Injection ratio calculation system, water treatment system, and injection ratio calculation method

The injection rate calculation system enhances chemical injection accuracy in water treatment by using upstream data and machine learning to correct and update models, addressing time lags and data mismatches in existing systems.

JP2024170201AActive Publication Date: 2024-12-06KUBOTA CORP
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
JP2023087229
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-26
Publication Date
2024-12-06
Estimated Expiration
2043-05-26

AI Technical Summary

Technical Problem

Existing water treatment systems face challenges in accurately determining the injection rate of chemicals like flocculants and chlorine due to time lags and mismatches in learning data with current water conditions, leading to suboptimal treatment outcomes.

Method used

An injection rate calculation system that utilizes upstream data and evaluation indices to estimate and correct the injection rate of chemicals using an estimation model, which is updated through machine learning with teacher data, integrating feedback and feedforward controls to enhance accuracy.

Benefits of technology

Improves the accuracy of chemical injection rates in water treatment systems by aligning estimates with real-time water conditions, reducing time delays and optimizing treatment efficacy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024170201000001_ABST
    Figure 2024170201000001_ABST
Patent Text Reader

Abstract

To improve the accuracy of the injection ratio of a chemical to be injected to treat raw water flowing into a water purification plant.SOLUTION: An injection ratio calculation system (2) comprises an acquiring unit (21) acquiring upstream data measured at least on one of a position of injecting a chemical and an upstream position relative to the injection position and an evaluation index evaluating the state of mixed water injected with a chemical, an injection ratio estimation unit (22) of estimating the injection ratio of the chemical from the upstream data using an estimation model, an injection ratio correction unit (41) of correcting the estimated injection ratio according to the evaluation index, and an updating unit (51) of updating the estimation model using teacher data using the upstream data as explanatory variables and using the corrected injection ratio as an object variable.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a technique for calculating the injection rate of a chemical agent used in a water purification facility. [Background technology]

[0002] In water treatment systems, various chemicals such as chlorine and coagulants are added to produce water with a quality that meets a predetermined standard. For this reason, it is important to control the amount of the above-mentioned chemicals added.

[0003] The model generation device described in Patent Document 1 generates a regression model for estimating the injection rate of a coagulant to be injected into inflow water flowing into a water purification plant. The model generation device generates a plurality of clusters by clustering a set of data sets including water quality data including pre-injection turbidity, which is the turbidity of the inflow water before the coagulant is injected, and the injection rate of the coagulant injected into the inflow water. Next, the model generation device generates the regression model for each of the generated clusters using learning data that has the water quality data as an explanatory variable and the injection rate as a target variable.

[0004] The flocculant injection control device described in Patent Document 2 performs feedback control using the flocculation state of flocs in mixed water, which is the water to be treated into which a flocculant has been injected, as a controlled variable and the injection rate of the flocculant to the water to be treated as a manipulated variable. The flocculant injection control device also determines a target value of the controlled variable in the feedback control based on the turbidity of a settling basin in which flocs in the mixed water are settled and its target value.

[0005] In the flocculant injection control system described in Patent Document 3, the raw water turbidity charge amount estimation means estimates the amount of charge on the surface of the turbidity particles contained in the raw water, and the post-flocculation charge state measurement means measures the charge state after the flocculant is injected. The flocculant injection rate setting device calculates a basic flocculant injection rate according to the amount of charge on the surface of the turbidity particles contained in the raw water, and corrects the basic flocculant injection rate according to the charge state after the flocculant is injected to determine the actual injection rate. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent Publication No. 2021-098191 [Patent Document 2] JP 2019-193916 A [Patent Document 3] JP 2002-205076 A Summary of the Invention [Problem to be solved by the invention]

[0007] In the model generating device described in Patent Document 1, if the learning data no longer matches the current conditions of the inflow water, the estimated value of the coagulant injection rate may not be the optimal value. In the coagulant injection control device described in Patent Document 2, a time lag occurs between measuring the turbidity of the settling basin and changing the coagulant injection rate. For this reason, if the water quality of the water to be treated changes suddenly, the turbidity of the settling basin will temporarily worsen. By combining feedforward (FF) control and feedback (FB) control as in Patent Document 3, the above problems of Patent Documents 1 and 2 can be solved to some extent, but there is still room for improvement.

[0008] An object of one aspect of the present invention is to provide an injection rate estimation system that can improve the accuracy of the injection rate of an agent injected to treat raw water flowing into a water purification facility. [Means for solving the problem]

[0009] In order to solve the above problems, an injection rate calculation system according to one embodiment of the present invention is an injection rate calculation system that calculates the injection rate of a chemical to be injected to treat raw water flowing into a water purification facility, and includes an acquisition unit that acquires upstream data measured at at least one of the injection position of the chemical and a position upstream of the injection position, and an evaluation index that evaluates the state of the mixed water after the chemical is injected, an estimation unit that estimates the injection rate of the chemical from the upstream data using an estimation model, a correction unit that corrects the injection rate estimated by the estimation unit based on the evaluation index, and an update unit that updates the estimation model using teacher data that uses the upstream data as an explanatory variable and the injection rate corrected by the correction unit as a target variable.

[0010] Another aspect of the present invention is an injection rate calculation system that calculates the injection rate of a chemical to be injected to treat raw water flowing into a water purification facility, and includes an acquisition unit that acquires upstream data measured at at least one of the injection position of the chemical and a position upstream of the injection position, and an optimization unit that optimizes the injection rate of the chemical using an estimation model constructed using teacher data in which the upstream data and the injection rate of the chemical are explanatory variables and an evaluation index that evaluates the state of the mixed water after the chemical is injected is an objective variable, so that the evaluation index estimated from the upstream data and the injection rate of the chemical becomes a target value.

[0011] A water treatment system according to yet another aspect of the present invention includes an injection rate calculation system having the above-described configuration, and a control device that controls injection of the chemical agent in accordance with the injection rate calculated by the injection rate calculation system.

[0012] An injection rate calculation method according to yet another aspect of the present invention includes an acquisition step of acquiring upstream data measured at at least one of the injection position of a chemical to be injected to treat raw water flowing into a water purification facility and a position upstream of the injection position, and an evaluation index for evaluating the state of the mixed water after the chemical is injected, an estimation step of estimating the injection rate of the chemical from the upstream data using an estimation model, a correction step of correcting the injection rate estimated in the estimation step based on the evaluation index, and an update step of updating the estimation model using teacher data in which the upstream data is an explanatory variable and the injection rate corrected by the correction unit is an objective variable.

