Apparatus, method, and program

Abstract

To provide a device that supports the operation of equipment. [Solution] A device for assisting the operation of equipment, comprising a processor, the processor acquires operational records including past process parameters of the equipment and past operation parameters used to control the equipment in relation to the past process parameters, and optimizes the operation parameters output by the controller according to the process parameters using an objective function that includes a cost based on the deviation between at least one of the process parameters or operation parameters and the operational records.

Description

Technical Field

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

Background Art

[0002] Citation Document 1 describes an operation support apparatus that can support optimal operation of a target according to an operation scenario. Citation Document 2 describes an operation support apparatus that supports operation of a plant. [Prior Art Document] [Patent Document] Patent Document 1 Patent No. 7207596 Patent Document 2 Patent No. 7060130

Summary of the Invention

[0003] (1) In a first aspect of the present disclosure, there is provided an apparatus for supporting operation of facilities, including a processor that acquires an operation record including past process parameters of the facilities and past operation parameters used for control of the facilities with respect to the past process parameters, and optimizes operation parameters output by a controller according to process parameters using an objective function including a cost based on a deviation between at least one of the process parameters or the operation parameters and the operation record.

[0004] (2) In the apparatus of (1) above, the processor may optimize operation parameters output by the controller according to process parameters using an objective function including a cost based on a deviation between the process parameters, the operation parameters, and the operation record.

[0005] (3) In the apparatus of (1) or (2) above, the processor may optimize operation parameters output by the controller according to process parameters using an objective function including a cost based on a deviation between the operation parameters and the operation record.

[0006] (4) In any of the devices described in (1) to (3) above, the cost may include a penalty that increases with the degree of discrepancy between the process parameters and the actual operational results.

[0007] (5) In any of the devices described in (1) to (4) above, the objective function may be a function that adds the cost based on the deviation between the process parameter and the actual operating results to the absolute value of the difference between the process parameter and the set value for the process parameter.

[0008] (6) In the apparatus described in (5) above, the objective function may be a function that adds the cost corresponding to the minimum value among the values ​​showing the deviation between a plurality of process parameters and a plurality of operational results to the absolute value of the difference between the process parameter and the set value for the process parameter.

[0009] (7) In the apparatus of (5) or (6) above, the objective function may be a function that adds the cost obtained by multiplying a value indicating the deviation between the process parameter and the actual operating performance by a weight parameter to the absolute value of the difference between the process parameter and the set value for the process parameter.

[0010] (8) In the apparatus described in (7) above, the processor may construct a plurality of objective functions to which a plurality of different weight parameters are applied, and use the plurality of objective functions to optimize a plurality of sets of parameters of the first model that outputs the operation parameters in the controller according to the process parameters.

[0011] (9) In any of the devices described in (1) to (8) above, the processor may optimize the first model that outputs the operation parameters in the controller according to the process parameters using the second model that simulates the state of the equipment and the objective function.

[0012] (10) A second aspect of the present disclosure provides a method for assisting the operation of equipment, comprising: acquiring operational records including past process parameters of the equipment and past operating parameters used to control the equipment with respect to the past process parameters; and optimizing the operating parameters output by a controller in accordance with the process parameters using an objective function that includes a cost based on the deviation between at least one of the process parameters or the operating parameters and the operational records.

[0013] (11) In a third aspect of this disclosure, a program that assists in the operation of equipment, The present invention provides a program that causes the processor to acquire operational data including past process parameters of the equipment and past operating parameters used to control the equipment in relation to those past process parameters, and to optimize the operating parameters output by the controller in accordance with the process parameters using an objective function that includes a cost based on the discrepancy between at least one of the process parameters or the operating parameters and the operational data.

