AU2020260535B2

AU2020260535B2 - Operation plan creation apparatus, operation plan creation method, and program

Info

Publication number: AU2020260535B2
Application number: AU2020260535A
Authority: AU
Inventors: Yusuke Kuroki; Naoyuki Matsumoto; Keiko Shimizu; Takufumi Yoshida
Original assignee: Toshiba Corp; Toshiba Energy Systems and Solutions Corp
Current assignee: Toshiba Corp; Toshiba Energy Systems and Solutions Corp
Priority date: 2018-03-16
Filing date: 2020-10-30
Publication date: 2022-09-29
Anticipated expiration: 2038-09-06
Also published as: JP2019162008A; JP6930938B2; AU2020260535A1; AU2018226475A1

Abstract

Do n .. .t6-30/10/2020 ABSTRACT An operation plan creation apparatus for creating an operation plan showing at least operation state change timing and maintenance implementation timing of a target being a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the operation plan creation apparatus comprising a frequency determiner configured to determine an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; and a timing determiner configured to determine operation state change timing and maintenance implementation timing in each section in the consideration term using the calculation model so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in each section. H-D LUcC CLU 00- ~ ZiLLH Z > < znf -J ~~ <f D<~~P wg-g LtJL c ____ 0 PRLIry LI 0C 0 < C n- cc Z cc LiL 0 zcC Cl z3 t~ / Z i-z pn C < -a- < Uo< cc LL - J C) H-- V)( :7C H- 0<

Description

H-D LUcC

CLU 00- ~ ZiLLH Z > <

znf

-J ~~ <f D<~~P wg-g

LtJL c

____ 0 PRLIry

LI 0C 0

< C n- cc Z cc LiL 0 zcC Cl z3 t~ / Z i-z pn C < -a- < Uo< C) cc LL - J

H-- V)(

:7C H- 0<

Australian Patents Act 1990

ORIGINAL COMPLETE SPECIFICATION STANDARD PATENT

Invention Title Operation plan creation apparatus, operation plan creation method, and program

The following statement is a full description of this invention, including the best method of performing it known to me/us:-

1a

CROSS-REFERENCE TO RELATED APPLICATION (S)

The entire content of the complete specification of Australian Patent Application No. 2018226475 as originally filed is incorporated herein by reference. This application is based upon and claims the benefit of priority from Japanese Patent Application No. 2018-050052, filed on March 16, 2018; the entire contents of which are incorporated herein by reference.

FIELD An embodiment relates to an operation plan creation apparatus, an operation plan creation method, and a non-transitory computer readable medium.

BACKGROUND From a viewpoint of cost reduction, it has been tried to reduce costs for operation by frequently changing an operation state of a facility, an apparatus, or the like. However, deterioration may be caused when the operation state is frequently changed. Moreover, legal inspection may be obligated in accordance with the number of change times of the operation state. For these reasons, there are also many apparatuses whose frequency of maintenance increases with changes of the operation state. Even when reducing an operation cost in a short term is continued by controlling the operation state for such an apparatus, the total cost in a long term may increase due to a maintenance cost as compared to a case where the operation is simply continued. Accordingly, it is necessary that such an apparatus is controlled the operation state by considering not only the operation cost but also the maintenance cost. In other words, not only costs in a short term but also costs in a long term should be considered also when creating an operation plan in the short term.

BRIEF SUMMARY OF THE INVENTION An aspect of the present invention provides an operation plan creation apparatus for creating an operation plan showing at least operation state change timing and maintenance implementation timing as a target a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the operation plan creation apparatus comprising: a frequency determiner configured to determine an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; a timing determiner configured to determine operation state change timing and maintenance implementation timing together in each section in the consideration term using the calculation model so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in each section, wherein the timing determiner assigns information regarding either the operation state or the maintenance of the target to each section in the consideration term based on the determined operation state change timing and maintenance implementation timing to create the operation plan indicating, either the operation state of the target or the maintenance implementation period for the target in each of the sections; an operation cost estimation model creator configured to create the operation cost estimation model on the basis of past operation performance of the target and each cost corresponding to each of the operation state; and a maintenance cost estimation model creator configured to create the maintenance cost estimation model on the basis of past operation performance of the target, past maintenance performance of the target, and each cost corresponding to each of the maintenance, wherein the target is a power plant, and the operation plan creation apparatus further comprises: a data acquirer configured to acquire the past operation performance and each cost corresponding to each of the operation state from the power plant; and an operation plan output device configured to output the operation state change timing determined by the timing determiner to the power plant, and the power plant is configured to change the operation state in accordance with the operation state change timing from the operation plan output device. Another aspect of the present invention provides an operation plan creation method for creating an operation plan showing at least operation state change timing and maintenance implementation timing as a target a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the operation plan creation method comprising: determining an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; determining operation state change timing and maintenance implementation timing in each section in the consideration term using the calculation model so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in each section; assigning information regarding either the operation state or the maintenance of the target to each section in the consideration term

