Water treatment control device, water treatment system, water treatment control method, and program

Abstract

The water treatment control device (200) controls and manages a water treatment device using an estimation model that estimates the water quality of treated water by machine learning using the operating data of the water treatment device, and comprises estimation condition acquisition means, first explanatory variable setting means, second explanatory variable setting means, and estimation means. The estimation condition acquisition means acquires estimation conditions for setting the explanatory variables of the estimation model. The first explanatory variable setting means sets the explanatory variables specified in the estimation conditions. The second explanatory variable setting means sets other explanatory variables other than those specified in the estimation conditions based on the current operating data of the water treatment device. The estimation means integrates each explanatory variable set by the first explanatory variable setting means and the second explanatory variable setting means and inputs it into the estimation model to obtain the estimation result of the water quality of treated water as the target variable.

Description

[Technical Field]

[0001] This disclosure relates to a water treatment control device, a water treatment system, a water treatment control method, and a program. [Background technology]

[0002] Water treatment technologies are being developed to improve water quality and make it suitable for specific uses. For example, water treatment systems using reverse osmosis membranes, which treat the water to be treated and separate it into permeate and concentrated water, are used for the production of ultrapure water with extremely high purity, medical water, and industrial water, as well as for the purification and reuse of industrial wastewater and the desalination of seawater.

[0003] For example, Patent Document 1 discloses a water treatment system that collects reverse osmosis membrane operation information including the water quality of the supply water, the flow rates of the permeate and concentrated water, predicts the water quality of the permeate based on a trained model obtained by machine learning using the collected reverse osmosis membrane operation information, and optimizes the operating conditions based on the prediction results. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Patent No. 7437998 [Overview of the project] [Problems that the invention aims to solve]

[0005] Generally, changing any of the operating conditions will affect other operating conditions as well. However, the technology disclosed in Patent Document 1 does not take this effect into consideration when changing conditions. As a result, there is a risk that the accuracy of estimating the water quality of treated water when the water treatment system is operated under the set operating conditions will deteriorate.

[0006] This disclosure is made in view of the circumstances described above and aims to improve the accuracy of the estimation of treated water quality. [Means for solving the problem]

[0007] To achieve the above objectives, the water treatment control device according to this disclosure controls and manages a water treatment device using an estimation model that estimates the water quality of treated water by machine learning using operating data of the water treatment device, and comprises estimation condition acquisition means, first explanatory variable setting means, second explanatory variable setting means, and estimation means. The estimation condition acquisition means acquires estimation conditions for setting explanatory variables of the estimation model. The first explanatory variable setting means sets the explanatory variables specified in the estimation conditions. The second explanatory variable setting means sets the current operating data of the water treatment device. In addition to the explanatory variables specified in the estimation conditions, other explanatory variables are calculated and set using a predetermined calculation formula that reflects the relationships between elements included in the operating data of the water treatment device, based on the numerical values ​​of each of the other explanatory variables that are affected by changes in the explanatory variables specified in the estimation conditions. The estimation means integrates the explanatory variables set by the first explanatory variable setting means and the second explanatory variable setting means and inputs them into the estimation model to obtain the estimated result of the treated water quality as the target variable. [Effects of the Invention]

[0008] According to this disclosure, the water treatment control device obtains the estimated result of the treated water quality as the target variable by inputting explanatory variables, which are appropriately set based on the estimation conditions and the operating data of the water treatment device, into the estimation model. This makes it possible to improve the accuracy of the estimation of the treated water quality. [Brief explanation of the drawing]

[0009] [Figure 1] Block diagram showing an example configuration of a water treatment system according to an embodiment of this disclosure. [Figure 2] Block diagram showing an example of the hardware configuration of a water treatment control system. [Figure 3] Flowchart showing the flow of water quality estimation and processing [Figure 4] A flowchart illustrating the process of updating the estimated model. [Figure 5] A diagram showing an example configuration of a biological processing apparatus according to a modified example of this disclosure. [Figure 6] Diagram showing an example configuration of an agglomeration treatment device. [Figure 7] Diagram showing an example configuration of a sludge dewatering system. [Modes for carrying out the invention]

[0010] The water treatment control device, water treatment system, water treatment control method, and program according to the embodiments of this disclosure will be described in detail below with reference to the drawings. The water treatment control device, water treatment system, water treatment control method, and program according to the embodiments of this disclosure improve the accuracy of the estimation of treated water quality by the estimation model.

