JP2015125593A - Energy demand prediction device and method, program, and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To predict energy demand quantity with higher predicting accuracy than a conventional technology.SOLUTION: In an energy demand prediction device including arithmetic prediction means for predicting energy demand quantity on the basis of the production plan of a predetermined product using a facility, the arithmetic prediction means determines a plurality of operation states of the facility in a production stage including at least either a production preparation stage and a production maintenance stage on the basis of the production event information of the production plan, and calculates the total sum of energy consumption in each operation state of each facility in time series on the basis of an energy consumption pattern indicating energy consumption with respect to time in each operation state to predict the energy demand quantity.

Description

  The present invention relates to an energy demand prediction apparatus and method, a program, and a recording medium, and more particularly to an energy demand prediction apparatus and method for predicting energy demand based on a production plan and an energy consumption pattern using a computer, and to be executed by a computer. And a computer-readable recording medium on which the program is recorded.

  In energy demand prediction, proposals such as a demand prediction method using a production plan and an energy consumption pattern creation method have been made (see, for example, Patent Documents 1 and 2).

  For example, in Patent Document 1, a cogeneration control system includes a prediction unit and a determination unit in order to provide a cogeneration control system, a control method, and a control program that can be efficiently operated. The prediction unit predicts the load demand of electric energy and thermal energy in the cogeneration system based on the production plan in the factory, the electric energy basic unit, and the thermal energy basic unit. The electric energy basic unit is the amount of consumed electric energy directly required for production per unit amount of products produced in a factory. The heat energy intensity is the amount of heat energy consumed that is directly required for production per unit amount of products produced in the factory. The determination unit determines an operation method of the cogeneration system and supply amounts of electric energy and thermal energy based on the load demand.

  Further, for example, in Patent Document 2, in order to provide an energy monitoring system in which waste is quantitatively calculated from energy measurement data and is manifested, energy consumption of the target facility is measured and stored as energy measurement data. Means for obtaining a minimum energy consumption amount by applying an ideal energy consumption pattern previously recorded or inputted for each operating state of the target equipment to the operating state of the target equipment, the energy measurement data and the A calculating unit that quantitatively calculates a difference from the minimum usage amount; and an output unit that outputs the difference calculated by the calculating unit as wasted energy.

JP 2005-163704 A JP 2012-027597 A

  However, energy consumption patterns based on these energy fluctuations can be taken into account when the energy consumption is almost the same but the operating conditions of the equipment are different or when the equipment does not repeat a certain energy consumption pattern. Absent. Therefore, when the energy demand prediction is performed using the above energy consumption pattern, the prediction accuracy may be deteriorated.

  An object of the present invention is to solve the above-described problems and to provide an energy demand prediction apparatus and method, a program, and a recording medium capable of predicting an energy demand with higher prediction accuracy than in the prior art.

The energy demand prediction apparatus according to the first invention is
An energy demand prediction device comprising an operation prediction means for predicting an energy demand based on a production plan of a predetermined product using equipment,
The calculation predicting means determines a plurality of operating states of the equipment in the production stage including at least one of the production preparation stage and the production maintenance stage based on the production event information of the production plan, and determines the time for each operating state. Based on the energy consumption pattern indicating the energy consumption amount for the above, the energy demand amount is predicted by calculating the sum of the energy consumption amounts of the respective operating states for each facility in time series.

  In the energy demand prediction apparatus, the calculation prediction means divides each unit in which repeatability due to production quantity or time appears in production of a product by equipment that does not repeat a certain energy consumption pattern, and a plurality of energy consumption patterns The energy demand is calculated by predicting the energy demand according to each repeatability using the created energy consumption patterns and calculating the sum of the predicted energy demand in time series. It is characterized by predicting.

Further, in the energy demand prediction device, the calculation prediction means extracts a minimum energy consumption pattern starting from the production start of the product based on the energy consumption pattern, and extracts the energy consumption pattern from the original energy consumption pattern. The original energy consumption pattern is divided by extracting a frequent pattern of the energy consumption pattern by subtracting the extracted energy consumption pattern.
Alternatively, in the energy demand prediction apparatus, the calculation prediction means extracts a minimum energy consumption pattern in a standby state of production of the product based on the energy consumption pattern, and extracts the extracted from the original energy consumption pattern The original energy consumption pattern is divided by extracting a minimum value pattern of the energy consumption pattern by subtracting the obtained energy consumption pattern.