[0013] An injection rate calculation method according to yet another aspect of the present invention includes an acquisition step of acquiring upstream data measured at at least one of the injection position of a chemical to be injected to treat raw water flowing into a water purification facility and a position upstream of the injection position, and an optimization step of optimizing the injection rate of the chemical using an estimation model in which the upstream data and the injection rate of the chemical are explanatory variables and an evaluation index for evaluating the state of the mixed water after the chemical is injected is an objective variable, so that the evaluation index estimated from the upstream data and the injection rate of the chemical becomes a target value. Effect of the Invention

[0014] According to one aspect of the present invention, it is possible to improve the accuracy of the injection rate of an agent injected to treat raw water flowing into a water purification facility. [Brief description of the drawings]

[0015] [Figure 1] 1 is a diagram showing an overview of a water treatment system according to an embodiment of the present invention. [Diagram 2] 2 is a block diagram showing an example of a configuration of a main part of an injection rate calculation system in the water treatment system. FIG. [Diagram 3] 4 is a flowchart showing an example of a flow of an injection rate calculation process in the water treatment system having the above configuration. [Figure 4]1 is a graph showing a change over time in raw water turbidity, which is an example of an explanatory variable in the injection rate calculation system, and the injection rate of the coagulant, which is the objective variable, in one embodiment of the water treatment system. [Diagram 5] 13 is a graph showing a variation of the water treatment system, illustrating changes over time in raw water turbidity, which is an example of the explanatory variable, and in the injection rate of the coagulant, which is the objective variable. [Figure 6] 13 is a graph showing a time variation of an injection rate of powdered activated carbon, which is an example of the explanatory variable, and an injection rate of a flocculant, which is the response variable, in another embodiment of the water treatment system. [Figure 7] FIG. 1 is a diagram showing an overview of a water treatment system according to another embodiment of the present invention. [Figure 8] 2 is a block diagram showing an example of a configuration of a main part of an injection rate calculation system in the water treatment system. FIG. [Figure 9] 5 is a flowchart showing an example of a flow of an injection rate calculation process in a front-stage in the water treatment system having the above configuration. [Figure 10] 4 is a flowchart showing an example of a flow of a middle stage injection rate calculation process in the water treatment system having the above configuration. [Figure 11] 5 is a flowchart showing an example of the flow of a latter-stage injection rate calculation process in the water treatment system having the above configuration. [Figure 12] 13 is a block diagram showing an example of a configuration of a main part of an injection rate calculation system in a water treatment system according to yet another embodiment of the present invention. FIG. [Figure 13] 4 is a flowchart showing an example of a flow of an injection rate calculation process in the water treatment system having the above configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, embodiments of the present invention will be described in detail. For the sake of convenience, the same reference numerals will be used to designate members having the same functions as those in the embodiments, and descriptions thereof will be omitted as appropriate.

[0017] [Embodiment 1] An embodiment of the present invention will be described with reference to FIGS.

[0018] (Water Treatment System) Fig. 1 is a diagram showing an overview of a water treatment system according to the present embodiment. The water treatment system 1 of the present embodiment is a system that treats raw water flowing into a water purification facility from, for example, a river, into clean water. Specifically, the water treatment system 1 of the present embodiment realizes a coagulation and sedimentation process in which suspended solids and the like contained in the raw water are coagulated by a coagulant and separated from the raw water by gravitational sedimentation.

[0019] As shown in FIG. 1, the water treatment system 1 includes a receiving well 101, a rapid mixing basin 102, a flocculation basin 103, and a settling basin 104 as facilities for implementing the coagulation and sedimentation process.

[0020] The receiving well 101 is a tank for suppressing the agitation of the water surface caused by the raw water sent through the water conveyance pipe and for ensuring the hydraulic stability of the raw water sent to the equipment following the receiving well 101. A chlorine agent and a pH (hydrogen ion concentration index) adjuster may be injected into the raw water. Here, the chlorine agent is an agent for disinfecting the raw water. The chlorine agent is, for example, an agent such as sodium hypochlorite, and is injected between the receiving well 101 and the rapid mixing basin 102 by an injection device not shown. The pH adjuster is an agent for adjusting the pH of the raw water. The pH adjuster is, for example, an agent such as sulfuric acid or sodium hydroxide (caustic soda), and is injected between the receiving well 101 and the rapid mixing basin 102 by an injection device not shown. Powdered activated carbon may be introduced between the intake point upstream of the receiving well 101 and the rapid mixing basin 102. Powdered activated carbon is used for removing odorous substances, trihalomethanes and trihalomethane precursors, and the like.

[0021] The receiving well 101 is provided with a water quality meter 111. The water quality meter 111 measures the quality of the raw water that has arrived at the receiving well 101. The water quality is at least turbidity, and other examples include color, water temperature, conductivity, pH (hydrogen ion concentration index), alkalinity (acid consumption), and ultraviolet absorbance. The water quality meter 111 may be provided in the rapid mixing basin 102, or in a waterway upstream of the rapid mixing basin 102. Data indicating the water quality measured by the water quality meter 111 is input to the injection rate calculation system 2.

[0022] A flow meter 112 is provided in the water conveyance pipe between the receiving well 101 and the rapid mixing basin 102. The flow meter 112 measures the flow rate of raw water sent from the receiving well 101 to the rapid mixing basin 102. The data of the flow rate measured by the flow meter 112 is input to a coagulant injection device 113.

[0023] The rapid mixing basin 102 is a mixing basin for injecting a coagulant into the raw water sent from the receiving well 101 to rapidly mix it. Here, the coagulant is a chemical agent for coagulating substances contained in the raw water. The coagulant is, for example, polyaluminum chloride (PAC) or aluminum sulfate (aluminum sulfate), and is injected into the rapid mixing basin 102 by a coagulant injector 113.

[0024] The rapid mixing basin 102 is provided with a rapid mixer 114 for carrying out the rapid mixing. The rapid mixer 114 is, for example, a flash mixer. The rapid mixer 114 may be one that operates at a constant mixing speed, or one that can adjust the mixing speed by controlling a motor. In the rapid mixing basin 102, minute flocs are formed by the injection of a coagulant and the mixing by the rapid mixer 114. The treated water containing such minute flocs is sent to the subsequent flocculation basin 103, where further agglomeration of the flocs is promoted in the facilities following the flocculation basin 103.

[0025] The flocculation basin 103 is a tank for slow stirring to form larger flocs in the treated water. The flocculation basin 103 is provided with a slow stirrer 115. Stirring of the treated water by the slow stirrer 115 promotes further agglomeration of the flocs. The slow stirrer 115 is, for example, a flocculator. The treated water in the flocculation basin 103 is sent to the downstream settling basin 104 after stirring for a predetermined period of time. The flocculation basin 103 may be of a bypass type that does not use an agitator.

[0026] The flocculation basin 103 is also provided with a camera 116. The camera 116 photographs the flocs formed in the flocculation basin 103. From the static photographed image of the flocs, the diameter, area, volume, etc. of the flocs can be estimated, and the formation state of the flocs can be confirmed. It is also possible to estimate the movement speed of the flocs from the dynamic photographed image of the flocs, and confirm the formation state of the flocs. Data of the photographed image is input to the injection rate calculation system 2 as an evaluation index for evaluating the flocculation state.

[0027] It is desirable to install the camera 116 at an appropriate position depending on the state of floc formation to be confirmed. When checking the state of floc formation at the earliest possible stage of floc formation, installing the camera at a more upstream position within the range where it can be photographed reduces the time delay between the estimation of the coagulant injection rate and the judgment of the quality of coagulation, and it is possible to suppress the adverse effect on the water quality of the settled water due to poor coagulation to a short period of time. Conversely, when checking the state of floc formation when floc formation has progressed sufficiently, installing the camera at a more downstream position within the range where it can be photographed is sufficient.

[0028] Also, a measuring device capable of measuring an index capable of evaluating the quality of the flocculation state, such as a zeta potential or a streaming current value, may be provided instead of the camera 116. In this case, the water quality data measured by the measuring device is input to the injection rate calculation system 2 as an evaluation index for feedback correction of the injection rate.