[0011] As shown in Figure 1, the water treatment system 1 according to the embodiment of this disclosure comprises a reverse osmosis membrane device 100 that permeates raw water through a reverse osmosis membrane to obtain permeate water, and a water treatment control device 200 that controls and manages the reverse osmosis membrane device 100. The reverse osmosis membrane device 100 and the water treatment control device 200 are connected to each other via any network. The network is composed of, for example, an internet line network, a LAN (Local Area Network), a WAN (Wide Area Network), a VPN (Virtual Private Network), a dedicated communication network, etc., and may include various network relay devices such as antennas, gateways, routers, and hubs. In this embodiment, the reverse osmosis membrane device 100 is described as an example of a water treatment device. However, it is not limited to this, and the water treatment device may be a device other than the reverse osmosis membrane device 100 that generates treated water according to the intended use. In this embodiment, the water supplied to the water treatment device and treated is referred to as "supply water," "raw water," etc., and the water treated by the water treatment device is referred to as "treated water," "permeate water," etc.

[0012] The reverse osmosis membrane apparatus 100 is a device that uses a reverse osmosis membrane with very small pores to effectively remove electrolytes that decompose into ions in solution and conduct electricity, such as sodium and calcium, as well as medium- and low molecular weight organic components such as pesticides and organic compounds, from the raw water supply water, and extracts the permeate as treated water. The reverse osmosis membrane apparatus 100 is equipped with a reverse osmosis membrane module RO having a reverse osmosis membrane. The reverse osmosis membrane apparatus 100 filters the supply water with the reverse osmosis membrane module RO to obtain permeate. The supply water that does not permeate is partially discharged to the outside as concentrated water, and part of it is returned to the supply water supply line as circulating water. The reverse osmosis membrane module RO is connected to piping for supplying the supply water, piping for discharging part of the concentrated water, piping for returning part of the concentrated water, and piping for extracting the permeate. Various measuring instruments such as water quality meters SQ, TQ for measuring water quality such as conductivity and water temperature, flow meters SF, TF, CF, RF for measuring water flow rate, and pressure gauges (not shown) for measuring water pressure are appropriately placed in these pipes. The reverse osmosis membrane apparatus 100 transmits the measurement results from these measuring instruments to the water treatment control device 200 as appropriate via a communication means (not shown). The reverse osmosis membrane apparatus 100 also performs water treatment according to the operation control information received from the water treatment control device 200 via the communication means. Although Figure 1 shows one reverse osmosis membrane module RO, multiple reverse osmosis membrane modules RO may be connected in series or in parallel. When multiple reverse osmosis membrane modules RO are connected in series, the permeate from the reverse osmosis membrane of the preceding reverse osmosis membrane module RO, i.e., the treated water, becomes the supply water for the reverse osmosis membrane of the subsequent reverse osmosis membrane module RO. The reverse osmosis membrane apparatus 100 is an example of a water treatment device.

[0013] The water treatment control device 200 is a general-purpose computer device such as a personal computer or a server computer, and controls and manages the reverse osmosis membrane device 100. The water treatment control device 200 uses an estimation model that has learned the relationship between the operation data indicating the operation state of the reverse osmosis membrane device 100 and the water quality of the permeate water by machine learning to determine the operation conditions of the reverse osmosis membrane device 100 for efficiently obtaining high-purity water quality, and controls the operation of the reverse osmosis membrane device 100 based on the determination result. Further, it determines whether it is necessary to update the estimation model based on the comparison between the estimation result and the measurement result of the water quality of the permeate water. When the water treatment control device 200 determines that it is necessary to update the estimation model, for example, it generates a new estimation model. Note that the water treatment control device 200 may be logically realized by cloud computing.

[0014] (Hardware configuration example of the water treatment control device 200) Next, a hardware configuration example of the water treatment control device 200 will be described. As shown in FIG. 2, physically, the water treatment control device 200 includes a processor 201, a memory 202, a storage 203, a display device 204, an input / output interface (input / output I / F (InterFace)) 205, and a communication interface (communication I / F) 206. These respective parts are electrically connected to each other via a bus line BL.

[0015] The processor 201 is an arithmetic device that controls the operation of the entire water treatment control device 200. The processor 201 is, for example, a general-purpose processor such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit). Further, the processor 201 is not limited to a general-purpose processor, and may be a dedicated processor composed of an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or the like.

[0016] The memory 202 is a main memory device and includes a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The processor 201 reads a control program and various data from the ROM or the storage 203 onto the RAM and executes processing, thereby realizing the control and functions of the entire water treatment control device 200.

[0017] The storage 203 is an auxiliary storage device that stores a control program and various data necessary when the control program is executed, and includes non-volatile storage devices such as an HDD (Hard Disk Drive) and an SSD (Solid State Drive). The storage 203 stores, for example, an OS (Operating System) which is basic software for controlling the entire water treatment control device 200, applications that are executed on the OS and provide various functions, etc. Further, the storage 203 stores plant information including an estimation model generated by machine learning, operation information of the reverse osmosis membrane device 100, and measurement information of each measuring instrument. Note that a part of the control program and various data necessary when the control program is executed may be stored in the ROM.