3a

based on the determined operation state change timing and maintenance implementation timing to create the operation plan indicating, either the operation state of the target or the maintenance implementation period for the target in each of the sections; creating the operation cost estimation model on the basis of past operation performance of the target and each cost corresponding to each of the operation state; and creating the maintenance cost estimation model on the basis of past operation performance of the target, past maintenance performance of the target, and each cost corresponding to each of the maintenance, wherein the target is a power plant, and the operation plan creation method further comprises: acquiring the past operation performance and each cost corresponding to each of the operation state from the power plant; and outputting the operation state change timing to the power plant, and the power plant changing the operation state in accordance with the operation state change timing. A further aspect of the present invention provides a program for creating an operation plan showing at least operation state change timing and maintenance implementation timing as a target a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the program comprising: determining an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; determining operation state change timing and maintenance implementation timing in each section in the consideration term using the calculation model so as to satisfy the operation state

3b

change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in the each section; assigning information regarding either the operation state or the maintenance of the target to each section in the consideration term based on the determined operation state change timing and maintenance implementation timing to create the operation plan indicating, either the operation state of the target or the maintenance implementation period for the target in each of the sections; creating the operation cost estimation model on the basis of past operation performance of the target and each cost corresponding to each of the operation state; and creating the maintenance cost estimation model on the basis of past operation performance of the target, past maintenance performance of the target, and each cost corresponding to each of the maintenance, wherein the target is a power plant, and the program further comprises: acquiring the past operation performance and each cost corresponding to each of the operation state from the power plant; and outputting the operation state change timing to the power plant, and the power plant changing the operation state in accordance with the operation state change timing.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram illustrating an example of a schematic configuration of a system including an operation plan creation apparatus according to an embodiment of the present invention; FIG. 2 is a diagram for explaining expected costs; FIG. 3 is a diagram illustrating an example of a created operation plan; FIG. 4 is a flowchart illustrating an example of an overall process of the operation plan creation apparatus according to an embodiment of the present invention; FIG. 5 is a flowchart illustrating an example of an overall process of a target according to an embodiment of the present invention; FIG. 6 is a flowchart illustrating an example of an overall process of a maintenance management system according to an embodiment of the present invention; and FIG. 7 is a block diagram illustrating an example of a hardware configuration in an embodiment of the present invention.

