Drug injection control system, drug injection control method, and automatic aggregation processing apparatus

Abstract

To provide a chemical injection control system, a chemical injection control method, and an automatic coagulation treatment system capable of appropriately controlling an injection rate of chemicals injected into raw water even when a sudden change in properties of raw water occurs.SOLUTION: A chemical injection control system 100 includes: an information acquisition unit 11 that acquires information having water quality data of raw water and operation condition data of a water treatment plant that treats the raw water; a prediction unit 12 which predicts an injection rate of the chemical to be injected into the raw water using a machine learning algorithm with a learned model that acquires explanatory variables including water quality data and operation condition data and outputs an objective variable including an optimal injection rate of a chemical to be injected into the raw water; a confirmation unit 13 which performs a confirmation test by injecting the chemical into the raw water based on the prediction result of the injection rate of the chemical and confirms whether the prediction result is appropriate by comparing the water quality data of the treated water obtained by the confirmation test with a reference value; and a chemical injection control unit 14 which, based on the confirmation result of the confirmation unit 13, controls the injection rate of chemicals to be injected into raw water.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a drug injection control system, a drug injection control method, and an automatic agglomeration treatment apparatus.

Background Art

[0002] From the perspective of environmental impact, the role of a water purification treatment apparatus is important. In a water purification treatment apparatus, a flocculant is injected into the water to be treated, whereby suspended substances are aggregated and flocs are formed. The flocs are separated into solid and liquid phases and further filtered, whereby the water to be treated is purified.

[0003] In water purification treatment, rather than injecting a flocculant blindly into raw water, it is common to conduct a test called a jar test to determine the appropriate injection rate of the flocculant. However, the implementation of this jar test and the determination of the results require skill and experience. In addition, there are significant individual differences in the implementation of the jar test and the determination of the results. Therefore, there is a problem that if there is a shortage of veteran technicians, the transfer of technology will be interrupted.

[0004] In recent years, the field of machine learning has been developing remarkably, and research on the injection control of flocculants using machine learning has been conducted. Machine learning generally automatically analyzes the patterns and rules of input data from past data by a computer algorithm. By this machine learning, anyone can quickly determine the injection rate of the flocculant without the need for the experience of veteran technicians or the like.

[0005] For example, Japanese Unexamined Patent Application Publication No. 2017-123088 (Patent Document 1) discloses a method of predicting drug injection data at the next time point from sensing data and drug injection data using a decision tree learning algorithm. Further, Japanese Unexamined Patent Application Publication No. 2021-146246 (Patent Document 2) discloses a method of predicting the water quality after a flocculation treatment test from water quality data or operation condition data using a learned model, and predicting the injection rate of the flocculant from the absolute value of the change rate of the injection rate of the flocculant and the water quality after the treatment.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0007] Predictions using artificial intelligence (AI) such as machine learning can generally maintain relatively high accuracy in controlling the injection rate of flocculants within the data range used for learning. However, the prediction accuracy during the calculation of out-of-range data such as during abnormal times tends to decrease. On the other hand, in recent years, abnormal situations such as guerrilla heavy rain that have never been experienced before may occur. When the quality of the influent raw water changes rapidly due to such abnormal situations, it may be difficult to cope only with the prediction of the flocculant injection rate based on machine learning that analyzes patterns and rules as described in Patent Documents 1 and 2.

[0008] In view of the above problems, the present invention provides a chemical injection control system, a chemical injection control method, and an automatic flocculation treatment apparatus capable of appropriately controlling the injection rate of chemicals injected into raw water even when a rapid change in the properties of the raw water occurs.

Means for Solving the Problems

[0009] As a result of intensive studies by the present inventors to solve the above problems, it has been found useful to provide a predetermined process for confirming whether the prediction result of the injection rate of a chemical using a machine learning algorithm is appropriate.

[0010] Based on the above findings, in one aspect, the present invention provides an information acquisition unit that acquires information including raw water quality data and operation condition data of a water treatment plant for treating raw water, a machine learning algorithm using a learned model that acquires explanatory variables including water quality data and operation condition data and outputs a target variable including the optimal injection rate of chemicals to be injected into the raw water, a prediction unit that predicts the injection rate of chemicals to be injected into the raw water, a confirmation unit that performs a confirmation test by injecting chemicals into the raw water based on the predicted result of the injection rate of the chemicals and compares the water quality data of the treated water obtained by the confirmation test with a reference value to confirm whether the prediction result is appropriate, and an injection control unit that controls the injection rate of chemicals to be injected into the raw water based on the confirmation result of the confirmation unit.

