WO2024047694A1 - Operation assistance device, operation assistance system, and operation assistance method - Google Patents

Operation assistance device, operation assistance system, and operation assistance method Download PDF

Info

Publication number
WO2024047694A1
WO2024047694A1 PCT/JP2022/032388 JP2022032388W WO2024047694A1 WO 2024047694 A1 WO2024047694 A1 WO 2024047694A1 JP 2022032388 W JP2022032388 W JP 2022032388W WO 2024047694 A1 WO2024047694 A1 WO 2024047694A1
Authority
WO
WIPO (PCT)
Prior art keywords
series data
time series
unit
search
feature amount
Prior art date
Application number
PCT/JP2022/032388
Other languages
French (fr)
Japanese (ja)
Inventor
健 今井
洋平 上野
Original Assignee
三菱電機株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 三菱電機株式会社 filed Critical 三菱電機株式会社
Priority to JP2022581011A priority Critical patent/JPWO2024047694A1/ja
Priority to PCT/JP2022/032388 priority patent/WO2024047694A1/en
Publication of WO2024047694A1 publication Critical patent/WO2024047694A1/en

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00Testing or monitoring of control systems or parts thereof
    • G05B23/02Electric testing or monitoring

Definitions

  • the present disclosure relates to an operation support device, an operation support system, and an operation support method that present operation information regarding the operation of plants such as water supply and sewage, electric power, chemical, steel, railway, and building air conditioning plants.
  • the information not collected by the monitoring and control device includes, for example, expected seasonal and weather changes, events outside the plant that affect the plant, and plant maintenance information.
  • the driving support information is selected and generated by an algorithm based on the quantized value of the measured values collected by the supervisory control device, and is presented to the operator.
  • appropriate operation support information was not presented when plant control decisions should be made using information that was not available.
  • Another possible method is to input information that is not collected by the monitoring and control equipment but is used to make plant control decisions all at once into the time-series data recording unit, but it is possible that time has passed since the monitoring and control work was performed. Even if the operator attempts to input information necessary for making plant control decisions after the system has been used, there is a problem in that the operator's memory becomes vague and the correct information is not input.
  • the present disclosure has been made to solve such problems, and aims to provide a driving support device, a driving support system, and a driving support method that can present appropriate driving support information. do.
  • an operation support device includes a time-series data recording unit that records supervisory control data collected from the plant as time-series data by a supervisory control device that monitors the plant, and a time-series data recording unit that records supervisory control data collected from the plant as time-series data.
  • a feature calculation logic recording unit that records feature calculation logic for calculating feature quantities, and a feature that calculates feature quantities from time-series data based on the feature calculation logic recorded in the feature calculation logic recording unit.
  • a quantity calculation unit a time-series data recording unit that records time-series data and calculated feature quantities, which are the feature quantities computed by the feature quantity calculation unit, in association with each other, and a search unit that divides the time series data recorded in the feature-added time series data recording unit based on the feature value, and searches the divided time series data for time series data that has the highest degree of matching with the search condition;
  • An operation support information creation unit that creates operation support information to support plant operation based on the time series data searched by the user and the calculated feature values associated with the time series data;
  • the driving support information creation unit includes a feature value adding unit that records additional feature values, which are additional feature values input by the operator, in a feature value added time series data recording unit in association with time series data.
  • Driving support information is created based on the time series data searched by the section, and the calculated feature amount and additional feature amount associated with the time series data.
  • FIG. 1 is a block diagram showing an example of a configuration of a driving support device according to a first embodiment
  • FIG. 1 is a block diagram showing an example of a configuration of a driving support device according to a first embodiment
  • FIG. 3 is a flowchart illustrating an example of the operation of the driving support device according to the first embodiment
  • 5 is a flowchart illustrating an example of the operation of the driving support device according to the first embodiment.
  • FIG. 2 is a schematic diagram of a feature amount calculation logic recording unit according to the first embodiment.
  • FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment.
  • FIG. 3 is a diagram for explaining an operation of searching for driving support information according to the first embodiment.
  • FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment.
  • FIG. 3 is a diagram for explaining the operation of the feature value adding section according to the first embodiment.
  • FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment.
  • FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment.
  • FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment.
  • FIG. 2 is a block diagram showing an example of the configuration of a driving support device according to a second embodiment.
  • 7 is a flowchart illustrating an example of the operation of the driving support device according to the second embodiment.
  • FIG. 7 is a flowchart illustrating an example of the operation of the driving support device according to the second embodiment.
  • FIG. 3 is a schematic diagram of a search logic recording unit according to a second embodiment.
  • FIG. 7 is a schematic diagram of a schedule stored in a scheduling unit according to the second embodiment.
  • FIG. 3 is a block diagram illustrating an example of the configuration of a driving support device according to a third embodiment.
  • 7 is a flowchart illustrating an example of the operation of the driving support device according to Embodiment 3.
  • 12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 3.
  • FIG. 12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 3.
  • FIG. 12 is a diagram for explaining an operation of adding a simulation and its evaluation to a time-series data recording unit to which feature amounts and evaluation values have been assigned according to the third embodiment;
  • FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a fourth embodiment.
  • FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a fifth embodiment.
  • 12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 5.
  • FIG. FIG. 7 is a schematic diagram of a time-series data recording unit according to Embodiment 5.
  • FIG. FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a sixth embodiment.
  • FIG. 12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 6.
  • FIG. FIG. 7 is a schematic diagram of a search time series group ID recording unit according to Embodiment 6;
  • FIG. 12 is a schematic diagram of a frequency probability recording unit according to Embodiment 6;
  • 12 is a flowchart illustrating an example of the operation of the driving support device according to the sixth embodiment.
  • 12 is a flowchart illustrating an example of the operation of the driving support device according to the sixth embodiment.
  • 12 is a flowchart illustrating an example of the operation of the driving support device according to the sixth embodiment.
  • FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a seventh embodiment.
  • FIG. 1 is a block diagram showing an example of a hardware configuration of a driving support device according to Embodiments 1 to 7.
  • FIG. 1 is a block diagram showing an example of a hardware configuration of a driving support device according to Embodiments 1 to 7.
  • FIG. 1 is a block diagram showing an example of a configuration of a driving support system according to Embodiments 1 to 7.
  • FIG. 1 is a block diagram showing an example of a hardware configuration of a driving support device according to Embodiments 1 to 7.
  • FIG. 1 is a block diagram showing an example of the configuration of a driving support device according to the first embodiment.
  • the driving support device shown in FIG. 1 shows the minimum necessary configuration of the driving support device according to the present disclosure.
  • FIG. 2 is a block diagram showing an example of the configuration of a driving support device according to another configuration including the driving support device shown in FIG. 1.
  • the driving support device shown in FIG. It includes a data recording section 201, a feature amount calculation logic recording section 202, and a feature amount added time series data recording section 203.
  • the present disclosure is characterized in that the driving support device includes a feature amount adding unit 104.
  • the supervisory control device 105 collects supervisory control data including measurement information output from measuring instruments installed in the plant and control input information input by an operator, and converts the collected supervisory control data into time series data. It is recorded in the recording unit 201. Additionally, the supervisory control device 105 transmits control input information input by the operator to each piece of equipment making up the plant.
  • the feature amount calculation logic recording unit 202 records feature amount calculation logic for calculating feature amounts from the time series data recorded in the time series data recording unit 201.
  • the feature quantity calculation unit 101 calculates feature quantities from the time series data recorded in the time series data recording unit 201 based on the feature quantity calculation logic recorded in the feature quantity calculation logic recording unit 202.
  • the feature value added time series data recording unit 203 stores the time series data recorded in the time series data recording unit 201, the feature values calculated by the feature value calculation unit 101, and the features input from the feature value adding unit 104. Record it in association with the amount.
  • the search unit 102 classifies the time-series data recorded in the feature-added time-series data recording unit 203 based on search conditions input by the operator via the input/output device 106. Then, the search unit 102 identifies time-series data that highly matches the search condition from among the divided time-series data.
  • the time series data (search results) specified by the search unit 102 may be recorded in a recording unit (not shown).
  • the driving support information creation unit 103 creates driving support information based on the search results of the search unit 102. Specifically, the driving support information creation unit 103 creates driving support information based on the time series data searched by the search unit 102 and the calculated feature amount and additional feature amount associated with the time series data. .
  • the input/output device 106 displays the driving support information created by the driving support information creation unit 103.
  • the input/output device 106 also receives input of search conditions or additional input of feature amounts by the operator.
  • the feature value adding unit 104 records information on the feature values input by the operator in the feature value added time series data recording unit 203.
  • FIG. 3 is a flowchart showing the operation of the driving support device from acquiring supervisory control data to displaying driving support information.
  • step S11 the supervisory control device 105 records the collected supervisory control data in the time-series data recording unit 201 as time-series data.
  • step S12 the feature quantity calculation unit 101 calculates the feature quantity from the time series data recorded in the time series data recording unit 201 according to the feature quantity calculation logic recorded in the feature quantity calculation logic recording unit 202. Record feature values in association with time series data.
  • step S13 the input/output device 106 receives search conditions input by the operator.
  • step S14 the search unit 102 searches the data recorded in the feature amount added time series data recording unit 203 according to the search conditions input by the operator.
  • step S15 the driving support information creation unit 103 creates driving support information based on the search results of the search unit 102.
  • the input/output device 106 then displays the driving support information created by the driving support information creation unit 103.
  • FIG. 4 is a flowchart showing the operation of recording feature quantities additionally inputted by the operator in the feature quantity assigned time series data recording unit 203.
  • step S21 the input/output device 106 displays driving support information.
  • step S22 the input/output device 106 receives the time series name and each time value of the time series data input by the operator.
  • step S23 the feature amount adding unit 104 adds an additional feature amount to the time series data based on the information input by the operator, and records it in the feature amount added time series data recording unit 203.
  • FIG. 5 is a schematic diagram of the feature amount calculation logic recording unit 202.
  • the feature amount calculation logic recording unit 202 includes a feature amount time series name 301, a feature amount time series unit 302, a feature amount type 303 used for calculation, an original time series 304, an original time series unit 305, and a feature amount type 306. , and a calculation formula 307.
  • feature amount 1 is to perform “integration (10 hours)” processing recorded as the feature amount type 303 used for calculation on "measurement value 1" recorded as the original time series 304. It is calculated by Specifically, “integral (10 hours)” is specified as a key from the feature quantity type 306, and “integral (10 hours)” is calculated using the formula corresponding to "integral (10 hours)” in the calculation formula 307. Process. In the arithmetic processing, the unit 305 of the original time series and the unit 302 of the feature amount time series are used, and unit conversion processing is performed as necessary.
  • FIG. 6 is a diagram showing an example of the screen of the input/output device 106 when searching for driving support information.
  • the screen for searching driving support information includes a search condition input 400, a search result list 410, a time series data selection 420, a trend graph 430, a search button 440, and an add feature button 450.
  • search condition input 400 the operator inputs search conditions 405, 406, 407 as time series name 401, and specifies search type 402, target time 403, and condition 404 for each input search condition 405, 406, 407. .
  • the search condition 405 "time zone" is required to be input, and the condition 404 is the start time and end time.
  • the start time can be input in the range 0:00 to 23:59, and the end time can be input any time after the start time.
  • the end time exceeds 24:00, it means the next day or later, the quotient when divided by 24:00 represents the number of elapsed days, and the remainder when divided by 24:00 represents the time.
  • Time series names other than time zones 401 include period, year, month, day, year/month, month/day, day of the week, weekday or holiday, measured value time series, and feature amount time. There are several series, and the operator selects an arbitrary search condition from these.
  • a search result list 410 that simultaneously satisfies each search condition input by the operator is output.
  • search condition 405 “time zone” is selected as the time series name 401, and “14:00 to 23:59” is selected as the condition 404.
  • search condition 406 “feature amount 1" is selected as the time series name 401, "numeric exact match” is selected as the search type 402, "23:59” is selected as the target time 403, and "40000 ⁇ ” is selected as the condition 404. .
  • search condition 407 "measured value 2" is selected as the time series name 401, "numerical similarity” is selected as the search type 402, "14:00” is selected as the target time 403, and "3.5” is selected as the condition 404.
  • search button 440 When the search button 440 is pressed with the search conditions 405, 406, 407 entered in this way, the search unit 102 searches the data that simultaneously satisfies the search conditions 405, 406, 407 in the time series data recording unit with added features. Search from 203.
  • search results are output in a ranking format in descending order of degree of match with the input search condition.
  • search types 402 "character string complete match”, “character string partial match”, “character string beginning match”, and “character string trailing match” can be selected.
  • Indices used when calculating the degree of match with the condition 404 at the target time 403 of a single or multiple time series for which "numerical similarity" is selected as the search type 402 include cosine similarity, Pearson's correlation coefficient, Deviation pattern similarity, Euclidean distance, scaled Euclidean distance, Manhattan distance, Minkowski distance, Chebyshev distance, and Mahalanobis distance can be used.
  • similarity and correlation coefficient are used as indicators, data with high similarity and correlation coefficient is determined to be data with high matching.
  • distance is used as an index
  • data with a close distance is determined to be data with a high degree of matching.
  • summary information is displayed in the form of a ranking 412 in descending order of the degree of match with the search conditions 405, 406, and 407.
  • the summary information includes information regarding the date and time and the time series name input as the search condition.
  • search condition if a search is related to a time series name in which a target time is entered, the value of the target time is displayed, if a search is related to a day of the week, the day of the week is displayed, if a search is related to a weekday or holiday, the matching string is displayed. .
  • the search result 413 displays the date and time of the search result
  • the search result 414 displays the value of "feature value 1 at 23:59”
  • the search result 415 displays "measurement value 2 at 14:00”.
  • the value of is displayed.
  • the trend graph 430 displays time series data selected from the time series data selection 420 in the period selected from the selection 411 of the search result list 410.
  • FIG. 7 is a diagram for explaining an operation in which the search unit 102 searches for driving support information, and is a schematic diagram of the time-series data recording unit 203 with added features.
  • search operation when the operator inputs search conditions 405, 406, and 407 shown in FIG. 6 will be described.
  • the search condition 406 "Feature 1" is selected as the time series name 401, "Numeric exact match” is selected as the search type 402, "23:59” is selected as the target time 403, and "40000 ⁇ ” is selected as the condition 404. Therefore, among the divided time series data, the data “40000 ⁇ ” at “23:59” of "feature amount 1” remains as a search result candidate. For example, the values of "feature quantity 1" of "23:59” in the time series data of sections 501 and 02 are "42400” and "58734", respectively, and satisfy the condition 404 "40000 ⁇ ", so the search is performed. It remains as a candidate for the result.
  • FIG. 8 is a diagram showing an example of a screen displayed on the input/output device 106 when an operator adds feature amounts to time series data.
  • a selection window 451 for selecting a feature quantity addition method is displayed.
  • a period selection bar 431 is displayed on the trend graph 430, and a period can be selected.
  • the feature name 432 and its value 433 to be given to the selected period can be input.
  • “2020/8/11 16:00 to 20:00” is input as the selection period
  • “event 1” is input as the feature name 432
  • “type A” is input as the value 433.
  • FIG. 9 is a diagram for explaining the operation in which the feature value adding unit 104 records the feature value in the feature value added time series data recording unit 203 when the operator performs an operation to add a feature value to time series data.
  • FIG. 2 is a schematic diagram of a time-series data recording unit 203 with feature amounts added.
  • the operator inputs "2020/8/11 16:00-20:00" as the selection period, "Event 1" as the feature name 432, and "Type A” as the value 433. If “Event 1" is not registered in the time-series data recording unit 203 with features added, "Event 1" is additionally registered in the last column 530 of the time-series data recording unit 203 with features added. be done. Then, "Type A” is registered in the cell corresponding to "2020/8/11 16:00-20:00" in the "Event 1" column. In addition, if “Event 1" is already registered, “Type A” should be additionally registered in the cell corresponding to "2020/8/11 16:00-20:00", or another value is already registered. If so, you can overwrite it and register it.
  • FIG. 10 is a diagram showing an example of a screen displayed on the input/output device 106 when performing a search using feature amounts assigned by an operator as search conditions.
  • Event 1 is registered as the time series name and "Type A” is registered as the value in the feature amount assigned time series data recording unit 203. Therefore, in the search condition 408 in FIG. 10, the time series name is It is possible to select "Event 1", "Character string complete match” as the search type, and "Type A” as the condition.
  • search condition 408 in addition to search conditions 405, 406, and 407, the data for “2020/8/11 16:00 to 23:59” that simultaneously satisfies search conditions 405, 406, 407, and 408 will be searched. Displayed in the results list.
  • FIG. 11 is a diagram showing an example of a screen displayed on the input/output device 106 when "search results" is selected as the feature amount addition method.
  • the time series name and value can be specified in the search result list.
  • the selection period is the date and time corresponding to the cell in which the value was input.
  • the operation in which the feature value adding unit 104 records the feature value in the feature value added time series data recording unit 203 is the same as the operation in which the feature value is recorded when “trend” is selected from the selection window 451 in the example of FIG. It is.
  • FIG. 12 is a diagram showing an example of a screen displayed on the input/output device 106 when "calendar" is selected as the feature amount addition method.
  • a calendar 460 is displayed.
  • the period unit selection button 461 can switch the unit of the display period of the calendar 460 to week, month, or year.
  • the ⁇ button 462 can return the display period of the calendar 460.
  • > button 463 can advance the display period of calendar 460.
  • Today button 464 can change the display period so that today's date is displayed.
  • the period selection bar 465 allows you to select any period.
  • a feature name 466 and a value 467 to be given to the selected period can be input.
  • "2020/7/28 0:00 to 2020/8/24 0:00" is selected as the selection period
  • "Event 3” is set as the feature name 466
  • "Type X” is set as the value 467. It has been entered.
  • the driving support device includes a feature amount adding section 104.
  • the feature value adding unit 104 records the feature values input by the operator in the feature value added time series data recording unit 203 in association with time series data. This makes it possible to present the operator with appropriate operation support information that takes into account "information that is not collected by the supervisory control device 105 but is necessary for making plant control decisions.”
  • Embodiment 2 In the first embodiment, a method has been described in which the operator inputs information not collected by the monitoring and control device while referring to the driving support information, and immediately searches for and displays appropriate driving support information. In the method described in Embodiment 1, new driving support information is displayed only when the operator inputs search conditions, but new driving support information is not displayed when the operator does not input search conditions. Embodiment 2 was created to solve this problem, and details thereof will be explained below.
  • FIG. 13 is a block diagram showing an example of the configuration of a driving support device according to the second embodiment.
  • the driving support device further includes a scheduling unit 107, an updating unit 108, and a search logic recording unit 204 in addition to the driving support device according to the first embodiment (see FIG. 2). It is characterized by being prepared.
  • the scheduling unit 107 specifies a schedule for the search unit 102 to perform the search.
  • the schedule is recorded in the scheduling section 107.
  • the search logic recording unit 204 records search logic for the search unit 102 to search.
  • the updating unit 108 updates the feature calculation logic recorded in the feature calculation logic recording unit 202, the schedule specified by the scheduling unit 107, and the search logic recording unit 204 according to instructions input by the operator via the input/output device 106. Update the search logic recorded in .
  • FIGS. 14 and 15 are flowcharts showing operations from when the driving support device acquires monitoring control data until displaying driving support information. Note that steps S31, S32, and S34 in FIG. 14 are the same processes as steps S11, S12, and S15 in FIG. 3, so the description thereof will be omitted here. Below, steps S33 and S35 in FIG. 14 and step S36 in FIG. 15 will be explained.
  • step S33 the search unit 102 searches the data in the feature-added time series data recording unit 203 according to the schedule specified by the scheduling unit 107 and according to the search logic recorded in the search logic recording unit 204.
  • step S35 the input/output device 106 determines whether the operator has determined that the information intended by the operator has been displayed on the input/output device 106 at the timing intended by the operator. If it is determined that the information intended by the operator has been displayed at the timing intended, the operation in FIG. 14 ends. On the other hand, if it is determined that the information intended by the operator is not displayed at the timing intended, the process moves to step S36 in FIG. 15.
  • step S36 the operator uses the input/output device to update the feature calculation logic, schedule, and search logic so that the information intended by the operator is displayed at the timing the operator intends, and performs feature calculation on each of them. It is recorded in the logic recording section, scheduling section, and search logic recording section.
  • FIG. 16 is a schematic diagram of the search logic recording unit 204.