DETAILED DESCRIPTION An embodiment of the present invention prevents an increase in costs in a long term by considering an operation cost and a maintenance cost in the long term when creating an operation plan in a short term. An operation plan creation apparatus as an aspect of the present invention creates an operation plan showing at least operation state change timing and maintenance implementation timing as a target a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases. The operation plan creation apparatus includes a frequency determiner and a timing determiner. The frequency determiner determines an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term. The timing determiner determines operation state change timing and maintenance implementation timing in each section in the consideration term so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term. An embodiment will be explained in detail below with reference to the accompanying drawings. The present invention is not limited to the embodiment. (An embodiment of the present invention) FIG. 1 is a block diagram illustrating an example of a system including an operation plan creation apparatus according to a first embodiment. The system in FIG. 1 includes an operation plan creation apparatus 1, a target 2 whose operation plan is created by the operation plan creation apparatus 1, and a maintenance management system 3 which manages maintenance for the target 2. The operation plan creation apparatus 1 according to the first embodiment includes a data acquirer 11, a storage 12, an operation plan creator 13, and an operation plan output device (instructor) 14. The operation plan creator 13 includes an operation cost estimation model creator 131, a maintenance cost estimation model creator 132, a frequency determiner (long-term operation plan creator) 133, and a timing determiner (short-term operation plan creator) 134. The target 2 in FIG. 1 is assumed to have a configuration suitable for use of the created operation plan, and includes as its components an operation controller 21, a constitution facility (constitution equipment) 22, and a measurer (sensor) 23. The operation plan creation apparatus 1 can exchange data with the target 2 and the maintenance management system 3. The operation plan creation apparatus 1 creates an operation plan as a target a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases. That is, the target 2 is assumed to be a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases. The operation plan created by the operation plan creation apparatus 1 shows at least operation state change timing and maintenance implementation timing of the target 2. The operation plan creation apparatus 1 creates the operation plan from both of a long-term viewpoint and a short-term viewpoint. An explanation will be made with an example. The target 2 for which an operation plan is created corresponds to, for example, a thermal power unit (composed of a power generator, and components such as a steam turbine or a gas turbine) or a thermal power plant including a plurality of the units. The unit needs maintenance in accordance with the cumulative number of times of change of the operation state (a total number of times after installation). For example, when the number of times of start and stop of a certain unit until now has exceeded a predetermined number, it is required to implement maintenance of inspection or replacement installation for some facilities in the unit. When the operation state of the unit is always set to a started state (ON), a cost for operation (operation cost) increases. Therefore, when power generation is unnecessary, it is preferable to set the operation state of the unit to a stopped state (OFF). When power demand required for the thermal power plant can be covered, it is preferable to set the operation states of some units to the stopped state. Therefore, it is preferable to create an operation plan such as to suppress the operation cost while satisfying constraint conditions such as power demand. However, as described before, when the cumulative number of times of start of the unit increases, maintenance is needed, so that a cost for maintenance (maintenance cost) increases. Therefore, due to the maintenance cost, the created operation plan is often uneconomical in a long term. FIG. 2 is a diagram for explaining expected costs. The vertical axis represents a cost, and the horizontal axis represents the number of change times of the operation state. A dashed line graph represents an operation cost, a dot-and-dash line graph represents a maintenance cost, and a solid line graph represents the sum of the operation cost and the maintenance cost. The graph of the operation cost shows that the operation cost decreases as the change frequency of the operation state is made higher to perform efficient operation. However, the graph of the maintenance cost shows that the maintenance cost increases when the change frequency of the operation state is high. Therefore, the graph of the sum of the operation cost and the maintenance cost becomes like a mortar, and the sum increases when the change frequency of the operation state is too low or too high. So, the operation plan creation apparatus 1 creates an operation plan such as to reduce the total cost in a long term while satisfying constraint conditions in a short term. Thereby, even when the operation state is controlled on a daily basis, unexpected cost excess can be avoided. Incidentally, in this explanation, it is assumed that it is not necessary to consider anything other than the maintenance cost and the operation cost, and the sum of the maintenance cost and the operation cost is regarded as a total cost. Although an explanation will be made by taking as an example suppression of the overall total cost inclusive of a plurality of targets 2 like a thermal power plant, there may be one target 2. The created operation plan shows at least timing to change the operation state and timing to implement maintenance. Since the operation plan shows these timings which have been unplanned, change of the operation state and maintenance can be implemented at appropriate timings. Incidentally, in this embodiment, it is assumed that the target 2 itself changes the operation state on the basis of the operation plan. In addition, it is assumed that maintenance is implemented by a maintenance agent who uses the maintenance management system 3 at timing shown in the operation plan. The target 2 and the maintenance management system 3 will be explained first. The operation controller 21 of the target 2 controls the constitution facility 22 to change the operation state at the operation state change timing shown in the operation plan. An operation state after the change may be shown in the operation plan, and the operation controller 21 may switch it to the shown operation state after the change. Alternatively, for example, when there are only two kinds of operation states, or when the order of change is determined in advance, the current operation state should just be changed to the other operation state. In addition, the operation controller 21 records a history of the control. The history will be described as an operation control history, and data on the operation control history will be described as operation control history data. The operation control history includes, for example, a date and time when the operation is changed, operation states before and after a change, or the like. The constitution facility (constitution equipment) 22 of the target 2 is a facility or equipment which is a component of the target 2. In the example of a power plant described above, the unit in the power plant corresponds to the constitution facility 22. The operation state of the constitution facility 22 is changed by the operation controller 21 in accordance with the operation plan. Information on the constitution facility 22 such as an operation situation or a surrounding situation is measured by the measurer (sensor) 23 of the target 2. The information on the constitution facility 22 may be any information measurable by a well-known sensor or the like, and corresponds to, for example, an output value of the constitution facility 22, a surrounding temperature, or the like. Data on the information will be described as facility data. Incidentally, there may be one or a plurality of operation controllers 21 and measurers 23, or they may exist for each constitution facility 22. Thus, the target 2 can have the operation state switched in accordance with the input operation plan, and output the operation control history data and the facility data. Since the operation control history data and the facility data are data showing past operation performance of the target 2, by creating an operation plan using the data, it is possible to create an operation plan more suitable for the target 2.

The maintenance management system 3 is assumed to be a system which manages maintenance of the target 2. For example, it is assumed that a maintenance agent of the target 2 checks the operation plan created by the operation plan creation apparatus 1 through the maintenance management system 3. It is also assumed that after maintenance is implemented, the maintenance agent records the maintenance in a history on maintenance that the maintenance management system 3 has. The history will be described as a maintenance history, and data on the maintenance history will be described as maintenance history data. The maintenance history includes at least a date and time of maintenance, and contents of maintenance. Since the maintenance history data is data showing past maintenance performance of the target 2, by creating an operation plan using the data, it is possible to create an operation plan more suitable for the target 2. Next, the components of the operation plan creation apparatus 1 will be explained. The data acquirer 11 of the operation plan creation apparatus 1 acquires data necessary to create the operation plan. Specifically, the operation control history data and the facility data are acquired from the target 2, and the maintenance history data is acquired from the maintenance management system. Incidentally, the data acquirer 11 may acquire other data. The storage 12 stores at least operation cost data and maintenance cost data necessary to create the operation plan. The operation cost data is data on costs corresponding to the operation state of the target 2. The operation cost data reveals costs in a certain operation state of the target 2. The maintenance cost data is data showing costs corresponding to maintenance. The maintenance cost data reveals costs required when certain maintenance is implemented. Although the operation cost data and the maintenance cost data are assumed to be stored in advance in the storage 12, they may be acquired by the data acquirer 11 from a specified location. Incidentally, data stored in the storage 12 is not limited in particular.

