Control device and processing system

Abstract

To provide a control device and a processing system in which an estimated value for a processing result can be accurately calculated in a processing facility.SOLUTION: A control device for calculating an estimated value for the result of prescribed processing in a processing facility comprises: a data acquisition unit for acquiring a first input value showing processing conditions on the processing facility at a first timing when the prescribed processing is performed; a first correction value calculation unit for calculating a first correction value corresponding to a first estimated value for the processing result at the first timing on the basis of the acquired first input value; and a data estimation unit for estimating the first estimated value at the first timing on the basis of the acquired first input value and the calculated first correction value.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to a control device and a processing system. [Background technology]

[0002] For example, in a water purification plant, a water treatment facility (hereinafter simply referred to as a water treatment facility) is installed to produce purified water (hereinafter also referred to as treated water) from raw water such as river water or well water (hereinafter also referred to as water to be treated). In such a water treatment facility, control is performed based on, for example, predicted values ​​of treatment results at a future timing. Specifically, in a water treatment facility, control is performed based on, for example, predicted values ​​of the temperature of the treated water (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-010614 Summary of the Invention [Problem to be solved by the invention]

[0004] Here, in various treatment systems (hereinafter also simply referred to as treatment systems) including treatment equipment such as the water treatment equipment described above (hereinafter also simply referred to as treatment equipment), it is desirable to accurately calculate predicted values ​​for the treatment results of the treatment equipment at future times, for example. [Means for solving the problem]

[0005] The control device in the present disclosure is a control device that calculates a predicted value for a processing result of a predetermined process in a processing facility, and includes: a data acquisition unit that acquires a first input value that indicates the processing conditions of the processing facility at a first timing when the predetermined process is executed; a first correction value calculation unit that calculates a first correction value that corresponds to a first predicted value for the processing result at the first timing based on the acquired first input value; and a data prediction unit that predicts the first predicted value at the first timing based on the acquired first input value and the calculated first correction value. [Effects of the Invention]

[0006] According to the control device and processing system of the present disclosure, it is possible to accurately calculate a predicted value for the processing result in the processing facility. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating a configuration of a processing system 100 according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating the hardware configuration of the control device 1. As shown in FIG. [Figure 3] FIG. 3 is a functional block diagram of the control device 1 in the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating a specific example of the configuration of the processing equipment 10. [Figure 5] FIG. 5 is a flowchart illustrating the learning process according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating the prediction process according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating the prediction process according to the first embodiment. [Figure 8] FIG. 8 is a flowchart illustrating the prediction process in the first modified example. [Figure 9] FIG. 9 is a flowchart illustrating the prediction process in the second modified example. [Figure 10] FIG. 10 is a diagram illustrating the prediction process in the second modified example. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. However, such descriptions should not be interpreted in a limiting sense, and do not limit the subject matter described in the claims. Furthermore, various changes, substitutions, and modifications can be made without departing from the spirit and scope of the present disclosure. Furthermore, different embodiments can be combined as appropriate.

[0009] [Processing system 100 according to the first embodiment] First, a description will be given of an example of the configuration of a processing system 100 according to the first embodiment. Fig. 1 is a diagram illustrating the configuration of a processing system 100 according to the first embodiment.

[0010] As shown in Fig. 1, the treatment system 100 includes, for example, treatment equipment 10 that performs a predetermined treatment, a monitoring device 2 that monitors the treatment equipment 10, and a control device 1 that controls the operation of the treatment equipment 10 based on the monitoring results by the monitoring device 2. In the example shown in Fig. 1, the control device 1 and the monitoring device 2 are each accessible to each other, for example, via a network NW. Below, we will explain a case where the treatment system 100 is a water treatment system that produces treated water from water to be treated, the predetermined treatment is a process such as filtration of the water to be treated, the treatment equipment 10 is a water treatment equipment that performs the filtration of the water to be treated, and the monitoring device 2 monitors the treatment status of the water treatment equipment.

[0011] The monitoring device 2 is, for example, an electronic device having an electronic circuit. Specifically, the monitoring device 2 is, for example, one or more physical machines or one or more virtual machines having a CPU (Central Processing Unit) and a memory. The monitoring device 2 monitors the processing state of the processing facility 10 by, for example, acquiring measured values ​​measured by a measuring device (not shown) installed in the processing facility 10. Specifically, the monitoring device 2 monitors the processing state of the processing facility 10 by, for example, determining whether the acquired measured values ​​are within a predetermined normal range.

[0012] The control device 1 is, for example, an electronic device having an electronic circuit. Specifically, the control device 1 is, for example, one or more physical machines or one or more virtual machines having a CPU and a memory. The control device 1 performs a process (hereinafter also simply referred to as a prediction process) to predict a predicted value (hereinafter also simply referred to as a predicted value) for a processing result in the processing facility 10.

[0013] Specifically, the control device 1 predicts, for example, a predicted value for the temperature of the treated water produced in the treatment facility 10. The control device 1 also predicts, for example, a predicted value for the water quality (for example, turbidity or concentration of suspended solids) of the treated water produced in the treatment facility 10.

