unit 240 and the process data storage unit 210. The grouping unit 250 groups a plurality of process data by using the correlation degree between each piece of process data stored in the process data storage unit 210. For example, the grouping unit 250 may group a set of two or more pieces of process data whose correlation degree with all other process data within the group is equal to or higher than a reference (for example, 0.8 or higher) as one group.

[0034] The group storage unit 260 is connected to the grouping unit 250. The group storage unit 260 may be realized by using an external storage device such as a hard disk drive (HDD) or a solid state drive (SSD), or a memory such as a DRAM. Alternatively, the group storage unit 260 may be provided outside the grouping device 150 and may be cloud storage or the like. The group storage unit 260 stores the grouping of a plurality of pieces of process data. The group storage unit 260 may be used as a temporary storage area for storing a provisional grouping during the grouping by the grouping unit 250.

[0035] The output unit 270 is connected to the grouping unit 250 and the group storage unit 260. The output unit 270 receives a notification from the grouping unit 250 indicating that the grouping of a plurality of pieces of process data has been completed. Then, the output unit 270 outputs at least one group obtained by grouping a plurality of pieces of process data. The output unit 270 may output at least one group of a plurality of facilities 100-1 to N corresponding to the grouping of a plurality of pieces of process data. The output unit 270 may output group information regarding a group of process data or facilities 100 that satisfies a predetermined condition or a condition specified by a user or the like among the generated plurality of groups. Further, the output unit 270 may output group information including information about process data that does not belong to any group or facilities 100 corresponding to such process data.

[0036] The output unit 270 may output by transmitting the group information to the group processing device 160. The group processing device 160 can make the group information output by the output unit 270 available for technical purposes such as changing the control parameters of the process data or the control device 130 that controls the facility 100 included in the group. Further, the output unit 270 may output by displaying the group information on a display device. By displaying the group information, the output unit 270 can make a technical contribution such as facilitating the work of analyzing the operation of the facility 100 corresponding to the process data included in the group indicated by the group information and optimizing the control of the facility 100.

[0037] FIG. 3 shows an example of a group of process data stored in the group storage unit 260 according to the present embodiment. The grouping unit 250 includes process data having a correlation degree equal to or higher than a threshold value with all other process data in the same group as the other process data. In other words, the grouping unit 250 groups the process data so that the correlation degree between any two process data in the same group is equal to or higher than the threshold value.

[0038] In the present embodiment, the grouping unit 250 determines the level of the group according to which range among the ranges where the correlation degree between each pair of process data in the group is 2 or more. Here, since the correlation degree between process data in the group is different for each pair of process data, the grouping unit 250 determines the level of the group according to which range among the ranges where the minimum correlation degree among the correlation degrees between each pair of process data in the group is 2 or more. For example, in a group including process data A to C, when the correlation degree between process data A and B is 0.8, the correlation degree between process data B and C is 0.75, and the correlation degree between process data A and C is 0.6, the level of this group is determined by which range the minimum correlation degree 0.6 (that is, the correlation degree between the least similar process data A and C) belongs to.

[0039] In the example of this figure, the group levels are classified into five levels from correlation level 1 to 5. Correlation level 1 is the level to which process data with a correlation less than 0.2 with any other process data belongs. Such process data is not grouped with any other process data. In the example of this figure, the process data 1-A to 1-C stored in the process data storage unit 210 as data files 1-A to 1-C belong to correlation level 1.

[0040] Correlation level 2 is the level to which a group belongs where the minimum correlation (also referred to as the "correlation coefficient") between process data within the group is 0.2 or more and less than 0.4. In the figure, the file group including two data files shown as data file group 2-A is a group consisting of two process data with a correlation of 0.2 or more and less than 0.4. Similarly, the file group including three data files shown as data file group 2-B is a group consisting of three process data with a minimum correlation between process data of 0.2 or more and less than 0.4.

[0041] Similarly hereinafter, correlation level 3 is the level to which a group belongs where the minimum correlation between process data within the group is 0.4 or more and less than 0.6, correlation level 4 is the level to which a group belongs where the minimum correlation between process data within the group is 0.6 or more and less than 0.8, and correlation level 5 is the level to which a group belongs where the minimum correlation between process data within the group is 0.8 or more.

[0042] Figure 4 shows the correlation calculation flow between process data according to this embodiment. In S400, the process data reception unit 200 receives new process data indicating the state of any facility 100 connected to the control device 130 from any control device 130.

[0043] Before receiving new process data, the grouping device 150 performs the iterative process between S410 and S450 for each of the existing process data already stored in the process data storage unit 210. For the sake of convenience of explanation in this figure, an example is shown in which the processes between S410 and S450 are performed sequentially for each of the existing process data one by one. Instead of this, the grouping device 150 may perform any parallel processing.

[0044] In S420, the data comparison unit 220 compares the time-series data of the values of each parameter of the new process data with the time-series data of the values of each parameter of the existing process data to be processed in the current iteration. Here, between the process data regarding different facilities 100, the number of parameters may be different. Therefore, the data comparison unit 220 may perform a pairwise comparison of the time-series data of the parameters between the new process data and the existing process data.

