Chemical injection control device, injection control method, and injection control program

The chemical injection control device uses dual models to predict and adjust chemical dosing in water treatment systems, addressing excessive injection issues and achieving efficient water quality and cost reduction by, adjusting rates to meet target turbidity levels, reducing excess chemical use and operational costs.

JP7891452B2Active Publication Date: 2026-07-16METAWATER CO LTD

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
METAWATER CO LTD
Filing Date
2023-09-13
Publication Date
2026-07-16

AI Technical Summary

Technical Problem

Existing chemical injection systems in water treatment, such as those using decision tree learning algorithms, often result in excessive chemical injection due to safety considerations, leading to inefficiencies and increased costs.

Method used

A chemical injection control device and method utilizing two trained models: a first model to predict chemical injection rates based on water quality, and a second model to predict treated water quality, with a determination unit to adjust injection rates based on turbidity feedback, ensuring appropriate chemical dosing.

Benefits of technology

The system accurately determines optimal chemical injection amounts, balancing water quality and cost efficiency by adjusting rates to meet target turbidity levels, reducing excess chemical use and operational costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007891452000001
    Figure 0007891452000001
  • Figure 0007891452000002
    Figure 0007891452000002
  • Figure 0007891452000003
    Figure 0007891452000003
Patent Text Reader

Abstract

To provide an injection control device, an injection control method, and an injection control program of an agent, capable of determining proper injection rate of an agent.SOLUTION: An injection control device of an agent of the present invention is an injection control device of an agent to be used in a water treatment system and comprises a first model learned so as to output an injection ratio of an agent for injection to water to be treated from a water quality of the water to be treated and a second model learned so as to output water quality of treatment water formed by injection of the agent to the water to be treated based on the injection ratio of the agent calculated by the water quality of the water to be treated and the first model.SELECTED DRAWING: Figure 6
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a chemical injection control device, an injection control method, and an injection control program used in a water treatment system.

Background Art

[0002] In a water treatment system, for example, by injecting a flocculant into a chemical mixing tank, turbidity and the flocculant are mixed to form minute flocs. Then, in a downstream sedimentation tank, the grown flocs settle, and water purification is performed. In such a water treatment system, various attempts have been made to determine an appropriate injection rate of the flocculant. For example, in Patent Document 1, it has been proposed to predict the injection rate of chemicals (flocculant, chlorine, activated carbon) using a decision tree learning algorithm.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the actual operation data used as teacher data in the above learning algorithm, there are cases where chemicals are injected excessively in consideration of the safety of water treatment. Therefore, in this learning algorithm, there is a possibility that an excessive injection rate is output as a predicted value, and there is room for improvement. In such water treatment, the above problems exist not only in the injection of flocculants but also in the injection of all chemicals for water treatment. The present invention has been made to solve this problem, and an object thereof is to provide a chemical injection control device, an injection control method, and an injection control program capable of determining an appropriate injection amount of chemicals.

Means for Solving the Problems

[0005] The chemical injection control device according to the present invention is a chemical injection control device used in a water treatment system, and comprises a first model that has been trained to output the injection rate of a chemical to be injected into the water to be treated based on the water quality of the water to be treated, and a second model that has been trained to output the water quality of the treated water produced by injecting the chemical into the water to be treated based on the water quality of the water to be treated and the injection rate of the chemical calculated by the first model.

[0006] The chemical injection control method according to the present invention is a chemical injection control method used in a water treatment system, comprising the steps of: outputting the chemical injection rate from the water quality of the water to be treated using a first model that has been trained to output the chemical injection rate from the water quality of the water to be treated; and outputting the water quality of the treated water from the water quality of the water to be treated and the chemical injection rate calculated by the first model using a second model that has been trained to output the water quality of the treated water generated by injecting the chemical into the water to be treated using the water quality of the water to be treated and the chemical injection rate calculated by the first model.

[0007] The chemical injection control program according to the present invention is a chemical injection control program used in a water treatment system, which causes a computer to perform the following steps: output the chemical injection rate from the water quality of the water to be treated using a first model that has been trained to output the chemical injection rate from the water quality of the water to be treated; and output the water quality of the treated water from the water quality of the water to be treated and the chemical injection rate calculated by the first model using a second model that has been trained to output the water quality of the treated water produced by injecting the chemical into the water to be treated using the water quality of the water to be treated and the chemical injection rate calculated by the first model. [Effects of the Invention]