[0029] The settling basin 104 is a basin for settling and separating agglomerated flocs contained in the inflow from the flocculation basin 103. The inflow is retained in the settling basin 104 for a predetermined time (for example, about 1 to 3 hours), whereby flocs having large particle sizes formed in the flocculation basin 103 settle by gravity. As a result, the flocs are separated from the treated water, and the supernatant liquid is sent to a filtration basin (not shown) as settled water. Note that a facility for carrying out additional treatment such as ozone treatment or biological activated carbon treatment on the treated water sent to the filtration basin may be provided downstream of the settling basin 104. The flocs that have settled in the settling basin 104 are extracted as sludge and sent to a sludge treatment facility (not shown).

[0030] When the flocculation basin 103 is omitted and the settling basin 104 is changed to a high-speed flocculation sedimentation basin, the state of floc formation may be evaluated in a sludge blanket zone where flocs are grown in the high-speed flocculation sedimentation basin.

[0031] The filter basin is a basin equipped with a filtration system that filters the sedimentation water flowing in from the sedimentation basin 104. In the filter basin, minute suspended solids remaining in the sedimentation water are separated by filtration. The filtered sedimentation water is disinfected with a chlorine agent and then supplied to consumers as tap water.

[0032] (Injection rate calculation system) As shown in Fig. 1, the water treatment system 1 includes an injection rate calculation system 2. The injection rate calculation system 2 calculates the injection rate of the coagulant to be injected into the raw water according to the attributes of the raw water, etc. Here, the injection rate is the ratio of the coagulant to be injected into the raw water relative to the raw water. Conventionally, the injection rate has been determined using the results of a jar test, past knowledge, a predetermined calculation formula, etc.

[0033] The injection rate calculation system 2 outputs the calculated injection rate to the flocculant injector 113. The flocculant injector 113 determines the injection amount of flocculant based on the flow rate data from the flow meter 112 and the injection rate from the injection rate calculation system 2, and injects it into the rapid mixing basin 102. The injection rate calculation system 2 may be configured by one information processing device equipped with a hardware and software configuration group, or may be configured by multiple information processing devices.

[0034] 2 is a block diagram showing an example of a configuration of a main part of the injection rate calculation system 2. The injection rate calculation system 2 includes an estimation device 11, a correction device 12, a model updating device 13, an input device 14, an output device 15, and a storage device 16.

[0035] The input device 14 accepts a user input and outputs an input signal based on the input to the estimation device 11, the correction device 12, or the model updating device 13. The input device 14 also outputs input signals from various devices to the estimation device 11 or the correction device 12.

[0036] The output device 15 outputs the information generated by the correction device 12. The output method by the output device 15 is not particularly limited. For example, the output device 15 may be a display device that displays the information as an image, or may be an audio output device that outputs the information as audio. The output device 15 may also be a control signal output device that outputs the information as an electrical signal to various devices such as the coagulant injection device 113.

[0037] The storage device 16 holds programs and data used in the injection rate calculation system 2. The storage device 16 includes an estimation model storage unit 31, a target value storage unit 32, and a teacher data storage unit 33. The data held (stored) in these storage units 31 to 33 will be described later.

[0038] (estimation device) The estimation device 11 uses an estimation model to estimate the injection rate of the coagulant to be injected into the raw water. The estimation device 11 includes a control unit 20. The control unit 20 controls each part of the estimation device 11. The control unit 20 is realized by a processor and a memory, for example. In this example, the processor accesses a storage (not shown), loads a program (not shown) stored in the storage into the memory, and executes a series of instructions included in the program. In this way, each part included in the control unit 20 is configured.

[0039] The control unit 20 includes an acquisition unit 21 and an injection rate estimation unit 22 (estimation unit). The estimation model storage unit 31 stores the estimation model.

[0040] The acquisition unit 21 acquires input data, which is data input from the input device 14. The input data is upstream data, which is data acquired at at least one of the injection position where the coagulant injection device 113 injects the coagulant and a position upstream of the injection position. The upstream data includes attribute data indicating the attributes of the raw water, the injection rate of chemicals other than the coagulant injected between the intake point upstream of the receiving well 101 and the rapid mixing basin 102, and the amount of return water from the distribution reservoir that is mixed with the raw water at the receiving well 101.

[0041] A typical example of the attribute data is the quality of raw water, including raw water turbidity, which is the turbidity of the raw water. Other examples of the attribute data include the flow rate of raw water, the presence or absence of discharge from a dam located upstream of a water purification facility, and the mixing ratio of water from multiple water sources when there are multiple sources of raw water. Examples of chemicals other than the coagulant include chlorine agents, acid agents such as sulfuric acid, alkali agents such as sodium hydroxide, powdered activated carbon, etc.

[0042] The acquiring unit 21 stores the acquired input data in the teacher data storage unit 33. The acquiring unit 21 stores the input data in the teacher data storage unit 33 at each predetermined timing, whereby a set of the input data is stored in the teacher data storage unit 33.

[0043] The injection rate estimation unit 22 estimates the injection rate of the flocculant injected into the raw water by using the estimation model read from the estimation model storage unit 31. The injection rate estimation unit 22 obtains the injection rate of the flocculant by inputting the upstream data to the estimation model. Then, the injection rate estimation unit 22 outputs the obtained injection rate to the correction device 12.

[0044] (Correction device) The correction device 12 corrects the injection rate of the flocculant estimated by the estimation device 11 based on an evaluation index of the flocculation state in the flocculation basin 103 after the injection of the flocculant. The correction device 12 includes a control unit 40. The control unit 40 controls each unit of the correction device 12. The control unit 40 has the same hardware configuration as the control unit 20, and therefore a description thereof will be omitted.

[0045] The control unit 40 includes an injection rate correction unit 41 (correction unit). Furthermore, the target value storage unit 32 of the storage device 16 stores a target value of an evaluation index for the flocculation state in the flocculation basin 103. The target value may be stored in the target value storage unit 32 via the input device 14.

[0046] The injection rate correction unit 41 acquires the above-mentioned evaluation index from the input device 14, and corrects the injection rate according to the difference between the acquired evaluation index and the target value of the evaluation index stored in the target value storage unit 32. Then, the injection rate correction unit 41 outputs the corrected injection rate as a calculation result to the output device 15. When the output device 15 is the above-mentioned control signal output device, the flocculant injector 113 can inject flocculant into the raw water based on the injection rate.

[0047] Furthermore, the injection rate correction unit 41 stores the corrected injection rate in the teacher data storage unit 33. As a result, the teacher data storage unit 33 stores a teacher data group, which is a collection of teacher data in which the upstream data is an explanatory variable and the corrected injection rate is an objective variable.

[0048] (Model Update Device) The model updating device 13 is an estimation model for estimating the injection rate of a flocculant to be injected into raw water, and updates the estimation model stored in the estimation model storage unit 31. The model updating device 13 includes a control unit 50. The control unit 50 controls each unit of the model updating device 13. The control unit 50 has the same hardware configuration as the control unit 40, and therefore a description thereof will be omitted.

[0049] The control unit 50 includes an update unit 51. The update unit 51 performs machine learning using a group of teacher data read from the teacher data storage unit 33, and constructs an estimation model as a learning model. In the teacher data of the group of teacher data, the upstream data is an explanatory variable, and the corrected injection rate is an objective variable. When the upstream data is input to the estimation model, the corrected injection rate corresponding to the upstream data is output from the estimation model.

[0050] The update unit 51 generates a regression model obtained by, for example, a random forest (RF), a gradient boosted tree regression (GBR), or a neural network (NN) as the estimation model. The update unit 51 updates the estimation model stored in the estimation model storage unit 31 using the constructed estimation model.