[0045] Also, the period for sampling the measurement data of the sensor 110 and the period for controlling the device 120 may be different depending on the control device 130, and the periods of the process data recorded by the control device 130 and transmitted to the grouping device 150 may be different. Therefore, between the process data, the time intervals for recording the values may also be different. Therefore, in the comparison of the time-series data of the parameters, the data comparison unit 220 may perform the comparison using a method capable of comparing time-series data with different numbers of samples or sample periods, such as DTW (Dynamic Time Warping), for example. The data comparison unit 220 may calculate an index value representing the similarity or approximation degree, such as the correlation coefficient of the time-series data, by comparing the time-series data of each pair of parameters of the new process data and the existing process data.

[0046] In S440, the correlation degree calculation unit 240 calculates the correlation degree between new process data and existing process data using the result of comparison by the data comparison unit 220. As an example, the correlation degree calculation unit 240 may use the average value of the similarity or the like between the time series data of the new process data and the existing process data, or a value depending on the average value, as the correlation degree between these process data. Also, the correlation degree calculation unit 240 may use the maximum value, minimum value, median value, etc. of the similarity between the time series data, or a value depending on these, as the correlation degree between the process data. Further, the correlation degree calculation unit 240 may use the average value, minimum value, median value, etc. of the similarity excluding the similarity below a predetermined threshold among the similarities between the time series data, or a value depending on these, as the correlation degree between the process data.

[0047] Also, the correlation degree calculation unit 240 may estimate the correspondence relationship of parameters between the process data using the result of comparison by the data comparison unit 220, and calculate the correlation degree between the new process data and the existing process data using the estimated correspondence relationship. For example, the correlation degree calculation unit 240 determines, as the parameter of the existing process data corresponding to the parameter X of the new process data, the parameter Y associated with the time series data that is most similar (i.e., has the highest similarity or the like) to the time series data of a certain parameter X in the new process data among the parameters in the existing process data. Then, the correlation degree calculation unit 240 may use the correlation (similarity or the like) of the time series data between the corresponding parameters, and use the maximum value, minimum value, median value, etc. of the similarity, or a value depending on these, as the correlation degree between the process data. In this case, the correlation degree calculation unit 240 may limit the correspondence relationship of parameters between the process data to a one-to-one relationship, or may allow a one-to-many or many-to-one relationship.

[0048] The correlation calculation unit 240 stores the correlation degrees of new process data and existing process data in the process data storage unit 210. The grouping device 150 can calculate the correlation degree between any pair of a plurality of process data including new process data and existing process data by executing the processes of S420 and S440 for each of the existing process data.

[0049] According to the grouping device 150 described above, a unified index value called the correlation degree can be calculated from the result of comparing process data with different parameter sets for different facilities 100. Thereby, the grouping device 150 can compare which pair of process data is more similar among pairs of a plurality of sets of process data with different parameter sets.

[0050] Note that the correlation degree between process data and other process data may decrease as the acquisition period is longer and the number of data points is larger. Therefore, the grouping device 150 may receive the process data for each predetermined period (for example, 1 hour, 1 day, or 1 week) from each control device 130 and calculate the correlation degree between the process data during this period. Further, the data comparison unit 220 may divide the time-series data included in one process data for each predetermined period, and use the similarity between the data in the period most similar to the divided time-series data among the time-series data included in the other process data as the comparison result between the time-series data.

[0051] FIG. 5 shows the grouping flow between process data according to the present embodiment. Before starting the grouping for new process data, the grouping unit 250 performs the iterative process between S500 and S540 for each of the existing groups already stored in the group storage unit 260. Here, for process data that does not belong to any group, the grouping unit 250 regards it as a group of single process data and performs the processing of this figure. In this figure, for the sake of convenience of explanation, an example is shown in which the processing between S500 and S540 is performed sequentially for each of the existing groups. Instead of this, the grouping unit 250 may perform any parallel processing.

[0052] In S510, the grouping unit 250 determines whether a new group including the new process data and at least some of the process data in the existing group to be processed can be generated by using the correlation degree between the new process data and each process data in the existing group to be processed. If the grouping unit 250 can generate a new group, the grouping unit 250 generates a new group including the new process data and at least some of the process data in the existing group, and stores the group information of the new group in the group storage unit 260.

[0053] The grouping unit 250 prevents process data whose correlation degree with any other process data among a plurality of process data is less than a predetermined lower limit value (correlation degree 0.2 in the example of FIG. 3) from being included in any group having two or more process data. Therefore, when the correlation degree between the new process data and any process data is less than the lower limit value, the grouping unit 250 stores the group information of the new process data in the group storage unit 260 on the assumption that the new process data does not belong to a group (or belongs to a group of only one process data).

[0054] In S520, the grouping unit 250 determines the level of the new group generated in S510. The grouping unit 250 determines the level of the new group according to which range among a plurality of ranges for each level the minimum value of the correlation degree between the process data included in the new group falls into.

[0055] In S530, when there are overlapping groups in the group storage unit 260 due to the addition of a new group, the grouping unit 250 deletes the overlapping groups from the group storage unit 260. The grouping unit 250 can store in the group storage unit 260 one or a plurality of groups obtained by grouping a plurality of process data including new process data by performing the processing between S500 and S540 for each existing group.

[0056] In S550, the output unit 270 outputs at least one group obtained by grouping a plurality of process data. The output unit 270 may output group information about at least one group among the groups of the plurality of facilities 100 according to the grouping of the plurality of process data.

[0057] Note that each control device 130 may transmit files or the like of process data to the grouping device 150 for the same facility 100 at predetermined intervals. Accordingly, the grouping device 150 will receive two or more sets of process data with different intervals for the same facility 100. In this case, the grouping device 150 may group a plurality of process data including two or more sets of process data for each facility 100.