[0011] In one embodiment, the chemical injection control system according to the present invention is such that when the prediction result of the injection rate of the chemical is appropriate, the confirmation unit determines the injection rate based on the prediction result as the injection rate of the chemical for performing water treatment by injecting the chemical into the raw water, and when the prediction result of the injection rate of the chemical is not appropriate, the confirmation unit changes the injection rate and performs a retest, and based on the retest, determines the optimal injection rate of the chemical for performing water treatment by injecting the chemical into the raw water.

[0012] In another embodiment, the chemical injection control system according to the present invention includes a treatment tank for treating raw water, a chemical injection unit for injecting chemicals into the treatment tank, a stirrer for stirring the inside of the treatment tank, a water quality analyzer for analyzing the water quality data of the treated water obtained in the treatment tank, and a control unit for controlling the injection rate of the chemicals to be injected into the treatment tank.

[0013] In another aspect, the present invention includes a step of predicting the injection rate of a chemical to be injected into raw water by using a machine learning algorithm that uses a learned model to obtain explanatory variables including the water quality data of the raw water and the operation condition data of a water treatment plant for treating the raw water, and outputs an objective variable including the optimal injection rate of the chemical to be injected into the raw water; a step of performing a confirmation test by injecting the chemical into the raw water based on the predicted result of the injection rate of the chemical, and comparing the water quality data of the treated water obtained by the confirmation test with a reference value to confirm whether the predicted result of the injection rate of the chemical is appropriate; and a step of controlling the injection rate of the chemical to be injected into the raw water based on the result of the confirmation. This is a chemical injection control method.

[0014] In one embodiment, the chemical injection control method according to the present invention is such that in the step of confirmation, when the predicted result of the injection rate of the chemical is appropriate, the injection rate based on the predicted result is determined as the injection rate of the chemical for performing water treatment by injecting the chemical into the raw water; when the predicted result of the injection rate of the chemical is not appropriate, the injection rate is changed and a retest is performed, and the retest is repeated until the water quality data of the treated water obtained by the retest is within the range of the reference value, and the optimal injection rate of the chemical for performing water treatment by injecting the chemical into the raw water is determined.

[0015] In another embodiment, the chemical injection control method according to the present invention is such that in the step of confirmation, a flocculant is injected as the chemical into the raw water to perform a flocculation sedimentation treatment, and at least any one of turbidity, chromaticity, pH, alkalinity, number of fine particles, TOC, COD, ultraviolet absorbance, and organic matter fraction is analyzed as the water quality data of the treated water obtained by the flocculation sedimentation treatment.

[0016] In yet another aspect, the present invention provides an information acquisition unit that obtains prediction results of the injection rate of a flocculant predicted by a machine learning algorithm using a learned model for predicting the optimal injection rate of the flocculant to be injected into raw water, a treatment tank that conducts a flocculation treatment test including a raw water sampling step, a chemical injection step, a stirring step, and a settling step based on the prediction results of the injection rate of the flocculant and preset test conditions, a water quality analyzer that analyzes the water quality data of the treated water obtained in the flocculation treatment test, a confirmation unit that compares the water quality data of the treated water analyzed by the water quality analyzer with a reference value to determine whether the prediction results are appropriate, and an injection control unit that controls the injection rate of the flocculant of chemical injection equipment for performing water treatment by injecting the flocculant into raw water based on the injection rate based on the prediction results when the prediction results are appropriate, and when the prediction results are not appropriate, conducts a flocculation treatment test at a new flocculant injection rate, and based on the optimal flocculant injection rate determined as a result of repeating the flocculation treatment test until the water quality data of the treated water obtained in the flocculation treatment test satisfies the reference value, controls the injection rate of the flocculant of the chemical injection equipment.

Advantages of the Invention

[0017] According to the present invention, it is possible to provide a chemical injection control system, a chemical injection control method, and an automatic flocculation treatment apparatus that can appropriately control the injection rate of chemicals to be injected into raw water even when a rapid change in the properties of the raw water occurs.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying Out the Invention

[0019] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description of the drawings, the same or similar parts are denoted by the same or similar reference numerals. Note that the embodiments shown below are examples of devices and methods for embodying the technical idea of the present invention, and the technical idea of the present invention does not specify the structure, arrangement, etc. of the components as follows.