An energy demand prediction method according to a second aspect of the present invention is an energy demand prediction method for an energy demand prediction apparatus comprising an operation prediction means for predicting an energy demand based on a production plan of a predetermined product using equipment. ,
The calculation predicting means determines a plurality of operating states of the equipment in the production stage including at least one of the production preparation stage and the production maintenance stage based on the production event information of the production plan, and determines the time for each operating state. Based on the energy consumption pattern indicating the energy consumption amount for the above, the method includes the step of predicting the energy demand amount by calculating the sum of the energy consumption amounts of the respective operating states for each facility in time series.

  In the energy demand prediction method, the calculation predicting means divides each unit in which repeatability due to production quantity or time appears in production of a product by equipment that does not repeat a certain energy consumption pattern, and a plurality of energy consumption patterns The energy demand is calculated by predicting the energy demand according to each repeatability using the created energy consumption patterns and calculating the sum of the predicted energy demand in time series. It is characterized by predicting.

Further, in the energy demand prediction method, the calculation prediction means extracts a minimum energy consumption pattern starting from the production start of the product based on the energy consumption pattern, and the energy consumption pattern is extracted from the original energy consumption pattern. The original energy consumption pattern is divided by extracting a frequent pattern of the energy consumption pattern by subtracting the extracted energy consumption pattern.
Alternatively, in the energy demand prediction method, the calculation prediction means extracts a minimum energy consumption pattern in a standby state of production of the product based on the energy consumption pattern, and extracts the extracted from the original energy consumption pattern The original energy consumption pattern is divided by extracting a minimum value pattern of the energy consumption pattern by subtracting the obtained energy consumption pattern.

  A program executable by a computer according to the third invention includes the steps of the energy demand prediction method.

  A computer-readable recording medium according to a fourth invention stores the above program.

  Therefore, according to the present invention, the error is smaller than the actual energy consumption due to the operation state of the equipment including the production preparation stage or the production maintenance stage and the division of the energy consumption pattern for each repeatability. Compared with, the prediction accuracy is improved.

It is a block diagram which shows the structure of the energy demand prediction apparatus 10 which concerns on one Embodiment of this invention. FIG. 2 is a block diagram illustrating a configuration of a hard disk memory 23 in FIG. 1. It is a flowchart which shows the energy demand prediction process performed by the energy demand prediction apparatus 10 of FIG. It is a figure which shows the energy consumption pattern table 23c of FIG. It is a graph which shows the production sequence table 23d of FIG. 2, and the energy consumption corresponding to it. It is a figure which shows the creation method of the frequent pattern of an energy consumption pattern in case the energy of the production start origin and time origin generate | occur | produces in the energy demand prediction apparatus 10 of FIG. It is a figure which shows the creation method of the frequent pattern of an energy consumption pattern in case the energy resulting from completion | finish of production generate | occur | produces in the energy demand prediction apparatus 10 of FIG. It is a graph which shows an example of the energy consumption which shows the extraction method of the energy consumption pattern by the energy demand prediction apparatus 10 of FIG. It is a table which shows the determination method of the operating state of an installation in the energy demand prediction apparatus 10 of FIG. It is a timing chart which shows an example of the prediction result of the energy demand amount by the energy demand prediction apparatus 10 of FIG. It is a figure which shows the energy demand prediction process by the energy demand prediction apparatus 10 of FIG.

  Hereinafter, embodiments according to the present invention will be described with reference to the drawings. In addition, in each following embodiment, the same code | symbol is attached | subjected about the same component.

  FIG. 1 is a block diagram showing a configuration of an energy demand prediction apparatus 10 according to an embodiment of the present invention. The energy demand prediction apparatus 10 in FIG. 1 is a digital computer, for example, and executes the energy demand prediction processing program in FIG. 3 to execute the energy in the production plan table 23b and the energy consumption pattern table 23c in FIG. Based on the consumption pattern, the operating state of the equipment is determined, the production sequence table 23c of FIG. 2 is created, and the energy demand is predicted.

  Hereinafter, the configuration and processing of the energy demand prediction apparatus 10 according to the present embodiment will be described in detail.