[0058] In addition, metadata may be associated with each process data. Such metadata includes, for example, text such as names or tags assigned to each parameter, the operation history of the facility 100, alarms generated in the facility 100, the description of the facility 100, the description of the industry type of the plant including the facility 100, and the like. In this case, the grouping unit 250 may further group the plurality of process data by using the metadata associated with each of the plurality of process data.

[0059] For example, the correlation calculation unit 240 may calculate the correlation between process data based on both the similarity between metadata and the similarity between time-series data. As an example, the correlation calculation unit 240 may calculate the weighted sum of the similarity between metadata and the similarity between time-series data as the correlation between process data. Thereby, the grouping unit 250 can group the plurality of process data by further taking into account the metadata associated with each of the plurality of process data.

[0060] Alternatively, the correlation calculation unit 240 may calculate the correlation between process data on the condition that the similarity between metadata exceeds a predetermined threshold, and determine that the process data are dissimilar when the similarity between metadata is less than the threshold. In this case, the grouping unit 250 can group the plurality of process data by using only the pairs for which the correlation has been calculated among the plurality of process data, and can reduce the computational processing amount of grouping.

[0061] Here, the correlation calculation unit 240 may calculate the similarity between metadata by using a text comparison technique. Alternatively, the correlation calculation unit 240 may extract and compare corresponding items in the metadata.

[0062] Figure 6 shows an example of the degree of correlation between new process data and each piece of process data included in each existing group. In the example of this figure, the process data storage unit 210 stores existing process data 3-1 to 3-9 in the form of data files 3-1 to 3-9. The group storage unit 260 stores group 3-A (data file group 3-A) including process data 3-1 to 3-3, group 3-B (data file group 3-B) including process data 3-4 to 3-6, and group 3-C (data file group 3-C) including process data 3-7 to 3-9. Groups 3-A to 3-C are all groups with a correlation level of 3 (correlation coefficient of 0.4 or more and less than 0.6).

[0063] When the grouping device 150 receives new process data 3-10 (data file 3-10) in this state (S400 in FIG. 4), as shown from S410 to S450 in FIG. 4, the grouping device 150 calculates the degree of correlation between the new process data 3-10 and each of the existing process data 3-1 to 3-9, and identifies within which range of levels the calculated degree of correlation falls. In the example of this figure, for process data 3-10, the degree of correlation with process data 3-1 to 2 and 3-4 is 0.2 or more and less than 0.4, the degree of correlation with process data 3-5 is 0.4 or more and less than 0.6, and the degree of correlation with process data 3-3 and 3-6 to 9 is 0.6 or more and less than 0.8.

[0064] Figure 7 shows an example of the result of updating the grouping by adding new process data 3-10 to the existing process data 3-1 to 9 using the degree of correlation shown in FIG. 6. As shown in FIG. 5, the grouping unit 250 in the grouping device 150 performs the processing from S500 to S540 for each of the existing groups 3-A to 3-C.

[0065] The grouping unit 250 generates a new group including new process data and determines the level of the new group by the method shown below (S510 and S520). Specifically, for each level to which a group can be added (levels 2 to 5 in this embodiment), the grouping unit 250 determines whether a group including the new process data and at least some of the process data in the existing groups can be generated.

[0066] In this embodiment, the grouping unit 250 determines that a group can be added to the target level in any of the following cases. Here, the grouping unit 250 may include the same process data in each of two or more groups. (Case 1) The correlation degree between the new process data and each of two or more process data in the existing group is equal to or higher than the lower limit value of the range of the target level, and the correlation degree of the existing group is equal to or higher than the lower limit value of the range of the target level. In this case, the group including the new process data and these two or more process data can be added to the target level. The grouping unit 250 extracts the maximum number of process data satisfying this condition from the existing groups. If a group including a set of the same process data can be added to a higher level (a level with a higher correlation degree), the grouping unit 250 does not add this group to the target level.

[0067] (Case 2) The correlation degree between the new process data and one piece of process data within the existing group is equal to or greater than the lower limit value of the target level range, and the correlation degree of the existing group is less than the lower limit value of the target level range. In this case, it is possible to add the new process data and the group including this one piece of process data to the target level. However, even if there are two or more pieces of process data within the existing group whose correlation degrees with the new process data are equal to or greater than the lower limit value of the target level range, since the correlation degree between these two or more pieces of process data may be less than the lower limit value, it is not possible to add the group including these two or more pieces of process data and the new process data to the target level. Note that the grouping unit 250 does not add this group to the target level if other groups including these process data can be added at the target level and higher levels.

[0068] In the example of this figure, the grouping unit 250 generates group 2-A and group 4-A according to the correlation relationships between the new process data 3-10 and each of the process data 3-1 to 3-3 within the existing group 3-A. The correlation degree between the new process data 3-10 and each of the three pieces of process data 3-1 to 3-3 within the existing group 3-A is 0.2 or more, and the correlation degree of the existing group 3-A is also 0.2 or more. Therefore, the grouping unit 250 applies Case 1 and adds the group 2-A including the process data 3-1 to 3-3 and 3-10 to the correlation level 2 (correlation degree: 0.2 or more and less than 0.4). Note that since the correlation degree between the new process data 3-10 and not only the process data 3-1 to 3-2 but also the process data 3-3 is 0.2 or more, a group at the correlation level 2 including only the process data 3-1 to 3-2 and 3-10 is not generated.