[0018] The display device 204 is an image display device such as an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), an organic EL (Electro-Luminescence) display, etc., and displays various images according to the control of the processor 201. The display device 204 displays, for example, the estimation result of the estimation model, the operation information of the reverse osmosis membrane device 100 indicated by the plant information, and the measurement information of each measuring instrument on the display screen. Note that the display device 204 may be in a form connected to the input / output interface 205 for use.

[0019] The input / output interface 205 is an interface for connecting to an input device such as a keyboard and a mouse that input an operation signal, and an output device including a speaker that outputs voice data. The input / output interface 205 receives, for example, estimation conditions input by the user via the input device.

[0020] The communication interface 206 connects to a communication network and is an interface for the water treatment control device 200 to communicate data with external devices. The communication interface 206 includes, for example, a network board, a LAN module, etc.

[0021] (Example of the functional configuration of the water treatment control device 200) Returning to Figure 1, the functional configuration of the water treatment control device 200 will be explained. As shown in Figure 1, the water treatment control device 200 functionally comprises a control unit 210, a storage unit 220, a display unit 230, an input / output unit 240, and a communication unit 250.

[0022] The control unit 210 provides overall control over the functions of the water treatment control device 200. The control unit 210 includes an estimation condition acquisition unit 211, a first explanatory variable setting unit 212, a second explanatory variable setting unit 213, an estimation unit 214, an operation guidance unit 215, an estimation model generation unit 216, an estimation model update determination unit 217, and a state observation unit 218. These components are realized, for example, by the process in which the processor 201 shown in Figure 2 executes a program that has been loaded from the storage 203 into the RAM of the memory 202. Some or all of these components may be realized by hardware such as LSI (Large Scale Integration), ASIC, FPGA, GPU, etc., or by the cooperation of software and hardware.

[0023] The estimation condition acquisition unit 211 acquires user-desired estimation conditions for setting explanatory variables of the estimation model via the input / output unit 240. The estimation conditions are conditions for setting explanatory variables of an estimation model that estimates the water quality of treated water produced when the reverse osmosis membrane apparatus 100 is operated under specific operating conditions. The user, for example, selects any element from among the elements included in the operating data, which are explanatory variables, and sets the selected element and its numerical value as the estimation condition. The operating data indicates the operating state of the reverse osmosis membrane apparatus 100 when producing treated water, and includes, for example, permeate volume, concentrated water volume, circulating water volume, reverse osmosis membrane inlet conductivity, and recycling rate. These elements have a high correlation with each other. The user, for example, sets changing the recycling rate from the current value to a desired value as the estimation condition. The estimation condition acquisition unit 211 is an example of an estimation condition acquisition means.

[0024] Here, the permeate rate is the amount of permeate produced per unit time after passing through the reverse osmosis membrane (flow rate: m³). 3 The amount of concentrated water is the amount of concentrated water that remains per unit time without passing through the reverse osmosis membrane (flow rate: m³). 3 The circulating water volume is the amount of circulating water per unit time that is returned to the supply line and reused as supply water (flow rate: m³). 3 The conductivity at the reverse osmosis membrane inlet is the electrical conductivity of the supply water supplied to the reverse osmosis membrane module RO. The recycling rate is the ratio of the amount of permeate to the sum of the amount of permeate and the amount of concentrated water, and is calculated by the following formula (1). Recycling rate = Permeate volume ÷ (Permeate volume + Concentrated volume) ……(1)

[0025] The first explanatory variable setting unit 212 sets the explanatory variables specified in the estimation conditions acquired by the estimation condition acquisition unit 211. For example, if a numerical value for the recycling rate is specified as an estimation condition, the first explanatory variable setting unit 212 sets the input value of the recycling rate included in the explanatory variables of the estimation model to the numerical value specified in the estimation condition. The first explanatory variable setting unit 212 is an example of a first explanatory variable setting means.

[0026] The second explanatory variable setting unit 213 sets explanatory variables other than those specified in the estimation conditions, based on the current operating data of the reverse osmosis membrane apparatus 100. For example, if a numerical value for the recycling rate is specified as an estimation condition, the second explanatory variable setting unit 213 sets explanatory variables other than the specified explanatory variable, the recycling rate. Other explanatory variables include permeate volume, concentrated water volume, circulating water volume, reverse osmosis membrane inlet conductivity, etc. The second explanatory variable setting unit 213 refers to the current, or most recent, operating data stored in the memory unit 220, calculates the numerical value of each of the other explanatory variables affected by the change in the recycling rate using a predetermined calculation formula, and sets the calculated numerical values ​​as explanatory variables. The second explanatory variable setting unit 213 is an example of a second explanatory variable setting means.