  • the search logic recording unit 204 includes a search logic ID 600 and search conditions 610.
  • the search conditions 610 include, for example, “search conditions 1 to 5”.
  • “Search condition 1” includes a time series name 611, a search type 612, a target time 613, a first condition 614, and a second condition 615.
  • “Search condition 2” includes a time series name 616, a search type 617, a target time 618, a first condition 619, and a second condition 620.
  • the time series name 611 is "time zone”
  • the first condition 614 is “same time as search”
  • the second condition 615 is "10 hours of search”.
  • “later time” is specified.
  • “Same time as search” is the time when “SL1” with search logic ID 600 was executed according to the schedule by the scheduling unit 107. For example, if it was executed at 5:00 on January 6, 2021, 5:00 is specified. be done. The "time 10 hours after the search” is specified as 15:00, which is the time 10 hours after 5:00.
  • the time series name 616 is "Feature amount 1”
  • the search type 617 is "Numeric exact match”
  • the target time 618 is "Time 10 hours after the search”
  • the first condition 619 is " 40000" is specified.
  • the second condition 620 is not specified. Note that when “numerical complete match” is specified as the search type, the lower limit value is specified as the first condition, and the upper limit value is specified as the second condition. In “SL1" of the search logic ID 600, "40000” is specified as the lower limit value in the first condition 619, so a value of "40000 ⁇ " is selected as the search result.
  • FIG. 17 is a schematic diagram of the schedule stored in the scheduling section 107.
  • the schedule includes a search logic ID 701, a start date and time 702, an end date and time 703, and a cycle 704.
  • the search logic ID 701 "SL1" has a regular cycle from the start date and time 702 of "2021/1/1 0:00" to the period 704 of "60 minutes", and the end date and time 703 of "2030/12/ 31 23:59" is repeatedly executed.
  • the update unit 108 updates the schedule, feature calculation logic, and search logic according to operator operations input via the input/output device 106.
  • the schedule recorded in the scheduling unit 107 is updated.
  • the feature amount calculation logic recorded in the feature amount calculation logic recording unit 202 is updated.
  • the search logic recorded in the search logic recording unit 204 is updated.
  • the driving support device includes a scheduling section 107 and a search logic recording section 204.
  • the search unit 102 searches the data in the feature value added time series data recording unit 203 according to the schedule recorded in the scheduling unit 107 and the search logic recorded in the search logic recording unit 204 . Thereby, new driving support information can be automatically presented to the operator.
  • the driving support device includes an update unit 108.
  • the update unit 108 updates the schedule, feature calculation logic, and search logic according to operator operations input via the input/output device 106. Thereby, the driving support information intended by the operator can be presented at the timing intended by the operator.
  • Embodiment 3 In the first embodiment, a method has been described in which the operator inputs information not collected by the monitoring and control device while referring to the driving support information, and immediately searches for and displays appropriate driving support information.
  • the past plant operation history collected by the supervisory control device is displayed as a search result, but an operation method that is not included in the past plant operation history is not displayed as a search result.
  • Embodiment 3 has been developed to solve this problem, and the details thereof will be explained below.
  • FIG. 18 is a block diagram showing an example of the configuration of a driving support device according to the third embodiment.
  • the driving support device has a time series data editing unit 109, a simulation execution unit 110, and an evaluation value calculation unit, in contrast to the driving support device according to the first embodiment (see FIG. 2). 111 , and a feature amount and evaluation value added time series data recording unit 205 in place of the feature value added time series data recording unit 203 .
  • the time series data editing unit 109 edits time series data according to instructions input by the operator via the input/output device 106.
  • the simulation execution unit 110 simulates the behavior of the plant based on the time series data edited by the time series data editing unit 109.
  • the evaluation value calculation unit 111 evaluates the behavior of the plant simulated by the simulation execution unit 110.
  • the feature quantity and evaluation value added time series data recording unit 205 records the simulation results by the simulation execution unit 110 and the evaluation results by the evaluation value calculation unit 111 in association with each other.
  • FIG. 19 is a flowchart showing the operation of the driving support device from editing time series data to evaluating and recording simulation results.
  • step S41 the driving support information creation unit 103 creates driving support information based on the data recorded in the feature amount and evaluation value added time series data recording unit 205.
  • the input/output device 106 then displays driving support information.
  • step S42 the operator uses the input/output device 106 to edit the time-series data related to past plant operations displayed on the input/output device 106 and some values of the time-series data generated by the simulation execution unit 110. do.
  • step S43 the simulation execution unit 110 executes a simulation based on the time series data edited by the time series data editing unit 109.
  • step S44 the evaluation value calculation unit 111 evaluates the simulation results.
  • step S45 the evaluated simulation results are recorded in the feature amount and evaluation value added time series data recording unit 205, and added to the search target in the subsequent search process.
  • FIG. 20 is a diagram showing an example of a screen displayed on the input/output device 106 when the time-series data editing unit 109 edits time-series data according to instructions input by the operator via the input/output device 106. .
  • the simulation input creation button 801 After pressing the simulation input creation button 801, the operator selects the value of the time series data to be edited in the trend graph 802. For example, time series data 803 of "measurement value 1" is selected, and simulation time series data 804 of "measurement value 1" is created by GUI (Graphical User Interface) operation. Then, when the simulation execution button 805 is pressed, the simulation execution unit 110 executes the simulation.
  • GUI Graphic User Interface
  • the simulation execution unit 110 executes the simulation using the edited time series data when the measurement value has been edited, and using the time series data of the measurement value before editing when the measurement value has not been edited.
  • FIG. 21 is a diagram showing an example of displaying the simulation execution result by the simulation execution unit 110 and the evaluation value calculated by the evaluation value calculation unit 111 on the screen of the input/output device 106.
  • the evaluation result list 900 is composed of selections 901, dates and times 902, scenarios 903, and evaluation values 904.
  • the trend graph 910 displays measured values and simulation results for each scenario 903.
  • the operator checks the trend graph 910 and the evaluation values, and selects a scenario to be added to the search target using the selection 901.
  • a scenario which is the scenario 903 is selected, and when the Add to Search Objects button 905 is pressed, "Simulation 1" is added to the search objects.
  • FIG. 22 is a schematic diagram of the time-series data recording unit 205 with feature amounts and evaluation values added.
  • the measured value is recorded in the column of measurement value 1001
  • the evaluation value of the measurement value is recorded in the column of evaluation value 1002
  • the measurement value of "Simulation 1" is recorded in the column of simulation measurement value 1003
  • the evaluation value of the measurement value is recorded in the column of simulation measurement value 1003.
  • the evaluation values of the measured values are recorded in the column of simulation evaluation values 1004. If the number of simulation scenarios increases, they will be added to the last column.
  • the respective evaluation values for the measured values and simulation measured values are recorded at the final time of the period in which the simulation and evaluation are performed.
  • the evaluation value of the measurement value is recorded in cell 1005.
  • the evaluation value of the measurement value of "Simulation 1" is recorded in the cell 1006.
  • the driving support device includes a time series data editing section 109, a simulation execution section 110, an evaluation value calculation section 111, and a time series data recording section 205 with feature amounts and evaluation values added.
  • the time series data editing unit 109 edits time series data according to instructions input by the operator via the input/output device 106.
  • the simulation execution unit 110 executes a simulation based on the time series data edited by the time series data editing unit 109.
  • the evaluation value calculation unit 111 evaluates the results of the simulation executed by the simulation execution unit 110.
  • the feature quantity and evaluation value added time series data recording unit 205 records the simulation results by the simulation execution unit 110 and the evaluation results by the evaluation value calculation unit 111 in association with each other. Thereby, an operating method that is not found in the past operation history of the plant can be displayed as a search result.
  • Embodiment 4 In the second embodiment, a method has been described in which new driving support information is automatically displayed by executing the search logic recorded in the search logic recording unit according to the schedule recorded in the scheduling unit.
  • the past plant operation history collected by the supervisory control device is displayed as a search result, but the operation method that is not included in the past plant operation history is not displayed as a search result.
  • Embodiment 4 is designed to solve this problem.
  • FIG. 23 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 4.
  • the driving support device has a time series data editing unit 109, a simulation execution unit 110, and an evaluation value calculation unit, in contrast to the driving support device according to the second embodiment (see FIG. 13). 111 , and a feature amount and evaluation value added time series data recording unit 205 in place of the feature value added time series data recording unit 203 . That is, the configuration and operation of the driving support device according to Embodiment 4 is a combination of the driving support device according to Embodiment 2 (see FIG. 13) and the driving support device according to Embodiment 3 (see FIG. 18). be.
  • new operation support information is automatically presented to the operator, the operation support information intended by the operator is presented at the timing the operator intends, and an operation method not found in the past operation history of the plant is searched. It can be displayed as a result.
  • Embodiment 5 In the first embodiment, a method has been described in which the operator inputs information not collected by the monitoring and control device while referring to the driving support information, and immediately searches for and displays appropriate driving support information.
  • the method described in Embodiment 1 although it is possible to narrow down and display the period of data recorded as a search result, there is a problem in that it is not possible to narrow down and display the time series name.
  • Embodiment 5 is designed to solve this problem.
  • FIG. 24 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 5.
  • the driving support device according to the fifth embodiment is different from the driving support device according to the first embodiment (see FIG. 2) in that it further includes a time-series data group recording unit 206.
  • the time series data group recording unit 206 records time series data for each group.
  • FIG. 25 is a diagram showing an example of a screen displayed on the input/output device 106.
  • the time series data selection 1100 is provided with a time series data group selection 1101.
  • time series data 1102 forming the selected group is displayed.
  • FIG. 26 is a schematic diagram of the time-series data group recording unit 206.
  • the time series data group recording unit 206 records, for each group ID 1201, the time series names 1202 that constitute the group.
  • the driving support device includes a time-series data group recording section 206. Thereby, it is possible to narrow down and display the number of time series data forming the driving support information.
  • Embodiment 5 describes a method in which an operator inputs information not collected by the monitoring and control device while referring to driving support information, and immediately searches for and displays appropriate driving support information by specifying the period and time series name. We explained how to filter and display results.
  • the method described in Embodiment 5 has the problem that it is time-consuming because it is necessary to define groups of time-series data in advance and record them in the time-series data group recording unit 206.
  • Embodiment 6 is designed to solve this problem.
  • FIG. 27 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 6.
  • the driving support device has a search time series group ID recording unit 207, a frequency probability recording unit 208, and It further includes a time series data group estimation section 112.
  • FIG. 28 is a diagram showing an example of a screen displayed on the input/output device 106.
  • a search condition 1321 that is a combination of arbitrary measurement values and feature amounts is input in the search condition input 1320 and a search is performed
  • a time series data combination 1301 to be displayed on the trend graph 1310 is selected in the time series data selection 1300.
  • FIG. 29 is a schematic diagram of the search time series group ID recording unit 207.
  • the search time series group ID recording unit 207 includes a search time series group ID 1401 and a search time series 1402.
  • search time series 1402 a combination (search condition 1321) of a measurement value and a feature quantity input as a time series name in the search condition input 1320 of FIG. 28 is recorded.
  • a unique ID is assigned to the search time series group ID 1401 each time a new combination of time series names is input as the search condition 1321 when the search button 1322 in FIG. 28 is pressed to execute a search. Ru.
  • FIG. 30 is a schematic diagram of the frequency probability recording unit 208.
  • the frequency probability recording unit 208 has a table of display frequencies and display probabilities for each search time series group ID.
  • the example in FIG. 30 shows a table with the search time series group ID "ST1".
  • the table shown in FIG. 30 is a table that has time series names recorded in the feature value added time series data recording unit 203 as items in each row and column.
  • the number of times “measurement value 1” was selected for display when “measurement value 2” was selected for display 1501 and a conditional probability 1502 that "measurement value 1" is selected for display when "measurement value 2" is selected for display are recorded.
  • the number of times 1501 is obtained from “f (measured value 1
  • the conditional probability 1502 is obtained from “p (measured value 1
  • the time series data group estimating unit 112 refers to the search time series 1402 in the search time series group ID recording unit 207 and searches for a matching search time series group ID 1401 every time a search condition is input and a search is executed. . If there is no matching search time series group ID, the search time series group associated with the search condition will not be selected because this is the first input. On the other hand, if there is a matching search time series group ID, refer to the cell in which the display probability conditional on each time series data of the set of search time series 1402 is recorded, and check the conditional probability that the display probability exceeds the predetermined threshold. A set of time-series data recorded in a cell with a time-series data group is recorded in the time-series data group ID recording unit 206 as a time-series data group.
  • ⁇ Operation> 31 and 32 are flowcharts showing operations from inputting a search condition to estimating a time series data group and displaying it on the input/output device 106.
  • step S51 the input/output device 106 receives search conditions input by the operator.
  • step S52 it is determined whether the set of search time series input as the search condition exists in the search time series group ID recording unit 207. If the set of search time series exists in the search time series group ID recording unit 207, the process moves to step S53. On the other hand, if the set of search time series does not exist in the search time series group ID recording unit 207, the process moves to step S55.
  • step S53 the time series data group estimating unit 112 records the display probability conditional on each time series of the set of search time series from the table of the search time series ID recorded in the frequency probability recording unit 208.
  • a set of time series recorded in cells having a conditional probability exceeding a predetermined threshold is recorded as a time series data group in the time series data group recording unit 206.
  • step S54 the input/output device displays the time series data as a time series data group when the operator searches.
  • step S55 the search time series group ID recording unit 207 assigns a new number to the search time series ID and registers the set of search time series input as the search condition.
  • step S56 the time series data group estimation unit 112 does not estimate the time series data group.
  • FIG. 33 is a flowchart showing the operation of updating the frequency probability recording unit 208 when the operator operates the input/output device 106.
  • step S61 the input/output device 106 receives search conditions input by the operator.
  • step S62 the input/output device 106 displays the search results.
  • step S63 the frequency probability recording unit 208 sets each time series data as a condition for each time series data that has already been selected for display at the timing when the time series data to be displayed in the time series data selection is added, Updates the count of the number of display selections for which the newly selected time series is the result.
  • step S64 the frequency probability recording unit 208 updates the probability that time series j will be displayed when time series i is selected for display, according to calculation formula p.
  • the calculation formula p is expressed by the following formula (1).
  • the driving support device includes a search time series group ID recording section 207, a frequency probability recording section 208, and a time series data group estimating section 112.
  • the time-series data group estimating unit 112 estimates a time-series data group based on the operator's operation history on the input/output device 106. This makes it possible to narrow down and display the number of time-series data that constitutes driving support information, without having to define time-series data groups in advance.
  • the operator inputs information not collected by the monitoring and control device while referring to the driving support information, immediately searches for and displays appropriate driving support information, and records the operator's operation history for the input/output device.
  • new driving support information is displayed only when the operator inputs search conditions, but new driving support information is not displayed when the operator does not input search conditions.
  • Embodiment 7 is designed to solve this problem.
  • FIG. 34 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 7.
  • the driving support device according to the seventh embodiment has a scheduling section 107, an updating section 108, and a search logic recording section 204 in addition to the driving support device according to the sixth embodiment (see FIG. 27).
  • the configuration and operation of the driving support device according to Embodiment 7 is a combination of the driving support device according to Embodiment 6 (see FIG. 27) and the driving support device according to Embodiment 2 (see FIG. 13). be.
  • new driving support information is automatically presented to the operator, driving support information intended by the operator is presented at the timing intended by the operator, and time-series data groups are not defined in advance. It is also possible to narrow down and display the number of time series data that make up the driving support information.
  • Each of the functions of the feature calculation unit 101, the search unit 102, the driving support information creation unit 103, and the feature addition unit 104 in the driving support device described in the first embodiment is realized by a processing circuit. That is, the driving support device calculates feature amounts from the time series data recorded in the time series data recording unit 201, searches the time series data based on search conditions input by the operator, and performs driving support based on the search results. It is provided with a processing circuit for creating information and recording information on feature quantities input by an operator in the feature quantity added time series data recording unit 203.
  • the processing circuit may be dedicated hardware, and may be a processor (CPU, central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, DSP (Digital Signal Processor)) that executes a program stored in memory. ).
  • the processing circuit 1600 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, or an ASIC (Application Specific Integrated Circuit). , FPGA (Field Programmable Gate Array), or a combination of these.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • Each of the functions of the feature calculation unit 101, the search unit 102, the driving support information creation unit 103, and the feature addition unit 104 may be realized by the processing circuit 1600, or each function may be realized by a single processing circuit 1600. You may.
  • each function of the feature calculation section 101, the search section 102, the driving support information creation section 103, and the feature amount adding section 104 can be implemented using software, firmware, or software and firmware. This is realized by a combination of Software or firmware is written as a program and stored in memory 1620.
  • Processor 1610 implements each function by reading and executing programs recorded in memory 1620. That is, the driving support device performs the following steps: calculating a feature amount from the time series data recorded in the time series data recording unit 201, searching the time series data based on the search conditions input by the operator, and searching the time series data based on the search results.
  • a memory 1620 is provided to store a program that will result in the steps of creating driving support information and recording feature information input by the operator in the feature-added time series data recording unit 203. Be prepared. It can also be said that these programs cause the computer to execute the procedures or methods of the feature amount calculating section 101, the search section 102, the driving support information creation section 103, and the feature amount adding section 104.
  • memory refers to nonvolatile or volatile memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), and EEPROM (Electrically Erasable Programmable Read Only Memory).
  • the storage medium may be a flexible semiconductor memory, a magnetic disk, a flexible disk, an optical disk, a compact disk, a DVD (Digital Versatile Disc), or any storage medium that will be used in the future.
  • feature calculation unit 101 search unit 102, driving support information creation unit 103, and feature addition unit 104 are realized by dedicated hardware, and other functions are implemented by software or firmware. It may be realized by
  • the processing circuit can realize each of the above functions using hardware, software, firmware, or a combination thereof.
  • FIG. 37 is a block diagram showing the configuration of the driving support system.
  • the driving support system includes a server 1700 and a terminal device 1710.
  • Server 1700 is a server installed on the cloud.
  • Terminal device 1710 is a device provided at a location where an operator is present.
  • Server 1700 and terminal device 1710 are communicably connected.
  • the server 1700 includes a monitoring control device 105, a time-series data recording section 201, a feature calculation logic recording section 202, a feature calculation section 101, a feature-added time-series data recording section 203, and a feature addition section. 104. Further, the terminal device 1710 includes a search section 102, a driving support information creation section 103, and an input/output device 106. Each component included in server 1700 and terminal device 1710 is the same as each component in the driving support device according to the first embodiment (see FIG. 2).
  • FIG. 37 shows a configuration in which each component of the driving support device according to the first embodiment is distributed and arranged in the server 1700 and the terminal device 1710, the configuration of the driving support system is limited to this. It's not a thing.
  • the driving support system may have a configuration in which each component of the driving support device shown in FIGS.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

A purpose of the present disclosure is to provide an operation assistance device that makes it possible to present appropriate operation assistance information. An operation assistance device according to the present disclosure comprises: a time series data recording unit that records time series data that is collected from a plant; a feature amount calculation unit that calculates a feature amount from the time series data on the basis of a feature amount calculation logic; a retrieval unit that retrieves time series data that has the highest matching degree with a retrieval condition from the time series data; an operation assistance information creation unit that creates operation assistance information that assists with operation of the plant, on the basis of the retrieved time series data and a calculated feature amount that is associated with said time series data; and a feature amount imparting unit that associates the time series data with an additional feature amount that is input by an operator with respect to the time series data, and records the time series data in a feature amount-imparted time series data recording unit, wherein the operation assistance information creation unit creates the operation assistance information on the basis of the retrieved time series data, and the calculated feature amount and the additional feature amount that are associated with said time series data.