[0069] In addition, the correlation degree between the new process data 3-10 and the process data 3-3 within the existing group 3-A is 0.6 or more. Therefore, the grouping unit 250 applies Case 2 and adds the group 4-A including the process data 3-3 and 3-10 to the correlation level 4 (correlation degree: 0.6 or more and less than 0.8).

[0070] In addition, the grouping unit 250 generates groups 2-B, 3-D, and 4-B according to the correlation relationship between the new process data 3-10 and each of the process data 3-4 to 6 in the existing group 3-B. The new process data 3-10 has a correlation degree of 0.2 or more with each of the three process data 3-4 to 6 in the existing group 3-B, and the correlation degree of the existing group 3-B is also 0.2 or more. Therefore, the grouping unit 250 applies Case 1 and adds group 2-B including the process data 3-4 to 6 and 3-10 to the correlation level 2 (correlation degree: 0.2 or more and less than 0.4).

[0071] In addition, the new process data 3-10 has a correlation degree of 0.4 or more with each of the two process data 3-5 to 6 in the existing group 3-B, and the correlation degree of the existing group 3-B is also 0.4 or more. Therefore, the grouping unit 250 applies Case 1 and adds group 3-D including the process data 3-5 to 6 and 3-10 to the correlation level 3 (correlation degree: 0.4 or more and less than 0.6).

[0072] In addition, the new process data 3-10 has a correlation degree of 0.6 or more with the process data 3-6 in the existing group 3-B. Therefore, the grouping unit 250 applies Case 2 and adds group 4-B including the process data 3-6 and 3-10 to the correlation level 4 (correlation degree: 0.6 or more and less than 0.8).

[0073] In addition, the grouping unit 250 generates a group 3-E and groups 4-C to 4-E according to the correlation between the new process data 3-10 and each of the process data 3-7 to 9 in the existing group 3-C. The new process data 3-10 has a correlation degree of 0.4 or more with each of the three process data 3-7 to 9 in the existing group 3-C, and the correlation degree of the existing group 3-C is also 0.4 or more. Therefore, the grouping unit 250 applies Case 1 and adds the group 3-E including the process data 3-7 to 9 and 3-10 to the correlation level 3 (correlation degree 0.4 or more and less than 0.6).

[0074] In addition, the new process data 3-10 has a correlation degree of 0.6 or more with the process data 3-7 to 9 in the existing group 3-C, but the correlation degree of the group 3-C is less than 0.6. Therefore, the grouping unit 250 applies Case 2 and adds the group 4-C including the process data 3-7 and 3-10, the group 4-D including the process data 3-8 and 3-10, and the group 4-E including the process data 3-9 and 3-10 to the correlation level 4 (correlation degree 0.6 or more and less than 0.8).

[0075] The grouping unit 250 deletes overlapping groups in S530 of FIG. 5. For a certain group, the grouping unit 250 deletes the group when there is a group at the same level or a higher level that includes all the process data of that group. The grouping unit 250 deletes the process data included in at least one group with a correlation level of 2 or more from the correlation level 1. When the new process data is not included in any group with a correlation level of 2 or more, the grouping unit 250 adds the new process data to the correlation level 1.

[0076] In the example of this figure, the newly generated group 3-E includes all the processes 3-7 to 9 of the existing group 3-C and is at the same level as group 3-C. Therefore, the grouping unit 250 deletes group 3-C. Also, assuming that a group 4-X including process data 3-7 to 8 already exists at the correlation level 4, since the correlation degree between the new process data 3-10 and each of the process data 3-7 to 8 of group 4-X is 0.6 or more, the grouping unit 250 applies Case 1 and adds a new group 4-Y including process data 3-7 to 8 and 3-10 to the correlation level 4. In this case, the new group 4-Y includes all the process data of groups 4-C and 4-D and is at the same level as groups 4-C and 4-D. Therefore, the grouping unit 250 deletes groups 4-C and 4-D.

[0077] As shown above, every time new process data is received, the grouping unit 250 can update the grouping stored in the group storage unit 260. Instead of this, the grouping unit 250 may perform grouping on all the process data stored in the process data storage unit 210 up to a certain point in a batch.

[0078] By the processing shown above, the grouping unit 250 can group a plurality of received process data and generate a plurality of groups as exemplified in FIG. 3.

[0079] FIG. 8 shows a first example of the output of group information by the grouping device 150 according to the present embodiment. The output unit 270 outputs at least one group obtained by grouping a plurality of process data in S550 of FIG. 5. The output unit 270 may output group information regarding at least one of a plurality of groups of the plurality of facilities 100 according to the grouping of the plurality of process data. Here, the output unit 270 may output group information regarding a group of process data or facility 100 that satisfies a predetermined condition or a condition specified by a user or the like.

[0080] In the example of this figure, the output unit 270 searches the group storage unit 260 for a group of process data in which the degree of correlation between the process data is equal to or higher than a predetermined threshold value and which includes process data for a predetermined number or more of facilities 100 that are different from each other. Then, the output unit 270 outputs group information regarding the searched group of process data. The output unit 270 may output group information regarding a group of facilities that includes, as elements of the group, the facilities 100 corresponding to each process data included in the searched group of process data. Here, when the group of process data itself includes information on the facilities 100 corresponding to each process data, the output unit 270 may output the group information regarding the searched group of process data as the group information of the facilities.