[0027] The estimation unit 214 obtains the estimated result of the treated water quality as the target variable for the explanatory variables based on the estimation conditions by inputting a dataset, which is an integrated dataset of the explanatory variables input from the first explanatory variable setting unit and the second explanatory variable setting unit, into the estimation model. The target variable is an index for evaluating the water quality of the treated water, for example, the conductivity of the treated water. The estimation unit 214 is an example of an estimation means.

[0028] The operation guidance unit 215 outputs at least one of the operating conditions for the reverse osmosis membrane apparatus 100 and the result of determining the suitability of the operating conditions, based on the estimation results obtained by the estimation unit 214. The operation guidance unit 215 is an example of an operation guidance means. For example, if the estimation result of the treated water quality obtained by the estimation unit 214 meets a predetermined water quality standard, the operation guidance unit 215 displays the operating data indicated by the explanatory variables based on the estimation conditions that form the basis of the estimation result as the operating conditions for the reverse osmosis membrane apparatus 100 on the display unit 230 and presents it to the user. In this case, in addition to presenting it to the user, the operation guidance unit 215 may also transmit operation control information to the reverse osmosis membrane apparatus 100, which uses the operating data indicated by the explanatory variables based on the estimation conditions as the operating conditions for the reverse osmosis membrane apparatus 100, to control the water treatment of the reverse osmosis membrane apparatus 100. Furthermore, if the estimation result does not meet predetermined water quality standards, the operation guidance unit 215 may refer to the plant information stored in the memory unit 220 and display the operating conditions suitable for the estimation conditions on the display unit 230 to present them to the user.

[0029] The estimation model generation unit 216 generates an estimation model that has learned the relationship between the operation data of the reverse osmosis membrane apparatus 100 and the water quality of the treated water. The estimation model generation unit 216 constructs an estimation model in which the operation data is the explanatory variable and the water quality of the treated water is the dependent variable by performing multivariate analysis using, for example, past operation data of the reverse osmosis membrane apparatus 100 stored in the plant information stored in the memory unit 220 and the water quality of the treated water at the time of operation based on that operation data. The learning algorithm used by the estimation model generation unit 216 can be a known algorithm such as supervised learning, unsupervised learning, or reinforcement learning. Examples of learning algorithms suitable for multivariate analysis include multiple regression, principal component regression (PCR), partial least squares regression (PLS), support vector regression (SVR), and deep learning using neural networks. The estimation model generation unit 216 stores the generated estimation model in the memory unit 220.

[0030] The estimation model update determination unit 217 determines whether the estimation model needs to be updated based on a comparison between the estimated water quality of the treated water obtained using the estimation model and the measured water quality of the treated water obtained by a measuring instrument installed in the reverse osmosis membrane device 100. The reverse osmosis membrane device 100 may experience a decrease in filtration characteristics due to clogging of the reverse osmosis membrane, deterioration over time, etc. In this case, the current estimation model may not be able to accurately estimate the water quality of the treated water. Therefore, it is necessary to ensure the accuracy of accurate water quality estimation of the treated water by determining whether the estimation model needs to be updated. For example, the estimation model update determination unit 217 compares the estimated water quality of the treated water obtained from the estimation model using operating data of the reverse osmosis membrane device 100 at a specific point in time with the measured water quality of the treated water obtained by the measuring instrument at the same point in time. If the difference between the two is greater than or equal to a preset threshold, it determines that the estimation model needs to be updated. On the other hand, if the difference between the estimated water quality of the treated water and the measured water quality is smaller than the threshold, it determines that the estimation model does not need to be updated. The estimated model update determination unit 217 is an example of an estimated model update determination means.

[0031] The status observation unit 218 collects the operating data of the reverse osmosis membrane apparatus 100 and the measured values ​​of each measuring instrument equipped in the reverse osmosis membrane apparatus 100 transmitted from the reverse osmosis membrane apparatus 100, and stores them in the storage unit 220 as plant information in time-series data.

[0032] The memory unit 220 stores control programs executed by the control unit 210, various data, etc. The memory unit 220 is implemented, for example, by the memory 202 and storage 203 shown in Figure 2. The memory unit 220 includes, for example, an estimated model memory unit 221 and a plant information memory unit 222. The estimated model memory unit 221 stores the estimated model generated by the estimated model generation unit 216. The plant information memory unit 222 stores the operating data of the reverse osmosis membrane apparatus 100 collected by the state observation unit 218 and the measured values ​​of each measuring instrument.

[0033] The display unit 230 displays various information according to the control of the control unit 210. The display unit 230 is implemented, for example, by the display device 204 shown in Figure 2. The display unit 230 displays, for example, driving data indicated by explanatory variables based on estimated conditions on the display screen according to the control of the driving guidance unit 215.