[0014] It should be noted that the above summary of the invention does not list all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0015] [Figure 1] This shows an example of the configuration of the control system 10 according to this embodiment. [Figure 2] This shows the operation of the control support device 40 during the optimization phase. [Figure 3] This shows the operation of the controller 30 during the operational phase. [Figure 4] Examples of a computer 2200 in which multiple aspects of the present invention may be embodied in whole or in part are shown. [Modes for carrying out the invention]

[0016] The present invention will be described below through embodiments of the invention, but these embodiments are not intended to limit the invention as defined in the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] Figure 1 shows an example of the configuration of the control system 10 according to this embodiment. The control system 10 according to this embodiment performs optimized control of the equipment 20 using past operational results.

[0018] Equipment 20 is installed in a plant, etc. Such a plant may be, for example, an industrial plant such as a chemical or metal plant, a plant that manages and controls wellheads and surrounding areas of gas or oil fields, a plant that manages and controls power generation such as hydroelectric, thermal, or nuclear power, a plant that manages and controls environmental power generation such as solar or wind power, a plant that manages and controls water supply and sewage systems or dams, etc. Equipment 20 may also be installed in a building or transportation facility, etc. Such equipment 20 may have one or more process devices, one or more power generation devices, and one or more other devices.

[0019] Equipment 20 may have one or more field devices. Field devices may include, for example, sensor devices such as pressure gauges, flow meters, and temperature sensors; valve devices such as flow control valves and on-off valves; actuator devices such as fans and motors; imaging devices such as cameras or video cameras for photographing the conditions or objects of the plant; acoustic devices such as microphones or speakers for collecting abnormal noises from the plant or emitting alarm sounds; position detection devices for outputting position information of Equipment 20; or other devices.

[0020] The control system 10 is connected to the facility 20. The control system 10 may be, for example, a distributed control system (DCS). The control system 10 includes a controller 30 and a control support device 40. The controller 30 is connected to the facility 20 and controls the facility 20. The controller 30 obtains process parameters measured by measuring devices such as sensors provided in the facility 20 from the facility 20. The controller 30 calculates operation parameters for controlling the facility 20 based on the process parameters obtained from the facility 20, and controls the facility 20 according to the calculated operation parameters. The facility 20 performs control such as changing the opening degree of a valve device or the operation amount of an actuator indicated by the operation parameters. The controller 30 may be installed inside or outside the control support device 40, or may be installed in a plant where the facility 20 is arranged.

[0021] Here, the process parameters indicate the operating state of the facility 20. The process parameters may indicate a physical quantity that can vary by the control of the facility 20, or may indicate an output value of the facility 20. As an example, the process parameters are measurement data such as temperature, pressure, or flow rate measured by sensor devices of the facility 20, the fuel consumption or cost of the facility 20 calculated from the measurement data, or the property value of a product manufactured by the facility 20.

[0022] Also, the operation parameters indicate the control content for the facility 20. The operation parameters may indicate a set value of the operation amount for the facility 20. As an example, the operation parameters are the raw material flow rate, temperature set value, operation amount of the actuator, or valve opening degree in the facility 20. The process parameters may vary by the control of the facility 20 according to the operation parameters.

[0023] The control support device 40 is connected to the controller 30 and sets control parameters for controlling the facility 20 for the controller 30. The control support device 40 has an acquisition unit 100, a storage unit 110, an objective function construction unit 130, a simulator construction unit 140, an optimization unit 150, and a setting unit 160.

[0024] The acquisition unit 100 is connected to the controller 30. The acquisition unit 100 acquires, via the controller 30, the operation results including the past process parameters of the facility 20 and the past operation parameters used for controlling the facility 20 with respect to the past process parameters. The acquisition unit 100 may acquire all the process parameters that can be acquired from the facility 20, or instead, may acquire some of the process parameters within the range where control support by the control support device 40 is possible. Note that the acquisition unit 100 may acquire at least some of the process parameters from the facility 20 without going through the controller 30. Also, the acquisition unit 100 may acquire one or more operation parameters set by the controller 30 for the facility 20 from the controller 30.