  In FIG. 1, an energy demand is connected to an external storage device 60 that is a hard disk memory and stores and provides information of a production plan table and an energy consumption pattern table in advance through a drive device interface 35 b of the energy demand prediction device 10. The prediction device 10 may acquire the information and store it in the hard disk memory 23 by accessing the external storage device 60.

In FIG. 1, an energy demand prediction device 10
(A) a CPU (central processing unit) 20 of a computer that calculates and controls the operation and processing of the energy demand prediction device 10;
(B) a ROM (read only memory) 21 for storing a basic program such as an operation program and data necessary for executing the basic program;
(C) A RAM (random access memory) 22 that operates as a working memory of the CPU 20 and temporarily stores parameters and data necessary for the energy demand prediction process;
(D) a hard disk memory 23 for storing data of various tables used in the energy demand prediction process (see FIG. 2);
(E) The processing program of the energy demand prediction process of FIG. 3 that is configured by, for example, a hard disk memory and is read using the CD-ROM drive device 45 (these programs are programs that can be executed by a computer) is stored. A program memory 24;
(F) A keyboard that is connected to a keyboard 41 for inputting predetermined data and instruction commands, receives data and instruction commands input from the keyboard 41, performs predetermined signal conversion and other interface processing, and transmits the data to the CPU 20 Interface 31;
(G) Connected to a mouse 42 for inputting instruction commands on the CRT display 43, receives data and instruction commands input from the mouse 42, performs predetermined signal conversion and other interface processing, and transmits them to the CPU 20. A mouse interface 32;
(H) Connected to a CRT display 43 that displays data processed by the CPU 20, setting instruction screen, generated energy demand prediction result data, etc., and converts image data to be displayed into an image signal for the CRT display 43. A display interface 33 for outputting and displaying on the CRT display 43;
(I) Connected to a printer 44 that prints data processed by the CPU 20 and prediction result data of a predetermined generated energy demand, and performs predetermined signal conversion of the print data to be printed and outputs it to the printer 44 A printer interface 34 for printing,
(J) Connected to a CD-ROM drive device 45 that reads program data of the program from a CD-ROM 45a in which the processing program of the energy demand prediction process of FIG. 3 is stored, and the read program data of the image processing program is predetermined. A drive device interface 35a for performing signal conversion of the data and transferring it to the program memory 24;
(K) For example, information data of a production plan table and an energy consumption pattern table is connected to an external storage device 60 such as a hard disk memory, for example, and the read data is subjected to predetermined signal conversion or the like, and the CPU 20 or the hard disk memory And a drive device interface 35b for transferring to the device 23.
These circuits 20 to 24, 31 to 34, 35 a and 35 b are connected via a bus 30.

FIG. 2 is a block diagram showing the configuration of the hard disk memory 23 of FIG. In FIG. 2, the hard disk memory 23 includes a data memory 23a for storing the following data files.
(A) Production plan table 23b: a table for storing data of the production plan table of FIG. In the production plan table of FIG. 10, the number of products for each product a to f is described for each facility.
(B) Energy consumption pattern table 23c: a table storing the energy consumption pattern table of FIG. In the table 23c of FIG. 4, for each facility, the operating state of the facility, the type of work used for each operating state, and the energy consumption pattern in each work are described. Here, the energy consumption pattern is data A1 to B2 indicating energy consumption with respect to time.
(C) Production sequence table 23d: a table for storing the production sequence table 23c of FIG. In the table 23c of FIG. 5, the operating state (production preparation and maintenance stage) and the operating state (production stage) of each facility are described from the production event information.
(D) Energy demand prediction result table 23e: a table that stores the prediction result of the energy demand predicted by the energy demand prediction device 10. In FIG. 10, the sum total of the energy consumption with respect to time is calculated in a time series and expressed as a prediction result.

  FIG. 3 is a flowchart showing an energy demand prediction process executed by the energy demand prediction apparatus 10 of FIG.