[0020] (Chemical injection control system) As shown in FIG. 1, a chemical injection control system 100 according to an embodiment of the present invention includes a chemical injection control device 10 for controlling the injection rate of a chemical injected into a water treatment plant 20 that treats raw water.

[0021] The water treatment plant 20 is not limited to the following, but a water purification treatment facility can be used. The water treatment plant 20 includes, for example, an intake well 21, a rapid mixing tank 22, a floc formation tank 23, a sedimentation tank 24, a chemical injection facility 25 for injecting chemicals into raw water, a rapid filtration tank 26, a clean water tank 27, and a distribution tank 28.

[0022] The intake well 21 adjusts the amount and water level of the raw water taken in. The rapid mixing tank 22 performs a mixing process by injecting chemicals such as a coagulant and then performing rapid mixing. The floc formation tank 23 forms flocs after injecting a flocculant into the raw water to aggregate turbidity. The chemical injection facility 25 is a device that injects chemicals into the rapid mixing tank 22 or the floc formation tank 23.

[0023] The sedimentation tank 24 sedimentates the coarse flocs formed in the floc formation tank 23 by sedimentation separation. The rapid filtration tank 26 performs rapid filtration treatment on the supernatant water obtained in the sedimentation tank 24. The clean water tank 27 stores the clean water after subjecting the filtered water to a predetermined sterilization treatment. The distribution tank 28 stores the clean water supplied from the clean water tank 27 and supplies this to each facility such as homes, schools, and factories by natural flow or the like.

[0024] Each facility of the water treatment plant 20 is provided with a measuring instrument (not shown). Although not limited to the following, in order to measure the same type of water quality before and after the injection of chemicals, it is preferable to be equipped with the same type of measuring instrument before and after the injection of chemicals. As the types of measuring instruments, various measuring instruments for measuring temperature, turbidity, transparency, chromaticity, pH, alkalinity, number of fine particles, coagulant injection rate, chemical injection rate for pH adjustment, TOC (total organic carbon), COD (chemical oxygen demand), ultraviolet absorbance, organic matter fraction, etc. can be provided.

[0025] The chemical injection control device 10 can be configured with a general hardware configuration and can include a processor, a memory (e.g., RAM, etc.), a storage medium (e.g., HDD, SSD, etc.), and a communication module. The chemical injection control device 10 may function as a server device or may function as a client device. The chemical injection control device 10 may be composed of one piece of hardware or may be distributed among a plurality of pieces of hardware.

[0026] The chemical injection control device 10 includes an information acquisition unit 11, a prediction unit 12, a confirmation unit 13, and an injection control unit 14. The information acquisition unit 11 is directly or indirectly communicably connected to the above-described measuring instrument (not shown) provided in the water treatment plant 20. The information acquisition unit 11 acquires water quality data of the treated water and raw water quality data measured by the measuring instrument. Further, the information acquisition unit 11 acquires various parameters related to the operation of the water treatment plant 20 that treats raw water, for example, operation condition data including the raw water inflow rate to each facility.

[0027] As the chemical to be injection-controlled, any chemical can be used as long as it is various chemicals used in the water treatment plant 20. Typically, a coagulant is used. Examples of the coagulant include ferric polysulfate, ferric chloride, PAC (polyaluminum chloride), or sulfuric acid band. In addition, polymer coagulants, coagulation aids, organic flocculants, inorganic flocculants, or flocculation improvers are also used, and these can be used alone or in combination.

[0028] In addition to the flocculant, a pH adjuster, an alkali agent, or methanol, organic substances added in nitrification and denitrification treatment, surfactants, chlorine, hypochlorous acid, etc. used in sterilization treatment may also be used as chemicals to be controlled for injection.

[0029] The prediction unit 12 uses a machine learning algorithm using a learned model that acquires predetermined explanatory variables including at least water quality data of raw water and operation condition data of the water treatment plant 20 that treats the raw water, and outputs a predetermined target variable including the optimal injection rate of the chemical to be injected into the raw water, to predict the injection rate of the chemical to be injected into the raw water.

[0030] The machine learning algorithm is not particularly limited, but the SVR method (Support Vector Regression method), PLS method (Partial Least Squares method), neural network method (for example, DeepLearning method), random forest method, or decision tree method, LSTM method (Long Short-Term Memory), etc. can be used. Among them, it is preferable to use the LSTM method as the machine learning algorithm in this embodiment.