[0025] Here, the control parameter may be a parameter that is set in the controller 30 and used in the controller 30 for calculating the operation parameter according to the process parameter. The control parameter may be a parameter of the first model that outputs one or more operation parameters in response to the input of one or more process parameters in the controller 30. As an example, when the first model is a neural network model, the control parameter is the value of the weight, bias, and number of layers of the first model. Also, when the controller 30 calculates the operation parameter according to the process parameter by PID calculation, the control parameter is the value of the proportional gain, the value of the integral gain, and the value of the derivative gain.

[0026] The storage unit 110 is connected to the acquisition unit 100. The storage unit 110 stores the operation results acquired by the acquisition unit 100.

[0027] The objective function construction unit 130 may construct an objective function used for optimizing control parameters. The objective function construction unit 130 constructs an objective function that includes costs based on the deviation between at least one of the process parameters or operation parameters and the actual operating results. The objective function construction unit 130 may construct an objective function that includes costs based on the deviation between the process parameters and operation parameters and the actual operating results. The objective function construction unit 130 may obtain information for constructing the objective function from users such as operators of the equipment 20. The objective function construction unit 130 may obtain at least one target value, such as production volume, operating rate, or load, for at least a part of the equipment 20 from the user as information for constructing the objective function. The information for constructing the objective function may include at least one of the same parameters as the process parameters. The objective function construction unit 130 may construct an objective function based on the information for constructing the objective function. Furthermore, the objective function construction unit 130 may construct an objective function that includes costs based on the deviation between the operation parameters and the actual operating results.

[0028] The simulator construction unit 140 is connected to the memory unit 110. The simulator construction unit 140 may generate a second model (simulator) that simulates the state of the equipment 20 based on the operational history of the equipment 20. For example, the simulator construction unit 140 may generate a second model that predicts one or more process parameters of the equipment 20 in the future in response to the input of one or more operational parameters of the equipment 20. Alternatively, the simulator construction unit 140 may generate a second model that predicts one or more process parameters of the equipment 20 in the future in response to the input of one or more operational parameters and one or more process parameters of the equipment 20.

[0029] The optimization unit 150 is connected to the storage unit 110, the objective function construction unit 130, and the simulator construction unit 140. The optimization unit 150 may optimize the first model in the controller 30, which outputs operation parameters in response to the input of process parameters, using the second model constructed by the simulator construction unit 140, which simulates the state of the equipment 20, and the objective function constructed by the objective function construction unit 130.

[0030] The setting unit 160 is connected to the optimization unit 150. The setting unit 160 causes the controller 30 to set the control parameters of the first model optimized by the optimization unit 150.

[0031] Figure 2 shows the operation of the control support device 40 during the optimization phase. During the optimization phase, the control support device 40 learns the first model and the second model.

[0032] In step S200, the acquisition unit 100 acquires the operational history of the equipment 20. The acquisition unit 100 may acquire past operation parameters and past process parameters for the equipment 20 in association with each other. The acquisition unit 100 may acquire past process parameters and past operation parameters at a longer period than the period during which the controller 30 acquires process parameters for controlling the equipment 20.

[0033] In step S210, the simulator construction unit 140 constructs a simulator using operational data. The simulator construction unit 140 may generate a second model that predicts the process parameter PV1(t+1) at the next time point t+1 for z (z is a positive integer) operation parameters MV1(t), MV2(t)..., MVz(t) at a certain time point t. Here, the operation parameters MV1(t), MV2(t)..., MVz(t) may be parameters of different types or detected at different locations. The simulator construction unit 140 may generate a mathematical model as the second model.

[0034] As an example, the simulator construction unit 140 may generate a second model using a subspace identification method. The simulator construction unit 140 may use the subspace identification method to estimate the parameters A, B, and C of the second model, which represents the linear time-invariant system in equations 1 and 2 of equation 1, using the operational performance data MV1(t), MV2(t), PV1(t), t=1, ..., T.