Description

運転支援装置、運転支援システム、および運転支援方法Driving support device, driving support system, and driving support method
 本開示は、上下水道、電力、化学、鉄鋼、鉄道、およびビル空調などのプラントの運転に関する運転情報を提示する運転支援装置、運転支援システム、および運転支援方法に関する。 The present disclosure relates to an operation support device, an operation support system, and an operation support method that present operation information regarding the operation of plants such as water supply and sewage, electric power, chemical, steel, railway, and building air conditioning plants.
 上下水道、電力、化学、鉄鋼、鉄道、およびビル空調などの大規模プラントの運用において、オペレータは、プラントを監視制御する監視制御装置が収集したプロセスデータに基づいてプラントの状態を推定し、プラントの状態が最適となるように設定値を入力する。このようなときにオペレータの判断を支援するものとして運転支援装置があり、運転支援装置には各種予測、シミュレーション、異常検知、および設定値ガイダンスなどの機能が実装されている。しかし、監視制御装置または運転支援装置の画面に表示することができるデータ項目数および期間には制約がある。従来、大規模プラントに設置された多数の計測機器から情報を収集する場合において、監視制御装置または運転支援装置の画面に表示する運転支援情報をアルゴリズムによって選択および生成してオペレータに提示する手法が開示されている(例えば、特許文献1参照)。 In the operation of large-scale plants such as water and sewage, electric power, chemical, steel, railway, and building air conditioning plants, operators estimate plant conditions based on process data collected by supervisory control equipment that monitors and controls the plant. Input the setting values so that the condition is optimal. Driving support devices are available to support the operator's decisions in such cases, and the driving support devices are equipped with functions such as various predictions, simulations, abnormality detection, and set value guidance. However, there are restrictions on the number and period of data that can be displayed on the screen of the supervisory control device or driving support device. Conventionally, when collecting information from a large number of measuring instruments installed in a large-scale plant, a method has been used to select and generate operation support information to be displayed on the screen of a monitoring control device or operation support device using an algorithm and present it to the operator. It has been disclosed (for example, see Patent Document 1).
特開2004-310492号公報Japanese Patent Application Publication No. 2004-310492
 オペレータがプラントの運転操作を決定する際には、監視制御装置が収集しているプラントの計測値の他に、監視制御装置が収集していない情報も用いて運転操作を決定している。ここで、監視制御装置が収集していない情報としては、例えば、季節および天候の変動見込み、プラントに影響するプラント外のイベント、およびプラントの維持管理情報などが挙げられる。 When an operator decides on a plant operation, in addition to the plant measurement values collected by the monitoring and control device, he also uses information not collected by the monitoring and control device. Here, the information not collected by the monitoring and control device includes, for example, expected seasonal and weather changes, events outside the plant that affect the plant, and plant maintenance information.
 特許文献1の技術では、監視制御装置が収集している計測値を量子化した値に基づいて、運転支援情報をアルゴリズムによって選択および生成してオペレータに提示しているため、監視制御装置が収集していない情報を用いてプラントの制御を判断すべき場合において適切な運転支援情報が提示されないという課題があった。また、監視制御装置は収集していないがプラントの制御の判断に用いる情報を、事前に一括して時系列データ記録部に入力する方式も考えられるが、監視制御業務を行ってから時間が経過した後にプラントの制御の判断に必要であった情報を入力しようとしても、オペレータの記憶が曖昧となって正確な情報が入力されないという課題があった。 In the technology of Patent Document 1, the driving support information is selected and generated by an algorithm based on the quantized value of the measured values collected by the supervisory control device, and is presented to the operator. There was a problem in that appropriate operation support information was not presented when plant control decisions should be made using information that was not available. Another possible method is to input information that is not collected by the monitoring and control equipment but is used to make plant control decisions all at once into the time-series data recording unit, but it is possible that time has passed since the monitoring and control work was performed. Even if the operator attempts to input information necessary for making plant control decisions after the system has been used, there is a problem in that the operator's memory becomes vague and the correct information is not input.
 本開示は、このような課題を解決するためになされたものであり、適切な運転支援情報を提示することが可能な運転支援装置、運転支援システム、および運転支援方法を提供することを目的とする。 The present disclosure has been made to solve such problems, and aims to provide a driving support device, a driving support system, and a driving support method that can present appropriate driving support information. do.
 上記の課題を解決するために、本開示による運転支援装置は、プラントを監視する監視制御装置がプラントから収集した監視制御データを時系列データとして記録する時系列データ記録部と、時系列データから特徴量を演算するための特徴量演算ロジックを記録する特徴量演算ロジック記録部と、特徴量演算ロジック記録部に記録された特徴量演算ロジックに基づいて、時系列データから特徴量を演算する特徴量演算部と、時系列データと、特徴量演算部が演算した特徴量である演算特徴量とを対応付けて記録する特徴量付与済み時系列データ記録部と、オペレータから入力された検索条件に基づいて、特徴量付与済み時系列データ記録部に記録された時系列データを区分し、区分した時系列データから検索条件との一致度が最も高い時系列データを検索する検索部と、検索部が検索した時系列データと、当該時系列データに対応付けられた演算特徴量とに基づいて、プラントの運転を支援する運転支援情報を作成する運転支援情報作成部と、時系列データに対してオペレータが入力した追加の特徴量である追加特徴量を、時系列データに対応付けて特徴量付与済み時系列データ記録部に記録する特徴量付与部とを備え、運転支援情報作成部は、検索部が検索した時系列データと、当該時系列データに対応付けられた演算特徴量および追加特徴量とに基づいて運転支援情報を作成する。 In order to solve the above problems, an operation support device according to the present disclosure includes a time-series data recording unit that records supervisory control data collected from the plant as time-series data by a supervisory control device that monitors the plant, and a time-series data recording unit that records supervisory control data collected from the plant as time-series data. A feature calculation logic recording unit that records feature calculation logic for calculating feature quantities, and a feature that calculates feature quantities from time-series data based on the feature calculation logic recorded in the feature calculation logic recording unit. A quantity calculation unit, a time-series data recording unit that records time-series data and calculated feature quantities, which are the feature quantities computed by the feature quantity calculation unit, in association with each other, and a search unit that divides the time series data recorded in the feature-added time series data recording unit based on the feature value, and searches the divided time series data for time series data that has the highest degree of matching with the search condition; An operation support information creation unit that creates operation support information to support plant operation based on the time series data searched by the user and the calculated feature values associated with the time series data; The driving support information creation unit includes a feature value adding unit that records additional feature values, which are additional feature values input by the operator, in a feature value added time series data recording unit in association with time series data. Driving support information is created based on the time series data searched by the section, and the calculated feature amount and additional feature amount associated with the time series data.
 本開示によれば、適切な運転支援情報を提示することが可能となる。 According to the present disclosure, it is possible to present appropriate driving support information.
 本開示の目的、特徴、態様、および利点は、以下の詳細な説明と添付図面とによって、より明白となる。 Objects, features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description and accompanying drawings.
実施の形態1による運転支援装置の構成の一例を示すブロック図である。1 is a block diagram showing an example of a configuration of a driving support device according to a first embodiment; FIG. 実施の形態1による運転支援装置の構成の一例を示すブロック図である。1 is a block diagram showing an example of a configuration of a driving support device according to a first embodiment; FIG. 実施の形態1による運転支援装置の動作の一例を示すフローチャートである。3 is a flowchart illustrating an example of the operation of the driving support device according to the first embodiment. 実施の形態1による運転支援装置の動作の一例を示すフローチャートである。5 is a flowchart illustrating an example of the operation of the driving support device according to the first embodiment. 実施の形態1による特徴量演算ロジック記録部の模式図である。FIG. 2 is a schematic diagram of a feature amount calculation logic recording unit according to the first embodiment. 実施の形態1による入出力装置に表示される画面の一例を示す図である。FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment. 実施の形態1による運転支援情報を検索する動作を説明するための図である。FIG. 3 is a diagram for explaining an operation of searching for driving support information according to the first embodiment. 実施の形態1による入出力装置に表示される画面の一例を示す図である。FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment. 実施の形態1による特徴量付与部の動作を説明するための図である。FIG. 3 is a diagram for explaining the operation of the feature value adding section according to the first embodiment. 実施の形態1による入出力装置に表示される画面の一例を示す図である。FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment. 実施の形態1による入出力装置に表示される画面の一例を示す図である。FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment. 実施の形態1による入出力装置に表示される画面の一例を示す図である。FIG. 3 is a diagram showing an example of a screen displayed on the input/output device according to the first embodiment. 実施の形態2による運転支援装置の構成の一例を示すブロック図である。FIG. 2 is a block diagram showing an example of the configuration of a driving support device according to a second embodiment. 実施の形態2による運転支援装置の動作の一例を示すフローチャートである。7 is a flowchart illustrating an example of the operation of the driving support device according to the second embodiment. 実施の形態2による運転支援装置の動作の一例を示すフローチャートである。7 is a flowchart illustrating an example of the operation of the driving support device according to the second embodiment. 実施の形態2による検索ロジック記録部の模式図である。FIG. 3 is a schematic diagram of a search logic recording unit according to a second embodiment. 実施の形態2によるスケジューリング部に記憶されたスケジュールの模式図である。FIG. 7 is a schematic diagram of a schedule stored in a scheduling unit according to the second embodiment. 実施の形態3による運転支援装置の構成の一例を示すブロック図である。FIG. 3 is a block diagram illustrating an example of the configuration of a driving support device according to a third embodiment. 実施の形態3による運転支援装置の動作の一例を示すフローチャートである。7 is a flowchart illustrating an example of the operation of the driving support device according to Embodiment 3. 実施の形態3による入出力装置に表示される画面の一例を示す図である。12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 3. FIG. 実施の形態3による入出力装置に表示される画面の一例を示す図である。12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 3. FIG. 実施の形態3による特徴量および評価値付与済み時系列データ記録部にシミュレーションおよびその評価を追加する動作を説明するための図である。FIG. 12 is a diagram for explaining an operation of adding a simulation and its evaluation to a time-series data recording unit to which feature amounts and evaluation values have been assigned according to the third embodiment; 実施の形態4による運転支援装置の構成の一例を示すブロック図である。FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a fourth embodiment. 実施の形態5による運転支援装置の構成の一例を示すブロック図である。FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a fifth embodiment. 実施の形態5による入出力装置に表示される画面の一例を示す図である。12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 5. FIG. 実施の形態5による時系列データ記録部の模式図である。FIG. 7 is a schematic diagram of a time-series data recording unit according to Embodiment 5. FIG. 実施の形態6による運転支援装置の構成の一例を示すブロック図である。FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a sixth embodiment. 実施の形態6による入出力装置に表示される画面の一例を示す図である。12 is a diagram showing an example of a screen displayed on an input/output device according to Embodiment 6. FIG. 実施の形態6による検索時系列グループID記録部の模式図である。FIG. 7 is a schematic diagram of a search time series group ID recording unit according to Embodiment 6; 実施の形態6による回数確率記録部の模式図である。FIG. 12 is a schematic diagram of a frequency probability recording unit according to Embodiment 6; 実施の形態6による運転支援装置の動作の一例を示すフローチャートである。12 is a flowchart illustrating an example of the operation of the driving support device according to the sixth embodiment. 実施の形態6による運転支援装置の動作の一例を示すフローチャートである。12 is a flowchart illustrating an example of the operation of the driving support device according to the sixth embodiment. 実施の形態6による運転支援装置の動作の一例を示すフローチャートである。12 is a flowchart illustrating an example of the operation of the driving support device according to the sixth embodiment. 実施の形態7による運転支援装置の構成の一例を示すブロック図である。FIG. 7 is a block diagram showing an example of the configuration of a driving support device according to a seventh embodiment. 実施の形態1~7による運転支援装置のハードウェア構成の一例を示すブロック図である。1 is a block diagram showing an example of a hardware configuration of a driving support device according to Embodiments 1 to 7. FIG. 実施の形態1~7による運転支援装置のハードウェア構成の一例を示すブロック図である。1 is a block diagram showing an example of a hardware configuration of a driving support device according to Embodiments 1 to 7. FIG. 実施の形態1~7による運転支援システムの構成の一例を示すブロック図である。1 is a block diagram showing an example of a configuration of a driving support system according to Embodiments 1 to 7. FIG.
 <実施の形態1>
 <構成>
 図1は、実施の形態1による運転支援装置の構成の一例を示すブロック図である。図1に示す運転支援装置は、本開示による運転支援装置の必要最小限の構成を示している。
<Embodiment 1>
<Configuration>
FIG. 1 is a block diagram showing an example of the configuration of a driving support device according to the first embodiment. The driving support device shown in FIG. 1 shows the minimum necessary configuration of the driving support device according to the present disclosure.
 図2は、図1に示す運転支援装置を含む他の構成に係る運転支援装置の構成の一例を示すブロック図である。図2に示す運転支援装置は、特徴量演算部101と、検索部102と、運転支援情報作成部103と、特徴量付与部104と、監視制御装置105と、入出力装置106と、時系列データ記録部201と、特徴量演算ロジック記録部202と、特徴量付与済み時系列データ記録部203とを備えている。本開示は、運転支援装置が特徴量付与部104を備えることを特徴としている。 FIG. 2 is a block diagram showing an example of the configuration of a driving support device according to another configuration including the driving support device shown in FIG. 1. The driving support device shown in FIG. It includes a data recording section 201, a feature amount calculation logic recording section 202, and a feature amount added time series data recording section 203. The present disclosure is characterized in that the driving support device includes a feature amount adding unit 104.
 監視制御装置105は、プラントに設置された計測機器が出力する計測情報と、オペレータが入力した制御入力情報とを含む監視制御データを収集し、収集した監視制御データを時系列データとして時系列データ記録部201に記録する。また、監視制御装置105は、オペレータが入力した制御入力情報を、プラントを構成する個々の設備に伝送する。 The supervisory control device 105 collects supervisory control data including measurement information output from measuring instruments installed in the plant and control input information input by an operator, and converts the collected supervisory control data into time series data. It is recorded in the recording unit 201. Additionally, the supervisory control device 105 transmits control input information input by the operator to each piece of equipment making up the plant.
 特徴量演算ロジック記録部202は、時系列データ記録部201に記録された時系列データから特徴量を演算するための特徴量演算ロジックを記録する。 The feature amount calculation logic recording unit 202 records feature amount calculation logic for calculating feature amounts from the time series data recorded in the time series data recording unit 201.
 特徴量演算部101は、特徴量演算ロジック記録部202に記録された特徴量演算ロジックに基づいて、時系列データ記録部201に記録された時系列データから特徴量を演算する。 The feature quantity calculation unit 101 calculates feature quantities from the time series data recorded in the time series data recording unit 201 based on the feature quantity calculation logic recorded in the feature quantity calculation logic recording unit 202.
 特徴量付与済み時系列データ記録部203は、時系列データ記録部201に記録された時系列データと、特徴量演算部101で演算された特徴量と、特徴量付与部104から入力された特徴量とを対応付けて記録する。 The feature value added time series data recording unit 203 stores the time series data recorded in the time series data recording unit 201, the feature values calculated by the feature value calculation unit 101, and the features input from the feature value adding unit 104. Record it in association with the amount.
 検索部102は、入出力装置106を介してオペレータが入力した検索条件に基づいて、特徴量付与済み時系列データ記録部203に記録された時系列データを区分する。そして、検索部102は、区分した時系列データの中から検索条件との一致度が高い時系列データを特定する。検索部102が特定した時系列データ(検索結果)は、図示しない記録部に記録してもよい。 The search unit 102 classifies the time-series data recorded in the feature-added time-series data recording unit 203 based on search conditions input by the operator via the input/output device 106. Then, the search unit 102 identifies time-series data that highly matches the search condition from among the divided time-series data. The time series data (search results) specified by the search unit 102 may be recorded in a recording unit (not shown).
 運転支援情報作成部103は、検索部102の検索結果に基づいて、運転支援情報を作成する。具体的には、運転支援情報作成部103は、検索部102が検索した時系列データと、当該時系列データに対応付けられた演算特徴量および追加特徴量とに基づいて運転支援情報を作成する。 The driving support information creation unit 103 creates driving support information based on the search results of the search unit 102. Specifically, the driving support information creation unit 103 creates driving support information based on the time series data searched by the search unit 102 and the calculated feature amount and additional feature amount associated with the time series data. .
 入出力装置106(入出力部)は、運転支援情報作成部103が作成した運転支援情報を表示する。また、入出力装置106は、オペレータによる検索条件の入力、または特徴量の追加入力を受け付ける。 The input/output device 106 (input/output unit) displays the driving support information created by the driving support information creation unit 103. The input/output device 106 also receives input of search conditions or additional input of feature amounts by the operator.
 特徴量付与部104は、オペレータが入力した特徴量の情報を特徴量付与済み時系列データ記録部203に記録する。 The feature value adding unit 104 records information on the feature values input by the operator in the feature value added time series data recording unit 203.
 <監視制御データを取得してから運転支援情報を表示するまでの動作>
 図3は、運転支援装置が監視制御データを取得してから運転支援情報を表示するまでの動作を示すフローチャートである。
<Operations from acquiring supervisory control data to displaying driving support information>
FIG. 3 is a flowchart showing the operation of the driving support device from acquiring supervisory control data to displaying driving support information.
 ステップS11において、監視制御装置105は、収集した監視制御データを時系列データとして時系列データ記録部201に記録する。 In step S11, the supervisory control device 105 records the collected supervisory control data in the time-series data recording unit 201 as time-series data.
 ステップS12において、特徴量演算部101は、時系列データ記録部201に記録された時系列データから、特徴量演算ロジック記録部202に記録された特徴量演算ロジックに従って特徴量を算出し、算出した特徴量を時系列データに対応付けて記録する。 In step S12, the feature quantity calculation unit 101 calculates the feature quantity from the time series data recorded in the time series data recording unit 201 according to the feature quantity calculation logic recorded in the feature quantity calculation logic recording unit 202. Record feature values in association with time series data.
 ステップS13において、入出力装置106は、オペレータが入力した検索条件を受け付ける。 In step S13, the input/output device 106 receives search conditions input by the operator.
 ステップS14において、検索部102は、オペレータが入力した検索条件に従って、特徴量付与済み時系列データ記録部203に記録されたデータを検索する。 In step S14, the search unit 102 searches the data recorded in the feature amount added time series data recording unit 203 according to the search conditions input by the operator.
 ステップS15において、運転支援情報作成部103は、検索部102の検索結果に基づいて運転支援情報を作成する。そして、入出力装置106は、運転支援情報作成部103が作成した運転支援情報を表示する。 In step S15, the driving support information creation unit 103 creates driving support information based on the search results of the search unit 102. The input/output device 106 then displays the driving support information created by the driving support information creation unit 103.
 <オペレータが追加入力した特徴量を記録する動作>
 図4は、オペレータが追加入力した特徴量を特徴量付与済み時系列データ記録部203に記録する動作を示すフローチャートである。
<Operation to record feature values additionally input by the operator>
FIG. 4 is a flowchart showing the operation of recording feature quantities additionally inputted by the operator in the feature quantity assigned time series data recording unit 203.
 ステップS21において、入出力装置106は、運転支援情報を表示する。 In step S21, the input/output device 106 displays driving support information.
 ステップS22において、入出力装置106は、オペレータが入力した時系列データの時系列名および各時刻の値を受け付ける。 In step S22, the input/output device 106 receives the time series name and each time value of the time series data input by the operator.
 ステップS23において、特徴量付与部104は、オペレータが入力した情報に基づいて時系列データに追加の特徴量を付与し、特徴量付与済み時系列データ記録部203に記録する。 In step S23, the feature amount adding unit 104 adds an additional feature amount to the time series data based on the information input by the operator, and records it in the feature amount added time series data recording unit 203.
 <特徴量演算ロジック記録部202の機能>
 図5は、特徴量演算ロジック記録部202の模式図である。特徴量演算ロジック記録部202は、特徴量時系列名301、特徴量時系列の単位302、演算に用いる特徴量の種別303、元時系列304、元時系列の単位305、特徴量の種別306、および計算式307で構成されている。
<Functions of feature value calculation logic recording unit 202>
FIG. 5 is a schematic diagram of the feature amount calculation logic recording unit 202. The feature amount calculation logic recording unit 202 includes a feature amount time series name 301, a feature amount time series unit 302, a feature amount type 303 used for calculation, an original time series 304, an original time series unit 305, and a feature amount type 306. , and a calculation formula 307.
 例えば、「特徴量1」は、元時系列304として記録された「計測値1」に対して、演算に用いる特徴量の種別303として記録された「積分(10時間)」の処理を行うことによって演算される。具体的には、特徴量の種別306から「積分(10時間)」をキーとして特定し、計算式307のうち「積分(10時間)」に対応する式を用いて「積分(10時間)」の処理を行う。演算処理では、元時系列の単位305、および特徴量時系列の単位302に用いて、必要に応じて単位の換算処理を行う。 For example, "feature amount 1" is to perform "integration (10 hours)" processing recorded as the feature amount type 303 used for calculation on "measurement value 1" recorded as the original time series 304. It is calculated by Specifically, "integral (10 hours)" is specified as a key from the feature quantity type 306, and "integral (10 hours)" is calculated using the formula corresponding to "integral (10 hours)" in the calculation formula 307. Process. In the arithmetic processing, the unit 305 of the original time series and the unit 302 of the feature amount time series are used, and unit conversion processing is performed as necessary.
 <運転支援情報を検索する際における入出力装置106の画面>
 図6は、運転支援情報を検索する際における入出力装置106の画面の一例を示す図である。運転支援情報を検索する際における画面は、検索条件入力400、検索結果一覧410、時系列データ選択420、トレンドグラフ430、検索ボタン440、および特徴量追加ボタン450で構成されている。
<Screen of input/output device 106 when searching driving support information>
FIG. 6 is a diagram showing an example of the screen of the input/output device 106 when searching for driving support information. The screen for searching driving support information includes a search condition input 400, a search result list 410, a time series data selection 420, a trend graph 430, a search button 440, and an add feature button 450.