[0081] In the example of this figure, the output unit 270 is set to search for a group of process data in which the degree of correlation between the process data is 0.8 or higher and which includes process data for five or more facilities 100, and output the searched group of process data. Here, the group G5-A in this figure includes process data 5-1, 3, 6, 10, and 13 for five facilities 100 (facilities 100-1, 3, 6, 10, and 13), and the degree of correlation between the process data is 0.8 or higher. Therefore, the output unit 270 searches for the group G5-A and outputs the group G5-A. The output unit 270 may output a group of facilities that includes, as elements, the facilities 100-1, 3, 6, 10, and 13 corresponding to each process data of the group G5-A.

[0082] By outputting a group of a certain number or more of process data or facilities 100 having a high degree of correlation of such process data, the grouping device 150 can summarize and analyze a certain number or more of facilities 100 having similar behaviors, and perform processes such as optimization of control.

[0083] Also, in the example of this figure, the output unit 270 outputs information indicating process data or equipment 100 among the plurality of equipment 100, where the corresponding process data is not included in any group of process data. Process data 5-2 and 5-11 have a correlation level of 1 and are not included in any group of process data (a group including two or more pieces of process data). Therefore, the output unit 270 outputs process data 5-2 and 5-11 as group information indicating process data not included in any group. The output unit 270 may output equipment 100-2 and equipment 100-11 corresponding to process data 5-2 and 5-11 respectively as group information indicating equipment 100 not included in any group. Note that the output unit 270 may output such process data or group information indicating equipment 100 corresponding to such process data, with the further condition that the process data of a certain equipment 100 could not be grouped with the process data of any other equipment 100 over a predetermined period (for example, a long period such as one year).

[0084] Equipment 100 whose process data is not similar to that of any other such equipment 100 is likely to be a special case, such as new equipment with no conventional usage examples or equipment used in a new industry type. By outputting information on such equipment 100 or process data related to such equipment 100, the grouping device 150 can perform a process of analyzing the operation of unconventional equipment 100 and establishing a control method.

[0085] Also, in the example of this figure, the output unit 270 does not output information regarding a group of correlation levels 2 to 4 or a group of equipment 100 corresponding to such a group, where the correlation level of the process data is below a predetermined threshold (below the lower limit value of correlation level 5). In this case, the grouping unit 250 may not generate a group of correlation levels 2 to 4.

[0086] FIG. 9 shows a second example of the output of group information by the grouping device 150 according to the present embodiment. The process data receiving unit 200 of the grouping device 150 may receive at least one of normal process data, which is process data when each facility 100 is normal (OK), or abnormal process data, which is process data when each facility 100 is abnormal (NG), for each of the plurality of facilities 100. Here, the control device 130 may automatically attach a normal or abnormal label to each process data based on the operating state of the facility 100. Alternatively, an administrator or monitor of the facility 100 may attach a normal or abnormal label to each process data.

[0087] In this case, the grouping unit 250 may separately group at least one normal process data and at least one abnormal process data among the plurality of process data. For example, the grouping unit 250 may perform the grouping of process data as illustrated in FIG. 3 separately for each of the normal process data and the abnormal process data.

[0088] The output unit 270 may output a group of facilities in which the correlation degree between the normal process data of each facility 100 is equal to or higher than a predetermined first threshold value, and the correlation degree between the abnormal process data of each facility 100 is equal to or higher than a predetermined second threshold value. In the example of this figure, the output unit 270 outputs a group of facilities in which the correlation degree between the normal process data of each facility 100 is 0.8 or higher (correlation degree level 5 or higher) and the correlation degree between the abnormal process data of each facility 100 is 0.8 or higher (correlation degree level 5 or higher). The output unit 270 generates and outputs a group of facilities 100-1, facilities 100-3, facilities 100-6, and facilities 100-13 corresponding to the process data of any group of the group G5-B of normal process data with a correlation degree of 0.8 or higher (the group including process data 5-1OK, 5-3OK, 5-6OK, 5-10OK, and 5-13OK) and the group G5-C of abnormal process data with a correlation degree of 0.8 or higher (the group including process data 5-1NG, 5-3NG, 5-6NG, 5-11NG, and 5-13NG). The output unit 270 may output a group of facilities 100 on the further condition that such a group of facilities 100 includes a predetermined number or more of facilities.

[0089] By outputting a group of facilities 100 with a high correlation degree for both normal process data and abnormal process data, the grouping device 150 can collectively analyze a plurality of facilities 100 whose usage patterns, used facilities, or industries are similar and whose causes of abnormalities are also similar, and can perform processes such as identifying the cause of the abnormality or improving the control by the control device 130.

[0090] FIG. 10 shows a third example of the output of group information by the grouping device 150 according to the present embodiment. The output unit 270 may output a group of facilities in which the correlation degree between the normal process data of each facility 100 is equal to or higher than a predetermined first threshold value, and the correlation degree between the abnormal process data of each facility 100 is less than a predetermined second threshold value. In the example of this figure, the output unit 270 outputs a group of facilities in which the correlation degree between the normal process data of each facility 100 is 0.8 or higher (correlation degree level 5 or higher) and the correlation degree between the abnormal process data is less than 0.8 (correlation degree level less than 5). The output unit 270 includes normal process data in the group G5-D of normal process data with a correlation degree of 0.8 or higher (a group including process data 5-1OK, 5-3OK, 5-6OK, 5-10OK, and 5-13OK), but the abnormal process data has a correlation degree of less than 0.8 with the abnormal process data of other facilities. A group of facilities 100-1, 100-3, 100-6, and 100-13 is generated and output. The output unit 270 may output a group of facilities 100 on the further condition that such a group of facilities 100 includes a predetermined number or more of facilities 100.