[0014] More specifically, the control device 1 acquires an input value (hereinafter also referred to as a first input value) indicating the processing conditions of the processing equipment 10 at the timing (hereinafter also referred to as a first timing) when a predetermined processing is executed. The first timing is, for example, the present timing or a future timing. The input value is, for example, data (values) indicating the flow rate, temperature, etc. of the water to be processed flowing into the processing equipment 10.

[0015] Then, the control device 1 calculates a correction value (hereinafter also referred to as the first correction value) corresponding to a predicted value (hereinafter also referred to as the first predicted value) for the processing result at the first timing, for example, based on the acquired first input value. The correction value is, for example, a value used to calculate the first predicted value at the first timing. Thereafter, the control device 1 predicts the first predicted value at the first timing, for example, based on the acquired first input value and the calculated first correction value.

[0016] That is, for example, when calculating a predicted value at a first timing, the control device 1 in this embodiment uses the first input value at the first timing to calculate a first correction value suitable for correcting the first predicted value at the first timing. Then, the control device 1 calculates the first predicted value at the first timing by using, for example, the calculated first correction value in addition to the first input value.

[0017] This allows the control device 1 in this embodiment to, for example, accurately calculate a predicted value at each timing.

[0018] Specifically, the control device 1 can calculate the first predicted value at the first timing with higher accuracy than when, for example, the same correction value is used to calculate the predicted value at each timing.

[0019] [Hardware configuration of control device 1] Next, a description will be given of the hardware configuration of the control device 1. Fig. 2 is a diagram illustrating the hardware configuration of the control device 1.

[0020] 2, the control device 1 includes, as electronic circuits, a CPU 101 which is a processor, a memory 102, a communication device 103, and a storage medium 104. Each unit is connected to one another via a bus 105.

[0021] The storage medium 104 has, for example, a program storage area (not shown) that stores a program 110 for performing the prediction process. The storage medium 104 also has, for example, a storage unit 130 (hereinafter also referred to as information storage area 130) that stores information used when performing the prediction process. The storage medium 104 may be, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0022] The CPU 101 performs the prediction process by executing a program 110 loaded from the storage medium 104 to the memory 102, for example.

[0023] The communication device 103 accesses the monitoring device 2 via the network NW, for example. The communication device 103 also accesses an operation terminal (not shown) operated by an operator via the network NW, for example.

[0024] The network NW may be, for example, the Internet. That is, the control device 1 may be located on a cloud, for example. The network NW may be, for example, a LAN (Local Area Network).

[0025] The control device 1 may also include, for example, an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). Furthermore, the control device 1 may also include, for example, a PIC (Peripheral Interface Controller). In this case, the prediction process may be executed in, for example, the FPGA or ASIC.

[0026] [Functions of the control device 1 in the first embodiment] Next, the functions of the control device 1 in the first embodiment will be described. Figure 3 is a block diagram of the functions of the control device 1 in the first embodiment.

[0027] As shown in FIG. 3, the control device 1 realizes various functions including a data acquisition unit 111, a first correction value calculation unit 112, a data prediction unit 113, a second correction value calculation unit 114, and a data management unit 115 by organically cooperating with hardware such as a CPU 101 and a memory 102 and a program.

[0028] 3, the control device 1 stores, for example, operating data 131 (hereinafter also referred to as correspondence information 131) and a prediction model MD in an information storage area 130.

[0029] [Functions in prediction processing] First, the functions in the prediction process will be described.

[0030] The data acquisition unit 111 acquires at least one of an input value (hereinafter also referred to as input value 131a) and an output value (hereinafter also referred to as output value 131b) measured by a measuring device provided in the treatment facility 10 at each predetermined timing (hereinafter also simply referred to as the predetermined timing), such as every minute, every hour, or every day. The input value 131a is, for example, data (value) indicating the processing conditions of the predetermined processing executed by the treatment facility 10 at each timing. The output value 131b is, for example, data (value) indicating the processing result of the predetermined processing executed by the treatment facility 10 at each timing. Specifically, the input value 131a is, for example, data indicating the flow rate, temperature, etc. of the water to be treated flowing into the treatment facility 10 at each timing. The output value 131b is, for example, data indicating the temperature, etc. of the treated water flowing out of the treatment facility 10 at each timing.

[0031] The first correction value calculation unit 112 calculates a correction value (hereinafter also referred to as correction value 131c) that is used by the data acquisition unit 111 to calculate the output value 131b at each timing, based on the input value 131a, for example.

[0032] Specifically, the first correction value calculation unit 112 identifies, for example, a past input value 131f (for example, a past input value 131f closest to the input value 131a acquired by the data acquisition unit 111) whose closeness to the input value 131a acquired by the data acquisition unit 111 satisfies a predetermined condition among past input values ​​(hereinafter also referred to as past input values ​​131f or second input values ​​131f) included in the operating data 131 stored in the information storage area 130. Then, the correction value calculation unit 112 identifies, for example, a past correction value (hereinafter also referred to as past correction value 131g or second correction value 131g) stored in association with the identified past input value 131f, as the correction value 131c corresponding to the input value 131a acquired by the data acquisition unit 111.