 検索条件入力400では、オペレータは、時系列名401として検索条件405,406,407を入力し、入力した検索条件405,406,407ごとに検索種別402、対象時刻403、および条件404を指定する。 In search condition input 400, the operator inputs search conditions 405, 406, 407 as time series name 401, and specifies search type 402, target time 403, and condition 404 for each input search condition 405, 406, 407. .
 検索条件405である「時間帯」の入力は必須であり、条件404として開始時刻および終了時刻を入力する。開始時刻については0:00~23:59の範囲で入力することができ、終了時刻については開始時刻以降の時刻を入力することができる。終了時刻が24:00を超えたときは、翌日以降を意味し、24:00で割ったときの商が経過日数、24:00で割ったときの余りが時刻を表している。 The search condition 405 "time zone" is required to be input, and the condition 404 is the start time and end time. The start time can be input in the range 0:00 to 23:59, and the end time can be input any time after the start time. When the end time exceeds 24:00, it means the next day or later, the quotient when divided by 24:00 represents the number of elapsed days, and the remainder when divided by 24:00 represents the time.
 時間帯以外の時系列名401(すなわち、時間帯以外の検索条件)としては、期間、年、月、日、年月、月日、曜日、平日または休日、計測値時系列、および特徴量時系列が挙げられ、オペレータはこれらの中から任意の検索条件を選択する。 Time series names other than time zones 401 (that is, search conditions other than time zones) include period, year, month, day, year/month, month/day, day of the week, weekday or holiday, measured value time series, and feature amount time. There are several series, and the operator selects an arbitrary search condition from these.
 検索結果一覧410としては、オペレータが入力した各検索条件を同時に満たしたものが出力される。例えば、検索条件405では、時系列名401として「時間帯」、条件404として「14:00~23:59」が選択されている。また、検索条件406では、時系列名401として「特徴量1」、検索種別402として「数値 完全一致」、対象時刻403として「23:59」、条件404として「40000~」が選択されている。さらに、検索条件407では、時系列名401として「計測値2」、検索種別402として「数値 類似」、対象時刻403として「14:00」、条件404として「3.5」が選択されている。このように検索条件405,406,407が入力された状態で検索ボタン440を押下すると、検索部102は、検索条件405,406,407を同時に満たすデータを、特徴量付与済み時系列データ記録部203から検索する。 A search result list 410 that simultaneously satisfies each search condition input by the operator is output. For example, in the search condition 405, “time zone” is selected as the time series name 401, and “14:00 to 23:59” is selected as the condition 404. Furthermore, in the search condition 406, "feature amount 1" is selected as the time series name 401, "numeric exact match" is selected as the search type 402, "23:59" is selected as the target time 403, and "40000~" is selected as the condition 404. . Furthermore, in the search condition 407, "measured value 2" is selected as the time series name 401, "numerical similarity" is selected as the search type 402, "14:00" is selected as the target time 403, and "3.5" is selected as the condition 404. . When the search button 440 is pressed with the search conditions 405, 406, 407 entered in this way, the search unit 102 searches the data that simultaneously satisfies the search conditions 405, 406, 407 in the time series data recording unit with added features. Search from 203.
 検索種別402として「数値 類似」が選択された場合は、入力された検索条件との一致度が高いものから順にランキング形式で検索結果が出力される。その他の検索種別402として、「文字列 完全一致」、「文字列 部分一致」、「文字列 前方一致」、および「文字列 後方一致」を選択することができる。 When "numerical similarity" is selected as the search type 402, search results are output in a ranking format in descending order of degree of match with the input search condition. As other search types 402, "character string complete match", "character string partial match", "character string beginning match", and "character string trailing match" can be selected.
 検索種別402として「数値 類似」が選択された単一または複数の時系列の対象時刻403における条件404との一致度を演算するときに用いる指標としては、コサイン類似度、ピアソンの相関係数、偏差パターンの類似度、ユークリッド距離、基準化ユークリッド距離、マンハッタン距離、ミンコフスキー距離、チェビシェフ距離、およびマハラノビス距離を用いることができる。類似度および相関係数を指標として用いる場合は、類似度および相関係数が高いデータが、一致度が高いデータであると判定される。また、距離を指標として用いる場合は、距離が近いデータが、一致度が高いデータであると判定される。 Indices used when calculating the degree of match with the condition 404 at the target time 403 of a single or multiple time series for which "numerical similarity" is selected as the search type 402 include cosine similarity, Pearson's correlation coefficient, Deviation pattern similarity, Euclidean distance, scaled Euclidean distance, Manhattan distance, Minkowski distance, Chebyshev distance, and Mahalanobis distance can be used. When similarity and correlation coefficient are used as indicators, data with high similarity and correlation coefficient is determined to be data with high matching. Furthermore, when distance is used as an index, data with a close distance is determined to be data with a high degree of matching.
 検索結果一覧410には、検索条件405,406,407との一致度が高いものから順にランキング412の形式でサマリ情報が表示される。サマリ情報は、日時と、検索条件として入力された時系列名に関する情報を含む。検索条件として、対象時刻が入力されている時系列名に関する検索では対象時刻の値、曜日に関する検索では曜日、平日または休日に関する検索では平日または休日、文字列に関する検索では一致した文字列を表示する。 In the search result list 410, summary information is displayed in the form of a ranking 412 in descending order of the degree of match with the search conditions 405, 406, and 407. The summary information includes information regarding the date and time and the time series name input as the search condition. As a search condition, if a search is related to a time series name in which a target time is entered, the value of the target time is displayed, if a search is related to a day of the week, the day of the week is displayed, if a search is related to a weekday or holiday, the matching string is displayed. .
 図6の例では、検索結果413に検索結果の日時が表示され、検索結果414に「23:59における特徴量1」の値が表示され、検索結果415に「14:00における計測値2」の値が表示される。トレンドグラフ430では、検索結果一覧410の選択411から選択した期間における、時系列データ選択420から選択した時系列データが表示される。 In the example of FIG. 6, the search result 413 displays the date and time of the search result, the search result 414 displays the value of "feature value 1 at 23:59", and the search result 415 displays "measurement value 2 at 14:00". The value of is displayed. The trend graph 430 displays time series data selected from the time series data selection 420 in the period selected from the selection 411 of the search result list 410.
 <検索部102が運転支援情報を検索する動作>
 図7は、検索部102が運転支援情報を検索する動作を説明するための図であり、特徴量付与済み時系列データ記録部203の模式図である。ここでは、オペレータが図6に示す検索条件405,406,407を入力した場合における検索の動作について説明する。
<Operation in which the search unit 102 searches for driving support information>
FIG. 7 is a diagram for explaining an operation in which the search unit 102 searches for driving support information, and is a schematic diagram of the time-series data recording unit 203 with added features. Here, the search operation when the operator inputs search conditions 405, 406, and 407 shown in FIG. 6 will be described.
 まず、検索条件405の時間帯として「14:00~23:59」が選択されているため、特徴量付与済み時系列データ記録部203に記録された時系列データ(日時の列500)を、日ごとに「14:00~23:59」で区分する。 First, since "14:00 to 23:59" is selected as the time period of the search condition 405, the time series data (date and time column 500) recorded in the feature value added time series data recording unit 203 is Each day is divided into "14:00-23:59".
 次に、検索条件406では、時系列名401として「特徴量1」、検索種別402として「数値 完全一致」、対象時刻403として「23:59」、条件404として「40000~」が選択されているため、区分した時系列データのうち、「特徴量1」の「23:59」における「40000~」のデータが検索結果の候補に残る。例えば、区分501,02の時系列データにおける「23:59」の「特徴量1」の値は、それぞれ「42400」および「58734」であり、条件404の「40000~」を満たしているため検索結果の候補に残る。 Next, in the search condition 406, "Feature 1" is selected as the time series name 401, "Numeric exact match" is selected as the search type 402, "23:59" is selected as the target time 403, and "40000~" is selected as the condition 404. Therefore, among the divided time series data, the data "40000~" at "23:59" of "feature amount 1" remains as a search result candidate. For example, the values of "feature quantity 1" of "23:59" in the time series data of sections 501 and 02 are "42400" and "58734", respectively, and satisfy the condition 404 "40000 ~", so the search is performed. It remains as a candidate for the result.
 最後に、検索条件407では、時系列名401として「計測値2」、検索種別402として「数値 類似」、対象時刻403として「14:00」、条件404として「3.5」が選択されているため、区分した時系列データのうち、「計測値2」の値が「3.5」に類似するデータから順に検索条件との一致度が高いと判定される。例えば、区分501の時系列データの「14:00」における「計測値2」の値である「3.55」と、区分502の時系列データの「14:00」における「計測値2」の値である「3.47」とを比較すると、「3.47」の方が「3.5」に類似する。従って、区分501の時系列データの方よりも区分502の時系列データの方が、検索条件との一致度が高いデータであると判定される。 Finally, in the search condition 407, "Measurement value 2" is selected as the time series name 401, "Numeric similarity" is selected as the search type 402, "14:00" is selected as the target time 403, and "3.5" is selected as the condition 404. Therefore, among the divided time series data, data having a value similar to "3.5" for "measurement value 2" is determined to have a higher degree of matching with the search condition. For example, the value of "measurement value 2" at "14:00" in the time series data of section 501 is "3.55", and the value of "measurement value 2" at "14:00" of the time series data of section 502 is "3.55". When compared with the value "3.47", "3.47" is more similar to "3.5". Therefore, it is determined that the time series data in section 502 matches the search condition more closely than the time series data in section 501.
 <オペレータが時系列データに特徴量を付与する際の動作>
 図8は、オペレータが時系列データに特徴量を付与する際に、入出力装置106に表示される画面の一例を示す図である。
<Operations when the operator adds features to time series data>
FIG. 8 is a diagram showing an example of a screen displayed on the input/output device 106 when an operator adds feature amounts to time series data.
 オペレータが特徴量追加ボタン450を押下すると、特徴量の追加方法を選択する選択ウィンドウ451が表示される。オペレータが選択ウィンドウ451の「トレンド」を選択すると、トレンドグラフ430に期間選択バー431が表示され、期間が選択できるようになる。オペレータが期間を選択すると、選択した期間に付与する特徴量名432およびその値433が入力できるようになる。図8の例では、選択期間として「2020/8/11 16:00~20:00」、特徴量名432として「イベント1」、値433として「種別A」が入力されている。 When the operator presses the feature quantity addition button 450, a selection window 451 for selecting a feature quantity addition method is displayed. When the operator selects "trend" in the selection window 451, a period selection bar 431 is displayed on the trend graph 430, and a period can be selected. When the operator selects a period, the feature name 432 and its value 433 to be given to the selected period can be input. In the example of FIG. 8, “2020/8/11 16:00 to 20:00” is input as the selection period, “event 1” is input as the feature name 432, and “type A” is input as the value 433.
 図9は、オペレータが時系列データに特徴量を付与する操作を行った際に、特徴量付与部104が特徴量付与済み時系列データ記録部203に特徴量を記録する動作を説明するための図であり、特徴量付与済み時系列データ記録部203の模式図である。 FIG. 9 is a diagram for explaining the operation in which the feature value adding unit 104 records the feature value in the feature value added time series data recording unit 203 when the operator performs an operation to add a feature value to time series data. FIG. 2 is a schematic diagram of a time-series data recording unit 203 with feature amounts added.
 例えば、図8に示すように、選択期間として「2020/8/11 16:00~20:00」、特徴量名432として「イベント1」、値433として「種別A」がオペレータによって入力されている場合において、特徴量付与済み時系列データ記録部203に「イベント1」が登録されていない場合は、特徴量付与済み時系列データ記録部203の最後尾列530に「イベント1」が追加登録される。そして、「イベント1」の列における「2020/8/11 16:00~20:00」に相当するセルに「種別A」を登録する。なお、既に「イベント1」が登録されている場合は、「2020/8/11 16:00~20:00」に相当するセルに「種別A」を追加登録、あるいは既に他の値が登録されている場合は上書きして登録すればよい。 For example, as shown in FIG. 8, the operator inputs "2020/8/11 16:00-20:00" as the selection period, "Event 1" as the feature name 432, and "Type A" as the value 433. If "Event 1" is not registered in the time-series data recording unit 203 with features added, "Event 1" is additionally registered in the last column 530 of the time-series data recording unit 203 with features added. be done. Then, "Type A" is registered in the cell corresponding to "2020/8/11 16:00-20:00" in the "Event 1" column. In addition, if "Event 1" is already registered, "Type A" should be additionally registered in the cell corresponding to "2020/8/11 16:00-20:00", or another value is already registered. If so, you can overwrite it and register it.
 図10は、オペレータが付与した特徴量を検索条件として検索する際に、入出力装置106に表示される画面の一例を示す図である。 FIG. 10 is a diagram showing an example of a screen displayed on the input/output device 106 when performing a search using feature amounts assigned by an operator as search conditions.
 図9に示すように、特徴量付与済み時系列データ記録部203に時系列名として「イベント1」、値として「種別A」が登録されたため、図10における検索条件408では、時系列名として「イベント1」、検索種別として「文字列 完全一致」、条件として「種別A」を選択することができる。 As shown in FIG. 9, "Event 1" is registered as the time series name and "Type A" is registered as the value in the feature amount assigned time series data recording unit 203. Therefore, in the search condition 408 in FIG. 10, the time series name is It is possible to select "Event 1", "Character string complete match" as the search type, and "Type A" as the condition.
 オペレータが検索条件405,406,407に加えて検索条件408を指定した場合、検索条件405,406,407,408を同時に満たす「2020/8/11 16:00~23:59」のデータが検索結果一覧に表示される。 If the operator specifies search condition 408 in addition to search conditions 405, 406, and 407, the data for “2020/8/11 16:00 to 23:59” that simultaneously satisfies search conditions 405, 406, 407, and 408 will be searched. Displayed in the results list.
 図11は、特徴量の追加方法として「検索結果」を選択した場合における、入出力装置106に表示される画面の一例を示す図である。 FIG. 11 is a diagram showing an example of a screen displayed on the input/output device 106 when "search results" is selected as the feature amount addition method.
 オペレータが選択ウィンドウ451から「検索結果」を選択すると、検索結果一覧において時系列名および値を指定することができる。選択期間は、値を入力したセルに対応する日時となる。 When the operator selects "Search Results" from the selection window 451, the time series name and value can be specified in the search result list. The selection period is the date and time corresponding to the cell in which the value was input.
 図11の例では、時系列名として「イベント2」、値として「種別B」が入力され、日時は「種別B」が入力されたセルに対応する(「種別B」が入力されたセルと同じ行の)「2020/8/11 14:00~23:59」となる。 In the example in Figure 11, "Event 2" is entered as the time series name, "Type B" is entered as the value, and the date and time corresponds to the cell in which "Type B" was entered (the cell in which "Type B" was entered). on the same line) becomes "2020/8/11 14:00-23:59".
 特徴量付与部104が特徴量付与済み時系列データ記録部203に特徴量を記録する動作は、図8の例で選択ウィンドウ451から「トレンド」を選択した際に特徴量を記録する動作と同様である。 The operation in which the feature value adding unit 104 records the feature value in the feature value added time series data recording unit 203 is the same as the operation in which the feature value is recorded when “trend” is selected from the selection window 451 in the example of FIG. It is.
 図12は、特徴量の追加方法として「カレンダー」を選択した場合における、入出力装置106に表示される画面の一例を示す図である。 FIG. 12 is a diagram showing an example of a screen displayed on the input/output device 106 when "calendar" is selected as the feature amount addition method.
 オペレータが選択ウィンドウ451から「カレンダー」を選択すると、カレンダー460が表示される。カレンダー460において、期間単位選択ボタン461は、カレンダー460の表示期間の単位を週、月、または年に切り替えることができる。<ボタン462は、カレンダー460の表示期間を戻すことができる。>ボタン463は、カレンダー460の表示期間を進めることができる。今日ボタン464は、今日の日付が表示されるように表示期間を変更することができる。 When the operator selects "Calendar" from the selection window 451, a calendar 460 is displayed. In the calendar 460, the period unit selection button 461 can switch the unit of the display period of the calendar 460 to week, month, or year. The < button 462 can return the display period of the calendar 460. > button 463 can advance the display period of calendar 460. Today button 464 can change the display period so that today's date is displayed.
 期間選択バー465は、任意の期間を選択することができる。期間選択バー465で期間を選択すると、選択した期間に付与する特徴量名466および値467を入力することができる。図12の例では、選択期間として「2020/7/28 0:00~2020/8/24 0:00」が選択され、特徴量名466として「イベント3」、値467として「種別X」が入力されている。 The period selection bar 465 allows you to select any period. When a period is selected using the period selection bar 465, a feature name 466 and a value 467 to be given to the selected period can be input. In the example of FIG. 12, "2020/7/28 0:00 to 2020/8/24 0:00" is selected as the selection period, "Event 3" is set as the feature name 466, and "Type X" is set as the value 467. It has been entered.
 <効果>
 実施の形態1による運転支援装置は、特徴量付与部104を備えている。特徴量付与部104は、オペレータが入力した特徴量を時系列データに対応付けて特徴量付与済み時系列データ記録部203に記録している。これにより、「監視制御装置105は収集していないがプラントの制御の判断に必要な情報」を考慮した適切な運転支援情報をオペレータに提示することができる。
<Effect>
The driving support device according to the first embodiment includes a feature amount adding section 104. The feature value adding unit 104 records the feature values input by the operator in the feature value added time series data recording unit 203 in association with time series data. This makes it possible to present the operator with appropriate operation support information that takes into account "information that is not collected by the supervisory control device 105 but is necessary for making plant control decisions."
 <実施の形態2>
 実施の形態1では、オペレータが運転支援情報を参照しながら監視制御装置が収集していない情報を入力し、即座に適切な運転支援情報を検索して表示する方法について説明した。実施の形態1で説明した方法では、オペレータが検索条件を入力したときのみに新たな運転支援情報が表示されるが、オペレータが検索条件を入力しない場合は新たな運転支援情報は表示されない。実施の形態2は、このような課題を解決するためになされたものであり、以下にその詳細を説明する。
<Embodiment 2>
In the first embodiment, a method has been described in which the operator inputs information not collected by the monitoring and control device while referring to the driving support information, and immediately searches for and displays appropriate driving support information. In the method described in Embodiment 1, new driving support information is displayed only when the operator inputs search conditions, but new driving support information is not displayed when the operator does not input search conditions. Embodiment 2 was created to solve this problem, and details thereof will be explained below.
 <構成>
 図13は、実施の形態2による運転支援装置の構成の一例を示すブロック図である。
<Configuration>
FIG. 13 is a block diagram showing an example of the configuration of a driving support device according to the second embodiment.
 図13に示すように、実施の形態2による運転支援装置は、実施の形態1による運転支援装置(図2参照)に対して、スケジューリング部107、更新部108、および検索ロジック記録部204をさらに備えることを特徴としている。 As shown in FIG. 13, the driving support device according to the second embodiment further includes a scheduling unit 107, an updating unit 108, and a search logic recording unit 204 in addition to the driving support device according to the first embodiment (see FIG. 2). It is characterized by being prepared.
 スケジューリング部107は、検索部102が検索を実行するスケジュールを指定する。当該スケジュールは、スケジューリング部107に記録されている。検索ロジック記録部204は、検索部102が検索するための検索ロジックを記録する。更新部108は、入出力装置106を介してオペレータが入力した指示に従って、特徴量演算ロジック記録部202に記録された特徴量演算ロジック、スケジューリング部107で指定されるスケジュール、および検索ロジック記録部204に記録された検索ロジックを更新する。 The scheduling unit 107 specifies a schedule for the search unit 102 to perform the search. The schedule is recorded in the scheduling section 107. The search logic recording unit 204 records search logic for the search unit 102 to search. The updating unit 108 updates the feature calculation logic recorded in the feature calculation logic recording unit 202, the schedule specified by the scheduling unit 107, and the search logic recording unit 204 according to instructions input by the operator via the input/output device 106. Update the search logic recorded in .
 <監視制御データを取得してから運転支援情報を表示するまでの動作>
 図14,15は、運転支援装置が監視制御データを取得してから運転支援情報を表示するまでの動作を示すフローチャートである。なお、図14のステップS31、ステップS32、およびステップS34は、図3のステップS11、ステップS12、およびステップS15と同様の処理であるため、ここでは説明を省略する。以下では、図14のステップS33およびステップS35と、図15のステップS36について説明する。
<Operations from acquiring supervisory control data to displaying driving support information>
FIGS. 14 and 15 are flowcharts showing operations from when the driving support device acquires monitoring control data until displaying driving support information. Note that steps S31, S32, and S34 in FIG. 14 are the same processes as steps S11, S12, and S15 in FIG. 3, so the description thereof will be omitted here. Below, steps S33 and S35 in FIG. 14 and step S36 in FIG. 15 will be explained.
 ステップS33において、検索部102は、スケジューリング部107において指定されたスケジュールで、検索ロジック記録部204に記録された検索ロジックに従って、特徴量付与済み時系列データ記録部203のデータを検索する。 In step S33, the search unit 102 searches the data in the feature-added time series data recording unit 203 according to the schedule specified by the scheduling unit 107 and according to the search logic recorded in the search logic recording unit 204.
 ステップS35において、入出力装置106は、オペレータが意図する情報が、オペレータが意図するタイミングで入出力装置106に表示されたとオペレータが判定したか否かを判断する。オペレータが意図する情報が意図するタイミングで表示されたと判定した場合は、図14の動作を終了する。一方、オペレータが意図する情報が意図するタイミングで表示されていないと判定した場合は、図15のステップS36に移行する。 In step S35, the input/output device 106 determines whether the operator has determined that the information intended by the operator has been displayed on the input/output device 106 at the timing intended by the operator. If it is determined that the information intended by the operator has been displayed at the timing intended, the operation in FIG. 14 ends. On the other hand, if it is determined that the information intended by the operator is not displayed at the timing intended, the process moves to step S36 in FIG. 15.
 ステップS36において、オペレータが意図する情報が、オペレータが意図するタイミングで表示されるように、オペレータが入出力装置を用いて特徴量演算ロジック、スケジュール、および検索ロジックを更新し、それぞれを特徴量演算ロジック記録部、スケジューリング部、および検索ロジック記録部に記録する。 In step S36, the operator uses the input/output device to update the feature calculation logic, schedule, and search logic so that the information intended by the operator is displayed at the timing the operator intends, and performs feature calculation on each of them. It is recorded in the logic recording section, scheduling section, and search logic recording section.
 <検索ロジック記録部204の機能>
 図16は、検索ロジック記録部204の模式図である。検索ロジック記録部204は、検索ロジックID600および検索条件610で構成されている。検索条件610は、例えば、「検索条件1~5」を含む。「検索条件1」は、時系列名611、検索種別612、対象時刻613、第1条件614、および第2条件615を含む。「検索条件2」は、時系列名616、検索種別617、対象時刻618、第1条件619、および第2条件620を含む。
<Function of search logic recording unit 204>
FIG. 16 is a schematic diagram of the search logic recording unit 204. The search logic recording unit 204 includes a search logic ID 600 and search conditions 610. The search conditions 610 include, for example, “search conditions 1 to 5”. “Search condition 1” includes a time series name 611, a search type 612, a target time 613, a first condition 614, and a second condition 615. “Search condition 2” includes a time series name 616, a search type 617, a target time 618, a first condition 619, and a second condition 620.
 例えば、検索ロジックID600の「SL1」では、「検索条件1」について、時系列名611として「時間帯」、第1条件614として「検索と同時刻」、第2条件615として「検索の10時間後の時刻」が指定されている。「検索と同時刻」とは、スケジューリング部107によるスケジュールで検索ロジックID600の「SL1」が実行された時刻であり、例えば2021/1/6 5:00に実行された場合は5:00が指定される。「検索の10時間後の時刻」とは、5:00の10時間後の時刻である15:00が指定される。 For example, in the search logic ID 600 "SL1", for "search condition 1", the time series name 611 is "time zone", the first condition 614 is "same time as search", and the second condition 615 is "10 hours of search". "later time" is specified. “Same time as search” is the time when “SL1” with search logic ID 600 was executed according to the schedule by the scheduling unit 107. For example, if it was executed at 5:00 on January 6, 2021, 5:00 is specified. be done. The "time 10 hours after the search" is specified as 15:00, which is the time 10 hours after 5:00.