[0031] As the learned model, for example, a data set in which water quality data of raw water, operation condition data of the water treatment plant 20 that treats the raw water, and the optimal injection rate of the chemical to be injected into the raw water are associated is used as learning data, and a predetermined model constructed to predict the injection rate of the chemical using the LSTM method as the machine learning algorithm is utilized.

[0032] Examples of the water quality data included in the learning data used for constructing the learned model include, for example, in the case of a water purification plant, temperature, turbidity, transparency, chromaticity, pH, alkalinity, number of fine particles, TOC, COD, ultraviolet absorbance, and organic matter fraction. In addition, for example, meteorological information such as weather, temperature, rainfall, wind force of typhoon, and central pressure, and chemical injection rate during pH adjustment may also be included. Regarding the water quality data, it may include the data before chemical injection and the data after chemical injection. When multiple chemical injections are performed, the information of the water quality data before and after injection may be included respectively. Examples of the operation condition data include various information related to the operation of each facility, such as the size of the treatment tank of each facility, the type of chemical, the rated value of the chemical injection rate, the inflow water volume, the stirring time, the stirring speed, the pH condition, the standing time, and the filtration speed.

[0033] In this embodiment, the "chemical injection rate" means, for example, the ratio of the chemical injection rate (mg) to the inflow water volume (L), and is typically expressed by the following formula. Injection rate (mg / L) = Chemical injection amount (mg) / Inflow water volume (L) The control of the chemical injection rate depends on the type of the chemical injection facility 25. For example, it is performed by controlling valves, pumps, etc. provided in the chemical injection facility 25.

[0034] Based on the prediction result of the chemical injection rate by the prediction unit 12, the confirmation unit 13 performs a confirmation test by injecting a chemical into the raw water, and compares the water quality data of the treated water obtained by the confirmation test with a predetermined reference value to confirm whether the prediction result is appropriate. The reference value can be set appropriately by the operator. For example, in the case of a water purification plant, the water quality standard value of tap water can be used as the reference value.

[0035] When the confirmation unit 13 determines that the prediction result of the chemical injection rate by the prediction unit 12 is appropriate as a result of the confirmation test, it determines the injection rate based on the prediction result predicted by the prediction unit 12 as the injection rate of the chemical for performing water treatment by injecting the chemical into the raw water. On the other hand, when the confirmation unit 13 determines that the prediction result of the chemical injection rate is not appropriate as a result of the confirmation test, it changes the injection rate and conducts a retest, and based on the retest, determines the optimal injection rate of the chemical for performing water treatment by injecting the chemical into the raw water. Then, the injection control unit 14 controls the injection rate of the chemical that the chemical injection facility 25 injects into the raw water based on the confirmation result of the confirmation unit 13.

[0036] Based on the prediction result of the chemical injection rate by the prediction unit 12, the confirmation unit 13 can be equipped with a simple test device as shown in Fig. 2 for injecting the chemical into the raw water to conduct a confirmation test. For example, the confirmation unit 13 includes a treatment tank 1 for treating the raw water, a chemical injection unit 3 for injecting the chemical into the treatment tank 1, a stirrer 2 for stirring the inside of the treatment tank 1, a water quality analyzer 5 for analyzing the water quality data of the treated water obtained in the treatment tank 1, and a control unit 6 for controlling the injection rate of the chemical injected into the treatment tank 1. The confirmation unit 13 may further include a pH injection unit 4 for injecting a pH adjuster into the treatment tank 1.

[0037] The control unit 6 is connected to the stirrer 2, the inflow valve 7, the drain valve 8, the chemical injection pump 31, the pH adjustment pump 41, and the sampling pump 51. The control unit 6 is configured to output a predetermined control signal to the stirrer 2, the inflow valve 7, the drain valve 8, the chemical injection pump 31, the pH adjustment pump 41, and the sampling pump 51 to control the operation of each device. The details of the operation of the confirmation test by the confirmation unit 13 will be described later.

[0038] According to the chemical injection control system 100 according to the embodiment of the present invention, the confirmation unit 13 conducts a confirmation test on the prediction result of the injection rate of the chemical using machine learning, and can determine the optimal injection rate of the chemical for performing water treatment by injecting the chemical into the raw water. Thereby, even if the prediction result by machine learning is inappropriate due to the influence of sudden weather changes or the like, the prediction result can be simply tested and confirmed with the test apparatus in FIG. 2, and an appropriate injection rate of the chemical can be determined, so that the chemical can always be injected into the raw water at an appropriate injection rate. As a result, even if a sudden change in the properties of the raw water occurs, the injection rate of the chemical injected into the raw water can be appropriately controlled, and a chemical injection control system 100 capable of suppressing a deterioration in the water quality of the treated water can be provided.