[0033] The data prediction unit 113 predicts a predicted value of the output value 131b at each timing (hereinafter also referred to as a predicted value 131d) based on, for example, the input value 131a acquired by the data acquisition unit 111 and the correction value 131c calculated by the first correction value calculation unit 112. Then, the data prediction unit 113 outputs the predicted predicted value 131d to, for example, an operation terminal or the like.

[0034] Specifically, the data prediction unit 113 uses, for example, a prediction model MD to calculate a predicted value 131d at each timing from the input value 131a acquired by the data acquisition unit 111 and the correction value 131c calculated by the first correction value calculation unit 112. The prediction model MD is, for example, a model formed of a mathematical formula. Specific examples of the prediction model MD will be described later.

[0035] The second correction value calculation unit 114 calculates a correction value 131c at each timing based on, for example, the input value 131a acquired by the data acquisition unit 111 and the output value 131b acquired by the data acquisition unit 111.

[0036] Specifically, the second correction value calculation unit 114 calculates a correction value 131c at each timing from the input value 131a acquired by the data acquisition unit 111 and the output value 131b acquired by the data acquisition unit 111, for example, by using a prediction model MD.

[0037] The data management unit 115 stores, in the information storage area 130, driving data 131 including, for example, an input value 131a acquired by the data acquisition unit 111, an output value 131b acquired by the data acquisition unit 111, and a correction value 131c calculated by the first correction value calculation unit 112 or the second correction value calculation unit 114.

[0038] The control device 1 may determine whether or not the processing equipment 10 is in operation, for example, based on the input value 131a acquired by the data acquisition unit 111. Specifically, the control device 1 may determine whether or not the input value 131a acquired by the data acquisition unit 111 is a value corresponding to the processing equipment 10 in operation. Then, the control device 1 (data prediction unit 113) may predict the predicted value 131d when it is determined that the processing equipment 10 is in operation, for example.

[0039] In addition, the following description will be given on the assumption that one control device 1 executes the prediction process, but the present invention is not limited to this. Specifically, the functions required to execute the prediction process may be distributed among a plurality of control devices 1 (hereinafter simply referred to as a plurality of control devices 1) that can access each other via a network NW. In this case, the prediction process may be executed by the plurality of control devices 1 cooperating with each other.

[0040] [Specific example of the configuration of the processing facility 10] Next, a specific example of the configuration of the treatment facility 10 in the first embodiment will be described. Fig. 4 is a diagram illustrating a specific example of the configuration of the treatment facility 10. Below, a case where the control device 1 predicts a predicted value for the temperature of the treated water produced in the treatment facility 10 will be described.

[0041] The treatment equipment 10 shown in FIG. 4 may be, for example, a settling basin into which the untreated water first flows and which settles and removes sediment and other particles contained in the untreated water, or a receiving well that adjusts the amount of untreated water supplied from the settling basin to downstream equipment. The treatment equipment 10 shown in FIG. 4 may be, for example, a mixing basin that injects a coagulant into the untreated water supplied from the receiving well, or a flocculation basin that agitates the untreated water supplied from the mixing basin to coagulate suspended matter contained in the untreated water and form flocs. The treatment equipment 10 shown in FIG. 4 may be, for example, a sedimentation basin that settles and separates flocs contained in the untreated water supplied from the flocculation basin, or a filtration basin that filters the untreated water supplied from the sedimentation basin. The treatment equipment 10 shown in FIG. 4 may be, for example, a purified water reservoir that temporarily stores treated water supplied from a filtration basin, or a distribution reservoir that temporarily stores treated water supplied from the purified water reservoir and supplies it to homes, etc.

[0042] That is, when the treatment equipment 10 is a mixing basin, the predetermined treatment performed in the treatment equipment 10 may be, for example, a treatment of injecting a coagulant into the water to be treated. When the treatment equipment 10 is a flocculation basin, the predetermined treatment performed in the treatment equipment 10 may be, for example, a treatment of aggregating suspended matter contained in the water to be treated with a coagulant to form flocs. When the treatment equipment 10 is a sedimentation basin, the predetermined treatment performed in the treatment equipment 10 may be, for example, a treatment of precipitating flocs contained in the water to be treated and separating them from the water to be treated. When the treatment equipment 10 is a filtration basin, the predetermined treatment performed in the treatment equipment 10 may be, for example, a treatment of filtering the water to be treated.

[0043] Furthermore, the example shown in FIG. 4 indicates, for example, that the flow rate (e.g., flow rate per unit time) of the water to be treated flowing into the treatment equipment 10 from the upstream equipment is M1, the temperature is Th1, and the amount of heat is Q1. The example shown in FIG. 4 also indicates, for example, that the amount of heat (e.g., radiant heat) given to the treatment equipment 10 when a predetermined treatment is performed on the water to be treated flowing in from the upstream equipment is Q2. The example shown in FIG. 4 also indicates, for example, that the temperature of the water to be treated (treated water) flowing out from the treatment equipment 10 to the downstream equipment is Th2 and the amount of heat is Q3. The example shown in FIG. 4 also indicates, for example, that the amount of heat lost from the treatment equipment 10 when a predetermined treatment is performed on the water to be treated flowing in from the upstream equipment is Q4. The example shown in FIG. 4 also indicates, for example, that the temperature of the outside air when the predetermined treatment is performed is Th0.