[0051] According to the above configuration, the coagulant injection rate estimated from the upstream data using the estimation model is corrected based on an evaluation index that evaluates the state of the mixed water after the coagulant is injected. Then, the estimation model is updated using teacher data that uses the corrected coagulant injection rate as a response variable and the upstream data as an explanatory variable. By using the updated estimation model, the coagulant injection rate can be accurately estimated from the upstream data. As a result, the accuracy of the coagulant injection rate can be improved.

[0052] (Injection rate calculation process) 3 is a flow chart showing an example of the flow of the injection rate calculation process in the water treatment system 1 having the above-mentioned configuration. First, the acquisition unit 21 acquires upstream side data acquired at least at the injection position of the coagulant and at a position upstream of the injection position, and stores the data in the teacher data storage unit 33 as explanatory variables (step S11, hereinafter, the description of "step" will be omitted). Next, the injection rate estimation unit 22 estimates the injection rate of the coagulant from the upstream side data acquired by the acquisition unit 21 using the estimation model stored in the estimation model storage unit 31 (S12).

[0053] Next, the injection rate correction unit 41 acquires an evaluation index of the aggregation state after the coagulant is injected, and corrects the injection rate estimated by the injection rate estimation unit 22 according to the difference between the acquired evaluation index and the target value of the evaluation index stored in the target value storage unit 32 (S13). Next, the injection rate correction unit 41 outputs the corrected injection rate as a calculation result, and stores it as an objective variable in the teacher data storage unit 33 (S14). As a result, a pair of the upstream data, which is the explanatory variable, and the corrected injection rate, which is the objective variable, is added to the teacher data group in the teacher data storage unit 33 as teacher data.

[0054] Next, the update unit 51 determines whether or not a predetermined period (for example, one day, one week, etc.) has elapsed since the start of the injection rate calculation process (S15). If the predetermined period has not elapsed (NO in S15), the process returns to step S11.

[0055] On the other hand, if the predetermined period has elapsed (YES in S15), the update unit 51 performs machine learning using the teacher data group read from the teacher data storage unit 33, reconstructs the estimation model as a learning model, and updates the estimation model in the estimation model storage unit 31 (S16). Then, the injection rate calculation process ends.

[0056] (Additional Notes) In this embodiment, the injection rate corrected by the injection rate correction unit 41 is output to the output device 15 as an estimation result, but the injection rate estimated by the injection rate estimation unit 22 may be output to the output device 15.

[0057] Example 1 FIG. 4 is a graph showing the time change of the raw water turbidity, which is an example of the explanatory variable, and the injection rate of the coagulant, which is the objective variable. In FIG. 4, the raw water turbidity is shown by a dashed line, and the injection rate of the present embodiment is shown by a solid line. In addition, in FIG. 4, as a comparative example, an injection rate by feedforward control (FF control) only, that is, an injection rate estimated from the raw water turbidity by only an estimation model, is shown by a dashed line. In addition, in FIG. 4, as a comparative example, an injection rate by feedback control (FB control) only, that is, an injection rate determined based only on the evaluation index and its target value, is shown by a two-dot chain line.

[0058] With reference to Figure 4, it can be seen that the injection rate based on FF control alone has an extremely small time lag from the above-mentioned change in raw water turbidity, but may differ from the value corresponding to the above-mentioned change in the coagulation state due to the above-mentioned change in raw water turbidity (it is lower in the example of Figure 4). On the other hand, it can be seen that the injection rate based on FB control alone has a value corresponding to the above-mentioned change in the coagulation state due to the above-mentioned change in raw water turbidity, but the time lag T1 from the above-mentioned change in raw water turbidity is large.

[0059] In contrast, the injection rate in this embodiment corresponds to the change in the flocculation state due to the change in the raw water turbidity, compared to the injection rate using only FF control, and it can be seen that there is less time delay from the change in the raw water turbidity, compared to the injection rate using only FB control.

[0060] (Variation 1) Incidentally, the raw water takes time to flow downstream from the acquisition position of the raw water turbidity in the upstream data (the position of the water quality meter 111 in the receiving well 101) to the acquisition position of the evaluation index (the position of the camera 116 in the flocculation pond 103).

[0061] Therefore, in this modification, the injection rate correction unit 41 stores the injection rate corrected based on the evaluation index at the time when the time has elapsed since the acquisition of the raw water turbidity, which is the explanatory variable in the embodiment, in the teacher data storage unit 33 as the objective variable of the teacher data. With the above configuration, the causal relationship between the explanatory variables and the objective variable in the teacher data is appropriately reflected. Therefore, by using the estimation model updated using this teacher data, the injection rate of the coagulant can be estimated more accurately from the raw water turbidity.

[0062] FIG. 5 is a graph showing the time change of the raw water turbidity, which is an example of the explanatory variable, and the injection rate of the coagulant, which is the objective variable. In FIG. 5, the raw water turbidity is shown by a dashed line, and the injection rate of the coagulant in this modified example is shown by a solid line. In addition, in FIG. 5, as in FIG. 4, as a comparative example, the injection rate of the coagulant only by the FF control is shown by a dashed line, and the injection rate of the coagulant only by the FB control is shown by a dashed line. With reference to FIG. 5, it can be seen that the injection rate of the coagulant in this modified example has an extremely small time delay from the change in the raw water turbidity compared to the injection rate of the coagulant in the embodiment shown in FIG. 4, and is about the same as the injection rate by only the FF control.

[0063] The time may be a hydraulic retention time, i.e., a value obtained by dividing the flow channel volume from the acquisition position of the raw water turbidity to the acquisition position of the evaluation index by the flow rate. Alternatively, the time may be a time obtained by a tracer test, a numerical analysis, etc. The time may also include a response time from acquisition of the evaluation index to output of the corrected injection rate.

[0064] Example 2 Fig. 6 is a graph showing the time change of the injection rate of powdered activated carbon, which is an example of the explanatory variable, and the injection rate of the coagulant, which is the objective variable. In Fig. 6, the injection rate of powdered activated carbon is shown by a dashed line, and the injection rate of the coagulant in this embodiment is shown by a solid line. In Fig. 6, as in Fig. 4, the injection rate of the coagulant only by FF control is shown by a dashed line, and the injection rate of the coagulant only by FB control is shown by a dashed double-dot line, as a comparative example.

[0065] In general, when powdered activated carbon is injected into the receiving well 101, the injection rate of the coagulant must be increased. Therefore, the injection rate of the powdered activated carbon is a variable with a high degree of contribution as an explanatory variable of the above estimation model.

[0066] Referring to Fig. 6, it can be seen that the coagulant injection rate by FB control alone corresponds to the change in the coagulation state caused by the change in the injection rate of powdered activated carbon, but the time lag T2 from the change in the injection rate of powdered activated carbon is large. On the other hand, the coagulant injection rate by FF control alone corresponds to an extremely small time lag from the change in the injection rate of powdered activated carbon, but it can be seen that there are cases where the value is different from the value caused by the change in the coagulation state caused by the change in the injection rate of powdered activated carbon (higher in the example of Fig. 6). Therefore, with FF control alone, the coagulant is injected in excess.

[0067] In contrast, it can be seen that the coagulant injection rate of this embodiment has a smaller time delay from the change in the powdered activated carbon injection rate than the coagulant injection rate with only FB control. Also, it can be seen that the coagulant injection rate of this embodiment has a value corresponding to the change in the coagulation state due to the change in the powdered activated carbon injection rate after the time delay T2 has elapsed since the change in the powdered activated carbon injection rate, compared to the coagulant injection rate with only FF control.