[0039] (Chemical injection control method) The chemical injection control method according to the embodiment of the present invention can be controlled according to the flowchart shown in FIG. 3 using the chemical injection control system 100 shown in FIG. 1. That is, the chemical injection control method according to the embodiment of the present invention includes a step S1 of acquiring water quality data of raw water and operation operation condition data of the water treatment plant 20 for treating the raw water, and acquiring a predetermined explanatory variable including at least the water quality data of the raw water and the operation operation condition data, and using a machine learning algorithm using a learned model that outputs a predetermined objective variable including the optimal injection rate of the chemical to be injected into the raw water to predict the injection rate of the chemical to be injected into the raw water in step S2, and based on the prediction result of the injection rate of the chemical, injecting the chemical into the raw water to conduct a confirmation test, and comparing the water quality data of the treated water obtained by the confirmation test with a reference value to confirm whether the prediction result of the injection rate of the chemical is appropriate (steps S3 to S7), and a step S8 of controlling the injection rate of the chemical to be injected into the raw water based on the result of the confirmation.

[0040] In step S1, the information acquisition unit 11 in FIG. 1 acquires the water quality data and operation condition data of the raw water to be treated in the water treatment plant 20. In step S2, the prediction unit 12 acquires the same water quality data and operation condition data as those input when constructing the learned model from among the water quality data and operation condition data acquired by the information acquisition unit 11, inputs this as explanatory variables into the learned model, and obtains a predicted value of the optimal injection rate of the chemical. In step S3, the prediction unit 12 transmits the predicted value of the chemical injection rate predicted by the learned model to the confirmation unit 13.

[0041] In step S4 of FIG. 3, the confirmation unit 13 in FIG. 1 receives the output of the predicted value of the chemical injection rate from the prediction unit 12, and uses the test apparatus in FIG. 2 to inject the chemical into the raw water and conducts a confirmation test. The details of the confirmation test in step S4 will be described later. In step S5, the confirmation unit 13 analyzes the water quality data of the treated water obtained by the confirmation test using the water quality analyzer 5 provided in the confirmation unit 13.

[0042] As the water quality analyzer 5 used in step S5, various measuring devices for obtaining water quality data such as temperature, turbidity, transparency, chromaticity, pH, alkalinity, number of fine particles, TOC, COD, ultraviolet absorbance, organic matter fraction, solid content (SS), MLSS, and pH are used.

[0043] In step S6, the confirmation unit 13 compares the water quality data analyzed by the water quality analyzer 5 with a predetermined reference value to confirm whether the prediction result of the chemical injection rate is appropriate. When the water quality data satisfies the reference value, that is, when the prediction result of the injection rate of the chemical is appropriate, the confirmation unit 13 determines the injection rate based on the prediction result as the injection rate of the chemical for injecting the chemical into the raw water and performing water treatment, and proceeds to step S8. On the other hand, when the water quality data does not satisfy the reference value, that is, when the prediction result of the injection rate of the chemical is not appropriate, it proceeds to step S7.

[0044] In step S7, the confirmation unit 13 changes the chemical injection rate to an injection rate different from the predicted value. The method of change is not limited to the following, but when the predicted value of the chemical injection rate exceeds a preset reference value, the confirmation unit 13 increases the chemical injection rate. When the predicted value of the chemical injection rate is below the reference value, the confirmation unit 13 determines the changed chemical injection rate so as to decrease the chemical injection rate and proceeds to step S4. The increase or decrease amount of the injection rate at the time of change can be set in advance.

[0045] Next, in step S4, a retest is performed by injecting chemicals at the changed chemical injection rate determined in step S7. The confirmation unit 13 determines the optimal chemical injection rate by repeating steps S4 to S7 until the water quality data meets the reference value as a result of the retest. When the optimal chemical injection rate is determined, the process proceeds to step S8.

[0046] In step S8, the injection control unit 14 transmits the optimal chemical injection rate for the treatment of raw water to the chemical injection facility 25 of the water treatment plant 20. The chemical injection facility 25 injects chemicals into the raw water at the optimal chemical injection rate based on the control signal output from the injection control unit 14.