 また、「検索条件2」について、時系列名616として「特徴量1」、検索種別617として「数値 完全一致」、対象時刻618として「検索の10時間後の時刻」、第1条件619として「40000」が指定されている。第2条件620は、指定されていない。なお、検索種別として「数値 完全一致」が指定されている場合は、第1条件に下限値、第2条件に上限値が指定される。検索ロジックID600の「SL1」では、第1条件619に下限値として「40000」が指定されているため、「40000~」の値が検索結果として選択される。 Regarding "Search condition 2", the time series name 616 is "Feature amount 1", the search type 617 is "Numeric exact match", the target time 618 is "Time 10 hours after the search", and the first condition 619 is " 40000" is specified. The second condition 620 is not specified. Note that when "numerical complete match" is specified as the search type, the lower limit value is specified as the first condition, and the upper limit value is specified as the second condition. In "SL1" of the search logic ID 600, "40000" is specified as the lower limit value in the first condition 619, so a value of "40000~" is selected as the search result.
 さらに、「検索条件3」について、時系列名として「計測値2」、検索種別として「数値 類似」、対象時刻として「検索と同時刻」、第1条件として「3.5」が指定されてる。検索種別として「数値 類似」が指定されている場合は、第2条件を指定することができない。 Furthermore, for "Search condition 3", "Measurement value 2" is specified as the time series name, "Numeric similarity" is specified as the search type, "Same time as search" is specified as the target time, and "3.5" is specified as the first condition. . If "numerical similarity" is specified as the search type, the second condition cannot be specified.
 <スケジューリング部107の機能>
 図17は、スケジューリング部107に記憶されたスケジュールの模式図である。スケジュールは、検索ロジックID701、開始日時702、終了日時703、および周期704で構成されている。
<Functions of scheduling section 107>
FIG. 17 is a schematic diagram of the schedule stored in the scheduling section 107. The schedule includes a search logic ID 701, a start date and time 702, an end date and time 703, and a cycle 704.
 例えば、検索ロジックID701の「SL1」は、開始日時702である「2021/1/1 0:00」から周期704である「60分」の定周期で、終了日時703である「2030/12/31 23:59」まで繰り返し実行される。 For example, the search logic ID 701 "SL1" has a regular cycle from the start date and time 702 of "2021/1/1 0:00" to the period 704 of "60 minutes", and the end date and time 703 of "2030/12/ 31 23:59" is repeatedly executed.
 更新部108は、入出力装置106を介して入力されたオペレータの操作に従って、スケジュール、特徴量演算ロジック、および検索ロジックを更新する。スケジュールを更新する際には、スケジューリング部107に記録されたスケジュールを更新する。特徴量演算ロジックを更新する際には、特徴量演算ロジック記録部202に記録された特徴量演算ロジックを更新する。検索ロジックを更新する際には、検索ロジック記録部204に記録された検索ロジックを更新する。 The update unit 108 updates the schedule, feature calculation logic, and search logic according to operator operations input via the input/output device 106. When updating the schedule, the schedule recorded in the scheduling unit 107 is updated. When updating the feature amount calculation logic, the feature amount calculation logic recorded in the feature amount calculation logic recording unit 202 is updated. When updating the search logic, the search logic recorded in the search logic recording unit 204 is updated.
 <効果>
 実施の形態2による運転支援装置は、スケジューリング部107および検索ロジック記録部204を備えている。検索部102はスケジューリング部107に記録されたスケジュールで、検索ロジック記録部204に記録された検索ロジックに従って、特徴量付与済み時系列データ記録部203のデータを検索する。これにより、自動で新たな運転支援情報をオペレータに提示することができる。
<Effect>
The driving support device according to the second embodiment includes a scheduling section 107 and a search logic recording section 204. The search unit 102 searches the data in the feature value added time series data recording unit 203 according to the schedule recorded in the scheduling unit 107 and the search logic recorded in the search logic recording unit 204 . Thereby, new driving support information can be automatically presented to the operator.
 また、実施の形態2による運転支援装置は、更新部108を備えている。更新部108は、入出力装置106を介して入力されたオペレータの操作に従って、スケジュール、特徴量演算ロジック、および検索ロジックを更新する。これにより、オペレータが意図する運転支援情報を、オペレータが意図するタイミングで提示することができる。 Further, the driving support device according to the second embodiment includes an update unit 108. The update unit 108 updates the schedule, feature calculation logic, and search logic according to operator operations input via the input/output device 106. Thereby, the driving support information intended by the operator can be presented at the timing intended by the operator.
 <実施の形態3>
 実施の形態1では、オペレータが運転支援情報を参照しながら監視制御装置が収集していない情報を入力し、即座に適切な運転支援情報を検索して表示する方法について説明した。実施の形態1で説明した方法では、監視制御装置が収集した過去のプラントの運転履歴は検索結果として表示されるが、過去のプラントの運転履歴にない運転方法は検索結果として表示されない。実施の形態3は、このような課題を解決するためになされたものであり、以下にその詳細を説明する。
<Embodiment 3>
In the first embodiment, a method has been described in which the operator inputs information not collected by the monitoring and control device while referring to the driving support information, and immediately searches for and displays appropriate driving support information. In the method described in Embodiment 1, the past plant operation history collected by the supervisory control device is displayed as a search result, but an operation method that is not included in the past plant operation history is not displayed as a search result. Embodiment 3 has been developed to solve this problem, and the details thereof will be explained below.
 <構成>
 図18は、実施の形態3による運転支援装置の構成の一例を示すブロック図である。
<Configuration>
FIG. 18 is a block diagram showing an example of the configuration of a driving support device according to the third embodiment.
 図18に示すように、実施の形態3による運転支援装置は、実施の形態1による運転支援装置(図2参照)に対して、時系列データ編集部109、シミュレーション実行部110、および評価値算出部111をさらに備え、特徴量付与済み時系列データ記録部203に代えて特徴量および評価値付与済み時系列データ記録部205を備えている。 As shown in FIG. 18, the driving support device according to the third embodiment has a time series data editing unit 109, a simulation execution unit 110, and an evaluation value calculation unit, in contrast to the driving support device according to the first embodiment (see FIG. 2). 111 , and a feature amount and evaluation value added time series data recording unit 205 in place of the feature value added time series data recording unit 203 .
 時系列データ編集部109は、入出力装置106を介してオペレータが入力した指示に従って、時系列データを編集する。シミュレーション実行部110は、時系列データ編集部109が編集した時系列データに基づいて、プラントの挙動をシミュレーションする。評価値算出部111は、シミュレーション実行部110がシミュレーションしたプラントの挙動を評価する。特徴量および評価値付与済み時系列データ記録部205は、シミュレーション実行部110によるシミュレーション結果と、評価値算出部111による評価結果とを対応付けて記録する。 The time series data editing unit 109 edits time series data according to instructions input by the operator via the input/output device 106. The simulation execution unit 110 simulates the behavior of the plant based on the time series data edited by the time series data editing unit 109. The evaluation value calculation unit 111 evaluates the behavior of the plant simulated by the simulation execution unit 110. The feature quantity and evaluation value added time series data recording unit 205 records the simulation results by the simulation execution unit 110 and the evaluation results by the evaluation value calculation unit 111 in association with each other.
 <時系列データの編集からシミュレーション結果を評価して記録するまでの動作>
 図19は、運転支援装置が時系列データを編集してからシミュレーション結果を評価して記録するまでの動作を示すフローチャートである。
<Operations from editing time series data to evaluating and recording simulation results>
FIG. 19 is a flowchart showing the operation of the driving support device from editing time series data to evaluating and recording simulation results.
 ステップS41において、運転支援情報作成部103は、特徴量および評価値付与済み時系列データ記録部205に記録されたデータに基づいて運転支援情報を作成する。そして、入出力装置106は、運転支援情報を表示する。 In step S41, the driving support information creation unit 103 creates driving support information based on the data recorded in the feature amount and evaluation value added time series data recording unit 205. The input/output device 106 then displays driving support information.
 ステップS42において、オペレータは、入出力装置106に表示された過去のプラント運転に関する時系列データ、およびシミュレーション実行部110が生成した時系列データの一部の値を、入出力装置106を用いて編集する。 In step S42, the operator uses the input/output device 106 to edit the time-series data related to past plant operations displayed on the input/output device 106 and some values of the time-series data generated by the simulation execution unit 110. do.
 ステップS43において、シミュレーション実行部110は、時系列データ編集部109で編集された時系列データに基づいてシミュレーションを実行する。 In step S43, the simulation execution unit 110 executes a simulation based on the time series data edited by the time series data editing unit 109.
 ステップS44において、評価値算出部111は、シミュレーション結果の評価を実施する。 In step S44, the evaluation value calculation unit 111 evaluates the simulation results.
 ステップS45において、評価を付与したシミュレーション結果を特徴量および評価値付与済み時系列データ記録部205に記録し、以降の検索処理での検索対象に追加する。 In step S45, the evaluated simulation results are recorded in the feature amount and evaluation value added time series data recording unit 205, and added to the search target in the subsequent search process.
 <時系列データの編集>
 図20は、入出力装置106を介してオペレータが入力した指示に従って、時系列データ編集部109が時系列データを編集する際に、入出力装置106に表示される画面の一例を示す図である。
<Editing time series data>
FIG. 20 is a diagram showing an example of a screen displayed on the input/output device 106 when the time-series data editing unit 109 edits time-series data according to instructions input by the operator via the input/output device 106. .
 オペレータは、シミュレーション入力作成ボタン801を押下した後に、トレンドグラフ802において編集したい時系列データの値を選択する。例えば、「計測値1」の時系列データ803を選択し、GUI(Graphical User Interface)操作によって「計測値1」のシミュレーション用時系列データ804を作成する。そして、シミュレーション実行ボタン805を押下すると、シミュレーション実行部110でシミュレーションが実行される。 After pressing the simulation input creation button 801, the operator selects the value of the time series data to be edited in the trend graph 802. For example, time series data 803 of "measurement value 1" is selected, and simulation time series data 804 of "measurement value 1" is created by GUI (Graphical User Interface) operation. Then, when the simulation execution button 805 is pressed, the simulation execution unit 110 executes the simulation.
 シミュレーション実行部110は、計測値が編集されている場合は編集後の時系列データを用い、計測値が編集されていない場合は編集前の計測値の時系列データを用いてシミュレーションを実行する。 The simulation execution unit 110 executes the simulation using the edited time series data when the measurement value has been edited, and using the time series data of the measurement value before editing when the measurement value has not been edited.
 <シミュレーションの実行結果と評価値>
 図21は、シミュレーション実行部110によるシミュレーションの実行結果と、評価値算出部111が算出した評価値とを入出力装置106の画面に表示する一例を示す図である。
<Simulation execution results and evaluation values>
FIG. 21 is a diagram showing an example of displaying the simulation execution result by the simulation execution unit 110 and the evaluation value calculated by the evaluation value calculation unit 111 on the screen of the input/output device 106.
 評価結果一覧900は、選択901、日時902、シナリオ903、および評価値904で構成されている。トレンドグラフ910には、計測値と、各シナリオ903のシミュレーション結果が表示される。 The evaluation result list 900 is composed of selections 901, dates and times 902, scenarios 903, and evaluation values 904. The trend graph 910 displays measured values and simulation results for each scenario 903.
 オペレータは、トレンドグラフ910および評価値を確認し、検索対象に加えたいシナリオを選択901で選択する。図21の例では、シナリオ903である「シミュレーション1」が選択されており、検索対象に追加ボタン905を押下すると「シミュレーション1」が検索対象に加わる。 The operator checks the trend graph 910 and the evaluation values, and selects a scenario to be added to the search target using the selection 901. In the example of FIG. 21, "Simulation 1" which is the scenario 903 is selected, and when the Add to Search Objects button 905 is pressed, "Simulation 1" is added to the search objects.
 図22は、特徴量および評価値付与済み時系列データ記録部205の模式図である。計測値は計測値1001の列に記録され、計測値の評価値は評価値1002の列に記録され、「シミュレーション1」の計測値はシミュレーション計測値1003の列に記録され、「シミュレーション1」の計測値の評価値はシミュレーション評価値1004の列に記録されている。シミュレーションシナリオが増えた場合は、最後尾列に追加される。 FIG. 22 is a schematic diagram of the time-series data recording unit 205 with feature amounts and evaluation values added. The measured value is recorded in the column of measurement value 1001, the evaluation value of the measurement value is recorded in the column of evaluation value 1002, the measurement value of "Simulation 1" is recorded in the column of simulation measurement value 1003, and the evaluation value of the measurement value is recorded in the column of simulation measurement value 1003. The evaluation values of the measured values are recorded in the column of simulation evaluation values 1004. If the number of simulation scenarios increases, they will be added to the last column.
 計測値およびシミュレーションの計測値に対するそれぞれの評価値は、シミュレーションおよび評価を行う期間の最終時刻に記録される。例えば、計測値の評価値は、セル1005に記録される。また、「シミュレーション1」の計測値の評価値は、セル1006に記録される。 The respective evaluation values for the measured values and simulation measured values are recorded at the final time of the period in which the simulation and evaluation are performed. For example, the evaluation value of the measurement value is recorded in cell 1005. Furthermore, the evaluation value of the measurement value of "Simulation 1" is recorded in the cell 1006.
 <効果>
 実施の形態3による運転支援装置は、時系列データ編集部109、シミュレーション実行部110、評価値算出部111、および特徴量および評価値付与済み時系列データ記録部205を備えている。時系列データ編集部109は、入出力装置106を介してオペレータが入力した指示に従って時系列データを編集する。シミュレーション実行部110は、時系列データ編集部109が編集した時系列データに基づいてシミュレーションを実行する。評価値算出部111は、シミュレーション実行部110が実行したシミュレーションの結果を評価する。特徴量および評価値付与済み時系列データ記録部205は、シミュレーション実行部110によるシミュレーション結果と、評価値算出部111による評価結果とを対応付けて記録する。これにより、過去のプラントの運転履歴にない運転方法を検索結果として表示することができる。
<Effect>
The driving support device according to the third embodiment includes a time series data editing section 109, a simulation execution section 110, an evaluation value calculation section 111, and a time series data recording section 205 with feature amounts and evaluation values added. The time series data editing unit 109 edits time series data according to instructions input by the operator via the input/output device 106. The simulation execution unit 110 executes a simulation based on the time series data edited by the time series data editing unit 109. The evaluation value calculation unit 111 evaluates the results of the simulation executed by the simulation execution unit 110. The feature quantity and evaluation value added time series data recording unit 205 records the simulation results by the simulation execution unit 110 and the evaluation results by the evaluation value calculation unit 111 in association with each other. Thereby, an operating method that is not found in the past operation history of the plant can be displayed as a search result.
 <実施の形態4>
 実施の形態2では、検索ロジック記録部に記録された検索ロジックをスケジューリング部に記録されたスケジュールで実行することによって、自動で新たな運転支援情報を表示する方法について説明した。実施の形態2で説明した方法では、監視制御装置が収集した過去のプラントの運転履歴は検索結果として表示されるが、過去のプラントの運転履歴にない運転方法は検索結果として表示されない。実施の形態4は、このような課題を解決するためになされたものである。
<Embodiment 4>
In the second embodiment, a method has been described in which new driving support information is automatically displayed by executing the search logic recorded in the search logic recording unit according to the schedule recorded in the scheduling unit. In the method described in Embodiment 2, the past plant operation history collected by the supervisory control device is displayed as a search result, but the operation method that is not included in the past plant operation history is not displayed as a search result. Embodiment 4 is designed to solve this problem.
 図23は、実施の形態4による運転支援装置の構成の一例を示すブロック図である。 FIG. 23 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 4.
 図23に示すように、実施の形態4による運転支援装置は、実施の形態2による運転支援装置(図13参照)に対して、時系列データ編集部109、シミュレーション実行部110、および評価値算出部111をさらに備え、特徴量付与済み時系列データ記録部203に代えて特徴量および評価値付与済み時系列データ記録部205を備えている。すなわち、実施の形態4による運転支援装置の構成および動作は、実施の形態2による運転支援装置(図13参照)と、実施の形態3による運転支援装置(図18参照)とを組み合わせたものである。 As shown in FIG. 23, the driving support device according to the fourth embodiment has a time series data editing unit 109, a simulation execution unit 110, and an evaluation value calculation unit, in contrast to the driving support device according to the second embodiment (see FIG. 13). 111 , and a feature amount and evaluation value added time series data recording unit 205 in place of the feature value added time series data recording unit 203 . That is, the configuration and operation of the driving support device according to Embodiment 4 is a combination of the driving support device according to Embodiment 2 (see FIG. 13) and the driving support device according to Embodiment 3 (see FIG. 18). be.
 実施の形態4によれば、自動で新たな運転支援情報をオペレータに提示し、オペレータが意図する運転支援情報をオペレータが意図するタイミングで提示し、過去のプラントの運転履歴にない運転方法を検索結果として表示することができる。 According to the fourth embodiment, new operation support information is automatically presented to the operator, the operation support information intended by the operator is presented at the timing the operator intends, and an operation method not found in the past operation history of the plant is searched. It can be displayed as a result.
 <実施の形態5>
 実施の形態1では、オペレータが運転支援情報を参照しながら監視制御装置が収集していない情報を入力し、即座に適切な運転支援情報を検索して表示する方法について説明した。実施の形態1で説明した方法では、検索結果として記録されたデータの期間を絞り込んで表示することはできるが、時系列名を絞り込んで表示することができないという課題があった。実施の形態5は、このような課題を解決するためになされたものである。
<Embodiment 5>
In the first embodiment, a method has been described in which the operator inputs information not collected by the monitoring and control device while referring to the driving support information, and immediately searches for and displays appropriate driving support information. In the method described in Embodiment 1, although it is possible to narrow down and display the period of data recorded as a search result, there is a problem in that it is not possible to narrow down and display the time series name. Embodiment 5 is designed to solve this problem.
 図24は、実施の形態5による運転支援装置の構成の一例を示すブロック図である。 FIG. 24 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 5.
 図24に示すように、実施の形態5による運転支援装置は、実施の形態1による運転支援装置(図2参照)に対して、時系列データグループ記録部206をさらに備えている。時系列データグループ記録部206は、時系列データをグループごとに記録する。 As shown in FIG. 24, the driving support device according to the fifth embodiment is different from the driving support device according to the first embodiment (see FIG. 2) in that it further includes a time-series data group recording unit 206. The time series data group recording unit 206 records time series data for each group.
 図25は、入出力装置106に表示される画面の一例を示す図である。時系列データ選択1100には、時系列データグループ選択1101が設けられている。時系列データグループ選択1101から任意のグループを選択すると、選択したグループを構成する時系列データ1102が表示される。 FIG. 25 is a diagram showing an example of a screen displayed on the input/output device 106. The time series data selection 1100 is provided with a time series data group selection 1101. When an arbitrary group is selected from the time series data group selection 1101, time series data 1102 forming the selected group is displayed.
 図26は、時系列データグループ記録部206の模式図である。時系列データグループ記録部206には、グループID1201ごとに、グループを構成する時系列名1202が記録されている。 FIG. 26 is a schematic diagram of the time-series data group recording unit 206. The time series data group recording unit 206 records, for each group ID 1201, the time series names 1202 that constitute the group.
 実施の形態5による運転支援装置は、時系列データグループ記録部206を備えている。これにより、運転支援情報を構成する時系列データの数を絞り込んで表示することができる。 The driving support device according to the fifth embodiment includes a time-series data group recording section 206. Thereby, it is possible to narrow down and display the number of time series data forming the driving support information.
 <実施の形態6>
 実施の形態5では、オペレータが運転支援情報を参照しながら監視制御装置が収集していない情報を入力し、即座に適切な運転支援情報を検索して表示する方法に関して、期間および時系列名を絞り込んで表示する方法について説明した。実施の形態5で説明した方法では、予め時系列データのグループを定義して時系列データグループ記録部206に記録する必要があるため、手間がかかるという課題があった。実施の形態6は、このような課題を解決するためになされたものである。
<Embodiment 6>
Embodiment 5 describes a method in which an operator inputs information not collected by the monitoring and control device while referring to driving support information, and immediately searches for and displays appropriate driving support information by specifying the period and time series name. We explained how to filter and display results. The method described in Embodiment 5 has the problem that it is time-consuming because it is necessary to define groups of time-series data in advance and record them in the time-series data group recording unit 206. Embodiment 6 is designed to solve this problem.
 <構成>
 図27は、実施の形態6による運転支援装置の構成の一例を示すブロック図である。
<Configuration>
FIG. 27 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 6.
 図27に示すように、実施の形態6による運転支援装置は、実施の形態5による運転支援装置(図24参照)に対して、検索時系列グループID記録部207、回数確率記録部208、および時系列データグループ推定部112をさらに備えている。 As shown in FIG. 27, the driving support device according to the sixth embodiment has a search time series group ID recording unit 207, a frequency probability recording unit 208, and It further includes a time series data group estimation section 112.
 図28は、入出力装置106に表示される画面の一例を示す図である。検索条件入力1320において任意の計測値および特徴量を組み合わせた検索条件1321を入力して検索した場合、時系列データ選択1300においてトレンドグラフ1310に表示する時系列データの組み合わせ1301を選択する。 FIG. 28 is a diagram showing an example of a screen displayed on the input/output device 106. When a search condition 1321 that is a combination of arbitrary measurement values and feature amounts is input in the search condition input 1320 and a search is performed, a time series data combination 1301 to be displayed on the trend graph 1310 is selected in the time series data selection 1300.
 図29は、検索時系列グループID記録部207の模式図である。検索時系列グループID記録部207は、検索時系列グループID1401と、検索時系列1402とで構成されている。 FIG. 29 is a schematic diagram of the search time series group ID recording unit 207. The search time series group ID recording unit 207 includes a search time series group ID 1401 and a search time series 1402.
 検索時系列1402には、図28の検索条件入力1320において、時系列名として入力された計測値と特徴量との組み合わせ(検索条件1321)が記録される。検索時系列グループID1401には、図28の検索ボタン1322が押下されて検索が実行されたときに、検索条件1321として新たな時系列名の組み合わせが入力されるたびに固有のIDが採番される。 In the search time series 1402, a combination (search condition 1321) of a measurement value and a feature quantity input as a time series name in the search condition input 1320 of FIG. 28 is recorded. A unique ID is assigned to the search time series group ID 1401 each time a new combination of time series names is input as the search condition 1321 when the search button 1322 in FIG. 28 is pressed to execute a search. Ru.