[0068] (Variation 2) Incidentally, the raw water takes time to flow downstream from the injection position of the powdered activated carbon in the upstream data (a predetermined position of the receiving well 101) to the acquisition position of the evaluation index (the position of the camera 116 in the flocculation pond 103).

[0069] Therefore, in this modification, the injection rate correction unit 41 stores the injection rate corrected based on the evaluation index at the time when the time has elapsed since the injection rate of the powdered activated carbon, which is the explanatory variable in the embodiment, was acquired, as the objective variable of the teacher data in the teacher data storage unit 33. With the above configuration, the causal relationship between the explanatory variables and the objective variable in the teacher data is appropriately reflected. Therefore, by using the estimation model updated using the teacher data, the injection rate of the coagulant can be estimated more accurately from the injection rate of the powdered activated carbon.

[0070] The above-mentioned time may be the hydraulic retention time as in the case of the modified example shown in Fig. 5, or may be the time obtained by a tracer test, a numerical analysis, etc. Also, the above-mentioned time may be added with the response time from the acquisition of the evaluation index to the output of the corrected injection rate.

[0071] [Embodiment 2] Another embodiment of the present invention will be described with reference to FIGS.

[0072] Fig. 7 is a diagram showing an outline of a water treatment system according to this embodiment. The water treatment system 1a of this embodiment performs disinfection treatment on the raw water or treated water obtained by treating the raw water using a chlorine agent. Conventionally, the chlorine demand is calculated using the raw water concentration of a substance that reacts with chlorine, such as ammonia nitrogen, and a theoretical formula based on the reaction formula, and the calculated chlorine demand is used as a reference for setting the injection rate of the chlorine agent.

[0073] As shown in Fig. 7, the water treatment system 1a includes, as facilities for realizing the above-mentioned disinfection process, a receiving well 101, a rapid mixing basin 102, a flocculation basin 103, a settling basin 104, a middle chlorine mixing basin 105, a filtration basin 106, a rear chlorine mixing basin 107, and a distributing basin 108. Note that the receiving well 101, the rapid mixing basin 102, the flocculation basin 103, and the settling basin 104 shown in Fig. 7 are similar to the receiving well 101, the rapid mixing basin 102, the flocculation basin 103, and the settling basin 104 shown in Fig. 1, respectively.

[0074] A flow meter 121 is provided in the water conveyance pipe upstream of the receiving well 101. The flow meter 121 measures the flow rate of raw water sent to the receiving well 101. Data on the flow rate measured by the flow meter 121 is input to a upstream chlorine agent injector 122. A upstream chlorine agent is injected into the receiving well 101 by the upstream chlorine agent injector 122. The upstream chlorine agent disinfects the raw water and oxidizes organic matter and the like contained in the raw water.

[0075] A concentration meter 123 is provided upstream of the rapid mixing basin 102. The concentration meter 123 measures the residual chlorine concentration of the mixed water in the rapid mixing basin 102. The measurement data of the residual chlorine concentration measured by the concentration meter 123 is input to the injection rate calculation system 2a.

[0076] A flow meter 124 is provided in the water conveyance pipe between the settling basin 104 and the middle-stage chlorine mixing basin 105. The flow meter 124 measures the flow rate of treated water sent from the settling basin 104 to the middle-stage chlorine mixing basin 105. The data of the flow rate measured by the flow meter 124 is input to the middle-stage chlorine agent injection device 125.

[0077] The middle-stage chlorine mixing basin 105 is a mixing basin for injecting a middle-stage chlorine agent into the sedimentation water sent from the sedimentation basin 104. The middle-stage chlorine agent is injected into the middle-stage chlorine mixing basin 105 by a middle-stage chlorine agent injector 125. The middle-stage chlorine agent disinfects the raw water, and soluble manganese contained in the raw water can be removed in the downstream filtration basin 106.

[0078] The filtration basin 106 is a basin equipped with a filtration system that filters the settled water that flows in from the settling basin 104 via the chlorine mixing basin 105 in the middle stage. In the filtration basin 106, minute suspended solids remaining in the settled water are separated by filtration. The water filtered in the filtration basin 106 is sent to the subsequent chlorine mixing basin 107 as purified water.

[0079] A concentration meter 126 is provided upstream of the filtration basin 106. The concentration meter 126 measures the residual chlorine concentration of the settled water sent to the filtration basin 106. The measurement data of the residual chlorine concentration measured by the concentration meter 126 is input to the injection rate calculation system 2a.

[0080] A flow meter 127 is provided in the water conveyance pipe between the filtration basin 106 and the downstream chlorine mixing basin 107. The flow meter 127 measures the flow rate of purified water sent from the filtration basin 106 to the downstream chlorine mixing basin 107. The data of the flow rate measured by the flow meter 127 is input to a downstream chlorine agent injection device 128.

[0081] The latter stage chlorine mixing tank 107 is a mixing tank for injecting the latter stage chlorine agent into the purified water sent from the filtration tank 106. The latter stage chlorine agent is injected into the latter stage chlorine mixing tank 107 by the latter stage chlorine agent injector 128. The latter stage chlorine agent is used to adjust the residual chlorine concentration of the water distributed from the distribution tank 108.

[0082] The distributing reservoir 108 is a reservoir that temporarily stores purified water flowing from the filtration reservoir 106 via the downstream chlorine mixing reservoir 107, and is equipped with a control facility that controls the outflow according to demand. The purified water is supplied from the distributing reservoir 108 to houses and other buildings via water pipes.

[0083] A concentration meter 129 is provided upstream of the distributing reservoir 108. The concentration meter 129 measures the residual chlorine concentration of the purified water sent to the distributing reservoir 108. The measurement data of the residual chlorine concentration measured by the concentration meter 129 is input to the injection rate calculation system 2a.

[0084] (Injection rate estimation system) As shown in Fig. 7, the water treatment system 1a includes an injection rate calculation system 2a. The injection rate calculation system 2a estimates the injection rates of the front, middle, and rear stages of the chlorine agent injected into the water according to the attributes of the raw water, etc. Here, the injection rate is the ratio of the chlorine agent injected into the water to the water. Conventionally, the injection rate has been determined using the results of a jar test, past knowledge, a predetermined calculation formula, etc.

[0085] The injection rate calculation system 2a outputs the estimated injection rate of the upstream chlorine agent (hereinafter, sometimes referred to as the "previous stage injection rate") to the upstream chlorine agent injection device 122. The upstream chlorine agent injection device 122 determines the injection amount of the upstream chlorine agent based on the flow rate data from the flowmeter 121 and the upstream injection rate from the injection rate calculation system 2a, and injects it into the receiving well 101.

[0086] Moreover, the injection rate calculation system 2a outputs the estimated injection rate of the middle stage chlorine agent (hereinafter, sometimes referred to as the "middle stage injection rate") to the middle stage chlorine agent injection device 125. The middle stage chlorine agent injection device 125 determines the injection amount of the middle stage chlorine agent based on the flow rate data from the flowmeter 124 and the middle stage injection rate from the injection rate calculation system 2a, and injects it into the middle stage chlorine mixing pond 105.

[0087] Furthermore, the injection rate calculation system 2a outputs the estimated injection rate of the chlorine agent in the subsequent stage (hereinafter, sometimes referred to as the "injection rate of the subsequent stage") to the chlorine agent injector 128 in the subsequent stage. The chlorine agent injector 128 in the subsequent stage determines the injection amount of the chlorine agent in the subsequent stage based on the flow rate data from the flowmeter 127 and the injection rate of the subsequent stage from the injection rate calculation system 2a, and injects it into the chlorine mixing tank 107 in the subsequent stage. The injection rate calculation system 2a may be configured by one information processing device having a group of hardware and software components, or may be configured by multiple information processing devices.