[0047] (Details of steps S4 and S5) The operation flow of the test step S4 and the water quality analysis step S5 using the test device in FIG. 2 provided in the confirmation unit 13 will be described below with reference to the flowchart of FIG. 4 and the test device in FIG. 2 as an example.

[0048] In the chemical injection rate setting step S41 of FIG. 4, when information on the chemical injection rate is input to the control unit 6 in FIG. 2 based on the prediction result of the chemical injection rate by the prediction unit 12, the control unit 6 in FIG. 2 sets the chemical injection rate by the chemical injection unit 3.

[0049] In the raw water sampling step S42, the control unit 6 opens the inflow valve 7 connected to the treatment tank 1 to sample a predetermined amount of the raw water treated by the water treatment plant 20 and let it flow into the treatment tank 1. The control of the inflow amount can be appropriately performed by adjusting the water level by the overflow pipe, controlling by the water level gauge, controlling by the inflow rate and the valve opening time, etc.

[0050] In the chemical injection step S43, the control unit 6 controls the chemical injection pump 31 to inject, as a chemical, for example, a flocculant into the treatment tank 1 so as to achieve the chemical injection rate set in the chemical injection rate setting step S41. At this time, if pH adjustment in the treatment tank 1 is necessary, the control unit 6 causes a pH adjuster to be injected into the treatment tank 1 via the pH adjustment pump 41. There are methods such as injecting a fixed amount of the pH adjuster and controlling by a pH measuring device (not shown) for pH adjustment.

[0051] In the rapid stirring step S44, the control unit 6 controls the stirrer 2 to stir the treated water at a preset stirring speed and stirring time. Generally, the stirring speed of rapid stirring is 100 - 150 / min, and the stirring time is about 3 minutes.

[0052] In the slow stirring step S45, the control unit 6 controls the stirrer 2 to stir the treated water at a preset stirring speed and stirring time. Slow stirring is generally slower than the stirring speed in the rapid stirring step S44, for example, about 30 / min, and the stirring time is about 10 minutes.

[0053] In the standing step S46, the control unit 6 stops the operation of the stirrer 2 and gently places it until a preset standing time. The standing time is preferably 5 minutes or more.

[0054] In the water quality analysis step S51, the control unit 6 sends the treated water at the upper part of the treatment tank 1 after the standing step S46 to the water quality analyzer 5 provided by the sampling pump 51 to analyze the water quality data of the treated water.

[0055] In the drainage step S52, the control unit 6 opens the drain valve 8 to drain the treated water in the treatment tank 1. Subsequently, in the cleaning step S53, the treatment tank 1 and the water quality analyzer 5 are cleaned with the treated water, pure water, or tap water, etc. after the confirmation test.

[0056] Thus, according to the chemical injection control method according to the embodiment of the present invention, a confirmation test is performed on the prediction result of the chemical injection rate using machine learning, and if necessary, the prediction result is corrected, so that the optimal chemical injection rate for injecting chemicals into raw water for water treatment can be determined. As a result, even if the prediction result by machine learning is not appropriate due to the influence of sudden weather changes or the like, the prediction result can be corrected to an appropriate injection rate. As a result, even if a sudden change in the properties of the raw water occurs, it is possible to appropriately control the injection rate of the chemicals injected into the raw water.

[0057] Although the present invention has been described by the above embodiments, it should not be understood that the discussions and drawings forming a part of this disclosure limit the invention. That is, the present disclosure is not limited to the above-described embodiments, and it goes without saying that the components can be combined and modified with each other within the scope not departing from the gist thereof and embodied.

[0058] (Water treatment plant 20) In the example of FIG. 1, a water purification treatment plant is shown as the water treatment plant 20. However, the water treatment plant 20 according to the embodiment of the present invention is not limited to the configuration of FIG. 1, and of course, it can be used for various facilities that inject predetermined chemicals to perform predetermined water treatment. For example, as the water treatment plant 20, it can be used for various water treatment plants such as a water purification treatment plant, a pure water production plant, a wastewater treatment plant, a sewage treatment plant, a night soil treatment (sludge regeneration) plant, a leachate treatment plant, a seawater desalination plant, and a sludge treatment plant.

[0059] (Automatic coagulation treatment device) The chemical injection control device 10 in FIG. 1 is configured alone as an automatic coagulation treatment device, and can be connected not only to the above-described water treatment plant 20 but also to various facilities including chemical injection equipment 25 that requires chemical injection control.