[0034] The input / output unit 240 receives various data from the input device and outputs various data to the output device according to the control of the control unit 210. The input / output unit 240 is implemented, for example, by the input / output interface 205 shown in Figure 2. The input / output unit 240 accepts estimation conditions from the user via the input device, for example.

[0035] The communication unit 250 transmits and receives various data with the reverse osmosis membrane apparatus 100 in accordance with the control of the control unit 210. The communication unit 250 is implemented, for example, by the communication interface 206 shown in Figure 2. The communication unit 250 receives measurement information transmitted from the reverse osmosis membrane apparatus 100 and transmits operation control information to the reverse osmosis membrane apparatus 100.

[0036] Next, the operation of the water treatment system 1 having the above configuration will be described. The flowchart shown in Figure 3 is an example of the operation of the water treatment system 1, and is a flowchart relating to the water quality estimation process performed by the water treatment control device 200. This operation corresponds to the water treatment control method of the water treatment control device 200 according to this embodiment.

[0037] The control unit 210 of the water treatment control device 200 starts the water quality estimation process in response to an operation input from the user of the water treatment control device 200, for example.

[0038] When the water quality estimation process is started, the control unit 210 first acquires estimation conditions (step S101). The estimation condition acquisition unit 211 of the control unit 210 acquires estimation conditions by receiving the estimation conditions input by the user via the input / output unit 240. The estimation conditions are conditions for setting explanatory variables of an estimation model that estimates the water quality of treated water produced when the reverse osmosis membrane device 100 is operated under specific operating conditions, and the user specifies at least one item included in the explanatory variables and its numerical value as the estimation conditions.

[0039] Next, the control unit 210 sets the explanatory variables specified in the estimation conditions (step S102). The first explanatory variable setting unit 212 of the control unit 210 sets the input value of the recycling rate included in the explanatory variables of the estimation model to the value specified in the estimation conditions, for example, if a numerical value of the recycling rate is specified as an estimation condition.

[0040] Next, the control unit 210 sets explanatory variables other than those specified in the estimation conditions (step S103). The second explanatory variable setting unit 213 of the control unit 210 sets input values ​​for items other than the recycling rate included in the explanatory variables of the estimation model, for example, when a numerical value of the recycling rate is specified as an estimation condition. Here, for example, if the recycling rate specified in the estimation conditions is called the new recycling rate, the amount of permeate in the explanatory variables input to the estimation model is called the new permeate amount, the amount of concentrated water in the explanatory variables input to the estimation model is called the new concentrated water amount, the current amount of permeate is called the current permeate amount, and the current amount of concentrated water is called the current concentrated water amount, then the new permeate amount is calculated by the following formula (2). However, the sum of the permeate amount and the concentrated water amount is assumed to be constant and does not change between the current situation and the time of estimation by the estimation model, as shown in formula (3). New permeate volume = New recycling rate × (New permeate volume + New concentrated water volume) ……(2) New permeated water volume + new concentrated water volume = current permeated water volume + current concentrated water volume ……(3)

[0041] For example, assume that under the estimation conditions, it is specified to set the recycling rate as an explanatory variable to 90%. In this case, the first explanatory variable setting unit 212 sets the input value of the recycling rate of the explanatory variable to 90%. On the other hand, the second explanatory variable setting unit 213 refers to the current operation data stored in the storage unit 220, and when the reverse osmosis membrane device 100 is operating at a recycling rate other than 90%, sets the numerical value of each of the other explanatory variables affected by the change in the recycling rate. When the reverse osmosis membrane device 100 is operating at a current recycling rate of 75% for example, the second explanatory variable setting unit 213 calculates the numerical value of each of the other explanatory variables affected by the change in the recycling rate to 90% under the estimation conditions using a predetermined calculation formula. When the reverse osmosis membrane device 100 is operating in a state where the permeate water volume is 100 m 3 / h, the concentrated water volume is 33.333 m 3 / h, and the recycling rate is changed from 75% to 90% under the estimation conditions, based on the above formulas (2) and (3), the input value in the explanatory variable of the permeate water volume is corrected from 100 m 3 / h to 120 m 3 / h. Also, the input value in the explanatory variable of the concentrated water volume is corrected from 33.333 m 3 / h to 13.333 m 3 / h. Thus, the second explanatory variable setting unit 213 sets the input value of each of the other explanatory variables corrected from the current operation data.

[0042] Subsequently, the control unit 210 estimates the quality of the treated water under the estimation conditions (step S104). The estimation unit 214 of the control unit 210 reads out the estimation model stored in the estimation model storage unit 221 of the storage unit 220, and estimates the quality of the treated water under the estimation conditions by inputting the data set integrating each of the explanatory variables set by the first explanatory variable setting unit 212 and the second explanatory variable setting unit 213 into the estimation model.