 図30は、回数確率記録部208の模式図である。回数確率記録部208は、検索時系列グループIDごとに表示回数および表示確率のテーブルを有する。図30の例は、検索時系列グループIDが「ST1」のテーブルを示している。図30に示すテーブルは、特徴量付与済み時系列データ記録部203に記録されている時系列名を行および列のそれぞれの項目として有するテーブルである。 FIG. 30 is a schematic diagram of the frequency probability recording unit 208. The frequency probability recording unit 208 has a table of display frequencies and display probabilities for each search time series group ID. The example in FIG. 30 shows a table with the search time series group ID "ST1". The table shown in FIG. 30 is a table that has time series names recorded in the feature value added time series data recording unit 203 as items in each row and column.
 例えば、「計測値2」および「計測値1」に関して、「計測値2」が表示選択(図28の時系列データ選択1300で選択)されたときに「計測値1」が表示選択された回数1501と、「計測値2」が表示選択されたときに「計測値1」が表示選択される条件付き確率1502とが記録される。回数1501は「f(計測値1|計測値2)」から求められ、条件付き確率1502は「p(計測値1|計測値2)」から求められる。 For example, regarding "measurement value 2" and "measurement value 1," the number of times "measurement value 1" was selected for display when "measurement value 2" was selected for display (selected in time series data selection 1300 in FIG. 28) 1501 and a conditional probability 1502 that "measurement value 1" is selected for display when "measurement value 2" is selected for display are recorded. The number of times 1501 is obtained from "f (measured value 1 | measured value 2)", and the conditional probability 1502 is obtained from "p (measured value 1 | measured value 2)".
 時系列データグループ推定部112は、検索条件が入力されて検索が実行されるたびに、検索時系列グループID記録部207の検索時系列1402を参照し、一致する検索時系列グループID1401を検索する。一致する検索時系列グループIDがない場合は、初回の入力であるため検索条件と紐づいた検索時系列グループは選択されない。一方、一致する検索時系列グループIDがある場合は、検索時系列1402の組の各時系列データを条件とする表示確率が記録されたセルを参照し、事前に定めた閾値を上回る条件付き確率を持つセルに記録された時系列データの集合を時系列データグループとして時系列データグループID記録部206に記録する。 The time series data group estimating unit 112 refers to the search time series 1402 in the search time series group ID recording unit 207 and searches for a matching search time series group ID 1401 every time a search condition is input and a search is executed. . If there is no matching search time series group ID, the search time series group associated with the search condition will not be selected because this is the first input. On the other hand, if there is a matching search time series group ID, refer to the cell in which the display probability conditional on each time series data of the set of search time series 1402 is recorded, and check the conditional probability that the display probability exceeds the predetermined threshold. A set of time-series data recorded in a cell with a time-series data group is recorded in the time-series data group ID recording unit 206 as a time-series data group.
 <動作>
 図31,32は、検索条件を入力してから時系列データグループを推定して入出力装置106に表示するまでの動作を示すフローチャートである。
<Operation>
31 and 32 are flowcharts showing operations from inputting a search condition to estimating a time series data group and displaying it on the input/output device 106.
 ステップS51において、入出力装置106は、オペレータが入力した検索条件を受け付ける。 In step S51, the input/output device 106 receives search conditions input by the operator.
 ステップS52において、検索条件として入力された検索時系列の組が検索時系列グループID記録部207に存在するか否かを判断する。検索時系列の組が検索時系列グループID記録部207に存在する場合は、ステップS53に移行する。一方、検索時系列の組が検索時系列グループID記録部207に存在しない場合は、ステップS55に移行する。 In step S52, it is determined whether the set of search time series input as the search condition exists in the search time series group ID recording unit 207. If the set of search time series exists in the search time series group ID recording unit 207, the process moves to step S53. On the other hand, if the set of search time series does not exist in the search time series group ID recording unit 207, the process moves to step S55.
 ステップS53において、時系列データグループ推定部112は、回数確率記録部208に記録された当該検索時系列IDのテーブルから、検索時系列の組の各時系列を条件とする表示確率が記録されたセルを参照し、事前に定めた閾値を上回る条件付き確率を持つセルに記録された時系列の集合を時系列データグループとして時系列データグループ記録部206に記録する。 In step S53, the time series data group estimating unit 112 records the display probability conditional on each time series of the set of search time series from the table of the search time series ID recorded in the frequency probability recording unit 208. With reference to the cells, a set of time series recorded in cells having a conditional probability exceeding a predetermined threshold is recorded as a time series data group in the time series data group recording unit 206.
 ステップS54において、入出力装置は、オペレータが検索する際に、時系列データが時系列データグループとして表示される。 In step S54, the input/output device displays the time series data as a time series data group when the operator searches.
 ステップS55において、検索時系列グループID記録部207は、検索時系列IDを新たに採番し、検索条件として入力された検索時系列の組を登録する。 In step S55, the search time series group ID recording unit 207 assigns a new number to the search time series ID and registers the set of search time series input as the search condition.
 ステップS56において、時系列データグループ推定部112は、時系列データグループを推定しない。 In step S56, the time series data group estimation unit 112 does not estimate the time series data group.
 図33は、オペレータが入出力装置106を操作したときに回数確率記録部208を更新する動作を示すフローチャートである。 FIG. 33 is a flowchart showing the operation of updating the frequency probability recording unit 208 when the operator operates the input/output device 106.
 ステップS61において、入出力装置106は、オペレータが入力した検索条件を受け付ける。 In step S61, the input/output device 106 receives search conditions input by the operator.
 ステップS62において、入出力装置106は、検索結果を表示する。 In step S62, the input/output device 106 displays the search results.
 ステップS63において、回数確率記録部208は、時系列データ選択に表示する時系列データが追加されたタイミングで、既に表示選択されていた各時系列データに対して、各時系列データを条件とし、新たに表示選択された時系列を結果とする表示選択回数のカウントを更新する。 In step S63, the frequency probability recording unit 208 sets each time series data as a condition for each time series data that has already been selected for display at the timing when the time series data to be displayed in the time series data selection is added, Updates the count of the number of display selections for which the newly selected time series is the result.
 ステップS64において、回数確率記録部208は、計算式pに従って、時系列iが表示選択されたときに時系列jが表示される確率を更新する。ここで、計算式pは、下記の式(1)で表される。 In step S64, the frequency probability recording unit 208 updates the probability that time series j will be displayed when time series i is selected for display, according to calculation formula p. Here, the calculation formula p is expressed by the following formula (1).
Figure JPOXMLDOC01-appb-M000001
Figure JPOXMLDOC01-appb-M000001
 <効果>
 実施の形態6による運転支援装置は、検索時系列グループID記録部207、回数確率記録部208、および時系列データグループ推定部112を備える。時系列データグループ推定部112は、入出力装置106に対するオペレータの操作履歴に基づいて、時系列データグループを推定する。これにより、予め時系列データグループを定義しておかなくても、運転支援情報を構成する時系列データの数を絞り込んで表示することができる。
<Effect>
The driving support device according to the sixth embodiment includes a search time series group ID recording section 207, a frequency probability recording section 208, and a time series data group estimating section 112. The time-series data group estimating unit 112 estimates a time-series data group based on the operator's operation history on the input/output device 106. This makes it possible to narrow down and display the number of time-series data that constitutes driving support information, without having to define time-series data groups in advance.
 <実施の形態7>
 実施の形態6では、オペレータが運転支援情報を参照しながら監視制御装置が収集していない情報を入力し、即座に適切な運転支援情報を検索して表示し、入出力装置に対するオペレータの操作履歴に基づいて時系列データグループを推定することによって予め時系列データグループを定義しておかなくても運転支援情報の期間を絞り込んで表示する方法について説明した。実施の形態6で説明した方法では、オペレータが検索条件を入力したときのみに新たな運転支援情報が表示されるが、オペレータが検索条件を入力しない場合は新たな運転支援情報は表示されない。実施の形態7は、このような課題を解決するためになされたものである。
<Embodiment 7>
In the sixth embodiment, the operator inputs information not collected by the monitoring and control device while referring to the driving support information, immediately searches for and displays appropriate driving support information, and records the operator's operation history for the input/output device. We have described a method for narrowing down and displaying the period of driving support information without having to define the time series data group in advance by estimating the time series data group based on the time series data group. In the method described in Embodiment 6, new driving support information is displayed only when the operator inputs search conditions, but new driving support information is not displayed when the operator does not input search conditions. Embodiment 7 is designed to solve this problem.
 図34は、実施の形態7による運転支援装置の構成の一例を示すブロック図である。 FIG. 34 is a block diagram showing an example of the configuration of a driving support device according to Embodiment 7.
 図34に示すように、実施の形態7による運転支援装置は、実施の形態6による運転支援装置(図27参照)に対して、スケジューリング部107、更新部108、および検索ロジック記録部204をさらに備えている。すなわち、実施の形態7による運転支援装置の構成および動作は、実施の形態6による運転支援装置(図27参照)と、実施の形態2による運転支援装置(図13参照)とを組み合わせたものである。 As shown in FIG. 34, the driving support device according to the seventh embodiment has a scheduling section 107, an updating section 108, and a search logic recording section 204 in addition to the driving support device according to the sixth embodiment (see FIG. 27). We are prepared. That is, the configuration and operation of the driving support device according to Embodiment 7 is a combination of the driving support device according to Embodiment 6 (see FIG. 27) and the driving support device according to Embodiment 2 (see FIG. 13). be.
 実施の形態7によれば、自動で新たな運転支援情報をオペレータに提示し、オペレータが意図する運転支援情報をオペレータが意図するタイミングで提示し、予め時系列データグループを定義しておかなくても運転支援情報を構成する時系列データの数を絞り込んで表示することができる。 According to the seventh embodiment, new driving support information is automatically presented to the operator, driving support information intended by the operator is presented at the timing intended by the operator, and time-series data groups are not defined in advance. It is also possible to narrow down and display the number of time series data that make up the driving support information.
 <ハードウェア構成>
 実施の形態1で説明した運転支援装置における特徴量演算部101、検索部102、運転支援情報作成部103、および特徴量付与部104の各機能は、処理回路により実現される。すなわち、運転支援装置は、時系列データ記録部201に記録された時系列データから特徴量を演算し、オペレータが入力した検索条件に基づいて時系列データを検索し、検索結果に基づいて運転支援情報を作成し、オペレータが入力した特徴量の情報を特徴量付与済み時系列データ記録部203に記録するための処理回路を備える。処理回路は、専用のハードウェアであってもよく、メモリに格納されるプログラムを実行するプロセッサ(CPU、中央処理装置、処理装置、演算装置、マイクロプロセッサ、マイクロコンピュータ、DSP(Digital Signal Processor)ともいう)であってもよい。
<Hardware configuration>
Each of the functions of the feature calculation unit 101, the search unit 102, the driving support information creation unit 103, and the feature addition unit 104 in the driving support device described in the first embodiment is realized by a processing circuit. That is, the driving support device calculates feature amounts from the time series data recorded in the time series data recording unit 201, searches the time series data based on search conditions input by the operator, and performs driving support based on the search results. It is provided with a processing circuit for creating information and recording information on feature quantities input by an operator in the feature quantity added time series data recording unit 203. The processing circuit may be dedicated hardware, and may be a processor (CPU, central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, DSP (Digital Signal Processor)) that executes a program stored in memory. ).
 処理回路が専用のハードウェアである場合、図35に示すように、処理回路1600は、例えば、単一回路、複合回路、プログラム化したプロセッサ、並列プログラム化したプロセッサ、ASIC(Application Specific Integrated Circuit)、FPGA(Field Programmable Gate Array)、またはこれらを組み合わせたものが該当する。特徴量演算部101、検索部102、運転支援情報作成部103、および特徴量付与部104の各機能をそれぞれ処理回路1600で実現してもよく、各機能をまとめて1つの処理回路1600で実現してもよい。 When the processing circuit is dedicated hardware, as shown in FIG. 35, the processing circuit 1600 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, or an ASIC (Application Specific Integrated Circuit). , FPGA (Field Programmable Gate Array), or a combination of these. Each of the functions of the feature calculation unit 101, the search unit 102, the driving support information creation unit 103, and the feature addition unit 104 may be realized by the processing circuit 1600, or each function may be realized by a single processing circuit 1600. You may.
 処理回路1600が図36に示すプロセッサ1610である場合、特徴量演算部101、検索部102、運転支援情報作成部103、および特徴量付与部104の各機能は、ソフトウェア、ファームウェア、またはソフトウェアとファームウェアとの組み合わせにより実現される。ソフトウェアまたはファームウェアは、プログラムとして記述され、メモリ1620に格納される。プロセッサ1610は、メモリ1620に記録されたプログラムを読み出して実行することにより、各機能を実現する。すなわち、運転支援装置は、時系列データ記録部201に記録された時系列データから特徴量を演算するステップ、オペレータが入力した検索条件に基づいて時系列データを検索するステップ、検索結果に基づいて運転支援情報を作成するステップ、オペレータが入力した特徴量の情報を特徴量付与済み時系列データ記録部203に記録するステップが結果的に実行されることになるプログラムを格納するためのメモリ1620を備える。また、これらのプログラムは、特徴量演算部101、検索部102、運転支援情報作成部103、および特徴量付与部104の手順または方法をコンピュータに実行させるものであるともいえる。ここで、メモリとは、例えば、RAM(Random Access Memory)、ROM(Read Only Memory)、フラッシュメモリ、EPROM(Erasable Programmable Read Only Memory)、EEPROM(Electrically Erasable Programmable Read Only Memory)等の不揮発性または揮発性の半導体メモリ、磁気ディスク、フレキシブルディスク、光ディスク、コンパクトディスク、DVD(Digital Versatile Disc)等、または、今後使用されるあらゆる記憶媒体であってもよい。 When the processing circuit 1600 is the processor 1610 shown in FIG. 36, each function of the feature calculation section 101, the search section 102, the driving support information creation section 103, and the feature amount adding section 104 can be implemented using software, firmware, or software and firmware. This is realized by a combination of Software or firmware is written as a program and stored in memory 1620. Processor 1610 implements each function by reading and executing programs recorded in memory 1620. That is, the driving support device performs the following steps: calculating a feature amount from the time series data recorded in the time series data recording unit 201, searching the time series data based on the search conditions input by the operator, and searching the time series data based on the search results. A memory 1620 is provided to store a program that will result in the steps of creating driving support information and recording feature information input by the operator in the feature-added time series data recording unit 203. Be prepared. It can also be said that these programs cause the computer to execute the procedures or methods of the feature amount calculating section 101, the search section 102, the driving support information creation section 103, and the feature amount adding section 104. Here, memory refers to nonvolatile or volatile memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), and EEPROM (Electrically Erasable Programmable Read Only Memory). The storage medium may be a flexible semiconductor memory, a magnetic disk, a flexible disk, an optical disk, a compact disk, a DVD (Digital Versatile Disc), or any storage medium that will be used in the future.
 なお、特徴量演算部101、検索部102、運転支援情報作成部103、および特徴量付与部104の各機能について、一部の機能を専用のハードウェアで実現し、他の機能をソフトウェアまたはファームウェアで実現するようにしてもよい。 Note that some of the functions of the feature calculation unit 101, search unit 102, driving support information creation unit 103, and feature addition unit 104 are realized by dedicated hardware, and other functions are implemented by software or firmware. It may be realized by
 このように、処理回路は、ハードウェア、ソフトウェア、ファームウェア、またはこれらの組み合わせによって、上述の各機能を実現することができる。 In this way, the processing circuit can realize each of the above functions using hardware, software, firmware, or a combination thereof.
 上記では、図2に示す運転支援装置のハードウェア構成について説明したが、図13,18,23,24,27,34に示す運転支援装置のハードウェア構成についても同様である。 Although the hardware configuration of the driving support device shown in FIG. 2 has been described above, the same applies to the hardware configuration of the driving support device shown in FIGS.
 <運転支援システム>
 図37は、運転支援システムの構成を示すブロック図である。運転支援システムは、サーバ1700および端末装置1710で構成される。サーバ1700は、クラウド上に設置されたサーバである。端末装置1710は、オペレータがいる場所に設けられた装置である。サーバ1700と端末装置1710とは、通信可能に接続されている。
<Driving support system>
FIG. 37 is a block diagram showing the configuration of the driving support system. The driving support system includes a server 1700 and a terminal device 1710. Server 1700 is a server installed on the cloud. Terminal device 1710 is a device provided at a location where an operator is present. Server 1700 and terminal device 1710 are communicably connected.
 サーバ1700は、監視制御装置105と、時系列データ記録部201と、特徴量演算ロジック記録部202と、特徴量演算部101と、特徴量付与済み時系列データ記録部203と、特徴量付与部104とを備えている。また、端末装置1710は、検索部102と、運転支援情報作成部103と、入出力装置106とを備えている。サーバ1700および端末装置1710のそれぞれが備える各構成要素は、実施の形態1による運転支援装置(図2参照)の各構成要素と同じである。 The server 1700 includes a monitoring control device 105, a time-series data recording section 201, a feature calculation logic recording section 202, a feature calculation section 101, a feature-added time-series data recording section 203, and a feature addition section. 104. Further, the terminal device 1710 includes a search section 102, a driving support information creation section 103, and an input/output device 106. Each component included in server 1700 and terminal device 1710 is the same as each component in the driving support device according to the first embodiment (see FIG. 2).
 なお、図37では、実施の形態1による運転支援装置の各構成要素をサーバ1700および端末装置1710のそれぞれに分散して配置する構成を示しているが、運転支援システムの構成は、これに限るものではない。運転支援システムは、図13,18,23,24,27,34に示す運転支援装置の各構成要素をサーバ1700および端末装置1710のそれぞれに分散して配置する構成であってもよい。 Note that although FIG. 37 shows a configuration in which each component of the driving support device according to the first embodiment is distributed and arranged in the server 1700 and the terminal device 1710, the configuration of the driving support system is limited to this. It's not a thing. The driving support system may have a configuration in which each component of the driving support device shown in FIGS.
 なお、本開示の範囲内において、各実施の形態を自由に組み合わせたり、各実施の形態を適宜、変形、省略したりすることが可能である。 Note that within the scope of the present disclosure, it is possible to freely combine the embodiments, or to modify or omit each embodiment as appropriate.
 本開示は詳細に説明されたが、上記した説明は、すべての態様において、例示であって、限定的なものではない。例示されていない無数の変形例が想定され得るものと解される。 Although the present disclosure has been described in detail, the above description in all aspects is illustrative and not restrictive. It is understood that countless variations not illustrated may be envisioned.
 101 特徴量演算部、102 検索部、103 運転支援情報作成部、104 特徴量付与部、105 監視制御装置、106 入出力装置、107 スケジューリング部、108 更新部、109 時系列データ編集部、110 シミュレーション実行部、111 評価値算出部、112 時系列データグループ推定部、201 時系列データ記録部、202 特徴量演算ロジック記録部、203 特徴量付与済み時系列データ記録部、204 検索ロジック記録部、205 特徴量および評価値付与済み時系列データ記録部、206 時系列データグループ記録部、207 検索時系列グループID記録部、208 回数確率記録部、301 特徴量時系列名、302 特徴量時系列の単位、303 演算に用いる特徴量の種別、304 元時系列、305 元時系列の単位、306 特徴量の種別、307 計算式、400 検索条件入力、401 時系列名、402 検索種別、403 対象時刻、404 条件、405 検索条件、406 検索条件、407 検索条件、408 検索条件、410 検索結果一覧、411 選択、412 ランキング、413 検索結果、414 検索結果、415 検索結果、420 時系列データ選択、430 トレンドグラフ、431 期間選択バー、432 特徴量名、433 値、440 検索ボタン、450 特徴量追加ボタン、451 選択ウィンドウ、460 カレンダー、461 期間単位選択ボタン、462 <ボタン、463 >ボタン、464 今日ボタン、465 期間選択バー、466 特徴量名、467 値、500 日時の列、501 区分、502 区分、510 計測値2の列、520 特徴量1の列、530 最後尾列、600 検索ロジックID、610 検索条件、611 時系列名、612 検索種別、613 対象時刻、614 第1条件、615 第2条件、616 時系列名、617 検索種別、618 対象時刻、619 第1条件、620 第2条件、701 検索ロジックID、702 開始日時、703 終了日時、704 周期、801 シミュレーション入力作成ボタン、802 トレンドグラフ、803 時系列データ、804 シミュレーション用時系列データ、805 シミュレーション実行ボタン、900 評価結果一覧、901 選択、902 日時、903 シナリオ、904 評価値、905 検索対象に追加ボタン、910 トレンドグラフ、1001 計測値、1002 評価値、1003 シミュレーション計測値、1004 シミュレーション評価値、1005 セル、1006 セル、1100 時系列データ選択、1101 時系列データグループ選択、1102 時系列データ、1201 グループID、1202 時系列名、1300 時系列データ選択、1301 時系列データの組み合わせ、1310 トレンドグラフ、1320 検索条件入力、1321 検索条件、1322 検索ボタン、1401 検索時系列グループID、1402 検索時系列、1501 回数、1502 確率、1600 処理回路、1610 プロセッサ、1620 メモリ、1700 サーバ、1710 端末装置。 101 Feature calculation unit, 102 Search unit, 103 Driving support information creation unit, 104 Feature provision unit, 105 Monitoring control device, 106 Input/output device, 107 Scheduling unit, 108 Update unit, 109 Time series data editing unit, 110 Simulation Execution unit, 111 Evaluation value calculation unit, 112 Time series data group estimation unit, 201 Time series data recording unit, 202 Feature value calculation logic recording unit, 203 Feature value assigned time series data recording unit, 204 Search logic recording unit, 205 Feature value and evaluation value assigned time series data recording unit, 206 Time series data group recording unit, 207 Search time series group ID recording unit, 208 Number probability recording unit, 301 Feature value time series name, 302 Unit of feature value time series , 303 Type of feature used for calculation, 304 Source time series, 305 Unit of source time series, 306 Type of feature, 307 Calculation formula, 400 Search condition input, 401 Time series name, 402 Search type, 403 Target time, 404 Condition, 405 Search condition, 406 Search condition, 407 Search condition, 408 Search condition, 410 Search result list, 411 Selection, 412 Ranking, 413 Search result, 414 Search result, 415 Search result, 420 Time series data selection, 430 Trend Graph, 431 Period selection bar, 432 Feature name, 433 Value, 440 Search button, 450 Add feature button, 451 Selection window, 460 Calendar, 461 Period unit selection button, 462 < button, 463 > button, 464 Today button, 465 Period selection bar, 466 Feature name, 467 Value, 500 Date and time column, 501 Classification, 502 Classification, 510 Measurement value 2 column, 520 Feature value 1 column, 530 Last column, 600 Search logic ID, 610 Search Condition, 611 Time series name, 612 Search type, 613 Target time, 614 First condition, 615 Second condition, 616 Time series name, 617 Search type, 618 Target time, 619 First condition, 620 Second condition, 701 Search Logic ID, 702 Start date and time, 703 End date and time, 704 Cycle, 801 Simulation input creation button, 802 Trend graph, 803 Time series data, 804 Time series data for simulation, 805 Simulation execution button, 900 Evaluation result list, 901 Selection, 902 Date and time, 903 Scenario, 904 Evaluation value, 905 Add to search button, 910 Trend graph, 1001 Measurement value, 1002 Evaluation value, 1003 Simulation measurement value, 1004 Simulation evaluation value, 1005 Cell, 1006 Cell, 1100 Time series data selection, 1101 Time series data group selection, 1102 Time series data, 1201 Group ID, 1202 Time series name, 1300 Time series data selection, 1301 Time series data combination, 1310 Trend graph, 1320 Search condition input, 1321 Search condition, 1322 Search button , 1401 Search time series group ID, 1402 Search time series, 1501 Number of times, 1502 Probability, 1600 Processing circuit, 1610 Processor, 1620 Memory, 1700 Server, 1710 Terminal device.