The operation plan creator 13 creates an operation plan for the target 2 on the basis of data from the data acquirer 11 and the storage 12. The operation cost estimation model creator 131 in the operation plan creator 13 performs simulation based on the operation control history data, the facility data, and the operation cost data. By the simulation, an operation cost estimation model for estimating an operation cost in a predetermined consideration term is created from an operation state change frequency in the consideration term. Incidentally, the operation state change frequency is represented by the number of change times of the operation state in the consideration term, and the estimated operation cost is a total amount in the entire consideration term. The consideration term may be freely determined in accordance with an implementation interval of maintenance or the like. For example, it is assumed that a thermal power plant corresponding to the target 2 has units 1 to "n" ("n" is a positive integer greater than 1). The operation state change frequency of a unit "i" ("i" is an integer equal to or greater than 1 and equal to or smaller than n) is denoted as "ai". The operation state change frequency "ai" represents the number of change times of the operation state per unit term. An operation cost "fi" in the consideration term of the thermal power plant is represented by the following function with the operation state change frequency "ai" as a variable.

[Formula 1] fi(a,, a.) = kiai + ko (1) "ki" is a coefficient corresponding to each operation state change frequency "ai". "ko" is a constant. The operation cost estimation model creator 131 calculates a value of the coefficient "ki" considered to be optimum by simulation. The operation control history data reveals the number of change times of the operation state in the past of each unit. In addition, the facility data and the operation cost data also reveal an operation cost in the past of each unit. Accordingly, by repeating simulation with the operation state change frequency "ai" as a variable, a value of the coefficient "ki" considered to be optimum can be calculated. Thus, operation cost estimation model is created. The maintenance cost estimation model creator 132 in the operation plan creator 13 creates an operation cost estimation model for estimating a maintenance cost in the consideration term from the operation state change frequency in the consideration term. First, the maintenance cost estimation model creator 132 performs survival time analysis of the constitution facility 22 on the basis of the operation control history data, the facility data, and the maintenance history data. The survival time analysis reveals a survival time of the constitution facility 22 with respect to each operation state. Next, the maintenance cost estimation model creator 132 calculates a function for estimating a maintenance implementation frequency from the operation state change frequency on the basis of the survival time. The maintenance cost estimation model creator 132 also calculates a function for estimating the maintenance cost from the maintenance implementation frequency on the basis of the maintenance cost data. Then, the maintenance cost estimation model creator 132 creates a maintenance cost estimation model for estimating the maintenance cost from the operation state change frequency by combining the function for estimating the maintenance implementation frequency from the operation state change frequency and the function for estimating the maintenance cost from the maintenance implementation frequency. Let a maintenance interval of the unit "i" be the maintenance implementation frequency "bi". Also, a function of the unit "i" for estimating the maintenance implementation frequency from the operation state change frequency is denoted as "f2 1". The maintenance implementation frequency "bi" of the unit "i" is represented by a function of the following formula with the operation state change frequency "ai" as a variable.

[Formula 2] bi = f2 i(ai) (2)

When a function for estimating the maintenance cost of the entire thermal power plant from the maintenance implementation frequency of each unit "i" is denoted as "f 3 , the following formula holds.

[Formula 3] f 3 (bi, --- , b.) = f3 {f 2 1 (a,), fzi(ai), ,f 2n (a.)} hiai + ho (3) Therefore, the maintenance cost estimation model in the consideration term is also represented by a function with the operation state change frequency "ai" as a variable. "hi" is a constant corresponding to each operation state change frequency "ai". "ho" is a constant. The frequency determiner (long-term operation plan creator) 133 determines the operation state change frequency "ai" and the maintenance implementation frequency "bi" in the consideration term so as to reduce a total cost of the target 2 in the consideration term on the basis of the operation cost estimation model and the maintenance cost estimation model. Specifically, the frequency determiner 133 solves an optimization problem which uses the operation state change frequency and the maintenance implementation frequency as explanatory variables and whose objective is to minimize a total cost.