[0044] That is, the example shown in FIG. 4 is an example in which, for example, Th0, Th1, M1, Q1, Q2, Q3, and Q4 are input values ​​131a, and Th2 is an output value 131b.

[0045] The control device 1 may acquire, for example, at least one of Th0, Th1, M1, Q1, Q2, Q3, and Q4 as the input value 131a. The control device 1 may also acquire, for example, other data such as the residence time of the water to be treated in the treatment facility 10 as the input value 131a.

[0046] [Example of prediction model MD] Next, a specific example of the prediction model MD will be described.

[0047] The prediction model MD is a model configured by, for example, the following formulas (1) to (5).

[0048]

number

[0049]

number

[0050]

number

[0051]

number

[0052]

number

[0053] Each of Th0, Th1, Th2, M1, Q1, Q2, Q3, and Q4 in the above formulas (1) to (5) is, for example, the same as each variable described in Fig. 4. Furthermore, f(Th0) in the above formulas (3) and (5) is, for example, a function of Th0. Furthermore, each of k2 in the above formula (3) and k4 in the above formula (5) is, for example, the correction value 131c.

[0054] That is, the control device 1 (first correction value calculation unit 112) can calculate the output value 131b, Th2, by inputting the input values ​​131a, Th0, Th1, M1, Q1, Q2, Q3, and Q4, and the correction values ​​131c, k2 and k4, into the prediction model MD constructed by the formulas shown in the above formulas (1) to (5).

[0055] Furthermore, the control device 1 (second correction value calculation unit 114) can calculate the correction values ​​131c, k2 and k4, by inputting the input values ​​131a, Th0, Th1, M1, Q1, Q2, Q3 and Q4, and the output value 131b, Th2, into the prediction model MD constructed by the formulas shown in the above formulas (1) to (5), for example.

[0056] [Prediction process in the first embodiment] Next, the prediction process in the first embodiment will be described. Fig. 5 is a flowchart illustrating the prediction process in the first embodiment. Fig. 6 and Fig. 7 are diagrams illustrating the prediction process in the first embodiment.

[0057] The prediction process in the first embodiment is a process that is performed, for example, when it is possible to determine that the time difference between the timing at which the prediction process is performed and the timing to be predicted by the prediction process (first timing) is small and that the difference between the input value 131a at the timing at which the prediction process is performed and the input value 131a at the first timing is small. Also, the prediction process in the first embodiment is a process that is performed, for example, when it is possible to determine that the change over time in the input value 131a at each timing is small even if the time difference between the timing at which the prediction process is performed and the timing to be predicted by the prediction process (first timing) is large.

[0058] As shown in FIG. 5, the data acquisition unit 111 acquires, for example, at each predetermined timing, an input value 131a measured by a measuring device provided in the processing facility 10 at each timing (step S1 in FIG. 5).

[0059] Specifically, as described with reference to FIG. 4, the data acquiring unit 111 acquires, for example, Th0, Th1, M1, Q1, Q2, Q3, and Q4 as the input values ​​131a.

[0060] Then, the first correction value calculation unit 112 calculates the correction value 131c at each timing based on the input value 131a acquired in step S1, for example (step S2 in FIG. 5).

[0061] Specifically, the first correction value calculation unit 112, for example, identifies a past input value 131f that satisfies a predetermined condition in terms of proximity to the input value 131a acquired by the data acquisition unit 111, from among the past input values ​​131f included in the driving data 131 stored in the information storage area 130. Then, the correction value calculation unit 112 identifies, for example, a past correction value 131g that is stored in association with the identified past input value 131f, as the correction value 131c that corresponds to the input value 131a acquired by the data acquisition unit 111.

[0062] Furthermore, the data prediction unit 113 predicts a predicted value 131d at each timing based on, for example, the input value 131a acquired in step S1 and the correction value 131c calculated in step S2 (step S3 in FIG. 5). Then, the data prediction unit 113 outputs the predicted value 131d to, for example, an operation terminal or the like.

[0063] Specifically, as shown in FIG. 6, the data prediction unit 113 predicts a predicted value 131d at each timing from the input value 131a acquired in step S1 and the correction value 131c calculated in step S2, for example, by using the prediction model MD described in FIG. 4.

[0064] Thereafter, the data acquiring unit 111 acquires, for example, the output value 131b measured by a measuring device provided in the processing facility 10 at each timing (step S4 in FIG. 5).

[0065] Specifically, as described with reference to FIG. 4, the data acquiring unit 111 acquires, for example, Th2 as the output value 131b.

[0066] Then, the data management unit 115 stores the operating data 131, which includes, for example, the input value 131a acquired in step S1, the correction value 131c calculated in step S2, and the output value 131b acquired in step S4, in the information storage area 130 (step S5 in FIG. 5).

[0067] It should be noted that the control device 1 may not perform, for example, steps S4 and S5 in the prediction process. Specific examples of the operating data 131 will be described below.

[0068] [Example of Operation Data 131] FIG. 7 is a diagram illustrating a specific example of the operating data 131.

[0069] In the example shown in FIG. 7, the operating data 131 acquired (calculated) at time T0 indicates, for example, that the input values ​​131a, Th0, Th1, and M1 are "30," "20," and "100," respectively, the output value 131b, Th2, is "20," and the correction values ​​131c, k2 and k4, are "0.2" and "0.5," respectively.