[0035]

number

[0036] The second model in Math 1 predicts the process parameter PV1(t+1) at the next time point t+1, given the operation parameters MV1(t) and MV2(t) at a given time point t. Here, x(t) is an n-dimensional state vector representing the estimated internal state. x(t) is calculated from the operation parameters MV1(t-1), MV2(t-1), MV1(t-2), MV2(t-2), ..., MV1(t-t_horizon), MV2(t-t_horizon) and the process parameters PV1(t-1), PV1(t-2), ..., PV1(t-t_horizon) at time points prior to t. Furthermore, in the second model, PV(t+2) can be calculated by substituting x(t) calculated in Equation 1 into x(t) in Equation 2, and by substituting the operational parameters MV1(t+1) and MV2(t+1) at time t+1 into MV1(t) and MV2(t) in Equation 2.

[0037] The second model may be a machine learning model, such as a neural network, random forest, gradient boosting, logistic regression, or support vector machine (SVM).

[0038] In step S220, the objective function construction unit 130 constructs an objective function that includes a penalty that increases with increasing deviation between the process parameter and the past process parameter in operational performance. For example, the objective function may be a function that adds a cost based on the deviation between the process parameter and the past process parameter in operational performance to the absolute value of the difference between the process parameter and the set value for the process parameter. Furthermore, the objective function may include a cost based on the deviation between the operation parameter and the past operation parameter in operational performance. The objective function may include a penalty that increases with increasing deviation between the operation parameter and the past operation parameter in operational performance.

[0039] The objective function may be a function that adds a cost corresponding to the minimum value among the values ​​indicating the deviation between the process parameter and each of several past process parameters in operational performance to the absolute value of the difference between the process parameter and the set value for that process parameter. The objective function may be a function that adds a cost obtained by multiplying the value indicating the deviation between the process parameter and past process parameters in operational performance by a weight parameter to the absolute value of the difference between the process parameter and the set value for that process parameter. As an example, the objective function construction unit 130 may construct the objective function C shown in Equation 3 below.

[0040] C=C1+w*C2...Equation 3 C1 = |SV1 - PV1|

[0041] C1 represents the cost corresponding to the absolute difference between the process parameter and the set value for that process parameter, for example, the absolute difference between the process parameter PV1 and the set value SV1 for that process parameter PV1. w represents the weight parameter. C2 represents the penalty corresponding to the deviation between the process parameter and the historical process parameter in operational performance, and the deviation between the operational parameter and the historical operational parameter in operational performance. C2 may be an absolute error, relative error, mean squared error, or a function that calculates the deviation using the k-nearest neighbor method.

[0042] The following is an example of C2, which calculates the deviation using the k-nearest neighbor method (for example, k=1). First, the distance D(t) between each of the operational parameters MV1(t), MV2(t), and process parameter PV1(t) of the operational performance at multiple time points t=1, ..., T (T is an integer greater than or equal to 2), and the target operational parameter MV1, MV2, and process parameter PV1 is calculated using Equation 4.

[0043] D(t)=|MV1-MV1(t)|+|MV2-MV2(t)|+|PV1-PV1(t)|...Equation 4 t=1, ..., T

[0044] Next, let tmin be the time t at which D(t) is minimized among several time points t=1, ..., T. tmin=arg min D(t) over t=1,...,T

[0045] D(tmin) can be calculated as a penalty C2 for extrapolation. C2 = D(tmin)

[0046] Furthermore, the objective function construction unit 130 may generate objective functions using different types of process parameters for C1 and C2. Also, Equation 4 may calculate only the distance D(t) between process parameter PV1(t) and process parameter PV1. Also, Equation 4 may calculate the distance (|PV1-PV1(t)|+|PV2-PV2(t)|···) from the operational results for multiple types of process parameters. Also, Equation 4 may calculate only the distance D(t) between the operational parameter (actual value) MV1(t) and operational parameter MV1.