  In this embodiment, in step S1 of FIG. 3, a production plan table 23b including a predetermined production plan (may be an equipment operation plan) is acquired. Next, in step S2, an energy consumption pattern table 23d in which the energy consumption amount of equipment necessary for production is patterned is created and acquired. The table 23d may be determined in advance, or may be created as described in detail later. Further, in step S3, the equipment acquisition status is determined and the production sequence table 23c is created and acquired. Then, based on the tables 23c and 23d, the energy demand prediction of the target facility (factory, plant, etc.) is performed, and the prediction result of the energy demand amount (total energy consumption with respect to the time during the prediction target period) is calculated. The table 23e is created and stored.

In the conventional example, the operating state of the facility is roughly divided into four types of operation, standby, stop, and suspension based on the production stage.
(1) Operation: A state where production is performed.
(2) Standby: A state in which production is not performed, but some functions related to production are moving.
(3) Stop: A state in which production is not performed and functions related to production are not operating (only some control units operate).
(4) Pause: A state where production is not performed and all functions are not moving.

However, in order to pattern the energy consumption, the operating state of the equipment is not sufficient, and in this embodiment, the operating state of the equipment in the production preparation and maintenance stages is also taken into consideration.
(5) Equipment start-up: A state where equipment start-up work is being performed.
(6) Facility shutdown: State in which facility shutdown is being performed.
(7) Pre-setup: A state in which setup work is performed immediately before production.
(8) Post-setup: A state in which setup work is performed immediately after production.
(9) Set-up change: A state where set-up work is performed in accordance with the change of the workpiece.
(10) Maintenance: A state where equipment maintenance work is performed.

  FIG. 4 is a diagram showing the energy consumption pattern table 23c of FIG. As is apparent from FIG. 4, the energy consumption pattern table 23c includes, for each facility, the operating state of the facility, the type of workpiece used for each operating state, and the energy consumption pattern in each workpiece. Here, the energy consumption pattern is data A1 to B2 indicating energy consumption with respect to time.

  Next, a method for creating an energy consumption pattern according to the present embodiment will be described below. FIG. 5 is a graph showing the production sequence table 23d of FIG. 2 and the energy consumption corresponding thereto. As is apparent from FIG. 5, the operating state of the equipment can be determined based on the production event information. In the example of FIG. 5, the operating state of the facility is determined for each period T1 to T8.

  In the production preparation and stage, depending on the characteristics of the equipment and the work content, in some cases, the energy consumption may be approximately the same as the operation state or standby state. Therefore, if the operating state of the equipment is determined using only the threshold value for the energy consumption, for example, the operating state of different equipment is determined, for example, the equipment start-up is in the standby state / the setup change is in the operating state. There is. Therefore, determine the production preparation stage using production event information based on production results, etc., and then determine the operation state of the equipment based on the threshold value for energy consumption, etc. Create an energy consumption pattern for each.

  Next, an energy consumption pattern division creation method according to the present embodiment will be described below.

  Among facilities composed of multiple main equipment, especially equipment that operates due to temperature, such as heaters and coolant devices, and equipment that operates due to environment such as removal of unnecessary oil and chips, these are directly related to production. Because it operates at a timing with no energy consumption pattern, it is not constant. In particular, temperature-derived equipment consumes a large amount of energy, and the difference between the energy consumption and the energy consumption timing cannot be ignored.

  Based on the minimum value of energy consumption starting from production event information such as the start of production for each unit that shows repeatability such as production quantity or time in facilities that do not repeat a certain energy consumption pattern as described above The energy consumption pattern is divided and created by extracting frequent patterns by extraction or pattern matching. Specific examples are shown below.

  FIG. 6 is a diagram illustrating a method for creating a frequent pattern of energy consumption patterns when energy caused by production start and time is generated in the energy demand prediction apparatus 10 of FIG. FIG. 6A shows a graph of energy consumption against time. Here, when a plurality of one product is produced, the minimum amount of energy consumption is extracted starting from the production start of producing each product. The graph is shown in FIG. Then, by subtracting the energy consumption amount of FIG. 6B from the original energy consumption amount of FIG. 6A, the graph of FIG. 6C is obtained, and the frequent pattern in FIG. 6C is obtained. (FIG. 6D) is obtained by extraction.

  FIG. 7 is a diagram showing a method for creating a frequent pattern of energy consumption patterns when energy resulting from the end of production occurs in the energy demand prediction apparatus 10 of FIG. FIG. 7A shows a graph of energy consumption against time. By extracting the minimum value in the standby state in the graph of FIG. 7A and subtracting the energy consumption of FIG. 7B from the original energy consumption of FIG. 7A, FIG. The graph of c) is obtained, and the minimum value pattern (FIG. 7 (d)) starting from the end of production is extracted and obtained.