[0070] In the example shown in FIG. 7, when the time is T N-C The operating data 131 acquired (calculated) at a timing indicates, for example, that the input values ​​131a, Th0, Th1, and M1 are "19," "9," and "91," respectively, the output value 131b, Th2, is "15," and the correction values ​​131c, k2 and k4, are "0.1" and "0.4," respectively.

[0071] In the example shown in FIG. 7, when the time is T N-2 The operating data 131 acquired (calculated) at a timing indicates, for example, that the input values ​​131a, Th0, Th1, and M1 are "10," "15," and "130," respectively, the output value 131b, Th2, is "85," and the correction values ​​131c, k2 and k4, are "0.15" and "0.7," respectively.

[0072] In the example shown in FIG. 7, when the time is T N-1The operating data 131 acquired (calculated) at a timing indicates, for example, that the input values ​​131a, Th0, Th1, and M1 are "15," "13," and "100," respectively, the output value 131b, Th2, is "30," and the correction values ​​131c, k2 and k4, are "0.2" and "0.4," respectively.

[0073] In the example shown in FIG. 7, when the time is T N The operating data 131 acquired (calculated) at the timing T indicates that, for example, the input values ​​131a, Th0, Th1, and M1, are "20," "10," and "90," respectively. N The operating data 131 acquired (calculated) at a timing indicates that, for example, Th2, which is the output value 131b, and k2 and k4, which are the correction values ​​131c, have not yet been acquired (calculated).

[0074] In the example shown in FIG. 7, when the time is T N The operating data 131 acquired (calculated) at a timing indicates that, for example, the input values ​​131a Th0, Th1, and M1, the output value 131b Th2, and the correction values ​​131c k2 and k4 have not yet been acquired (calculated).

[0075] [Example (1) of the process in step S2] Next, a first specific example of the process in step S2 will be described.

[0076] The first correction value calculation unit 112, for example, refers to the driving data 131 stored in the information storage area 130, and identifies the past input value 131f corresponding to the input value 131a acquired in step S1. Then, the first correction value calculation unit 112, for example, identifies the past correction value 131g stored in association with the identified past input value 131f, as the correction value 131c corresponding to the input value 131a acquired in step S1.

[0077] Specifically, the first correction value calculation unit 112 identifies, for example, a past input value 131f (for example, a past input value 131f closest to the input value 131a acquired in step S1) whose closeness to the input value 131a acquired in step S1 satisfies a predetermined condition among the past input values ​​131f included in the driving data 131 stored in the information storage area 130. Then, the correction value calculation unit 112 identifies, for example, a past correction value 131g stored in association with the identified past input value 131f, as the correction value 131c corresponding to the input value 131a acquired in step S1.

[0078] More specifically, in the example shown in FIG. N In the operation data 131 acquired (calculated) at the timing T , for example, "20", "10", and "90" are set as the input values ​​131a, Th0, Th1, and M1, respectively. N-C In the operating data 131 acquired (calculated) at a timing T, for example, "19", "9", and "91" are set as Th0, Th1, and M1, which are input values ​​131a. N-C The values ​​of Th0, Th1, and M1 at the timing when the time is T N If the values ​​of Th0, Th1, and M1 are closest to the values ​​of Th0, Th1, and M1 at the timing T N-C The values ​​"0.1" and "0.4" of k2 and k4 at the timing T N are respectively identified as k2 and k4 at the timings.

[0079] [Specific example (2) of the process in step S2] Next, a second specific example of the process in step S2 will be described.

[0080] The first correction value calculation unit 112, for example, refers to the driving data 131 stored in the information storage area 130 and identifies a plurality of past correction values ​​131g corresponding to each of a plurality of times. Then, the first correction value calculation unit 112, for example, identifies a value calculated from each of the identified plurality of past correction values ​​131g as the correction value 131c corresponding to the input value 131a acquired in step S1.

[0081] Specifically, the first correction value calculation unit 112 identifies, for example, the average value or median value (hereinafter simply referred to as the average value, etc.) of the past correction values ​​131g included in each of the driving data 131 stored in the information storage area 130 as the correction value 131c corresponding to the input value 131a acquired in step S1.

[0082] 7, for example, values ​​including "0.2", "0.1", "0.15", and "0.2" are set as the correction value 131c k2 in each of the operation data 131. Therefore, the correction value calculation unit 112 calculates the average value of each value including "0.2", "0.1", "0.15", and "0.2", and sets the calculated value as the time T N 7, the correction value 131c is set to k4, which is the correction value 131c, for example, values ​​including "0.5", "0.4", "0.7", and "0.4". Therefore, the correction value calculation unit 112 calculates the average value of the values ​​including "0.5", "0.4", "0.7", and "0.4", and sets the calculated value as k2 at the timing when the time is T N The timing is identified as k4.

[0083] [Example (3) of the process in step S2] Next, a third specific example of the process in step S2 will be described.