[0088] Fig. 8 is a block diagram showing an example of a configuration of a main part of an injection rate calculation system 2a. The injection rate calculation system 2a of this embodiment is different from the injection rate calculation system 2 shown in Fig. 2 in terms of data stored in a storage device 16, but is otherwise similar in configuration.

[0089] The estimation model storage unit 31 of the storage device 16 stores a front-stage estimation model for estimating the injection rate of the front-stage chlorine agent, a middle-stage estimation model for estimating the injection rate of the middle-stage chlorine agent, and a rear-stage estimation model for estimating the injection rate of the rear-stage chlorine agent. The target value storage unit 32 of the storage device 16 stores a target value of the front-stage residual chlorine concentration, a target value of the middle-stage residual chlorine concentration, and a target value of the rear-stage residual chlorine concentration as target values ​​of the evaluation index.

[0090] The teacher data memory unit 33 of the memory device 16 stores first-stage teacher data for constructing the first-stage estimation model, middle-stage teacher data for constructing the middle-stage estimation model, and latter-stage teacher data for constructing the latter-stage estimation model.

[0091] The teacher data of the preceding stage includes the upstream data described above as an explanatory variable. The teacher data of the preceding stage includes the corrected injection rate of the preceding stage as a target variable. The upstream data is data acquired upstream of the injection position of the chlorine agent of the preceding stage. The upstream data includes attribute data indicating attributes of the raw water.

[0092] The teacher data in the middle section includes the upstream data, the injection rate of the chlorine agent in the front section (first position) and the residual chlorine concentration after injection as explanatory variables. The teacher data in the middle section includes the injection rate in the middle section (second position downstream of the first position) after correction as a response variable.

[0093] The latter teaching data includes, as explanatory variables, the upstream data, the injection rate of the chlorine agent in the front stage (first position) and the residual chlorine concentration after injection, and the injection rate of the chlorine agent in the middle stage (first position) and the residual chlorine concentration after injection. The latter teaching data includes, as a response variable, the injection rate in the rear stage (second position downstream of the first position) after correction.

[0094] According to the above configuration, the injection rate of the chlorine agent estimated from the upstream data using the estimation model is corrected based on the residual chlorine concentration that evaluates the state of the mixed water after the chlorine agent is injected. Then, the estimation model is updated using teacher data that uses the corrected injection rate of the chlorine agent as the objective variable and the upstream data as the explanatory variable. By using the updated estimation model, the injection rate of the chlorine agent can be accurately estimated from the upstream data. As a result, the accuracy of the injection rate of the chlorine agent can be improved.

[0095] (Previous stage injection rate calculation process) 9 is a flow chart showing an example of the flow of the injection rate calculation process of the upstream stage in the water treatment system 1a having the above-mentioned configuration. First, the acquisition unit 21 acquires upstream data acquired at at least one of the injection position of the upstream chlorine agent and a position upstream of the injection position, and stores the data in the teacher data storage unit 33 as explanatory variables (S21). Next, the injection rate estimation unit 22 estimates the injection rate of the upstream chlorine agent from the upstream data acquired by the acquisition unit 21 using the estimation model of the upstream stage stored in the estimation model storage unit 31 (S22).

[0096] Next, the injection rate correction unit 41 acquires the residual chlorine concentration after the injection of the chlorine agent in the upstream stage, that is, the upstream residual chlorine concentration measured by the concentration meter 123 of the rapid mixing basin 102, and corrects the injection rate of the chlorine agent in the upstream stage estimated by the injection rate estimation unit 22 according to the difference between the acquired upstream residual chlorine concentration and the target value of the upstream residual chlorine concentration stored in the target value storage unit 32 (S23). Next, the injection rate correction unit 41 outputs the injection rate of the chlorine agent in the upstream stage after the correction as an estimation result, and stores it in the teacher data storage unit 33 as the objective variable of the teacher data in the upstream stage (S24). As a result, a set of the upstream data, which is the explanatory variable, and the injection rate in the upstream stage after the correction, which is the objective variable, is added to the teacher data group in the teacher data storage unit 33 as the teacher data in the upstream stage.

[0097] Next, the update unit 51 determines whether or not a predetermined period (for example, one day, one week, etc.) has elapsed since the start of the previous injection rate calculation process (S25). If the predetermined period has not elapsed (NO in S25), the process returns to step S21.

[0098] On the other hand, if the predetermined period has elapsed (YES in S25), the update unit 51 performs machine learning using the previous-stage teacher data group read from the teacher data storage unit 33, and reconstructs the previous-stage estimation model as a learning model (S26). The update unit 51 updates the previous-stage estimation model stored in the estimation model storage unit 31 with the reconstructed previous-stage estimation model. Thereafter, the above-mentioned previous-stage injection rate calculation process ends.

[0099] (Injection rate calculation process in the middle) 10 is a flow chart showing an example of the flow of the middle stage injection rate calculation process in the water treatment system 1a having the above configuration. First, the acquisition unit 21 acquires the upstream data, the injection rate of the chlorine agent in the previous stage, and the residual chlorine concentration after injection, and stores them in the teacher data storage unit 33 as explanatory variables (S31). Next, the injection rate estimation unit 22 estimates the injection rate of the chlorine agent in the middle stage using the middle stage estimation model stored in the estimation model storage unit 31 from the upstream data acquired by the acquisition unit 21, the injection rate of the chlorine agent in the previous stage, and the residual chlorine concentration after injection (S32).

[0100] Next, the injection rate correction unit 41 acquires the residual chlorine concentration after the injection of the chlorine agent in the middle stage, that is, the residual chlorine concentration in the middle stage measured by the concentration meter 126 of the filtration basin 106, and corrects the injection rate of the chlorine agent in the middle stage estimated by the injection rate estimation unit 22 according to the difference between the acquired residual chlorine concentration in the middle stage and the target value of the residual chlorine concentration in the middle stage stored in the target value storage unit 32 (S33). Next, the injection rate correction unit 41 outputs the injection rate of the chlorine agent in the middle stage after the correction as an estimation result, and stores it in the teacher data storage unit 33 as the objective variable of the teacher data in the middle stage (S34). As a result, a set of the upstream data and the injection rate of the chlorine agent in the front stage and the residual chlorine concentration after injection, which are the explanatory variables, and the injection rate of the chlorine agent in the middle stage after the correction, which is the objective variable, is added to the teacher data group in the middle stage of the teacher data storage unit 33 as the teacher data in the middle stage.

[0101] Next, the update unit 51 determines whether a predetermined period of time has elapsed since the start of the middle stage injection rate calculation process (S35). If the predetermined period of time has not elapsed (NO in S35), the process returns to step S31. On the other hand, if the predetermined period of time has elapsed (YES in S35), the update unit 51 performs machine learning using the middle stage teacher data group read from the teacher data storage unit 33, and reconstructs the middle stage estimation model as a learning model (S36). The update unit 51 updates the middle stage estimation model stored in the estimation model storage unit 31 with the reconstructed middle stage estimation model. Thereafter, the injection rate calculation process of the previous stage is terminated.