[0060] That is, the chemical injection control device 10 according to the embodiment of the present invention includes an information acquisition unit 11 that acquires the prediction result of the injection rate of the flocculant predicted by a machine learning algorithm using a learned model for predicting the optimal injection rate of the flocculant to be injected into the raw water, a treatment tank 1 that conducts a flocculation treatment test including a raw water sampling step S42, a chemical injection step S43, stirring steps S44 and S45, and a standing step S46 based on the prediction result of the injection rate of the flocculant and a preset test condition, a water quality analyzer 5 that analyzes the water quality data of the treated water obtained in the flocculation treatment test, a confirmation unit 13 that compares the water quality data of the treated water analyzed by the water quality analyzer 5 with a reference value to determine whether the prediction result is appropriate, and an injection control unit 14 that controls the injection rate of the flocculant of the chemical injection facility 25 for performing water treatment by injecting the flocculant into the raw water based on the injection rate based on the prediction result when the prediction result is appropriate, and when the prediction result is not appropriate, conducts a flocculation treatment test at a new flocculant injection rate, and controls the injection rate of the flocculant of the chemical injection facility 25 based on the optimal flocculant injection rate determined as a result of repeating the flocculation treatment test until the water quality data of the treated water obtained in the flocculation treatment test satisfies the reference value.

[0061] According to the chemical injection control device 10 according to the embodiment of the present invention, since the prediction result of the chemical injection rate by machine learning can be verified using a simple test device, even if an abnormal meteorological event such as a guerrilla heavy rain occurs and the prediction result may deviate greatly, the prediction result can be appropriately corrected and the chemical can be injected into the raw water at an appropriate injection rate. As a result, the amount of flocculant used can be optimized, efficient flocculation sedimentation treatment can be performed, and clean water with good water quality can be obtained.

Description of Reference Numerals

[0062] 1... Treatment tank 2... Stirrer 3... Chemical injection unit 4... pH injection unit 5... Water quality analyzer 6... Control unit 7... Inflow valve 8... Drain valve 10... Chemical injection control device 11... Information acquisition unit 12… Prediction Unit 13… Verification Unit 14… Injection Control Unit 20… Water Treatment Plant 21… Injection Well 22… Rapid Mixing Tank 23… Flocculation Tank 24… Sedimentation Tank 25… Chemical Injection Equipment 26… Rapid Filtration Tank 27… Clear Water Tank 28… Distribution Tank 31… Chemical Injection Pump 41… pH Adjustment Pump 51… Sampling Pump 100… Chemical Injection Control System

Claims

1. An information acquisition unit that acquires information including water quality data containing at least any one of the temperature, turbidity, transparency, chromaticity, pH, alkalinity, number of fine particles, TOC, COD, ultraviolet absorbance, and organic matter fraction of raw water, and the size of a treatment tank for treating the raw water, the type of chemical, the rated value of the chemical injection rate, the inflow water volume, the stirring time, the stirring speed, the pH condition, the standing time, and the filtration speed. At least any one of the operating operation condition data of the water treatment plant, and A machine learning algorithm that acquires explanatory variables including the water quality data and the operating operation condition data, and uses a learned model that outputs the injection rate of a chemical that becomes the optimal injection rate in light of the water quality data and the operating operation condition data as the target variable. A prediction unit that predicts the injection rate of the chemical to be injected into the raw water, A simple test device for performing a confirmation test by injecting the chemical into the raw water at the optimal injection rate predicted by the prediction unit, and comparing the water quality data of the treated water obtained by the confirmation test by the simple test device with a reference value. A confirmation unit that confirms whether the prediction result using the machine learning algorithm is appropriate, An injection control unit that controls the injection rate of the chemical to be injected into the raw water based on the confirmation result of the confirmation unit A chemical injection control system characterized by comprising.

2. When the confirmation unit When the prediction result of the injection rate of the chemical is appropriate, the injection rate based on the prediction result is determined as the injection rate of the chemical for performing water treatment by injecting the chemical into the raw water, When the prediction result of the injection rate of the chemical exceeds the reference value, a retest is performed at an injection rate increased from the injection rate predicted by the prediction unit, and when it is below the reference value, the injection rate is lower than the injection rate predicted by the prediction unit. The chemical injection control system according to claim 1, wherein a retest is performed at a reduced injection rate, and based on the retest, the optimal injection rate of the chemical for performing water treatment by injecting the chemical into the raw water is determined.