[0008] According to the present invention, it is possible to determine the appropriate amount of chemical to be injected into a filtration system. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram showing an example of a rapid filtration system to which the flocculant injection control device according to the present invention is applied. [Figure 2] This is an example of a block diagram showing the hardware configuration of one embodiment of a coagulant injection control device according to the present invention. [Figure 3] This is an example of a block diagram showing the software configuration of one embodiment of a coagulant injection control device according to the present invention. [Figure 4] Figure 3 shows an example of the operation of the determination unit. [Figure 5] Figure 3 shows an example of the operation of the determination unit. [Figure 6] This flowchart shows an example of a method for controlling the injection of a coagulant. [Modes for carrying out the invention]

[0010] Hereinafter, an embodiment of the chemical injection control device according to the present invention applied to a flocculant injection control device will be described with reference to the drawings. First, a rapid filtration system in which this injection control device is used will be described, and then the injection control device will be described.

[0011] <1. Filtration System> Figure 1 is a schematic diagram showing an example of a rapid filtration system. As shown in Figure 1, this rapid filtration system comprises an intake well 11, a chemical mixing tank 12, a flocculation tank 13, a sedimentation tank 14, and a rapid filtration tank 15, arranged from upstream to downstream, and water is supplied in this order. The intake well 11 contains raw water (water to be treated) taken from an intake facility located in a river or the like. The raw water contained in the intake well 11 is sent to the chemical mixing tank 12. In addition, the water quality (turbidity, pH, alkalinity, water temperature, color, UV, etc.) of the raw water in the intake well 11 is measured by a water quality measuring instrument 16. In the chemical mixing tank 12, a coagulant is injected by a coagulant injection device 17 and quickly agitated. This mixes the turbidity and the coagulant. In the flocculation tank 13, the micro-flocs formed in the chemical mixing tank 12 are gently agitated to promote floc growth. Then, in the sedimentation tank 14, the grown flocs settle, reducing the load of suspended solids. The turbidity of the water (treated water) discharged from the sedimentation tank 14 is measured by the turbidimeter 18. In the rapid filtration tank 15, the water after the flocs have settled is purified through a fine sand layer, and the suspended solids are finally removed. Subsequently, although not shown in the diagram, chlorine is added to the purified water and it is sent to the distribution reservoir.

[0012] <2. Hardware configuration of the injection control device> The injection control device 2 according to this embodiment is a device that controls the injection of a coagulant into a rapid filtration system. Figure 2 shows an example of the hardware configuration of the injection control device 2. This injection control device 2 is a computer in which a control unit 21, a storage unit 22, an external interface 23, and a communication interface 24 are electrically connected. Such a computer can be a general-purpose personal computer, a dedicated computer, or a tablet computer. Furthermore, the injection control device 2 can be configured with multiple computers. In Figure 2, the external interface 23 and the communication interface 24 are referred to as "external I / F" and "communication I / F," respectively.

[0013] The control unit 21 includes a CPU, RAM, ROM, etc., and is configured to perform various information processing based on programs and data. The storage unit 22 is composed of an auxiliary storage device such as an HDD or SSD, and stores the injection control program 221, raw water quality data 222, coagulant injection rate data 223, sediment water turbidity data 224, control data 225, and various data for driving the injection control device 2.

[0014] The injection control program 221 is a program for controlling the injection of coagulant, as will be described later. The raw water quality data 222 is data on the raw water quality measured by the water quality measuring instrument 16 over a predetermined period. The coagulant injection rate data 223 is data on the injection rate of coagulant injected into the chemical mixing tank 12 over a predetermined period. The sedimentation tank 14 turbidity data 224 is data on the turbidity of the sedimentation tank measured by the turbidimeter 18 over a predetermined period. The control data 225 is various data for controlling the rapid filtration tank.

[0015] The external interface 23 is an interface for connecting to an external device and is configured appropriately depending on the external device to be connected. In this embodiment, the external interface 23 is connected to the display device 4 and the input device 5. The display device 4 is, for example, a display and is used to display various data such as inputs and outputs. The display is not particularly limited, and a known liquid crystal display or the like can be used. The input device 5 is a keyboard, mouse, or the like and is used for the inputs described above. In addition, various external devices can be connected to the external interface 23 as appropriate. For example, a touch panel display that serves as both the display device 4 and the input device 5 can be used.

[0016] The communication interface 24 is, for example, a wired LAN (Local Area Network) module, a wireless LAN module, etc., and is an interface for performing wired or wireless communication. That is, the communication interface 24 is an example of a communication unit configured to communicate with the water quality measuring device 16, the flocculant injection device 17, the turbidimeter 18, and other devices.