[0043] Next, the control unit 210 outputs the operating conditions and estimation results (step S105). The operation guidance unit 215 of the control unit 210 displays the operating conditions of the reverse osmosis membrane apparatus 100, indicated by the explanatory variables input by the estimation unit 214 into the estimation model based on the estimation conditions, and the estimation results output by the estimation model on the display screen of the display unit 230, and presents them to the user.

[0044] After executing the process in step S105, the control unit 210 terminates the water quality estimation process. In the process in step S105, the operation guidance unit 215 may display the result of the determination of the suitability of the operating conditions of the reverse osmosis membrane apparatus 100 on the display screen of the display unit 230, based on the estimation result obtained by the estimation unit 214. The operation guidance unit 215 may also control the operation of the reverse osmosis membrane apparatus 100 according to the result of the determination of the suitability of the operating conditions of the reverse osmosis membrane apparatus 100.

[0045] Next, the estimation model update process performed by the water treatment control device 200 will be explained with reference to the flowchart shown in Figure 4.

[0046] The control unit 210 of the water treatment control device 200 starts the estimation model update process, for example, in response to an operation input from the user of the water treatment control device 200 that instructs it to start. Alternatively, the estimation model update process may be performed periodically based on a pre-set plan.

[0047] When the estimated model update process is started, the control unit 210 first acquires operating data for the reverse osmosis membrane apparatus 100 at a specific point in time (step S201). The control unit 210 reads the operating data for the specific point in time from the plant information stored in the plant information storage unit 222 of the storage unit 220. The specific point in time can be any point in the past or present. In the following explanation, the specific point in time will be assumed to be the present, and in this step, the control unit 210 will acquire the current operating data.

[0048] Next, the control unit 210 estimates the water quality of the treated water at a specific point in time (step S202). The estimation unit 214 of the control unit 210 inputs the current operating data acquired in step S201 as explanatory variables into the estimation model, for example, and estimates the water quality of the treated water.

[0049] Next, the control unit 210 acquires the measurement results of the treated water quality at a specific point in time (step S203). The control unit 210 reads current operating data from the plant information stored in the plant information storage unit 222 of the storage unit 220, for example.

[0050] Next, the control unit 210 determines whether or not an update to the estimation model is necessary (step S204). The estimation model update determination unit 217 of the control unit 210 compares the current estimated result and measurement result of the treated water quality and makes the determination in this step according to the comparison result. For example, if the difference between the current estimated result and measurement result of the treated water quality is greater than or equal to a preset threshold, the estimation model update determination unit 217 determines that an update to the estimation model is necessary. On the other hand, if the difference between the estimated result and measurement result of the treated water quality is less than the threshold, it determines that an update to the estimation model is not necessary.

[0051] If it is determined that the estimation model needs to be updated (step S204: YES), the control unit 210 generates a new estimation model (step S205). The estimation model generation unit 216 of the control unit 210 generates a new estimation model using, for example, past operating data of the reverse osmosis membrane apparatus 100 stored in the plant information stored in the storage unit 220, and the water quality of the treated water at the time of operation based on that operating data, with the operating data as the explanatory variable and the water quality of the treated water as the dependent variable. The estimation model generation unit 216 replaces the conventional estimation model with the newly generated estimation model and stores it in the estimation model storage unit 221 of the storage unit 220.

[0052] If it is determined in step S204 that an update to the estimated model is not necessary (step S204: NO), or after executing the process in step S205, the control unit 210 terminates the estimated model update process. The estimated model update determination unit 217 may also notify the user of the determination result in step S204 regarding the necessity of updating the estimated model, and the fact that the estimated model has been updated, by displaying them on the display screen of the display unit 230.

[0053] As described above, in the water treatment system 1 according to this embodiment, the water treatment control device 200 acquires estimation conditions for setting explanatory variables of the estimation model, sets the explanatory variables specified in the acquired estimation conditions, and sets other explanatory variables other than those specified in the estimation conditions based on the current operating data of the reverse osmosis membrane device 100. Then, the water treatment control device 200 integrates each set explanatory variable and inputs it into the estimation model to obtain the estimated result of the treated water quality as the objective variable. This makes it possible to appropriately correct not only the explanatory variables corresponding to the estimation conditions that the user wants to estimate, but also other explanatory variables that are affected by those changes. For this reason, the estimation accuracy of the treated water quality can be improved.