[0047] The weight parameter w may be set by a user, such as the operator of the equipment 20. The weight parameter w may be set according to the types of process parameters and operation parameters in the objective function, and may be set for adjustment between C1 and C2. The larger the weight parameter w, the greater the impact of the penalty corresponding to the deviation of the objective function from the actual operational results. Therefore, by setting the weight parameter w to a larger value, the user can generate a first model that allows control of the equipment 20 within a range closer to the actual operational results. The objective function construction unit 130 may construct multiple objective functions to which multiple different weight parameters are applied. The objective function construction unit 130 may allow the user to set multiple weight parameters, and may also generate multiple weight parameters based on one weight parameter set by the user. As an example, the objective function construction unit 130 generates weight parameters by multiplying one weight parameter set by the user by a predetermined coefficient.

[0048] In step S230, the optimization unit 150 optimizes the operation parameters output by the controller 30 according to the process parameters using an objective function. The optimization unit 150 may optimize the first model in the controller 30 that outputs operation parameters according to the input of process parameters. The optimization unit 150 may optimize the first model by reinforcement learning using the objective function constructed by the objective function construction unit 130 and the second model generated by the simulator construction unit 140. The optimization unit 150 may use a neural network, a support vector machine (SVM), or other machine learning model as the first model.

[0049] The optimization unit 150 inputs one or more operational parameters output from the first model to the second model in response to the input of one or more process parameters. Next, the optimization unit 150 may obtain one or more process parameters output from the second model in response to the input of one or more operational parameters output from the first model. Next, the optimization unit 150 substitutes the operational parameters output from the first model and the target process parameters output from the second model into an objective function (e.g., MV1, MV2, and PV1) and trains the first model to minimize the value calculated by the objective function. The optimization unit 150 may optimize the first model while repeating the training process.

[0050] As an example, when the controller 30 is implemented with a first neural network model, the optimization unit 150 learns to optimize the control parameters of the first model using SAC (Soft Actor-Critic) with the second model and an objective function. The optimization unit 150 acquires multiple operational parameters output from the first model in response to inputs of multiple past process parameters included in operational performance. The optimization unit 150 may also acquire process parameters output from the second model in response to inputs of multiple operational parameters. The optimization unit 150 calculates the cost using the objective function with the multiple operational parameters output from the first model and the process parameters output from the second model. The optimization unit 150 learns an evaluation function using the "multiple operational parameters output from the first model and the process parameters output from the second model" and the cost output from the objective function. The optimization unit 150 evaluates the first model with the evaluation function and learns the first model to maximize the evaluation by the evaluation function. By repeating this learning process, the optimization unit 150 can optimize the control parameters of the first model.

[0051] The optimization unit 150 may optimize multiple sets of control parameters for the first model that outputs operation parameters in the controller 30 according to process parameters, using multiple objective functions. The optimization unit 150 may generate multiple first models using multiple objective functions to which multiple different weight parameters are applied. As a result, multiple first models may output operation parameters with different values ​​when the same process parameters are input. By learning using objective functions with larger weight parameters, the optimization unit 150 can generate a first model that controls the equipment 20 so that the process parameters become closer to the past process parameters of operational performance.

[0052] In step S240, the setting unit 160 outputs the control parameters of the first model to the controller 30 for setting. The setting unit 160 may output the control parameters of multiple first models to the controller 30 along with information indicating the corresponding weight parameters (such as the magnitude of the weight parameters).

[0053] Figure 3 shows the operation of the controller 30 during the operational phase. During the operational phase, the controller 30 controls the equipment 20 using the first model.

[0054] In step S300, the controller 30 receives the control parameters of the first model generated by the control support device 40 and sets them for the operation of the equipment 20. The controller 30 may set one set of control parameters from among the multiple first models generated by the control support device 40 for the operation of the equipment 20. The controller 30 may present information indicating the weight parameters corresponding to each first model to a user such as an operator (displayed on a user terminal, etc.) and set one set of control parameters from among the multiple first models selected by the user for the operation of the equipment 20.

[0055] In step S305, the controller 30 acquires process parameters such as measurement data measured by each sensor installed in the equipment 20.