[0017] Note that the specific hardware configuration of the flocculant injection control device 2 can be appropriately omitted, replaced, and added according to the embodiment. For example, the control unit 21 may include a plurality of processors. Also, the control unit 21 may be configured by an FPGA. The storage unit 22 may be configured by a RAM and a ROM included in the control unit 21.

[0018] <3. Software Configuration of Chemical Injection Control Device> FIG. 3 is an example of the software configuration of the chemical injection control device. In the injection control device 2, the following processing is performed. That is, when the control unit 21 of the injection control device 2 expands the injection control program 221 stored in the storage unit 22 into the RAM, the injection control program 221 is interpreted and executed by the CPU, and functions as a first model 211, a second model 212, and a determination unit 213 as shown in FIG. 3.

[0019] The first model 211 is a trained model that takes the water quality of raw water as input and outputs the injection rate of the flocculant injected into the chemical mixing tank 12. That is, this first model 211 has been machine-learned using, as teacher data, the water quality of the raw water measured by the water quality measuring instrument 16 and the injection rate of the flocculant injected into the raw water over a predetermined period. Thereby, when the water quality of the raw water measured by the water quality measuring instrument 16 is input to the first model 211, the corresponding injection rate of the flocculant is output. Note that the above-mentioned predetermined period is not particularly limited as long as it is a period during which teacher data necessary for performing machine learning can be collected. Also, it is not necessary to use all of the parameters such as turbidity described above for the water quality of the raw water as input, and at least one can be used. This also applies to the second model 212.

[0020] The second model 212 is a trained model that takes the injection rate of the flocculant output by the first model 211 and the water quality of the raw water as input and outputs the turbidity of the settled water. That is, the second model 212 has been machine-learned using, as teacher data, the injection rate of the flocculant output by the first model 211 and the water quality of the raw water, and the turbidity of the settled water measured by the turbidimeter 18 corresponding thereto over a predetermined period. Thereby, when the injection rate of the flocculant output by the first model 2 | 11 and the water quality of the raw water measured by the water quality measuring instrument 16 are input to the second model 212, the corresponding turbidity of the settled water is output.

[0021] The machine learning used in constructing the first model 211 and the second model 212 is not particularly limited, and a machine learning model with teacher data as described above can be used. For example, a neural network, Light GBM (Light Gradient Boosting Machine), etc. can be used, but it is not limited thereto.

[0022] [[ID=ll]] The determination unit 213 outputs an appropriate coagulant injection rate based on the turbidity of the sediment output by the second model 212. For example, as shown in Figure 4, if the target turbidity is 1.0 degrees and the appropriate range is set to be within 0.1 degrees of the target (0.9 to 1.0 degrees), then if the turbidity of the sediment output after passing through the first model 211 and the second model 212 is 0.5 degrees (in this case, the injection rate is 30 mg / L), it is considered that the turbidity has been excessively reduced. Therefore, in this case, the determination unit 213 can determine that an excessive amount of coagulant has been injected. When the determination unit 213 makes such a determination, it reduces the coagulant injection rate to be injected into the second model 212. In the example in Figure 4, 90% of the coagulant injection rate calculated by the first model 211 is input to the second model 212 as the second injection rate, and the turbidity of the sedimentation tank 14 is output. As a result, if the turbidity is 0.7 degrees, the determination unit 213 determines that it is still outside the appropriate range.

[0023] Therefore, the determination unit 213 inputs 80% of the coagulant injection rate output by the first model 211 as the third injection rate to the second model 212 and outputs the turbidity of the sedimentation tank 14. As a result, if the turbidity is 0.9 degrees, the determination unit 213 determines that the turbidity is appropriate and outputs the injection rate of 24 mg / L, which is the appropriate injection rate. Accordingly, the injection control device 2 drives the coagulant injection device 17 and injects the coagulant into the chemical mixing tank 12 according to this injection rate.

[0024] In the example shown in Figure 4, the coagulant injection rate is reduced by 10% each time, but this is just one example, and the setting for reducing the coagulant injection rate from the second time onward can be changed as appropriate. In other words, the rate of reduction in the injection rate does not have to be constant and can be changed as appropriate. Furthermore, it is not limited to the rate of reduction in the injection rate, but the amount of reduction in the injection rate itself can also be adjusted, such as reducing it by 1 mg / L each time. The amount of reduction in the injection rate also does not have to be constant and can be changed as appropriate. In addition, depending on the output turbidity, the injection rate can be increased. For example, if the appropriate turbidity is exceeded after the third injection of coagulant (for example, if the turbidity becomes greater than 1.0), the coagulant can be injected again with a higher injection rate than the third time (for example, an injection rate between the second and third injection rates, such as 25 mg / L). Also, the target value and appropriate range of turbidity mentioned above are just examples and can be set as appropriate.