[0091] Among the facilities 100 where the correlation degree between the normal process data is high but the correlation degree between the abnormal process data is low in this way, although the usage form, used facilities, or industry type are similar, it is highly possible that abnormalities are occurring due to different factors. By outputting such a group of facilities 100, the grouping device 150 can collectively analyze a plurality of facilities 100 with similar usage forms, used facilities, or industry types, identify the causes of various abnormalities, and collectively improve the control of each facility 100.

[0092] FIG. 11 shows a computing system 1100 according to another embodiment together with facilities 100-1 to N. In FIG. 11, components denoted by the same reference numerals as those in FIG. 1 have the same functions and configurations as the corresponding components in FIG. 1, and thus the description thereof will be omitted except for differences. The computing system 1100 according to the present embodiment groups process data received from each collection device 1130 according to the degree of correlation, using a grouping device 150 connected to one or more collection devices 1130, each of which is connected to one or two or more facilities 100.

[0093] In the present embodiment, each of the one or more facilities 100 may be controlled by a control device (e.g., "control device 130") not shown in this figure. One or more collection devices 1130-1 to M (also denoted as "collection device 1130") may be installed at a site where one or two or more facilities 100 that are the collection targets of process data are installed. The collection device 1130 may be a computer such as a server computer, a general-purpose computer, a workstation, or a PC (personal computer), or may be a computer system to which a plurality of computers are connected. Further, the collection device 1130 may be a communication device such as a hub that performs wired or wireless communication with at least one sensor 110.

[0094] The collection device 1130 collects process data from the one or more connected facilities 100. In the present embodiment, the process data may include data used for controlling each facility 100, and may also include measurement data measured by monitoring / observation sensors 110 that are not used for controlling each facility 100.

[0095] The collection device 1130 may constantly transmit process data to the grouping device 150. Alternatively, the collection device 1130 may transmit the process data for a specified period to the grouping device 150 in response to an instruction from the administrator of the collection device 1130. Note that at least one sensor 110 may be an IoT sensor that can be directly connected to the Internet without going through the collection device 1130. Such a sensor 110 may directly transmit process data to the grouping device 150 without going through the collection device 1130.

[0096] The network 140 and the grouping device 150 may be the same as the network 140 and the grouping device 150 in FIG. 1. The display device 1160 displays information regarding a group of process data or a group of groups of facilities 100 output by the grouping device 150.

[0097] According to the computing system 1100 described above, the grouping device 150 can classify process data from each of the plurality of facilities 100 into groups. Further, the grouping device 150 may classify the plurality of facilities 100 into groups of facilities 100 having similar operation characteristics based on the grouping of the process data. By outputting information regarding such groups, the grouping device 150 enables the identification of common process data or groups of facilities 100 from the vast amount of process data from the plurality of facilities 100, and can optimize the control methods of the plurality of facilities 100 by promoting improvements such as analysis and modification of the control system, analysis and modification of control parameters, and introduction of new control devices.

[0098] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where the blocks may represent (1) stages of a process in which operations are performed or (2) sections of an apparatus having a role of performing operations. Specific stages and sections may be implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable medium. The dedicated circuits may include digital and / or analog hardware circuits, including integrated circuits (ICs) and / or discrete circuits. The programmable circuits may include reconfigurable hardware circuits including memory elements such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), etc.

[0099] A computer-readable medium may include any tangible device capable of storing instructions executable by an appropriate device, such that a computer-readable medium having instructions stored therein will comprise a product including instructions executable to create means for performing the operations specified in a flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy (registered trademark) disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (registered trademark) disc, memory stick, integrated circuit card, etc.

[0100] Computer-readable instructions may include source code or object code written in any combination of one or more programming languages, including assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or object-oriented programming languages such as Smalltalk®, JAVA®, C++, and conventional procedural programming languages such as the "C" programming language or similar programming languages.

[0101] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN), the Internet, etc. to a processor or programmable circuit of a programmable data processing apparatus such as a general-purpose computer, a special-purpose computer, or other computers, and may be executed to create means for performing the operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0102] FIG. 12 shows an example of a computer 2200 in which multiple aspects of the present invention may be embodied in whole or in part. Programs installed on the computer 2200 can cause the computer 2200 to function as operations associated with the apparatus according to embodiments of the present invention or as one or more sections of the apparatus, or to execute such operations or such one or more sections, and / or can cause the computer 2200 to execute a process according to embodiments of the present invention or a stage of such a process. Such programs may be executed by the CPU 2212 to cause the computer 2200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0103] The computer 2200 according to this embodiment includes a CPU 2212, a RAM 2214, a graphic controller 2216, and a display device 2218, which are mutually connected by a host controller 2210. The computer 2200 also includes an input / output unit such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0104] The CPU 2212 operates according to programs stored in the ROM 2230 and the RAM 2214, thereby controlling each unit. The graphic controller 2216 acquires image data generated by the CPU 2212 in a frame buffer provided in the RAM 2214 or the like or in itself, and causes the image data to be displayed on the display device 2218.

[0105] The communication interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads a program or data from the DVD-ROM 2201 and provides the program or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from an IC card and / or writes programs and data to the IC card.