[0054] Furthermore, the water treatment control device 200 outputs at least one of the operating conditions for the reverse osmosis membrane device 100 and the result of determining the suitability of the operating conditions, based on the estimation of the water quality of the treated water obtained using the estimation model. This allows for appropriate control of the operation of the reverse osmosis membrane device 100 based on the estimation result of the water quality of the treated water.

[0055] Furthermore, the water treatment control device 200 determines whether or not to update the estimation model based on a comparison between the estimated water quality of the treated water obtained using the estimation model and the measured water quality of the treated water obtained by the measuring instrument installed in the reverse osmosis membrane device 100. In this way, the accuracy of the estimation of the treated water quality can be improved by checking the estimation results of the estimation model in comparison with the measured values.

[0056] This disclosure is not limited to the embodiments described above, and various modifications and applications are possible without departing from the spirit of this disclosure.

[0057] In the above embodiment, a reverse osmosis membrane device 100 was described as an example of a water treatment device whose operation is controlled and water quality is managed by the water treatment control device 200. However, the water treatment device is not limited to a filtration device such as the reverse osmosis membrane device 100. For example, the object controlled and managed by the water treatment control device 200 may be the biological treatment device 300 shown in Figure 5. In this case, the explanatory variables are the amount of water supplied to the biological treatment tank, the quality of the supplied water, the aeration rate, the dissolved oxygen in the biological treatment, and the water temperature. For example, the estimation model assumes that the aeration rate is the current 100 m³. 3 / h to 90m 3 The water quality of the treated water is estimated when the aeration rate is changed to / h. At this time, the second explanatory variable setting unit 213 sets the explanatory variables by correcting for dissolved oxygen and other factors that need to be corrected when the aeration rate is changed.

[0058] Furthermore, the object controlled and managed by the water treatment control device 200 may be the coagulation treatment device 400 shown in Figure 6. The explanatory variables are the amount of water supplied to the coagulation tank, the amount of coagulant added, the water temperature in the coagulation tank, and the pH. The estimation model estimates the water quality of the treated water when, for example, the amount of coagulant added is changed from the current 10 L / h to 9 L / h. At this time, the second explanatory variable setting unit 213 sets the explanatory variables by correcting pH and other parameters that need to be corrected when the amount of coagulant added is changed.

[0059] Furthermore, the object controlled and managed by the water treatment control device 200 may be the sludge dewatering device 500 shown in Figure 7. In this case, it may be the estimation of the water content of the dewatered sludge. The explanatory variables are the amount of water supplied to the reaction tank, the amount of coagulant added, the water temperature in the reaction tank, and the pH. The estimation model estimates, for example, the water content of the dewatered sludge when the amount of coagulant added is changed from the current 1 L / h to 0.9 L / h. At this time, the second explanatory variable setting unit 213 sets the explanatory variables by correcting pH and other values ​​that need to be corrected when the amount of coagulant added is changed.

[0060] In the above embodiment, the water treatment control device 200 estimated the water quality of the treated water using the estimation model generated by the estimation model generation unit 216. However, the water treatment control device 200 may also incorporate an estimation model generated by an estimation model generation function provided in another water treatment system, for example, and use it to estimate the water quality of the treated water of the reverse osmosis membrane device 100. In this case, the water treatment control device 200 does not need to have the estimation model generation unit 216. Furthermore, the estimation model generation unit 216 may be implemented by a learning device independent of the water treatment system 1. Moreover, when updating the estimation model, the water treatment control device 200 may replace it with an estimation model generated externally.

[0061] Furthermore, the functions of the water treatment control device 200 described in the above embodiment may be implemented in a distributed manner by multiple computer devices. For example, the functions mainly related to estimating the water quality of treated water and the functions mainly related to maintaining the estimation model may be separated and processed by separate computer devices.

[0062] In the above embodiment, for example, the control program executed by the processor 201 that realizes the control unit 210 of the water treatment control device 200 was mainly stored in storage 203 beforehand. However, the disclosure is not limited thereto, and the control program for executing the above-mentioned various processes may be implemented in an existing general-purpose computer, framework, workstation, etc., thereby enabling it to function as a device equivalent to the water treatment control device 200 according to the above embodiment.

[0063] The method of providing such programs is optional. For example, they may be distributed by storing them on a computer-readable storage medium (flexible disk, CD (Compact Disc)-ROM, DVD (Digital Versatile Disc)-ROM), or they may be stored on network storage such as the Internet and provided for download.

[0064] Furthermore, if the above processing is performed through a division of labor between the OS and the application program, or through collaboration between the OS and the application program, only the application program may be stored on a recording medium, storage, etc. It is also possible to superimpose the program onto the carrier wave and distribute it over a network. For example, the above program may be posted on a bulletin board system (BBS) on a network and distributed over the network. The program may then be designed to execute the above processing by launching it and running it under the control of the OS, just like any other application program.