  In the present embodiment, the energy consumption pattern has one or more energy consumption patterns for each operating state of the facility. At this time, when the energy consumption varies depending on the type of workpiece, as shown in FIG. 4, an energy consumption pattern for each type of workpiece is used.

Further, the above-described division of the energy consumption pattern is created by the following sequential method of extracting the energy consumption pattern.
(SS1) An energy consumption pattern is extracted for each unit in which repeatability appears based on a minimum value starting from production event information such as production start with respect to past energy consumption.
(SS2) The energy consumption corresponding to the extracted energy consumption pattern is subtracted from the past energy consumption.
(SS3) The processes in steps SS1 and SS2 are repeated until there is no remaining energy consumption.

  Here, in general, the energy consumption associated with production is extracted from the energy consumption pattern caused by the production quantity. The energy consumption pattern resulting from the production quantity can be extracted based on the minimum value at each elapsed time by superimposing the energy consumption amounts in a plurality of production cycle times starting from the start of production (see FIG. 8).

  FIG. 8 is a graph showing an example of the energy consumption indicating the method of extracting the energy consumption pattern by the energy demand prediction apparatus 10 of FIG. As is clear from FIG. 8, the energy consumption related to the production of the three products is almost the same, but the minimum values can be extracted for different portions as indicated by 101 to 103.

  The above extraction method is the same for extraction of energy consumption patterns caused by the end of production. The energy consumption pattern repeated due to time is not directly related to the production event information, but can be extracted by a general pattern matching method or the like.

  FIG. 9 is a table showing a method for determining the operating state of equipment in the energy demand prediction apparatus 10 of FIG. The present embodiment is characterized in that the operating state of the equipment including the production preparation and maintenance stages is determined. Here, at least one of the production preparation stage and the production maintenance stage may be performed. As is clear from FIG. 9, the operating state of the equipment is determined based on the production plan, equipment operation rules, etc. (X minutes before the production start time, etc.). At this time, for some production preparation stages such as setup change and maintenance, production event information (production start / end time of setup change, start / end time of maintenance, etc.) for which production time is specified more clearly than operation rules etc. ). This determines the operating state of the equipment including the production preparation stage.

  Next, energy demand prediction considering repeatability will be described below.

  FIG. 10 is a timing chart showing an example of a prediction result of the energy demand amount by the energy demand prediction apparatus 10 of FIG. As described above, using the production plan, energy consumption pattern information, and equipment operating state, the energy consumption pattern is applied to each equipment operating state on the time axis during the forecast period, and the energy demand is predicted. Do. Here, when the energy consumption pattern is divided for each unit in which the production plan repeatability appears, the energy demand amount is predicted by a method according to the repeatability, and the prediction result is the sum. For example, even if the operating states of the facilities are different, the time-based energy demand consumes energy based on a certain time interval, and therefore, a prediction method that takes the time interval into consideration is adopted.

  As is clear from the example of FIG. 10, the prediction of the energy demand due to the production quantity, the prediction of the energy demand due to the end of production, and the prediction of the energy demand due to the time are mixed. It can be seen that it constitutes the sum.

  FIG. 11 is a diagram showing an energy demand prediction process by the energy demand prediction apparatus 10 of FIG. As is clear from FIG. 11, according to the energy demand prediction device 10, it is possible to obtain a prediction result indicating the amount of energy demand with respect to time based on the production plan table 23 b and the energy consumption pattern.

  As described above, according to the present embodiment, the energy consumption pattern in consideration of these energy fluctuations can be obtained by dividing the energy consumption pattern for each operation state and repeatability of the equipment including the production preparation and maintenance stages. Use to predict energy demand. Thereby, the error is smaller than the actual energy consumption, and the prediction accuracy is improved.

  In the above embodiment, it may be executed using a CD-ROM 45a readable by a computer storing the processing program of FIG. 3, or may be a CD-R, CD-RW, DVD, DVD-R, DVD-RW. Various recording media readable by a computer such as a DVD-RAM may be used.