[0056] In step S310, the controller 30 obtains the operation parameters output by the first model in response to the process parameters being input to the first model.

[0057] In step S320, the controller 30 controls the equipment 20 according to the operation parameters. The controller 30 controls the equipment 20 to the value indicated by the operation parameters. Alternatively, a user such as an operator may determine the operation parameters to be used to control the equipment 20 according to the operation parameters output by the first model, and the controller 30 may control the equipment 20 according to the operation parameters determined by the user.

[0058] After control, the controller 30 proceeds to step S305 to acquire process parameters. This acquires process parameters with the equipment 20 controlled by the operation parameters. In this way, the controller 30 may repeat the process from step S305 to step S320.

[0059] According to this embodiment, a first model can be generated that is trained while taking into account the constraint of keeping process parameters and operational parameters close to those of actual operational performance. The simulator can predict process parameters with higher accuracy in the vicinity of actual operational performance, thus maintaining the reliability of the controller online.

[0060] Furthermore, the controller 30 may, during operation, receive instructions from the user to change from a set of control parameters to another set of control parameters, and may then set the other set of control parameters and perform control accordingly.

[0061] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where a block may represent (1) a stage in a process in which an operation is performed or (2) a section of a device having the role of performing the operation. Specific stages and sections may be implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable medium, and / or processors supplied with computer-readable instructions stored on a computer-readable medium. Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuits may include reconfigurable hardware circuits, including logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logic operations, flip-flops, registers, memory elements such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), etc.

[0062] Computer-readable media may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, computer-readable media having instructions stored therein will comprise a product containing instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0063] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0064] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to the processor or programmable circuit of a programmable data processing device such as a general-purpose computer, a special-purpose computer, or another computer, and the computer-readable instructions may be executed to create means for performing operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0065] Figure 4 shows an example of a computer 2200 in which multiple aspects of the present invention may be embodied in whole or in part. A program installed on the computer 2200 can cause the computer 2200 to function as an operation or one or more sections of an apparatus according to an embodiment of the present invention, or to execute such operation or one or more sections, and / or to cause the computer 2200 to execute a process or a stage of such process according to an embodiment of the present invention. Such a program may be executed by the CPU 2212 to cause the computer 2200 to perform a particular operation associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0066] The computer 2200 according to this embodiment includes a CPU 2212, RAM 2214, a graphics controller 2216, and a display device 2218, which are interconnected by a host controller 2210. The computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0067] The CPU 2212 operates according to programs stored in the ROM 2230 and RAM 2214, thereby controlling each unit. The graphics controller 2216 retrieves image data generated by the CPU 2212 from a frame buffer provided in RAM 2214 or from itself, and displays the image data on the display device 2218.

[0068] The communication interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides them to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.

[0069] The ROM 2230 stores boot programs and / or programs that depend on the computer 2200's hardware, which are executed by the computer 2200 when activated. The input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0070] The program is provided on a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from the computer-readable medium and installed on a hard disk drive 2224, RAM 2214, or ROM 2230, which are also examples of computer-readable medium, and executed by the CPU 2212. The information processing described within these programs is read by the computer 2200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the manipulation or processing of information in accordance with the use of the computer 2200.

[0071] For example, when communication is performed between a computer 2200 and an external device, the CPU 2212 may execute a communication program loaded into RAM 2214 and, based on the processing described in the communication program, instruct the communication interface 2222 to perform communication processing. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in a recording medium such as RAM 2214, a hard disk drive 2224, a DVD-ROM 2201, or an IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer processing area provided on the recording medium.

[0072] Furthermore, the CPU 2212 may read all or necessary parts of files or databases stored on external storage media such as the hard disk drive 2224, DVD-ROM drive 2226 (DVD-ROM 2201), or IC card into the RAM 2214, and perform various types of processing on the data in the RAM 2214. The CPU 2212 then writes the processed data back to the external storage media.