[Formula 4] minimize: f1 (a 1 ,---, an)+f 3 (b 1 , --- , b) (4) Thereby, an operation state change frequency considered to be optimum is calculated, and a maintenance implementation frequency considered to be optimum is calculated from the above formula (2) on the basis of the operation state change frequency considered to be optimum. As an arithmetic method for the optimization problem, well-known approaches may be used such as a gradient method or a Nelder-Mead method. The calculated operation state change frequency and maintenance implementation frequency will be described as an optimum change frequency and optimum maintenance frequency, respectively. Incidentally, it does not matter whether they are actually optimal or not.

The timing determiner 134 determines the operation state change timing and the maintenance implementation timing so as to satisfy the optimum change frequency and optimum maintenance frequency in the consideration term. Incidentally, the timing determiner 134 may partition the consideration term into a plurality of sections and may determine operation state change timing and maintenance implementation timing in each section. Incidentally, the length of each section may be equal or different. The consideration term is determined in accordance with a frequency of maintenance. For example, when maintenance is exchange of components, the frequency is once every a plurality of years, so that the consideration term will span a plurality of years. Meanwhile, the target 2 often has constraint conditions to be satisfied on a daily basis or a monthly basis. Therefore, the timing determiner 134 may create a short-term operation plan to satisfy constraint conditions in a shorter term (short-term) than the consideration term (long-term). In an example that the target 2 is a power plant, the operation plan needs to be created so as to satisfy power demand on a daily basis or a monthly basis. In addition, in a case where power demand is satisfied even without operating all units belonging to the power plant, economical efficiency is higher when units with a high operation cost are stopped. Thus, it is preferable to also create a short-term operation plan such as to achieve a short-term objective while satisfying short-term constraint conditions. Therefore, the timing determiner 134 may determine the operation state change timing and the maintenance implementation timing in each section so as to further satisfy constraints on the operation state determined in each section in the consideration term. That is, the timing determiner 134 may create the short-term operation plan by solving an optimization problem in a shorter term than the consideration term. The optimization problem will be described as a short-term optimum planning problem. Meanwhile, an optimization problem in the consideration term will be described as a long-term optimum planning problem.

A specific example will be explained. The timing determiner 134 receives the maintenance implementation frequency "bi" of the unit "i" as an input from the frequency determiner 133. In addition, the timing determiner 134 receives other inputs, from the storage 12 or the like, such as a maintenance date margin (suspended term) "a", power demand Pd(d) of a power plant on a certain date "d", a minimum power generation amount Minout(i) and a maximum power generation amount Maxout(i) of the unit "i". The maintenance date margin "a" means the number of days by which a maintenance implementation date can be shifted. For example, while maintenance is implemented at a certain interval, it may not be possible to stop the unit "i" on the next scheduled maintenance date due to various reasons. Therefore, it is assumed that maintenance should just be performed during a few days around the scheduled maintenance date. Thus, an acceptable difference of days between the maintenance implementation date and the scheduled maintenance date is defined as the maintenance date margin. The timing determiner 134 solves the short-term optimum planning problem from the above inputs. Variables of the short term optimum planning problem include the operation state "Sid" and an output power value "Xid" on the certain date "d" of the unit "i". In addition, the "k"-th maintenance implementation date "Zik" of the unit "i" is also a variable of the short-term optimum planning problem. Incidentally, an explanation is made here by assuming one kind of maintenance, but there may be a plurality of kinds of maintenance and the "n"-th maintenance implementation date "Zikn" of maintenance "k" of the unit "i" may be a variable of the short term optimum planning problem. Constraint conditions of the short-term optimum planning problem include, for example, satisfaction of daily power demand, a minimum power generation amount and a maximum power generation amount per unit, or the like. An example of an objective function and constraint conditions of the short-term optimum planning problem will be described below. Incidentally, the operation state "Sid" includes three states of a "started state (ON)", a "stopped state (OFF)", and "maintenance".

[Formula 5] minimize: f 1 (a 1,---,an)+f 3 (b 1 , --- ,b) (5)

Xid = Pd(d) Vd (6) subject to :