  As described above in detail, according to the present invention, compared with the conventional example, these energy fluctuations are caused by dividing the operation state of the equipment including the production preparation and maintenance stages and the energy consumption pattern for each repeatability. Demand forecast using energy consumption pattern considering Thereby, the error is smaller than the actual energy consumption, and the prediction accuracy is improved. The present invention can be applied to prediction of demand amounts of various energy such as electricity and heat.

10 ... Energy demand forecasting device,
20 ... CPU,
21 ... ROM,
22 ... RAM,
23. Hard disk memory,
23a ... Data memory,
23b ... Production plan table,
23c ... Energy consumption pattern table,
23d ... Production sequence table,
23e ... Prediction result table of energy demand,
30 ... Bus
31 ... Keyboard interface,
32 ... Mouse interface,
33 ... Display interface,
34 ... Printer interface,
35a, 35b ... drive device interface,
41 ... Keyboard,
42 ... mouse,
43 ... CRT display
44 ... Printer,
45 ... CD-ROM drive device,
45a ... CD-ROM.

Claims (10)

An energy demand prediction device comprising an operation prediction means for predicting an energy demand based on a production plan of a predetermined product using equipment,
The calculation predicting means determines a plurality of operating states of the equipment in the production stage including at least one of the production preparation stage and the production maintenance stage based on the production event information of the production plan, and determines the time for each operating state. An energy demand prediction device for predicting energy demand by calculating in time series the sum of energy consumption in each operating state for each facility based on an energy consumption pattern indicating energy consumption for .   In the production of products by equipment that does not repeat a certain energy consumption pattern, the calculation predicting means divides the unit into units that appear to be repeatable due to production quantity or time, and creates a plurality of energy consumption patterns. The energy demand is predicted by calculating the energy demand according to each repeatability using a plurality of energy consumption patterns, and calculating the sum of the predicted energy demand in time series. The energy demand prediction apparatus according to claim 1 to be performed.   The calculation prediction unit extracts a minimum energy consumption pattern starting from the production start of the product based on the energy consumption pattern, and subtracts the extracted energy consumption pattern from the original energy consumption pattern. 3. The energy demand prediction apparatus according to claim 2, wherein the original energy consumption pattern is divided by extracting a frequent pattern of the energy consumption pattern.   The calculation predicting means extracts a minimum energy consumption pattern in the production standby state of the product based on the energy consumption pattern, and subtracts the extracted energy consumption pattern from the original energy consumption pattern. 3. The energy demand prediction apparatus according to claim 2, wherein the original energy consumption pattern is divided by extracting a minimum value pattern of the energy consumption pattern. An energy demand prediction method for an energy demand prediction device comprising an operation prediction means for predicting an energy demand based on a production plan of a predetermined product using equipment,
The calculation predicting means determines a plurality of operating states of the equipment in the production stage including at least one of the production preparation stage and the production maintenance stage based on the production event information of the production plan, and determines the time for each operating state. An energy consumption pattern including a step of predicting an energy demand by calculating a time series of a sum of energy consumption in each operating state for each facility based on an energy consumption pattern indicating energy consumption with respect to Demand forecast method.   In the production of products by equipment that does not repeat a certain energy consumption pattern, the above calculation prediction means divides into units that show repeatability due to production quantity or time, and creates a plurality of energy consumption patterns. The energy demand is predicted by calculating the energy demand according to each repeatability using a plurality of energy consumption patterns, and calculating the sum of the predicted energy demand in time series. The energy demand prediction method according to claim 5.   Based on the energy consumption pattern, the calculation prediction means extracts a minimum value energy consumption pattern starting from the production start of the product, and subtracts the extracted energy consumption pattern from the original energy consumption pattern. The energy demand prediction method according to claim 6, wherein the original energy consumption pattern is divided by extracting a frequent pattern of the energy consumption pattern.   The calculation predicting means extracts a minimum energy consumption pattern in the production standby state of the product based on the energy consumption pattern, and subtracts the extracted energy consumption pattern from the original energy consumption pattern. The energy demand prediction method according to claim 6, wherein the original energy consumption pattern is divided by extracting a minimum value pattern of the energy consumption pattern.   A computer-executable program comprising the steps of the energy demand prediction method according to any one of claims 5 to 8.   A computer-readable recording medium storing the program according to claim 9.

Images