[0025] Furthermore, if the turbidity of the sedimentation tank output in the second model 212 is higher than the target value, the opposite procedure to that in Figure 4 is performed, as shown in Figure 5. That is, the injection rate of the coagulant is increased by a predetermined amount (for example, 10% at a time) until the turbidity of the sedimentation tank falls below the target value. This ensures that an appropriate injection amount can be obtained even when the output turbidity is higher than the target value.

[0026] In addition to the above-mentioned controls, the injection control device 2 can also perform various controls on the rapid filtration system, such as controlling the stirring intensity and rotation speed in the floc formation tank 13.

[0027] <4. Operation of the injection control device> Next, the operation of the flocculant injection control device 2 configured as described above will be explained with reference to the flowchart in Figure 6.

[0028] As shown in Figure 6, first, the injection control device 2 measures the quality of the raw water and inputs this to the first model 211 to output the coagulant injection rate (step S1). Next, the injection control device 2 inputs the coagulant injection rate output by the first model 211 and the quality of the raw water to the second model 212 and outputs the turbidity of the settled water (step S2). Subsequently, the determination unit 213 determines that the output turbidity is below the target value (YES in step S3), and further determines that the turbidity is lower than the target value by a predetermined value or more (YES in step S4), then, as described above, the coagulant injection rate is reduced by a predetermined percentage (for example, by 10%) and a new coagulant injection rate is set (step S5). Then, the injection control device 2 inputs the newly set coagulant injection rate to the second model 212 and outputs the turbidity of the settled water (step S6). If the determination unit 213 determines that the turbidity of the output sediment is lower than the target value by a predetermined value or more (YES in step S4), the coagulant injection rate is further reduced by a predetermined percentage (for example, by another 10%), and a new coagulant injection rate is set (step S5).

[0029] Steps S4 to S6 are repeated, and if the output turbidity is not determined to be lower than the target value by a predetermined value or more (NO in step S4), the coagulant injection rate is deemed appropriate, and the coagulant is injected from the coagulant injection device 17 into the chemical mixing tank 12 (step S7).

[0030] On the other hand, if the determination unit 213 determines that the output turbidity is higher than the target value (NO in step S3), it increases the coagulant injection rate by a predetermined percentage (for example, by 10%) and sets a new coagulant injection rate (step S8). The injection control device 2 then inputs the newly set coagulant injection rate to the second model 212 and outputs the turbidity of the precipitated water (step S9). If the determination unit 213 determines that the output turbidity of the precipitated water is higher than the target value (YES in step S10), it further increases the coagulant injection rate by a predetermined percentage (for example, by another 10%) and sets a new coagulant injection rate (step S8).

[0031] Steps S8 to S10 are repeated, and if the output turbidity is not determined to be higher than the target value (NO in step S10), the coagulant injection rate is deemed appropriate, and the coagulant is injected from the coagulant injection device 17 into the chemical mixing tank 12 (step S7).

[0032] <5. Features> As described above, the following effects can be obtained according to this embodiment. (1) In this embodiment, the appropriate amount of coagulant to be injected can be determined by combining the first model 211 and the second model 212. The first model 211 can predict the coagulant injection rate corresponding to the raw water quality by constructing a relationship between the raw water quality and the coagulant injection rate for that water quality. The reason for combining it with the second model 212 is as follows.

[0033] In the operation of the rapid filtration system, the injection rate of the coagulant may be set high for safety reasons. Therefore, the first model 211, which is learned using actual operating data, may output an injection rate that is higher than necessary. In this case, by predicting the turbidity of the sedimentation tank using the second model 212, it is possible to determine whether the injection rate is appropriate or not. As described above, for example, if the predicted turbidity is lower than the target value by a predetermined value or more, it can be determined that the injection rate is higher than necessary. Based on this, a decision can be made to reduce the injection rate, thereby reducing the cost of the coagulant. Thus, the injection control device 2 of this embodiment can achieve both water quality improvement and cost reduction.

[0034] (2) By providing the determination unit 213 as described above, if the turbidity of the sedimentation tank is lower than a predetermined value, the appropriate injection rate of coagulant can be automatically obtained to achieve an appropriate turbidity.

[0035] <6. Variation> Although one embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications are possible without departing from the spirit of the invention. Furthermore, the following modifications can be combined as appropriate. Furthermore, the following modifications can also be combined with the above-described embodiment.

