Aeration amount control device and aeration amount control method

Abstract

An aeration amount control device includes an ammonia concentration sensor, a conductivity sensor, a conductivity-concentration correlation information storage unit, a first estimation unit, a target aeration amount calculation unit, and a conductivity-concentration correlation information update unit. The ammonia concentration sensor measures an ammonia concentration of treated water after biological treatment of treated water in a biological reaction tank. The conductivity sensor measures a conductivity of the treated water flowing into the biological reaction tank. The first estimation unit estimates a first ammonia concentration estimation value of the treated water from the conductivity-concentration correlation information based on a conductivity value. The target aeration amount calculation unit calculates a target value of an aeration amount supplied to the biological reaction tank according to the first ammonia concentration estimation value and a measurement value of the ammonia concentration sensor. The conductivity-concentration correlation information update unit has an acceptance unit that accepts a second ammonia concentration estimation value of the treated water measured or estimated by a method different from a method of estimating the first ammonia concentration estimation value, and an update processing unit that updates the conductivity-concentration correlation information according to the second ammonia concentration estimation value and the conductivity value.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to an aeration amount control device and an aeration amount control method that control an amount of air, i.e., an aeration amount, supplied to a reaction tank that performs biological treatment. BACKGROUND

[0002] As a method of treating the effluent water containing organic matter and ammonia nitrogen, there is an activated sludge method. The activated sludge method is a method of storing activated sludge, which is a microorganism group having a purification function, in a reaction tank, mixing and contacting the activated sludge with the effluent water, and at the same time, supplying air, i.e., performing aeration, thereby oxidizing and decomposing the contaminants in the effluent water. It is necessary to supply an appropriate amount of air to the biological reaction tank in response to a load variation of the contaminants flowing in, and the aeration amount is feedforward controlled by measuring the ammonia concentration of the inflow water. However, an ammonia concentration meter is very expensive. Therefore, in Patent Literature 1, an aeration amount control method is disclosed, in which the ammonia concentration value is estimated from a correlation between the conductivity value of the inflow water and the ammonia concentration value, which is measured in advance, and the aeration amount is controlled in accordance with the estimated ammonia concentration value.

[0003] PRIOR ART DOCUMENTS

[0004] PATENT LITERATURE

[0005] Patent Literature 1: Japanese Patent Application Publication No. 2009-119329 SUMMARY

[0006] PROBLEMS TO BE SOLVED BY THE INVENTION

[0007] However, the inflow water contains coexisting substances such as other ions that affect the conductivity in addition to ammonia. One example of the coexisting substances is a chloride ion. In the case where the concentration of the coexisting substances varies, the correlation between the conductivity value of the inflow water and the ammonia concentration value changes from the correlation set in advance. Therefore, an error can occur between the ammonia concentration value estimated from the measured conductivity value and the actual ammonia concentration of the treated water. However, in the related art, it has not been considered that the correlation between the conductivity value and the ammonia concentration value changes from the correlation set in advance due to the variation in the concentration of the coexisting substances, and thus an error occurs between the ammonia concentration value estimated from the measured conductivity value and the actual ammonia concentration. That is, in the related art, since the variation in the concentration of the coexisting substances of the inflow water is not taken into account, there is a problem that an appropriate amount of air cannot be supplied to the biological reaction tank in response to a load variation of the ammonia flowing in.

[0008] The present disclosure was achieved in view of the above-described circumstances, and aims to obtain an aeration amount control device that can supply an appropriate amount of air to a biological reaction tank in response to a load variation of ammonia flowing in even in the case where the concentration of the coexisting substances of the inflow water varies.