Claims (10)

  1.  プラントを監視する監視制御装置が前記プラントから収集した監視制御データを時系列データとして記録する時系列データ記録部と、
     前記時系列データから特徴量を演算するための特徴量演算ロジックを記録する特徴量演算ロジック記録部と、
     前記特徴量演算ロジック記録部に記録された前記特徴量演算ロジックに基づいて、前記時系列データから前記特徴量を演算する特徴量演算部と、
     前記時系列データと、前記特徴量演算部が演算した前記特徴量である演算特徴量とを対応付けて記録する特徴量付与済み時系列データ記録部と、
     オペレータから入力された検索条件に基づいて、前記特徴量付与済み時系列データ記録部に記録された前記時系列データを区分し、区分した前記時系列データから前記検索条件との一致度が最も高い前記時系列データを検索する検索部と、
     前記検索部が検索した前記時系列データと、当該時系列データに対応付けられた前記演算特徴量とに基づいて、前記プラントの運転を支援する運転支援情報を作成する運転支援情報作成部と、
     前記時系列データに対して前記オペレータが入力した追加の特徴量である追加特徴量を、前記時系列データに対応付けて前記特徴量付与済み時系列データ記録部に記録する特徴量付与部と、
    を備え、
     前記運転支援情報作成部は、前記検索部が検索した前記時系列データと、当該時系列データに対応付けられた前記演算特徴量および前記追加特徴量とに基づいて前記運転支援情報を作成する、運転支援装置。
    a time-series data recording unit that records supervisory control data collected from the plant by a supervisory control device that monitors the plant as time-series data;
    a feature amount calculation logic recording unit that records feature amount calculation logic for calculating feature amounts from the time series data;
    a feature amount calculation unit that calculates the feature amount from the time series data based on the feature amount calculation logic recorded in the feature amount calculation logic recording unit;
    a feature amount added time series data recording unit that records the time series data in association with a calculated feature amount that is the feature amount calculated by the feature amount calculation unit;
    Based on the search conditions input by the operator, the time series data recorded in the feature value added time series data recording unit is divided, and the degree of match with the search conditions is highest among the divided time series data. a search unit that searches the time series data;
    an operation support information creation unit that creates operation support information that supports operation of the plant based on the time series data searched by the search unit and the calculated feature amount associated with the time series data;
    a feature amount adding unit that records an additional feature amount that is an additional feature amount input by the operator to the time series data in the feature amount added time series data recording unit in association with the time series data;
    Equipped with
    The driving support information creation unit creates the driving support information based on the time series data searched by the search unit, and the calculated feature amount and the additional feature amount associated with the time series data. Driving support equipment.
  2.  前記運転支援情報作成部が作成した前記運転支援情報を表示し、前記オペレータが入力した前記検索条件および前記追加特徴量を受け付ける入出力部をさらに備える、請求項1に記載の運転支援装置。 The driving support device according to claim 1, further comprising an input/output unit that displays the driving support information created by the driving support information creation unit and receives the search condition and the additional feature amount input by the operator.
  3.  前記検索部が前記検索するための検索ロジックを記録する検索ロジック記録部と、
     前記検索部が前記検索を実行するスケジュールを指定するスケジューリング部と、
    をさらに備え、
     前記検索部は、前記スケジューリング部が指定した前記スケジュールで、前記検索ロジック記録部が記録した前記検索ロジックに基づいて前記検索を実行する、請求項1に記載の運転支援装置。
    a search logic recording unit that records search logic for the search by the search unit;
    a scheduling unit that specifies a schedule for the search unit to execute the search;
    Furthermore,
    The driving support device according to claim 1, wherein the search unit executes the search based on the search logic recorded by the search logic recording unit in the schedule specified by the scheduling unit.
  4.  前記時系列データを編集する時系列データ編集部と、
     前記時系列データ編集部が編集した前記時系列データに基づいて、前記プラントの挙動をシミュレーションするシミュレーション実行部と、
     前記シミュレーション実行部がシミュレーションした前記プラントの挙動を評価する評価値算出部と、
     前記シミュレーション実行部によるシミュレーション結果と、前記評価値算出部による評価結果とを対応付けて記録する特徴量および評価値付与済み時系列データ記録部と、
    を備える、請求項1に記載の運転支援装置。
    a time series data editing unit that edits the time series data;
    a simulation execution unit that simulates the behavior of the plant based on the time series data edited by the time series data editing unit;
    an evaluation value calculation unit that evaluates the behavior of the plant simulated by the simulation execution unit;
    a feature amount and evaluation value assigned time series data recording unit that records simulation results by the simulation execution unit and evaluation results by the evaluation value calculation unit in association with each other;
    The driving assistance device according to claim 1, comprising:
  5.  前記時系列データを編集する時系列データ編集部と、
     前記時系列データ編集部が編集した前記時系列データに基づいて、前記プラントの挙動をシミュレーションするシミュレーション実行部と、
     前記シミュレーション実行部がシミュレーションした前記プラントの挙動を評価する評価値算出部と、
     前記シミュレーション実行部によるシミュレーション結果と、前記評価値算出部による評価結果とを対応付けて記録する特徴量および評価値付与済み時系列データ記録部と、
    を備える、請求項3に記載の運転支援装置。
    a time series data editing unit that edits the time series data;
    a simulation execution unit that simulates the behavior of the plant based on the time series data edited by the time series data editing unit;
    an evaluation value calculation unit that evaluates the behavior of the plant simulated by the simulation execution unit;
    a feature amount and evaluation value assigned time series data recording unit that records simulation results by the simulation execution unit and evaluation results by the evaluation value calculation unit in association with each other;
    The driving support device according to claim 3, comprising:.
  6.  前記時系列データをグループごとに記録する時系列データグループ記録部をさらに備える、請求項1に記載の運転支援装置。 The driving support device according to claim 1, further comprising a time-series data group recording unit that records the time-series data group by group.
  7.  前記検索条件として入力された前記時系列データのグループを、当該グループのIDに対応付けて記録する検索時系列グループID記録部と、
     前記グループのIDごとに、前記オペレータが前記運転支援情報から一の前記時系列データを選択した場合に他の前記時系列データが選択される回数と、前記オペレータが前記運転支援情報から一の前記時系列データを選択した場合に他の前記時系列データが選択される確率とを記録する回数確率記録部と、
     前記検索時系列グループID記録部に記録された前記グループおよび当該グループのIDと、前記回数確率記録部に記録された前記回数および前記確率とに基づいて、前記時系列データグループ記録部に記録すべき前記時系列データのグループを推定する時系列データグループ推定部と、
    を備える、請求項6に記載の運転支援装置。
    a search time series group ID recording unit that records a group of the time series data input as the search condition in association with an ID of the group;
    For each ID of the group, the number of times when the operator selects one of the time series data from the driving support information, the other time series data is selected, and the number of times the operator selects one of the time series data from the driving support information. a frequency probability recording unit that records the probability that other time series data will be selected when time series data is selected;
    Recording in the time series data group recording unit based on the group and the ID of the group recorded in the search time series group ID recording unit, and the number of times and the probability recorded in the number probability recording unit. a time series data group estimating unit that estimates the group of the time series data to be
    The driving assistance device according to claim 6, comprising:
  8.  前記検索部が前記検索するための検索ロジックを記録する検索ロジック記録部と、
     前記検索部が前記検索を実行するスケジュールを指定するスケジューリング部と、
    をさらに備え、
     前記検索部は、前記スケジューリング部が指定した前記スケジュールで、前記検索ロジック記録部が記録した前記検索ロジックに基づいて前記検索を実行する、請求項7に記載の運転支援装置。
    a search logic recording unit that records search logic for the search by the search unit;
    a scheduling unit that specifies a schedule for the search unit to execute the search;
    Furthermore,
    The driving support device according to claim 7, wherein the search unit executes the search based on the search logic recorded by the search logic recording unit in the schedule specified by the scheduling unit.
  9.  サーバと、前記オペレータがいる場所に設けられた端末装置とを備える運転支援システムであって、
     前記サーバは、
     プラントを監視する監視制御装置が前記プラントから収集した監視制御データを時系列データとして記録する時系列データ記録部と、
     前記時系列データから特徴量を演算するための特徴量演算ロジックを記録する特徴量演算ロジック記録部と、
     前記特徴量演算ロジック記録部に記録された前記特徴量演算ロジックに基づいて、前記時系列データから前記特徴量を演算する特徴量演算部と、
     前記時系列データと、前記特徴量演算部が演算した前記特徴量である演算特徴量とを対応付けて記録する特徴量付与済み時系列データ記録部と、
     前記時系列データに対して前記オペレータが入力した追加の特徴量である追加特徴量を、前記時系列データに対応付けて前記特徴量付与済み時系列データ記録部に記録する特徴量付与部と、
    を有し、
     前記端末装置は、
     オペレータから入力された検索条件に基づいて、前記特徴量付与済み時系列データ記録部に記録された前記時系列データを区分し、区分した前記時系列データから前記検索条件との一致度が最も高い前記時系列データを検索する検索部と、
     前記検索部が検索した前記時系列データと、当該時系列データに対応付けられた前記演算特徴量とに基づいて、前記プラントの運転を支援する運転支援情報を作成する運転支援情報作成部と、
    を有し、
     前記運転支援情報作成部は、前記検索部が検索した前記時系列データと、当該時系列データに対応付けられた前記演算特徴量および前記追加特徴量とに基づいて前記運転支援情報を作成する、運転支援システム。
    A driving support system comprising a server and a terminal device provided at a location where the operator is located,
    The server is
    a time-series data recording unit that records supervisory control data collected from the plant by a supervisory control device that monitors the plant as time-series data;
    a feature amount calculation logic recording unit that records feature amount calculation logic for calculating feature amounts from the time series data;
    a feature amount calculation unit that calculates the feature amount from the time series data based on the feature amount calculation logic recorded in the feature amount calculation logic recording unit;
    a feature amount added time series data recording unit that records the time series data in association with a calculated feature amount that is the feature amount calculated by the feature amount calculation unit;
    a feature amount adding unit that records an additional feature amount that is an additional feature amount input by the operator to the time series data in the feature amount added time series data recording unit in association with the time series data;
    has
    The terminal device is
    Based on the search conditions input by the operator, the time series data recorded in the feature value added time series data recording unit is divided, and the degree of match with the search conditions is highest among the divided time series data. a search unit that searches the time series data;
    an operation support information creation unit that creates operation support information that supports operation of the plant based on the time series data searched by the search unit and the calculated feature amount associated with the time series data;
    has
    The driving support information creation unit creates the driving support information based on the time series data searched by the search unit, and the calculated feature amount and the additional feature amount associated with the time series data. Driving assistance system.
  10.  プラントを監視する監視制御装置が前記プラントから収集した監視制御データを時系列データとして記録し、
     前記時系列データから特徴量を演算するための特徴量演算ロジックを記録し、
     前記特徴量演算ロジックに基づいて、前記時系列データから前記特徴量を演算し、
     前記時系列データと、演算した前記特徴量である演算特徴量とを対応付けて記録し、
     オペレータから入力された検索条件に基づいて、記録された前記時系列データを区分し、区分した前記時系列データから前記検索条件との一致度が最も高い前記時系列データを検索し、
     検索した前記時系列データと、当該時系列データに対応付けられた前記演算特徴量とに基づいて、前記プラントの運転を支援する運転支援情報を作成し、
     前記時系列データに対して前記オペレータが入力した追加の特徴量である追加特徴量を、前記時系列データに対応付け、
     検索した前記時系列データと、当該時系列データに対応付けられた前記演算特徴量および前記追加特徴量とに基づいて前記運転支援情報を作成する、運転支援方法。
    A supervisory control device that monitors a plant records supervisory control data collected from the plant as time series data,
    Recording feature amount calculation logic for calculating feature amounts from the time series data,
    Calculating the feature amount from the time series data based on the feature amount calculation logic,
    Correlating and recording the time series data and a calculated feature amount that is the calculated feature amount,
    dividing the recorded time-series data based on search conditions input by an operator, searching the divided time-series data for the time-series data that has the highest degree of agreement with the search conditions;
    creating operation support information for supporting the operation of the plant based on the retrieved time series data and the calculated feature amount associated with the time series data;
    Associating an additional feature quantity that is an additional feature quantity input by the operator with respect to the time series data with the time series data,
    A driving support method, wherein the driving support information is created based on the retrieved time series data, the calculated feature amount, and the additional feature amount associated with the time series data.
PCT/JP2022/032388 2022-08-29 2022-08-29 Operation assistance device, operation assistance system, and operation assistance method WO2024047694A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022581011A JPWO2024047694A1 (en) 2022-08-29 2022-08-29
PCT/JP2022/032388 WO2024047694A1 (en) 2022-08-29 2022-08-29 Operation assistance device, operation assistance system, and operation assistance method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/032388 WO2024047694A1 (en) 2022-08-29 2022-08-29 Operation assistance device, operation assistance system, and operation assistance method