[0102] (Later injection rate calculation process) 11 is a flow chart showing an example of the flow of the injection rate calculation process of the latter stage in the water treatment system 1a having the above-mentioned configuration. First, the acquisition unit 21 acquires the upstream data, the injection rate of the chlorine agent in the former stage and the residual chlorine concentration after injection, and the injection rate of the chlorine agent in the middle stage and the residual chlorine concentration after injection, and stores them in the teacher data storage unit 33 as explanatory variables (S41). Next, the injection rate estimation unit 22 estimates the injection rate of the chlorine agent in the latter stage using the estimation model of the latter stage stored in the estimation model storage unit 31 from the upstream data acquired by the acquisition unit 21, the injection rate of the chlorine agent in the former stage and the residual chlorine concentration after injection, and the injection rate of the chlorine agent in the middle stage and the residual chlorine concentration after injection (S42).

[0103] Next, the injection rate correction unit 41 acquires the residual chlorine concentration after the injection of the latter stage chlorine agent, that is, the latter stage residual chlorine concentration measured by the concentration meter 129 of the water reservoir 108, and corrects the injection rate of the latter stage chlorine agent estimated by the injection rate estimation unit 22 according to the difference between the acquired residual chlorine concentration of the latter stage and the target value of the residual chlorine concentration of the latter stage stored in the target value storage unit 32 (S43). Next, the injection rate correction unit 41 outputs the injection rate of the latter stage chlorine agent after the correction as an estimation result, and stores it in the teacher data storage unit 33 as the objective variable of the teacher data of the latter stage (S44). As a result, a set of the upstream data, the injection rate of the former stage chlorine agent and the residual chlorine concentration after injection, the injection rate of the middle stage chlorine agent and the residual chlorine concentration after injection, which are the explanatory variables, and the injection rate of the latter stage chlorine agent after the correction, which is the objective variable, is added to the teacher data group of the latter stage of the teacher data storage unit 33 as the teacher data of the latter stage.

[0104] Next, the update unit 51 determines whether or not a predetermined period has elapsed since the start of the injection rate calculation process of the subsequent stage (S45). If the predetermined period has not elapsed (NO in S45), the process returns to step S41. On the other hand, if the predetermined period has elapsed (YES in S45), the update unit 51 performs machine learning using the subsequent stage teacher data group read from the teacher data storage unit 33, and reconstructs the subsequent stage estimation model as a learning model (S46). The update unit 51 updates the subsequent stage estimation model stored in the estimation model storage unit 31 with the reconstructed subsequent stage estimation model. Thereafter, the injection rate calculation process of the previous stage is terminated.

[0105] (Additional Notes) In this embodiment, the front stage chlorine agent, the middle stage chlorine agent, and the rear stage chlorine agent are used in the water treatment system 1a, but this is not limited to this. Depending on the water purification facility, any two of the front stage chlorine agent, the middle stage chlorine agent, and the rear stage chlorine agent may be used, or any one of them may be used. The configuration and processing related to the chlorine agent that is not used among the front stage chlorine agent, the middle stage chlorine agent, and the rear stage chlorine agent can be omitted. In addition, in this embodiment, the residual chlorine concentration is used as the evaluation index, but this is not limited to this, and other indices such as electrical conductivity can be used as the evaluation index.

[0106] As described above, the injection rate calculation system 2a of the present embodiment has the same configuration as the injection rate calculation system 2 shown in Fig. 2. Therefore, by incorporating the injection rate calculation system 2a of the present embodiment into the injection rate calculation system 2 shown in Fig. 2, the water treatment system 1a of the present embodiment can be easily incorporated into the water treatment system 1 shown in Figs. 1 to 3.

[0107] [Embodiment 3] Yet another embodiment of the present invention will be described with reference to Figures 12 and 13. A water treatment system 1 of this embodiment is different from the water treatment system 1 shown in Figures 1 to 3 in that an injection rate calculation system 3 is provided instead of the injection rate calculation system 2, but the other configurations are similar.

[0108] Fig. 12 is a block diagram showing an example of a configuration of a main part of the injection rate calculation system 3 of this embodiment. The injection rate calculation system 3 of this embodiment is different from the injection rate calculation system 2 shown in Fig. 2 in that an optimization device 17 is provided instead of the estimation device 11 and the correction device 12, a model construction device 18 is provided instead of the model updating device 13, and an estimation model storage unit 34 and a teacher data storage unit 35 are provided instead of the estimation model storage unit 31 and the teacher data storage unit 33 in the storage device 16, but is otherwise similar.

[0109] The teacher data storage unit 35 pre-stores a teacher data group that is a collection of teacher data that has the upstream data and the coagulant injection rate as explanatory variables and the evaluation index of the coagulation state as a response variable.

[0110] The model construction device 18 constructs an estimation model for estimating an evaluation index of the flocculation state in the flocculation basin 103 after the coagulant is injected. The model construction device 18 stores the constructed estimation model in the estimation model storage unit 31. The model construction device 18 includes a control unit 70. The control unit 70 comprehensively controls each unit of the model construction device 18. Note that the control unit 70 has the same hardware configuration as the control unit 50 shown in Fig. 2, and therefore a description thereof will be omitted.

[0111] The control unit 70 includes a construction unit 71. The construction unit 71 performs machine learning using a group of teacher data read from the teacher data storage unit 35, and constructs an estimation model as a learning model. When the upstream data and the injection rate are input to the estimation model, the evaluation index corresponding to the upstream data and the injection rate is output from the estimation model. The construction unit 71 generates the regression model described above as the estimation model. The construction unit 71 stores the constructed estimation model in the estimation model storage unit 34.

[0112] The estimation model storage unit 34 stores an estimation model for estimating the evaluation index of the flocculation state from the upstream data and the injection rate of the flocculant.

[0113] The optimization device 17 optimizes the injection rate of the flocculant so that the evaluation index estimated from the upstream data and the injection rate of the flocculant using the estimation model becomes a target value. The optimization device 17 includes a control unit 60. The control unit 60 controls each unit of the optimization device 17. The control unit 60 has the same hardware configuration as the control units 20 and 40 shown in FIG. 2, and therefore a description thereof will be omitted.

[0114] The control unit 60 includes an acquisition unit 61 and an injection rate optimization unit 62 (optimization unit). The acquisition unit 61 acquires the upstream data from the input device 14. The acquisition unit 61 stores the acquired upstream data in the teacher data storage unit 35. The acquisition unit 61 stores the upstream data in the teacher data storage unit 35 at predetermined timings, whereby a set of the upstream data is stored in the teacher data storage unit 35.

[0115] The injection rate optimization unit 62 optimizes the injection rate of the flocculant using the upstream data acquired by the acquisition unit 61, the estimation model read from the estimation model storage unit 34, and the target value of the evaluation index read from the target value storage unit 32, so that the evaluation index estimated from the upstream data and the injection rate of the flocculant using the estimation model becomes the target value. The injection rate optimization unit 62 outputs the optimized injection rate to the output device 15. When the output device 15 is the above-mentioned control signal output device, the flocculant injector 113 can inject the flocculant into the raw water based on the injection rate.

[0116] According to the above configuration, the injection rate of the flocculant is optimized so that an evaluation index for evaluating the state of the mixed water after the flocculant is injected, which is estimated from the upstream data and the injection rate of the flocculant using an estimation model, becomes a target value. Therefore, the accuracy of the injection rate of the flocculant can be improved using the upstream data, the estimation model, and the target value of the evaluation index.