[0106] The ROM 2230 stores therein a boot program or the like executed by the computer 2200 when activated, and / or a program that depends on the hardware of the computer 2200. The input / output chip 2240 may also be connected to the input / output controller 2220 via various input / output units such as a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0107] The program is provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from the computer-readable medium, installed in the hard disk drive 2224, the RAM 2214, or the ROM 2230, which are also examples of computer-readable media, and executed by the CPU 2212. The information processing described in these programs is read by the computer 2200, resulting in the cooperation between the programs and the various types of hardware resources described above. The device or method may be configured by realizing the operation or processing of information according to the use of the computer 2200.

[0108] For example, when communication is executed between the computer 2200 and an external device, the CPU 2212 may execute a communication program loaded in the RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 2212, the communication interface 2222 reads the transmission data stored in the transmission buffer processing area provided in a recording medium such as the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or the IC card, transmits the read transmission data to the network, or writes the received data received from the network to the reception buffer processing area provided on the recording medium, etc.

[0109] Further, the CPU 2212 may cause all or necessary portions of files or databases stored in external recording media such as a hard disk drive 2224, a DVD-ROM drive 2226 (DVD-ROM 2201), an IC card, etc. to be read into the RAM 2214, and execute various types of processing on the data on the RAM 2214. The CPU 2212 then writes back the processed data to the external recording media.

[0110] Various types of information such as various types of programs, data, tables, and databases may be stored in the recording media and may undergo information processing. The CPU 2212 may execute various types of processing on the data read from the RAM 2214, including various types of operations, information processing, condition judgment, conditional branch, unconditional branch, information search / replacement, etc. described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 2214. Also, the CPU 2212 may search for information in files, databases, etc. within the recording media. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording media, the CPU 2212 searches for an entry that matches the condition where the attribute value of the first attribute is specified from among the plurality of entries, reads the attribute value of the second attribute stored within the entry, and thereby may obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0111] The programs or software modules described above may be stored on a computer-readable medium on or near the computer 2200. Also, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable medium, thereby providing the program to the computer 2200 via the network.

[0112] As described above, the present invention has been described using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that forms with such changes or improvements can also be included in the technical scope of the present invention.

[0113] In the claims, the specification, and the drawings, for the operations, procedures, steps, stages, and other processes in the apparatuses, systems, programs, and methods shown, the execution order of each process, such as the operation order, procedure, step, and stage, is not explicitly stated as "earlier" or "preceding" etc., and it should be noted that it can be realized in any order as long as the output of the previous process is not used in the subsequent process. Regarding the operation flow in the claims, the specification, and the drawings, even if it is described for convenience using "first," "next," etc., it does not mean that it is essential to implement in this order.

Explanation of Reference Numerals

[0114] 10 Computing system 100 - 1 to N Facilities 110 - 1 to K Sensors 120 - 1 to L Devices 130 - 1 to M Control Devices 140 Network 150 Grouping Device 160 Group Processing Device 200 Process Data Receiving Unit 210 Process Data Storage Unit 220 Data Comparison Unit 240 Correlation Degree Calculation Unit 250 Grouping Unit 260 Group Storage Unit 270 Output Unit 1100 Computing system 1130 - 1 to M Collection Devices 1160 Display Device 2200 Computer 2201 DVD-ROM 2210 Host Controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Device 2220 Input / Output Controller 2222 Communication Interface 2224 Hard Disk Drive 2226 DVD-ROM Drive 2230 ROM 2240 Input / Output Chip 2242 Keyboard

Claims

1. A process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; A data comparison unit that compares the time-series data of the values of each parameter between each of the plurality of process data; A correlation degree calculation unit that calculates the correlation degree between each of the process data using the result of the comparison by the data comparison unit; A grouping unit that groups the plurality of process data using the correlation degree between each of the process data; An output unit that outputs at least one group obtained by grouping the plurality of process data and comprising: When a new group including new process data and at least a part of the process data in an existing group can be generated, the grouping unit generates a new group including the new process data and the at least a part of the process data in the existing group device.

2. A process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; A data comparison unit that compares the time-series data of the values of each parameter between each of the plurality of process data; A correlation degree calculation unit that calculates the correlation degree between each of the process data using the result of the comparison by the data comparison unit; A grouping unit that groups the plurality of process data using the correlation degree between each of the process data; An output unit that outputs at least one group obtained by grouping the plurality of process data and comprising: The grouping unit does not include process data whose correlation degree with any other process data among the plurality of process data is less than a predetermined lower limit value in any group, The output unit outputs information indicating process data of which corresponding process data among the plurality of facilities is not included in any group device.

3. A process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; A data comparison unit that compares the time-series data of the values of each parameter between each of the plurality of process data; A correlation degree calculation unit that calculates the correlation degree between each process data by using the result of comparison by the data comparison unit; A grouping unit that groups the plurality of process data by using the correlation degree between each process data; An output unit that outputs at least one group obtained by grouping the plurality of process data; Comprising; The output unit outputs a group of facilities in which the correlation degree between the normal process data of each facility is equal to or greater than a predetermined first threshold value and the correlation degree between the abnormal process data of each facility is equal to or greater than a predetermined second threshold value. Device.

4. A process data receiving unit that receives each of a plurality of process data including time series data of values of one or more parameters indicating the state of each of a plurality of facilities; A data comparison unit that compares the time series data of the values of each parameter between each of the plurality of process data; A correlation degree calculation unit that calculates the correlation degree between each process data by using the result of comparison by the data comparison unit; A grouping unit that groups the plurality of process data by using the correlation degree between each process data; An output unit that outputs at least one group obtained by grouping the plurality of process data; Comprising; The output unit outputs a group of facilities in which the correlation degree between the normal process data of each facility is equal to or greater than a predetermined first threshold value and the correlation degree between the abnormal process data of each facility is less than a predetermined second threshold value. Device.