[0084] For example, the first correction value calculation unit 112 inputs the input value 131a acquired in step S1 to a learning model (not shown) generated in advance, and identifies a value output from the learning model to which the input value 131a has been input as the correction value 131c corresponding to the input value 131a acquired in step S1. The learning model here may be, for example, a learning model generated by learning a plurality of teacher data (not shown) each including the input value 131a and the correction value 131c included in each driving data 131.

[0085] In this manner, the control device 1 in this embodiment acquires, for example, first input values ​​131a indicating processing conditions of the processing equipment 10 at a first timing when a predetermined process is executed. Then, the control device 1 calculates, for example, a first correction value 131c corresponding to a first predicted value 131d for the processing result at the first timing based on the acquired first input values ​​131a. Thereafter, the control device 1 predicts the first predicted value 131d at the first timing based on, for example, the acquired first input values ​​131a and the calculated first correction value 131c.

[0086] Specifically, the control device 1 acquires, for example, the second correction value 131g included in the operating data 131 stored in the information storage area 130. Then, the control device 1 calculates the first correction value 131c by using, for example, the acquired second correction value 131g. Thereafter, the control device 1 calculates the first predicted value 131d from the first input value 131a and the first correction value 131c by using, for example, the prediction model MD.

[0087] More specifically, in the process of calculating the first correction value 131c, the control device 1 calculates, for example, an average value of the acquired second correction values ​​131g as the first correction value 131c.

[0088] Furthermore, the control device 1, for example, refers to the information storage area 130 that stores the operating data 131, and identifies the first correction value 131c that corresponds to the first input value 131a. Then, the control device 1 calculates the first predicted value 131d from the first input value 131a and the first correction value 131c, for example, by using the prediction model MD.

[0089] More specifically, for example, in the process of calculating the first correction value 131c, the control device 1 identifies the second input value 131f that is closest to the first input value 131a from among the second input values ​​131f included in the driving data 131 stored in the information storage area 130, and identifies the second correction value 131g stored in correspondence with the identified second input value 131f as the first correction value 131c.

[0090] This allows the control device 1 in this embodiment to accurately calculate the predicted value at the first timing, for example.

[0091] Specifically, the control device 1 can calculate the predicted value at the first timing with higher accuracy than when, for example, the same correction value is used to calculate the predicted value at each timing.

[0092] [Prediction process in the first modified example] Next, a prediction process in a modified example of the first embodiment (hereinafter also referred to as the first modified example) will be described. Fig. 8 is a flowchart illustrating the prediction process in the first modified example.

[0093] The prediction process in the first modified example is a prediction process that is performed, for example, when it is possible to determine that there is a large time difference between the timing at which the prediction process is performed and the timing (first timing) to be predicted by the prediction process, and that there is a large change over time in the input value 131a at each timing. That is, the prediction process in the first modified example is a prediction process that is performed, for example, when it is possible to determine that there is a large difference between the input value 131a at the timing at which the prediction process is performed and the input value 131a at the timing (first timing) to be predicted by the prediction process. Below, differences from the prediction process in the first embodiment described with reference to FIG. 5 etc. will be described.

[0094] For example, instead of step S1 described in FIG. 5, the correction value calculation unit 112 calculates a predicted value of the input value 131a at the first timing (hereinafter also referred to as input predicted value 131e) from the past input value 131f included in the driving data 131 stored in the information storage area 130 (step S11 in FIG. 8).

[0095] Specifically, the data acquisition unit 111 acquires, for example, the driving data 131 shown in FIG. 7 from T0 to T N Then, the first correction value calculation unit 112 obtains Th0, Th1, and M1 included in the operating data 131 corresponding to each of the above. N From the rate of change of Th0 between N+1 Calculate Th0 corresponding to T0 and N The change rate of Th1 between 1 and 20 N+1 Calculate the corresponding Th1 and calculate the time from T0 to T N The rate of change of M1 between N+1 Furthermore, the first correction value calculation unit 112 calculates M1 corresponding to T0 to T N Th0 to T N+1 Calculate Th0 corresponding to T0 and N Th1 to T N+1 Calculate the corresponding Th1 and calculate the time from T0 to TN M1 to T corresponding to each N+1 Calculate M1 corresponding to

[0096] Then, the first correction value calculation unit 112 calculates the correction value 131c at each timing based on the input predicted value 131e calculated in step S11, for example (step S12 in FIG. 8). Specifically, the first correction value calculation unit 112 performs the same process as the process in step S2 in the first embodiment, for example, by using the input predicted value 131e calculated in step S11 as the input value 131a.

[0097] Thereafter, the control device 1 performs, for example, the same processes as steps S3 to S5 in FIG. 5 (steps S13 to S15 in FIG. 8).

[0098] In this manner, the control device 1 in this modification acquires, for example, the second input value 131f included in the operating data 131 stored in the information storage area 130. Then, the control device 1 calculates the predicted input value 131e, for example, by using the second input value 131f. Furthermore, the control device 1 identifies, for example, the first correction value 131c corresponding to the calculated predicted input value 131e. That is, in this case, the control device 1 identifies the first correction value 131c, for example, by using the predicted input value 131e as the first input value 131a (by using the predicted input value 131e instead of the first input value 131a).