[0065] This disclosure allows for various embodiments and modifications without departing from the broad spirit and scope of this disclosure. Furthermore, the embodiments described above are for illustrative purposes only and do not limit the scope of this disclosure. In other words, the scope of this disclosure is indicated by the claims, not by the embodiments. Various modifications made within the scope of the claims and the equivalent significance of the disclosure are considered to be within the scope of this disclosure. [Explanation of Symbols]

[0066] 1...Water treatment system, 100...Reverse osmosis membrane device, 200...Water treatment control device, 201...Processor, 202...Memory, 203...Storage, 204...Display device, 205...Input / output interface, 206...Communication interface, 210...Control unit, 211...Estimated condition acquisition unit, 212...First explanatory variable setting unit, 213...Second explanatory variable setting unit, 214...Estimation unit, 215...Operation guidance unit, 216...Estimation model generation unit, 217...Estimation model update judgment unit, 218...Status observation unit, 220...Storage unit, 221...Estimation model storage unit, 222...Plant information storage unit, 230...Display unit, 240...Input / output unit, 250...Communication unit, 300...Biological treatment device, 400...Coagulation treatment device, 500...Sludge dewatering device, BL...Bus line, CF,SF,TF,RF...Flow meter, RO...Reverse osmosis membrane module, SQ,TQ...Water quality meter.

Claims

1. A water treatment control device that controls and manages a water treatment device using an estimation model that estimates the water quality of treated water by machine learning using operating data of the water treatment device, An estimation condition acquisition means for acquiring estimation conditions for setting explanatory variables of the estimation model, A first explanatory variable setting means for setting the explanatory variables specified in the estimation conditions, A second explanatory variable setting means calculates and sets explanatory variables other than those specified in the estimation conditions, based on the current operating data of the water treatment device, using a predetermined calculation formula that reflects the relationships between elements included in the operating data of the water treatment device, for each of the other explanatory variables that are affected by changes in the explanatory variables specified in the estimation conditions. The system includes an estimation means that integrates the explanatory variables set by the first explanatory variable setting means and the second explanatory variable setting means and inputs them into the estimation model to obtain the estimation result of the treated water quality as the objective variable, Water treatment control device.

2. The system further comprises an operation guidance means that outputs at least one of the operating conditions of the water treatment device and a determination result of the suitability of the operating conditions, based on the estimation results obtained by the estimation means. The water treatment control device according to claim 1.

3. The system further includes an estimation model update determination means that determines whether or not the estimation model needs to be updated based on a comparison between the estimation results obtained using the estimation model and the water quality measurement results of the treated water obtained by a measuring instrument installed in the water treatment device. The water treatment control device according to claim 1 or 2.

4. The water treatment device is a filtration device, The water quality estimated by the estimation means is the water quality of the permeate from the filtration device. The water treatment control device according to claim 1.

5. The water treatment apparatus and, The water treatment control device described in claim 1, The water treatment apparatus generates treated water according to its intended use, under the control and management of the water treatment control device. Water treatment system.

6. A water treatment control method executed by a water treatment control device that controls the operation of a water treatment device using an estimation model that estimates the water quality of treated water by machine learning using the operation data of the water treatment device, The computer provided in the aforementioned water treatment control device Obtain the estimation conditions for setting the explanatory variables of the estimation model, The explanatory variables specified in the estimation conditions are set, Based on the current operating data of the water treatment device, other explanatory variables other than those specified in the estimation conditions are calculated and set using a predetermined calculation formula that reflects the relationships between elements included in the operating data of the water treatment device, and the numerical values ​​of each of the other explanatory variables that are affected by changes in the explanatory variables specified in the estimation conditions are calculated. The set explanatory variables are integrated and input into the estimation model, and the estimated result of the treated water quality is obtained as the objective variable. Water treatment control method.

7. A computer in a water treatment control device that controls and manages the water treatment device is provided, which uses an estimation model that estimates the water quality of treated water by machine learning using the operating data of the water treatment device. Estimation condition acquisition means for acquiring estimation conditions for setting explanatory variables of the estimation model, A first explanatory variable setting means for setting the explanatory variables specified in the estimation conditions, A second explanatory variable setting means calculates and sets explanatory variables other than those specified in the estimation conditions, based on the current operating data of the water treatment device, using a predetermined calculation formula that reflects the relationships between elements included in the operating data of the water treatment device, for each of the numerical values ​​of the other explanatory variables that are affected by changes in the explanatory variables specified in the estimation conditions. The first explanatory variable setting means and the second explanatory variable setting means integrate the explanatory variables set by the first explanatory variable setting means and input them into the estimation model, and function as an estimation means to obtain the estimated result of the treated water quality as the target variable. program.

Images