[0117] (Injection rate calculation process) 13 is a flowchart showing an example of the flow of the injection rate calculation process in the water treatment system 1 having the above configuration. Note that, before the injection rate calculation process is executed, the teacher data storage unit 35 stores the teacher data group, and the model construction device 18 constructs an estimation model using the teacher data and stores it in the estimation model storage unit 34.

[0118] First, the acquisition unit 61 acquires upstream data acquired at least at the injection position of the flocculant and at a position upstream of the injection position (S51). Next, the injection rate optimization unit 62 optimizes the injection rate of the flocculant so that the evaluation index estimated from the upstream data and the injection rate of the flocculant using the estimation model in the estimation model storage unit 34 becomes the target value in the target value storage unit 32 (S52). Next, the injection rate optimization unit 62 outputs the optimized injection rate as a calculation result (S53). Then, the injection rate calculation process ends.

[0119] (Additional Notes) The injection rate optimization unit 62 may add, as new teacher data, the upstream data, the optimized injection rate, and the evaluation index estimated from the upstream data and the optimized injection rate using the estimation model, to the teacher data group in the teacher data storage unit 35. Then, the model construction device 18 may update the estimation model stored in the estimation model storage unit 34 by using the teacher data group to which the new teacher data has been added.

[0120] In addition, although the water treatment system 1 of the above embodiment is used to control the injection of a coagulant or chlorine agent, the present invention is not limited to this and can be used to control the injection of any agent, such as a pH adjuster or powdered activated carbon, injected in a water treatment system.

[0121] [Software implementation example] The functions of the estimation device 11, the correction device 12, the model updating device 13, the optimization device 17, and the model construction device 18 (hereinafter referred to as the "devices") can be realized by a program for causing a computer to function as the devices, and for causing a computer to function as each control block of the devices (particularly each part included in the control units 20, 40, 50, 60, 70).

[0122] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program to realize each function described in each of the above embodiments.

[0123] The program may be non-transitory and may be recorded in one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be provided to the device via any wired or wireless transmission medium.

[0124] In addition, some or all of the functions of each of the control blocks can be realized by a logic circuit. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of each of the control blocks can be realized by, for example, a quantum computer.

[0125] Furthermore, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI ​​may be executed by the control device or another device (for example, an edge computer or a cloud server).

[0126] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0127] 1. 1a Water treatment system 2, 2a, 3 Injection rate calculation system 11 Estimation device 12 Correction device 13 Model Update Device 14 Input Devices 15 Output Devices 16 Storage device 17 Optimization Device 18 Model Building Equipment 20, 40, 50, 60, 70 Control section 21, 61 Acquisition Department 22 Injection rate estimation section (estimation section) 34 Estimation model memory section 32 Target value storage section 33, 35 Teacher data storage unit 41 Injection rate correction section (correction section) 51 Update section 62 Injection rate optimization section (optimization section) 71 Construction Department 101 Water landing well 102 Rapid mixing basin 103 Flocculation Pond 104 Sedimentation pond 105, 107 Chlorine mixing tank 106 Filtration pond 108 Reservoir 111 Water quality meter 112, 121, 124, 127 flowmeter 113 Coagulant injection device 114 Rapid Mixer 115 Slow Mixer 116 Cameras 122, 125, 128 Chlorine injection device 123, 126, 129 Densitometer

Claims

1. An injection rate calculation system for calculating an injection rate of a chemical to be injected to treat raw water flowing into a water purification facility, an acquisition unit that acquires upstream data measured at at least one of the injection position of the drug and a position upstream of the injection position, and an evaluation index that evaluates the state of the mixed water after the drug is injected; an estimation unit that estimates an injection rate of the drug from the upstream data by using an estimation model; a correction unit that corrects the injection rate estimated by the estimation unit based on the evaluation index; an update unit that updates the estimation model using teacher data in which the upstream data is an explanatory variable and the injection rate corrected by the correction unit is an objective variable.

2. An injection rate calculation system for calculating an injection rate of a chemical to be injected to treat raw water flowing into a water purification facility, an acquisition unit that acquires upstream data measured at at least one of the injection position of the medicine and a position upstream of the injection position; an optimization unit that optimizes the drug injection rate using an estimation model constructed using teacher data in which the upstream data and the drug injection rate are explanatory variables and an evaluation index that evaluates the state of the mixed water after the drug is injected is an objective variable, so that the evaluation index estimated from the upstream data and the drug injection rate becomes a target value.

3. The upstream data includes raw water turbidity, which is the turbidity of raw water flowing into the water purification facility, The injection rate calculation system according to claim 1 or 2, wherein the evaluation index is an evaluation index at the time elapsed from the point at which the raw water turbidity was acquired to the point at which the mixed water state was acquired, the time elapsed from the point at which the raw water turbidity was acquired.

4. The injection rate calculation system of claim 1 or 2, wherein the upstream data includes at least one of attribute data indicating attributes of the raw water, an injection rate of a chemical other than the chemical that is injected at a position upstream of the injection position of the chemical, and a volume of water that is treated from the raw water and mixed with the raw water.

5. the agent is a flocculating agent, The injection rate calculation system according to claim 1 or 2, wherein the evaluation index is obtained from a photographed image of the floc.

6. The agent is a chlorine agent, 3. The injection rate calculation system according to claim 1, wherein the evaluation index is a residual chlorine concentration.

7. the chlorine agent is injected at a first location and at a second location downstream from the first location; The injection rate calculation system according to claim 6, wherein the estimation model including the injection rate of the chlorine agent injected at the second position as an explanatory variable or a target variable includes the injection rate of the chlorine agent injected at the first position and the residual chlorine concentration after injection as explanatory variables.

8. The injection rate calculation system according to claim 1 or 2, A control device that controls the injection of the chemical agent according to the injection rate calculated by the injection rate calculation system.

9. 2. An injection rate calculation program for causing a computer to function as the injection rate calculation system according to claim 1, the injection rate calculation program causing a computer to function as the estimation unit, the correction unit, and the update unit.

10. 3. An injection rate calculation program for causing a computer to function as the injection rate calculation system according to claim 2, the injection rate calculation program causing a computer to function as the optimization unit.

11. An acquisition step of acquiring upstream data measured at at least one of an injection position of a chemical agent to be injected to treat raw water flowing into the water purification facility and a position upstream of the injection position, and an evaluation index for evaluating the state of the mixed water after the chemical agent is injected; an estimation step of estimating an injection rate of the drug from the upstream data using an estimation model; a correction step of correcting the injection rate estimated in the estimation step based on the evaluation index; an updating step of updating the estimation model by using teacher data having the upstream data as an explanatory variable and the injection rate corrected in the correction step as a response variable.

12. An acquisition step of acquiring upstream data measured at at least one of an injection position of a chemical to be injected to treat raw water flowing into the water purification facility and a position upstream of the injection position; an optimization step of optimizing the injection rate of a chemical using an estimation model in which the upstream data and the injection rate of the chemical are explanatory variables and an evaluation index that evaluates the state of the mixed water after the chemical is injected is an objective variable, so that the evaluation index estimated from the upstream data and the injection rate of the chemical becomes a target value.

Citation Information

Patent Citations

  • Flocculant pouring control apparatus in water treatment

    JP1983040113A

  • Chemical injection control method and chemical injection controller

    JP2013094686A

  • Method for manufacturing database, and water treatment or sludge treatment system

    JP2019215743A

  • Teacher data update device, estimation model construction device, and teacher data update method

    JP2022099913A

  • Flocculating agent injection control system

    JP2002205076A