Publications (1)

Publication Number Publication Date
WO2024047694A1 true WO2024047694A1 (en) 2024-03-07

Family

ID=90099069

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/032388 WO2024047694A1 (en) 2022-08-29 2022-08-29 Operation assistance device, operation assistance system, and operation assistance method

Country Status (2)

Country Link
JP (1) JPWO2024047694A1 (en)
WO (1) WO2024047694A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012022506A (en) * 2010-07-14 2012-02-02 Mitsubishi Electric Corp Operation history data management device and operation history data management system using the same
JP2018092511A (en) * 2016-12-07 2018-06-14 三菱重工業株式会社 Operational support device, apparatus operation system, control method, and program
WO2022054256A1 (en) * 2020-09-11 2022-03-17 三菱電機株式会社 Abnormality detection device
JP7045531B1 (en) * 2021-05-28 2022-03-31 三菱電機株式会社 Plant operation support system, plant operation support method, and plant operation support program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012022506A (en) * 2010-07-14 2012-02-02 Mitsubishi Electric Corp Operation history data management device and operation history data management system using the same
JP2018092511A (en) * 2016-12-07 2018-06-14 三菱重工業株式会社 Operational support device, apparatus operation system, control method, and program
WO2022054256A1 (en) * 2020-09-11 2022-03-17 三菱電機株式会社 Abnormality detection device
JP7045531B1 (en) * 2021-05-28 2022-03-31 三菱電機株式会社 Plant operation support system, plant operation support method, and plant operation support program

Also Published As

Publication number Publication date
JPWO2024047694A1 (en) 2024-03-07

Similar Documents

Publication Publication Date Title
JP6817426B2 (en) Yield prediction system and method for machine learning-based semiconductor manufacturing
JP6129028B2 (en) Energy consumption prediction method for building power equipment
US9047559B2 (en) Computer-implemented systems and methods for testing large scale automatic forecast combinations
US7225113B2 (en) Systems and methods for statistical modeling of complex data sets
JP4135726B2 (en) Manufacturing condition setting system, manufacturing condition setting method, control program, and computer-readable recording medium recording the same
JP6319271B2 (en) Event analysis device, event analysis system, event analysis method, and event analysis program
JP6467264B2 (en) Plan creation support apparatus and plan creation support method
TW583567B (en) Automatic intelligent system for performing yield rate improvement and multivariate analysis of production process parameters and method thereof
CN113283924A (en) Demand forecasting method and demand forecasting device
JP2007004728A (en) Method, device and computer program for controlling operation state of process
WO2024047694A1 (en) Operation assistance device, operation assistance system, and operation assistance method
CN110580253A (en) Time sequence data set loading method and device, storage medium and electronic equipment
JP2009294952A (en) Production planning system and method
CN117829318A (en) Digital twin system based on large model algorithm
JP7283105B2 (en) Analysis device and analysis method
JP6461397B2 (en) Wholesale electricity price prediction system and wholesale electricity price prediction method
US11126948B2 (en) Analysis method and computer
JP7562384B2 (en) Dam management system, runoff prediction device, and dam operation support method
CN115145903A (en) Data interpolation method based on production process
JP6795134B1 (en) Power management device
CN111079842A (en) Simulation generation method of time series structure data
WO2016163008A1 (en) Fault diagnostic device and fault diagnostic method
JP7321406B2 (en) Validation method determination device and validation method determination method
JP6945511B2 (en) Estimator and estimation method
Visoiu Performance Criteria for Software Metrics Model Refinement

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022581011

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22957298

Country of ref document: EP

Kind code of ref document: A1