[0073] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 2212 may perform various types of processing on the data read from RAM 2214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to RAM 2214. The CPU 2212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 2212 may search among the multiple entries for an entry that matches the condition for which the attribute value of the first attribute is specified, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0074] The programs or software modules described above may be stored on or near computer 2200 on a computer-readable medium. Alternatively, recording media such as hard disks or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as computer-readable media, thereby providing programs to computer 2200 via the network.

[0075] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0076] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before," "prior to," etc., and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," "next," etc. for convenience, it does not mean that it is essential to perform the operations in that order.

[0077] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0078] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before," "prior to," etc., and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," "next," etc. for convenience, it does not mean that it is essential to perform the operations in that order. [Explanation of Symbols]

[0079] 10 Control Systems 20 Equipment 30 controllers 40 Control support device 100 Acquisition Department 110 Storage section 130 Objective Function Construction Section 140 Simulator Construction Department 150 Optimization Unit 160 Setting section 2200 Computers 2201 DVD-ROM 2210 Host Controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Devices 2220 Input / Output Controller 2222 Communication Interface 2224 Hard Disk Drive 2226 DVD-ROM drive 2230 ROM 2240 Input / Output Chip 2242 keyboard

Claims

1. A device that assists in the operation of equipment, Equipped with a processor, The aforementioned processor, The operational history of the equipment, including past process parameters and past operating parameters used to control the equipment for those past process parameters, is acquired. The operation parameters output by the controller according to the process parameters are optimized using an objective function that includes a cost based on the discrepancy between at least one of the process parameters or the operation parameters and the actual operational results. Device.

2. The aforementioned processor, The operation parameters output by the controller according to the process parameters are optimized using an objective function that includes the process parameters, the operation parameters, and the cost based on the discrepancy between the operation parameters and the actual operational results. The apparatus according to claim 1.

3. The aforementioned processor, The operation parameters output by the controller according to the process parameters are optimized using an objective function that includes costs based on the discrepancy between the operation parameters and the actual operational results. The apparatus according to claim 1.

4. The aforementioned cost includes a penalty that increases with the degree of discrepancy between the process parameters and the actual operational results. The apparatus according to claim 1.

5. The objective function is a function that adds the cost based on the deviation between the process parameter and the actual operating results to the absolute value of the difference between the process parameter and the set value for the process parameter. The apparatus according to claim 1.

6. The objective function is a function that adds the cost corresponding to the minimum value among the values ​​indicating the deviation between the process parameter and each of the multiple operational results to the absolute value of the difference between the process parameter and the set value for the process parameter. The apparatus according to claim 5.

7. The objective function is a function that adds the cost obtained by multiplying the value representing the deviation between the process parameter and the actual operating results by a weight parameter to the absolute value of the difference between the process parameter and the set value for the process parameter. The apparatus according to claim 5.

8. The aforementioned processor, Multiple objective functions are constructed by applying a plurality of different weight parameters to each of them, Using each of the multiple objective functions, optimize multiple sets of parameters for the first model that outputs the operation parameters in the controller according to the process parameters. The apparatus according to claim 7.

9. The aforementioned processor, In the controller, the first model that outputs the operation parameters according to the process parameters is optimized using the second model that simulates the state of the equipment and the objective function. The apparatus according to claim 1.

10. A method for supporting the operation of equipment, To acquire operational records including past process parameters of the equipment and past operating parameters used to control the equipment with respect to those past process parameters, The system includes optimizing the operation parameters output by the controller according to the process parameters using an objective function that includes a cost based on the discrepancy between at least one of the process parameters or the operation parameters and the actual operational results. method.

11. A program that supports the operation of equipment, In the processor, To acquire operational records including past process parameters of the equipment and past operating parameters used to control the equipment with respect to those past process parameters, The controller outputs operation parameters according to process parameters, and this is performed using an objective function that includes a cost based on the discrepancy between at least one of the process parameters or operation parameters and the actual operational results. program.

Images