[0099] Thereafter, the control device 1 calculates the first predicted value 131d from the input predicted value 131e and the first correction value 131c, for example, by using the prediction model MD. That is, in this case, the control device 1 specifies the first predicted value 131d by using the input predicted value 131e as the first input value 131a (by using the input predicted value 131e instead of the first input value 131a).

[0100] This allows the control device 1 in this modification to more accurately calculate the predicted value at the first timing, for example.

[0101] [Prediction process in the second modified example] Next, a prediction process in a modified example of the second embodiment (hereinafter also referred to as the second modified example) will be described. Fig. 9 is a flowchart illustrating the prediction process in the second modified example. Fig. 10 is a diagram illustrating the prediction process in the second modified example.

[0102] The prediction process in the second modified example is, for example, a process that is performed when accumulating the operating data 131 as a pre-stage process before predicting the predicted value 131d at the first timing.

[0103] As shown in FIG. 9, the data acquiring unit 111 acquires, for example, at each predetermined timing, an input value 131a measured by a measuring device provided in the processing facility 10 at each timing (step S21 in FIG. 9).

[0104] Then, the data acquiring unit 111 acquires, for example, the output value 131b measured by a measuring device provided in the processing facility 10 at each timing (step S22 in FIG. 9).

[0105] Thereafter, the second correction value calculation unit 114 calculates a correction value 131c (hereinafter also referred to as a correction value 131c1) at each timing based on, for example, the input value 131a acquired in step S21 and the output value 131b acquired in step S22 (step S23 in Figure 9).

[0106] Specifically, as shown in FIG. 10, the second correction value calculation unit 114 predicts a correction value 131c at each timing from the input value 131a obtained in step S21 and the output value 131b obtained in step S22, for example, by using the prediction model MD described in FIG. 4.

[0107] Then, the data management unit 115 stores new operating data 131 including, for example, the input value 131a acquired in step S21, the output value 131b acquired in step S22, and the correction value 131c calculated in step S23 in the information storage area 130 (step S24 in FIG. 9).

[0108] In the process of step S23, the second correction value calculation unit 114 may, for example, specify as the input value 131a a past input value 131f (e.g., a past input value 131f closest to the input value 131a acquired in step S1) that satisfies a predetermined condition in terms of proximity to the input value 131a acquired in step S21, among the past input values ​​131f included in the driving data 131 stored in the information storage area 130. Then, the correction value calculation unit 112 may, for example, specify as the correction value 131c (hereinafter, correction value 131c2) corresponding to the input value 131a acquired in step S21 a past correction value 131g that is stored in association with the specified past input value 131f. That is, the first correction value calculation unit 112 may, for example, calculate the correction value 131c2 at each timing by performing a process similar to the first specific example of the process of step S2. Thereafter, the data prediction unit 113 may calculate a predicted value 131d at each timing from the input value 131a acquired in step S21 and the calculated correction value 131c2, for example, by using the prediction model MD described in FIG. 4.

[0109] As a result, for example, if the predicted value 131d calculated in step S23 and the output value 131b acquired in step S22 satisfy a predetermined relationship (for example, if the difference between the predicted value 131d calculated in step S23 and the output value 131b acquired in step S22 is less than a predetermined threshold), the second correction value calculation unit 114 may adopt the correction value 131c2 as the correction value 131c calculated in step S23. On the other hand, for example, if the calculated predicted value 131d and the output value 131b acquired in step S22 do not satisfy the predetermined relationship, the second correction value calculation unit 114 may adopt the correction value 131c1 as the correction value 131c calculated in step S23.

[0110] In this manner, the control device 1 in this modification acquires, for example, an output value 131b (hereinafter also referred to as a first output value 131b) indicating a processing result at a first timing. Then, the control device 1 calculates a correction value 131c (hereinafter also referred to as another correction value 131c) from the first input value 131a and the first output value 131b, for example, by using the prediction model MD. Thereafter, the control device 1 stores, in the information storage area 130, new operating data 131 that associates the first input value 131a, the another correction value 131c, and the first output value 131b, for example.

[0111] Furthermore, the control device 1 in this modification, for example, refers to the information storage area 130 that stores the operating data 131, and identifies the correction value 131c (hereinafter also referred to as the other correction value 131c) that corresponds to the first input value 131a and the first output value 132b. Then, the control device 1 stores, in the information storage area 130, new operating data 131 that associates the first input value 132a, the other correction value 131c, and the first output value 132b, for example.

[0112] Specifically, for example, when the first predicted value 131d and the first output value 131b satisfy a predetermined condition, the control device 1 stores new operating data 131 in the information storage area 130, which associates the first input value 132a, another correction value 131c, and the first output value 132b.

[0113] This allows the control device 1 in this modification to more accurately calculate the predicted value at the first timing, for example.

[0114] In the above example, the treatment system 100 is a water treatment system that produces treated water from water to be treated, and the treatment equipment 10 is a water treatment equipment that performs predetermined processing such as filtration of the water to be treated, but this is not limited to this.

[0115] Specifically, the treatment system 100 is an incineration system that incinerates sludge (hereinafter simply referred to as sludge) such as sewage sludge, and the treatment equipment 10 may be a dehydrator (hereinafter simply referred to as a dehydrator) that dehydrates sludge or an incinerator (hereinafter simply referred to as an incinerator) that incinerates sludge.