Minout(i) 5 Xid Maxout(i) (Sid = ON) Vi vd(7) Xid 0 (Sid # ON) Vi Vd (8) bi - a< Zik+l-Zik : bi + a (9) Although the formula (5) is the same as the formula (4), the formula (4) is minimization in the consideration term, while the formula (5) is minimization in one section in the consideration term. The formula (9) shows that the "k+1"-th maintenance implementation date "Zik+1" of the unit "i" should just be within "a" days around the scheduled maintenance date "Zik+bi". Thus, the short-term optimum planning problem is solved, and the operation state "Sid" and the maintenance implementation date "Zik" are determined for each unit, so that an operation plan showing the operation state change timing and the maintenance implementation timing is created. The created operation plan is an operation plan which is economically excellent both in a long term and in a short term. Creation of an operation plan in a long term over a plurality of years is complex due to the number of considerations, variations of power demand, or the like. It is however possible to efficiently respond to both a long-term constraint such as maintenance and a short-term constraint such as demanded power by separating into the long-term optimum planning problem and the short-term optimum planning problem. Incidentally, a general purpose mathematical programming solver should just be used to solve the short-term optimum planning problem. FIG. 3 is a diagram illustrating an example of a created operation plan. Shown is a daily operation state of each unit in the example of the thermal power plant described above. Before creating this operation plan, maintenance implementation dates have been undetermined. Therefore, a maintenance agent can recognize the maintenance implementation dates by receiving the operation plan. In addition, since the maintenance implementation timing shown in the created operation plan includes the maintenance date margin, it can be prevented to recreate the operation plan because maintenance cannot be implemented on the scheduled maintenance date. The operation plan output device (instructor) 14 transmits the created operation plan to the target 2 and the maintenance management system 3. Incidentally, the operation plan output device 14 may edit the created operation plan to create an operation plan including only information required by a transmission partner. For example, the operation plan output device 14 may create an operation plan obtained by excerpting information on the operation state for the target 2 which changes the operation state, and transmit it to the target 2. Similarly, the operation plan output device 14 may create the operation plan obtained by excerpting information on maintenance, and transmit it to the maintenance management system 3. In addition, the operation plan output device 14 may output the created operation plan so that a user who uses the operation plan creation apparatus 1 can check the created operation plan. The operation plan may be output, for example, in a file format or as an image. The operation plan output device 14 may edit the operation plan in accordance with changes made in an output destination. For example, when the user wants to postpone a maintenance date shown in the operation plan, the data acquirer 11 may receive a modified file, and the operation plan output device 14 may update contents of the operation plan. Next, a flow of processes by respective components will be explained. FIG. 4 is a diagram illustrating an example of a schematic flowchart of an overall process of the operation plan creation apparatus according to an embodiment of the present invention. First, the data acquirer 11 acquires data necessary to create of an operation plan (S101). Thereby, the operation plan creator