5. The device according to any one of claims 1 to 4, wherein the grouping unit determines the level of the group according to which range among ranges where the minimum correlation degree among the correlation degrees between each process data in the group is 2 or more is included.

6. The device according to any one of claims 1 to 5, wherein the process data receiving unit receives at least one of normal process data that is process data when each facility is normal or abnormal process data that is process data when each facility is abnormal for each of the plurality of facilities.

7. The device according to claim 6, wherein the grouping unit separately groups at least one normal process data and at least one abnormal process data among the plurality of process data.

8. The grouping unit further uses metadata associated with each of the plurality of process data to group the plurality of process data, according to the apparatus of any one of claims 1 to 7.

9. Receiving each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; Comparing the time-series data of the values of each parameter among the respective pieces of process data of the plurality of process data; Calculating a degree of correlation between each pair of process data using the result of the comparison; Grouping the plurality of process data using the degree of correlation between each pair of process data; Outputting at least one group obtained by grouping the plurality of process data; including In the grouping, when a new group including new process data and at least some of the process data in an existing group can be generated, generating a new group including the new process data and the at least some of the process data in the existing group Method.

10. Receiving each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; Comparing the time-series data of the values of each parameter among the respective pieces of process data of the plurality of process data; Calculating a degree of correlation between each pair of process data using the result of the comparison; Grouping the plurality of process data using the degree of correlation between each pair of process data; Outputting at least one group obtained by grouping the plurality of process data; including In the grouping, not including in any group the process data for which the degree of correlation with any other process data among the plurality of process data is less than a predetermined lower limit value; In the output of the at least one group, outputting information indicating the process data of which the corresponding process data among the plurality of facilities is not included in any group; Method.

11. Receiving each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; comparing time-series data of the values of each parameter between each of the plurality of process data; calculating a correlation degree between each of the process data using the result of the comparison; grouping the plurality of process data using the correlation degree between each of the process data; outputting at least one group obtained by grouping the plurality of process data; comprising: in the output of the at least one group, outputting a group of facilities in which the correlation degree between normal process data of each facility is equal to or greater than a predetermined first threshold value and the correlation degree between abnormal process data of each facility is equal to or greater than a predetermined second threshold value; a method.

12. Receiving each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; comparing time-series data of the values of each parameter between each of the plurality of process data; calculating a correlation degree between each of the process data using the result of the comparison; grouping the plurality of process data using the correlation degree between each of the process data; outputting at least one group obtained by grouping the plurality of process data; comprising: in the output of the at least one group, outputting a group of facilities in which the correlation degree between normal process data of each facility is equal to or greater than a predetermined first threshold value and the correlation degree between abnormal process data of each facility is less than a predetermined second threshold value; a method.

13. executed by a computer, causing the computer to function as a process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; a data comparison unit that compares time-series data of the values of each parameter between each of the plurality of process data; a correlation degree calculation unit that calculates a correlation degree between each of the process data using the result of the comparison by the data comparison unit; a grouping unit that groups the plurality of process data using the correlation degree between each of the process data; and an output unit that outputs at least one group obtained by grouping the plurality of process data. ​ When a new group containing new process data and at least some of the process data within an existing group can be generated, the grouping unit generates a new group containing the new process data and the at least some of the process data within the existing group. Program. **Claim 14**: A program executed by a computer, causing the computer to function as a process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities, a data comparison unit that compares the time-series data of the values of each parameter between each pair of the plurality of process data, a correlation degree calculation unit that calculates the correlation degree between each pair of process data using the result of the comparison by the data comparison unit, a grouping unit that groups the plurality of process data using the correlation degree between each pair of process data, and an output unit that outputs at least one group obtained by grouping the plurality of process data. When functioning as such, the grouping unit does not include any process data whose correlation degree with any other process data among the plurality of process data is less than a predetermined lower limit value in any group. The output unit outputs information indicating process data for which the corresponding process data is not included in any group among the plurality of facilities. Program. **Claim 15**: A program executed by a computer, causing the computer to function as a process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities, a data comparison unit that compares the time-series data of the values of each parameter between each pair of the plurality of process data, a correlation degree calculation unit that calculates the correlation degree between each pair of process data using the result of the comparison by the data comparison unit, a grouping unit that groups the plurality of process data using the correlation degree between each pair of process data, and an output unit that outputs at least one group obtained by grouping the plurality of process data. When functioning as such, the output unit outputs a group of facilities in which the correlation degree between normal process data of each facility is equal to or greater than a predetermined first threshold value and the correlation degree between abnormal process data of each facility is equal to or greater than a predetermined second threshold value. Program.

16. Executed by a computer, causing the computer to a process data receiving unit that receives each of a plurality of process data including time-series data of values of one or more parameters indicating the state of each of a plurality of facilities; a data comparison unit that compares the time-series data of the values of each parameter between each of the plurality of process data; a correlation degree calculation unit that calculates the correlation degree between each of the process data using the result of the comparison by the data comparison unit; a grouping unit that groups the plurality of process data using the correlation degree between each of the process data; an output unit that outputs at least one group obtained by grouping the plurality of process data to function, wherein the output unit outputs a group of facilities in which the correlation degree between the normal process data of each facility is equal to or greater than a predetermined first threshold value and the correlation degree between the abnormal process data of each facility is less than a predetermined second threshold value Program.

Images