[0036] (1) In the above embodiment, the injection control device 2 has a determination unit 213 as part of its software configuration, but the determination unit 213 is not necessarily required. For example, the injection control device 2 can be configured to output the turbidity of the sedimentation water. In this case, the user of the injection control device 2 can determine whether the output turbidity of the sedimentation tank is appropriate and decide on the amount of coagulant to be injected based on that determination.

[0037] (2) Generally, when a rapid filtration system is in normal operation, the water quality in the intake well 11 is often below a predetermined value (i.e., the water quality is not poor), and a lot of operational data can be obtained. In addition, since jar tests can be performed at predetermined intervals, it is also possible to add supplementary operational data. In such cases, as described above, the injection rate of the coagulant tends to be set high, so the first model 211 and the second model 212 are used in combination as described above.

[0038] On the other hand, during rainy weather or other non-normal operating conditions, i.e., when the water quality in the intake well 11 is higher than the predetermined value (i.e., when the water quality is poor), there is not much operating data and there is little jar test data, so the accuracy of predicting the turbidity of the settled water when the coagulant injection rate is varied is considered to be low. Furthermore, when the water quality is fluctuating in this way, the operation is often carried out with an emphasis on the treated water quality, and there is considered to be little need to consider the appropriateness of the cost of the coagulant. In such cases, the coagulant injection rate can be calculated using only the first model 211 and the coagulant can be injected using this. In other words, the operation can be carried out by reproducing past operating conditions without using the second model 212.

[0039] (3) The configuration of the rapid filtration system is not limited to that shown in Figure 1, and can be modified as appropriate, as long as the first model 211 and the second model 212 described above can be constructed.

[0040] Furthermore, although the above embodiment shows an example of applying the present invention to an injection control device for injecting a coagulant into a rapid filtration system, it is not limited to coagulants and can be applied to all water treatment systems for improving the water quality of treated water by injecting chemicals such as chlorine, activated carbon, and chemicals that remove moldy odors.Therefore, when applying the injection control device of the present invention to such a water treatment system, the location where the chemical is injected into the water to be treated and the location where the water quality of the treated water improved by the chemical is evaluated can be appropriately changed depending on the type of chemical.

[0041] (4) In the above embodiment, the turbidity of the sedimentation tank is output in the second model, but it is also possible to output the water quality of the sedimentation tank and the filtration tank. For example, the color of the sedimentation water, the turbidity of the filtered water, the UV of the filtered water, etc., can be used as the water quality of the sedimentation tank and the filtration tank.

[0042] (5) In the first model 211 and the second model 212, the coagulant injection rate is used as the output or input, but an equivalent value to the coagulant injection rate, such as the amount of coagulant injected, can also be used. Therefore, in the present invention, the coagulant injection rate can be considered equivalent to the amount of coagulant injected. [Explanation of Symbols]

[0043] 2: Coagulant injection control device 211: First Model 212: Second Model 213: Judgment section

Claims

1. A chemical injection control device used in a water treatment system, A first model, trained to output the injection rate of chemicals to be injected into the treated water based on the water quality of the treated water, A second model, which has been trained to output the water quality of treated water produced by injecting the chemicals into the treated water, based on the water quality of the treated water and the injection rate of the chemicals calculated by the first model, It comprises a determination unit and, The determination unit, when the water quality of the water to be treated has deteriorated below a first predetermined value, stops the second model and determines the chemical injection rate using the first model, thereby providing a chemical injection control device.

2. The chemical injection control device according to Claim 1, wherein the determination unit determines whether the water quality of the treated water calculated by the second model is suitable.

3. The determination unit, If the water quality of the treated water calculated by the second model is determined to be better than the target value, the first step is to reduce the injection rate of the chemicals input to the second model according to the specified criteria, and then output the water quality of the treated water using the second model. A chemical injection control device according to claim 2, comprising the steps of: performing a second step of determining whether the water quality of the output treated water is closer to the target value than a second predetermined value.

4. The determination unit, The chemical injection control device according to claim 3, wherein in the second step, the first step and the second step are performed at least once until it is determined that the water quality of the output treated water is closer to the target value than the second predetermined value.

5. The chemical injection control device according to Claim 1, wherein the determination unit, if the water quality of the water to be treated has not deteriorated below a first predetermined value, inputs the water quality of the water to be treated to the first model and outputs the chemical injection rate to be injected into the water to be treated; inputs the water quality of the water to be treated and the chemical injection rate calculated by the first model to the second model and outputs the water quality of the water to be treated; and if the water quality of the treated water calculated by the second model is appropriate, extracts the chemical injection rate calculated by the first model as the chemical injection rate to be injected into the water to be treated.