13 can use the operation control history data, the facility data, the maintenance history data, the operation cost data, and the maintenance cost data. The operation cost estimation model creator 131 performs simulation based on the operation control history data, the facility data, and the operation cost data to create an operation cost estimation model (S102). Meanwhile, the maintenance cost estimation model creator 132 performs survival time analysis on the basis of the operation control history data, the facility data, and the maintenance history data (S103). Then, the maintenance cost estimation model creator 132 creates a maintenance cost estimation model on the basis of a result of the survival time analysis and the maintenance cost data (S104). The frequency determiner 133 solves the long-term optimum planning problem in which the operation cost estimation model and the maintenance cost estimation model are used for an objective function to determine the operation state change frequency and the maintenance frequency in the consideration term (S105). Next, the timing determiner 134 solves the short-term optimum planning problem to determine the operation state change timing and the maintenance implementation timing in each section in the consideration term (S106), so that an operation plan showing the operation state change timing and the maintenance implementation timing is created. Then, the operation plan output device 14 transmits the operation plan to a specified destination (S107). This flow ends by the above, so that a receiving destination of the operation plan can recognize at least the operation state change timing or the maintenance implementation timing. Incidentally, this flowchart is an example, and the order of the processes or the like is not limited as long as a necessary processing result can be obtained. In addition, a processing result of each process may be sequentially stored in the storage 12, and each component may acquire a processing result with reference to the storage 12. The same also applies to the subsequent flowchart. FIG. 5 is a flowchart illustrating an example of an overall process of a target according to an embodiment of the present invention. The operation controller 21 changes the operation state at the operation state change timing shown in the operation plan (S201). Then, the change is recorded in the operation control history (S202). Meanwhile, the constitution facility 22 changes its operation state (S203) on the basis of control from the operation controller 21 (S201). The measurer 23 measures an operation situation or the like of the constitution facility 22, and records it as the facility data (S204). Thus this flow ends, and the operation state control history data and the facility data are updated. Thereby, the operation plan creation apparatus 1 can use the latest data on the target 2. FIG. 6 is a flowchart illustrating an example of an overall process of a maintenance management system according to an embodiment of the present invention. The maintenance management system 3 outputs the maintenance implementation timing or the like shown in the operation plan in a form checkable by a maintenance agent (S301). Thereby, the maintenance agent can recognize the maintenance implementation timing, and maintenance is implemented at the timing. Then, the maintenance management system 3 receives the inputs (S302) since the maintenance agent inputs a report of maintenance to the maintenance management system 3. The maintenance management system 3 records a maintenance history on the basis of the input (S303). Thus the flow ends, and the maintenance history is updated. Thereby, the operation plan creation apparatus 1 can use the latest maintenance history on the target 2. Incidentally, the components of the above embodiments may be modified as appropriate in accordance with specifications or the like. For example, each component may be plurally divided in accordance with processing contents, data used for processes, or the like. For example, the data acquirer 11 may be divided in accordance with data to be acquired. In addition, the operation plan output device 14 may be divided into an operation plan output device for the target 2, and an operation plan output device for the maintenance management system 3. Some components may exist in an external apparatus, and data may be exchanged with the external apparatus. Alternatively, each component may be included individually in a plurality of apparatuses which perform data communication. That is, a system composed of a plurality of apparatuses may perform each process of the operation plan creation apparatus 1. Incidentally, at least part of the above embodiments may be realized by a dedicated electronic circuit (i.e., hardware) such as an IC (Integrated Circuit) in which a processor, a memory, and the like are implemented. In addition, at least part of the above embodiments may be realized by executing software (program). For example, the processes of the above embodiments can be realized by using a general computer apparatus as basic hardware and causing a processor such as a central processing unit (CPU) mounted on the computer apparatus to execute a program. For example, a computer can be used as the apparatus of the above embodiments by the computer reading out dedicated software stored in a storage medium readable by the computer. The kinds of storage media are not limited in particular. In addition, a computer can be used as the apparatus of the above embodiments by the computer installing dedicated software downloaded through a communication network. Thus, information processes by software are specifically implemented using hardware resources. FIG. 7 is a block diagram illustrating an example of a hardware configuration in an embodiment of the present invention. The operation plan creation apparatus 1 can be realized as a computer apparatus 4 which includes a processor 41, a main storage device 42, an auxiliary storage device 43, a network interface 44, and a device interface 45, and in which they are connected via a bus 46. Incidentally, the computer apparatus 4 in FIG. 7 includes one of each component, but it may include a plurality of the same components. Although one computer apparatus 4 is illustrated in FIG. 7, software may be installed in a plurality of computer apparatuses, and each of the plurality of computer apparatuses may execute a process of a different part of the software. The processor 41 is an electronic circuit including a control device and an arithmetic device of a computer. The processor 41 performs an arithmetic process on the basis of data input from each device or the like of internal components of the computer apparatus 4 or on a program to output an arithmetic result or a control signal to each device or the like. Specifically, the processor 41 executes an OS (Operating System) of the computer apparatus 4 or an application to control each device composing the computer apparatus 4. The processor 41 is not limited in particular as long as the above processes can be performed. The processes of the operation plan creator or the like can be realized by the processor 41. The main storage device 42 is a storage device storing instructions executed by the processor 41, various data and the like, and information stored in the main storage device 42 can be read out directly by the processor 41. The auxiliary storage device 43 is a storage device other than the main storage device 42. Incidentally, these storage devices mean any electronic component capable of storing electronic information, and may be a memory or a storage. Although memories include a volatile memory and a non volatile memory, any of them may be used. The storage 12 may be realized by any of the main storage device 42 and the auxiliary storage device 43. The network interface 44 is an interface for connecting to a communication network 5 wirelessly or by wire. As the network interface 44, it suffices to use one conforming to existing communication standards. The network interface 44 may be used to exchange information with an external apparatus 6A communicably connected via the communication network 5. The external apparatus 6A includes, for example, an external sensor or the like. In addition, the external apparatus 6A may be an apparatus having part of processing functions of the operation plan creation apparatus 1, and may be a server (cloud server) or the like which provides necessary data. That is, the computer apparatus 4 may receive data to be used via the communication network 5 like a cloud service. The device interface 45 is an interface such as USB for directly connecting to the external apparatus 6B. The external apparatus 6B may be an external storage medium or a storage device such as a database. The external apparatus 6B may be an output apparatus. The output apparatus may be, for example, a display apparatus for displaying images, or an apparatus for outputting audio or the like. For example, although an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube), a PDP (Plasma Display Panel), and a speaker are included, it is not limited to them. Incidentally, the external apparatus 6B may be an input apparatus. The input apparatus includes devices such as a keyboard, a mouse, a touch panel or the like, and gives information input from these devices to the computer apparatus 4. Signalsfrom the input apparatus are output to the processor 41. While certain embodiments have been described, these embodiments have been presented by way of example only, and are not intended to limit the scope of the inventions. Indeed, the novel embodiments described herein may be embodied in a variety of other forms; furthermore, various omissions, substitutions and changes in the form of the embodiments described herein may be made without departing from the spirit of the inventions. The accompanying claims and their equivalents are intended to cover such forms or modifications as would fall within the scope and spirit of the inventions. Throughout this specification and the claims which follow, unless the context requires otherwise, the word "comprise", and variations such as "comprises" and "comprising", will be understood to imply the inclusion of a stated integer or step or group of integers or steps but not the exclusion of any other integer or step or group of integers or steps.

The reference in this specification to any prior publication (or information derived from it), or to any matter which is known, is not, and should not be taken as an acknowledgment or admission or any form of suggestion that that prior publication (or information derived from it) or known matter forms part of the common general knowledge in the field of endeavor to which this specification relates.