[0116] More specifically, when the treatment facility 10 is a dehydrator, the input value 131a may be, for example, at least one of the flow rate, temperature, solid concentration, and viscosity of the sludge supplied to the dehydrator, and the output value 131b may be, for example, the moisture content of the sludge discharged from the dehydrator (the sludge after dehydration). When the treatment facility 10 is an incinerator, the input value 131a may be, for example, at least one of the flow rate, temperature, and moisture content of the sludge supplied to the incinerator, and the output value 131b may be, for example, the amount of thermal energy recovered in a heat exchanger (not shown) that is a downstream facility of the incinerator. [Explanation of symbols]

[0117] 1: Control device 2: Monitoring device 10: Processing equipment 101: CPU 102: Memory 103: Communication device 104: Storage medium 105: Bus 110: Program 111: Data acquisition section 112: First correction value calculation unit 113: Data prediction unit 114: Second correction value calculation unit 115: Data storage unit 130: Memory unit 131: Operation data 131a: Input value 131b: Output value 131c: Corrected value 131d: Predicted value 131e: Forecast value 131f: Past input value 131g: Past correction value 100: Processing system MD: Prediction model NW: Network

Claims

1. A control device that calculates a predicted value for a processing result of a predetermined process in a processing facility, a data acquisition unit that acquires a first input value that indicates a processing condition of the processing equipment at a first timing when the predetermined processing is executed; a first correction value calculation unit that calculates a first correction value corresponding to a first predicted value for the processing result at the first timing based on the acquired first input value; a data prediction unit that predicts the first predicted value at the first timing based on the acquired first input value and the calculated first correction value.

2. The data acquisition unit acquires a first output value indicating the processing result at the first timing, and further a second correction value calculation unit that calculates another first correction value from the first input value and the first output value by using a prediction model; The control device according to claim 1 , further comprising: a storage unit configured to store other correspondence information that associates the first input value, the other first correction value, and the first output value.

3. further comprising a storage unit configured to store correspondence information associating a second input value indicating a processing condition of the processing equipment at a second timing, the second input value indicating a processing condition of the processing equipment at a second timing that is a timing prior to the first timing and at which the predetermined processing is executed, a second correction value corresponding to a predicted value of the processing result at the second timing, and a second output value indicating the processing result at the second timing; The first correction value calculation unit refer to the storage unit that stores the correspondence information, and acquire the second correction value; Calculating the first correction value by using the acquired second correction value; The control device according to claim 1 , wherein the data prediction unit calculates a first predicted value from the first input value and the first correction value by using a prediction model.

4. further comprising a storage unit configured to store correspondence information associating a second input value indicating a processing condition of the processing equipment at a second timing, the second input value indicating a processing condition of the processing equipment at a second timing that is a timing prior to the first timing and at which the predetermined processing is executed, a second correction value corresponding to a predicted value of the processing result at the second timing, and a second output value indicating the processing result at the second timing; the first correction value calculation unit refers to a storage unit that stores the correspondence information, and identifies the first correction value that corresponds to the first input value; The control device according to claim 1 , wherein the data prediction unit calculates a first predicted value from the first input value and the first correction value by using a prediction model.

5. The data acquisition unit acquires a first output value indicating the processing result at the first timing, and further a storage unit that stores correspondence information that associates a second input value that indicates a processing condition of the processing equipment at a second timing that is a timing before the first timing and when the predetermined processing is executed, a second correction value that corresponds to a predicted value for the processing result at the second timing, and a second output value that indicates the processing result at the second timing; a second correction value calculation unit that refers to a storage unit that stores the correspondence information and identifies another first correction value that corresponds to the first input value and the first output value, The control device according to claim 1 , wherein the storage unit stores other correspondence information that associates the first input value, the other first correction value, and the first output value.

6. 6. The control device according to claim 5, wherein the storage unit stores other correspondence information that associates the first input value, the other first correction value, and the first output value when the first predicted value and the first output value satisfy a predetermined condition.

7. further comprising a storage unit configured to store correspondence information associating a second input value indicating a processing condition of the processing equipment at a second timing, the second input value indicating a processing condition of the processing equipment at a second timing that is a timing prior to the first timing and at which the predetermined processing is executed, a second correction value corresponding to a predicted value of the processing result at the second timing, and a second output value indicating the processing result at the second timing; The first correction value calculation unit refer to the storage unit that stores the correspondence information, and acquire the second input value; calculating a predicted input value that is a predicted value of the first input value by using the second input value; referring to the storage unit that stores the correspondence information, and specifying a first correction value that corresponds to the input predicted value; The control device according to claim 1 , wherein the data prediction unit calculates the first predicted value from the input predicted value and the first correction value by using a prediction model.

8. A processing system comprising a processing facility and a control device that calculates a predicted value for a processing result of a predetermined process in the processing facility, The control device a data acquisition unit that acquires a first input value that indicates a processing condition of the processing equipment at a first timing when the predetermined processing is executed; a first correction value calculation unit that calculates a first correction value corresponding to a first predicted value for the processing result at the first timing based on the acquired first input value; a data prediction unit that predicts the first predicted value at the first timing based on the acquired first input value and the calculated first correction value.

Images