3. The simple test device is A treatment tank for treating the raw water, A chemical injection unit for injecting the chemical into the treatment tank, A stirrer for stirring the inside of the treatment tank, A water quality analyzer for analyzing the water quality data of the treated water obtained in the treatment tank, A control unit for controlling the injection rate of the chemical to be injected into the treatment tank The chemical injection control system according to claim 1 or 2, characterized by comprising.

4. Obtain explanatory variables including water quality data containing at least any one of the temperature, turbidity, transparency, chromaticity, pH, alkalinity, particle count, TOC, COD, ultraviolet absorbance, and organic matter fraction of the raw water, and the size of the treatment tank for treating the raw water, the type of chemical, the rated value of the chemical injection rate, the inflow water volume, the stirring time, the stirring speed, the pH condition, the standing time, and the filtration speed. Use a machine learning algorithm with a learned model that outputs the injection rate of the chemical that becomes the optimal injection rate in light of the water quality data of the raw water and the operation and operation condition data to predict the injection rate of the chemical to be injected into the raw water. Perform a confirmation test using a simple test device for performing a confirmation test by injecting the chemical into the raw water at the optimal injection rate predicted using the machine learning algorithm, and compare the water quality data of the treated water obtained by the confirmation test with a reference value to confirm whether the prediction result in the step of predicting the injection rate of the chemical using the machine learning algorithm is appropriate. Based on the confirmation result in the confirmation step, control the injection rate of the chemical to be injected into the raw water. A chemical injection control method characterized by including the above.

5. The confirmation step is as follows. When the prediction result of the injection rate of the chemical is appropriate, determine the injection rate based on the prediction result as the injection rate of the chemical for performing water treatment by injecting the chemical into the raw water. When the prediction result of the injection rate of the chemical is not appropriate, if it exceeds the reference value, change it to an injection rate increased from the injection rate predicted by the prediction unit, and if it is below the reference value, change it to an injection rate decreased from the injection rate predicted by the prediction unit and perform a retest. Repeat the retest until the water quality data of the treated water obtained by the retest is within the range of the reference value, and determine the optimal injection rate of the chemical for performing water treatment by injecting the chemical into the raw water. The chemical injection control method according to claim 4.

6. The confirmation step is as follows. Inject a flocculant as the chemical into the raw water and perform a flocculation and sedimentation treatment. The chemical injection control method according to claim 4 or 5, including analyzing at least any one of the temperature, turbidity, transparency, chromaticity, pH, alkalinity, particle count, TOC, COD, ultraviolet absorbance, and organic matter fraction as the water quality data of the treated water obtained by the flocculation and sedimentation treatment.

7. An information acquisition unit that obtains a prediction result of the injection rate of the flocculant predicted by a machine learning algorithm using a learned model for predicting an optimal injection rate in light of water quality data including at least any one of the temperature, turbidity, transparency, chromaticity, pH, alkalinity, number of fine particles, TOC, COD, ultraviolet absorbance, and organic matter fraction of the raw water, and operation operation condition data of the water treatment plant including at least any one of the size of the treatment tank for treating the raw water, the type of chemical, the rated value of the chemical injection rate, the inflow water volume, the stirring time, the stirring speed, the pH condition, the standing time, and the filtration speed. A treatment tank that conducts a flocculation treatment test including a raw water sampling step, a chemical injection step, a stirring step, and a standing step based on the prediction result of the injection rate of the flocculant and a preset test condition. A water quality analyzer connected to the treatment tank and analyzing water quality data including at least any one of the temperature, turbidity, transparency, chromaticity, pH, alkalinity, number of fine particles, TOC, COD, ultraviolet absorbance, and organic matter fraction of the treated water obtained in the flocculation treatment test. A confirmation unit that compares the water quality data of the treated water analyzed by the water quality analyzer with a reference value and determines whether the prediction result predicted by the machine learning algorithm is appropriate. When the prediction result is appropriate according to the confirmation unit, based on the prediction result, determine the injection rate of the flocculant of the chemical injection equipment for injecting the flocculant into the raw water to perform water treatment. When the prediction result is not appropriate according to the confirmation unit, the flocculation treatment test is carried out at a new flocculant injection rate, and the flocculation treatment test is repeated until the water quality data of the treated water obtained in the flocculation treatment test satisfies the reference value, and the injection rate of the flocculant of the chemical injection equipment whose water quality data of the treated water is within the range of the reference value is determined. An injection control unit that performs control. An automatic flocculation treatment apparatus characterized by comprising the above.

Images