Claims

THE CLAIMS DEFINING THE INVENTION ARE AS FOLLOWS:

1. An operation plan creation apparatus for creating an operation plan showing at least operation state change timing and maintenance implementation timing of a target being a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the operation plan creation apparatus comprising: a frequency determiner configured to determine an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; a timing determiner configured to determine operation state change timing and maintenance implementation timing together in each section in the consideration term using the calculation model so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in each section, wherein the timing determiner assigns information regarding either the operation state or the maintenance of the target to each section in the consideration term based on the determined operation state change timing and maintenance implementation timing to create the operation plan indicating, either the operation state of the target or the maintenance implementation period for the target in each of the sections; an operation cost estimation model creator configured to create the operation cost estimation model on the basis of past operation performance of the target and each cost corresponding to each of the operation state; and a maintenance cost estimation model creator configured to create the maintenance cost estimation model on the basis of past operation performance of the target, past maintenance performance of the target, and each cost corresponding to each of the maintenance, wherein the target is a power plant, and the operation plan creation apparatus further comprises: a data acquirer configured to acquire the past operation performance and each cost corresponding to each of the operation state from the power plant; and an operation plan output device configured to output the operation state change timing determined by the timing determiner to the power plant, and the power plant is configured to change the operation state in accordance with the operation state change timing from the operation plan output device.

2. The operation plan creation apparatus according to claim 1, wherein when there are a plurality of the targets, the frequency determiner determines an operation state change frequency and a maintenance implementation frequency in the consideration term so as to reduce the total sum of operation costs and maintenance costs in the plurality of targets, and the timing determiner determines the information assigned to the each section for each of the targets so as to further satisfy a constraint on the operation state determined in the each section and related to all of the plurality of targets.

3. The operation plan creation apparatus according to claim 1 or claim 2, wherein the maintenance implementation timing includes a suspended term.

4. The operation plan creation apparatus according to any one of claims 1 to 3, wherein the data acquirer is configured to acquire the past maintenance performance of the target and each cost corresponding to each of the maintenance from a maintenance management system, and the operation plan output device is configured to output the maintenance implementation timing determined by the timing determiner to the maintenance management system.

5. The operation plan creation apparatus according to any one of claims 1 to 4, wherein the power plant is a thermal power plant.

6. An operation plan creation method for creating an operation plan showing at least operation state change timing and maintenance implementation timing of a target being a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the operation plan creation method comprising: determining an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; determining operation state change timing and maintenance implementation timing in each section in the consideration term using the calculation model so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in each section; assigning information regarding either the operation state or the maintenance of the target to each section in the consideration term based on the determined operation state change timing and maintenance implementation timing to create the operation plan indicating, either the operation state of the target or the maintenance implementation period for the target in each of the sections; creating the operation cost estimation model on the basis of past operation performance of the target and each cost corresponding to each of the operation state; and creating the maintenance cost estimation model on the basis of past operation performance of the target, past maintenance performance of the target, and each cost corresponding to each of the maintenance, wherein the target is a power plant, and the operation plan creation method further comprises: acquiring the past operation performance and each cost corresponding to each of the operation state from the power plant; and outputting the operation state change timing to the power plant, and the power plant changing the operation state in accordance with the operation state change timing.

7. A program for creating an operation plan showing at least operation state change timing and maintenance implementation timing of a target being a facility or equipment having a tendency that the number of times of maintenance increases as the number of change times of an operation state increases, the program comprising: determining an operation state change frequency and a maintenance implementation frequency in a consideration term so as to reduce the sum of an operation cost and a maintenance cost of the target in the consideration term using a calculation model including an operation cost estimation model and a maintenance cost estimation model, the operation cost estimation model being for calculating the operation cost which uses an operation state change frequency in the consideration term as a variable, and the maintenance cost estimation model being for calculating the maintenance cost which uses the operation state change frequency as a variable; determining operation state change timing and maintenance implementation timing in each section in the consideration term using the calculation model so as to satisfy the operation state change frequency and the maintenance implementation frequency in the consideration term, and a constraint on the operation state determined in the each section; assigning information regarding either the operation state or the maintenance of the target to each section in the consideration term based on the determined operation state change timing and maintenance implementation timing to create the operation plan indicating, either the operation state of the target or the maintenance implementation period for the target in each of the sections; creating the operation cost estimation model on the basis of past operation performance of the target and each cost corresponding to each of the operation state; and creating the maintenance cost estimation model on the basis of past operation performance of the target, past maintenance performance of the target, and each cost corresponding to each of the maintenance, wherein the target is a power plant, and the program further comprises: acquiring the past operation performance and each cost corresponding to each of the operation state from the power plant; and outputting the operation state change timing to the power plant, and the power plant changing the operation state in accordance with the operation state change timing.