[0009] Technical means for solving technical problems

[0010] To solve the above technical problem and achieve the object, the present disclosure relates to an aeration amount control device that controls an amount of oxygen-containing gas, i.e., an aeration amount, supplied to a biological reaction tank that biologically treats water to be treated, including an ammonia concentration sensor, a conductivity sensor, a conductivity concentration correlation information storage section, a first estimation section, a target aeration amount calculation section, and a conductivity concentration correlation information update section. The ammonia concentration sensor measures an ammonia concentration of the treated water after the water to be treated in the biological reaction tank is biologically treated. The conductivity sensor measures a conductivity of the water to be treated that flows into the biological reaction tank. The conductivity concentration correlation information storage section stores conductivity concentration correlation information that indicates a correlation between the conductivity of the water to be treated and the ammonia concentration of the water to be treated. The first estimation section estimates, based on a conductivity value measured by the conductivity sensor, a first ammonia concentration estimation value from the conductivity concentration correlation information. The target aeration amount calculation section calculates a target value of the aeration amount supplied to the biological reaction tank from the first ammonia concentration estimation value of the water to be treated and an ammonia concentration value of the treated water measured by the ammonia concentration sensor. The conductivity concentration correlation information update section updates the conductivity concentration correlation information. The conductivity concentration correlation information update section has an acceptance section and an update processing section. The acceptance section accepts a second ammonia concentration estimation value of the water to be treated measured or estimated in a method different from the method of estimating the first ammonia concentration estimation value. The update processing section updates the conductivity concentration correlation information based on the second ammonia concentration estimation value accepted by the acceptance section and the conductivity value measured by the conductivity sensor.

[0011] Effects of the invention

[0012] The aeration amount control device according to the present disclosure can achieve the following effect: even in a case where the concentration of a coexisting substance of the inflow water varies, an appropriate amount of air can be supplied to the biological reaction tank in response to a variation in the load of ammonia inflow. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 is a diagram that schematically represents one example of a structure of an aeration amount control system that has the aeration amount control device according to Embodiment 1.

[0014] Figure 2 is a block diagram that schematically represents one example of a structure of a database update section of the aeration amount control device according to Embodiment 1.

[0015] Figure 3 is a flowchart that represents one example of processing steps of the aeration amount control method according to Embodiment 1.

[0016] Figure 4is a flowchart showing an example of the steps of the method of updating the conductivity concentration-related information in the aeration amount control device according to Embodiment 1.

[0017] Figure 5 is a block diagram showing an example of the structure of the database updating section of the aeration amount control device according to Embodiment 2.

[0018] Figure 6 is a diagram showing an example of the structure of the learning device for generating the completed learning model of the aeration amount control device according to Embodiment 2.

[0019] Figure 7 is a diagram schematically showing an example of the neural network used by the model generating section of Figure 6

[0020] Figure 8 is a flowchart showing an example of the steps of the learning processing performed by the learning device.

[0021] Figure 9 is a diagram schematically showing an example of the structure of the second estimation section of the aeration amount control device according to Embodiment 2.

[0022] Figure 10 is a flowchart showing an example of the steps of the estimation processing performed by the second estimation section of the aeration amount control device according to Embodiment 2.

[0023] Figure 11 is a flowchart showing an example of the steps of the method of updating the conductivity concentration-related information in the aeration amount control device according to Embodiment 2.

[0024] Figure 12 is a diagram showing an example of the hardware structure of the control circuit. DETAILED DESCRIPTION

[0025] Hereinafter, the aeration amount control device and the aeration amount control method according to the embodiments of the present disclosure will be described in detail based on the drawings.

[0026] Embodiment 1.

[0027] Figure 1 is a diagram schematically showing an example of the structure of the aeration amount control system provided with the aeration amount control device according to Embodiment 1. The aeration amount control system 1 includes a bioreactor tank 10, a diffuser plate 11, a blower 12, a wind amount adjusting section 13, a conductivity sensor 15, a treated water ammonia concentration sensor 14, and an aeration amount control device 30.

[0028] ​The biological reaction tank 10 is a water tank that biologically treats the treated water. Specifically, the biological reaction tank 10 is a water tank that internally accumulates activated sludge, and uses the activated sludge to biologically treat the treated water to the treated water 101 having a prescribed nitrogen concentration or less. The biological reaction tank 10 is provided in a water purification site, a sewage treatment site, a wastewater treatment facility of a factory, or the like. The inflow portion 102 and the outflow portion 103 are connected to the biological reaction tank 10. The inflow portion 102 is a pipe or a waterway through which the treated water that is a treatment target flows in. The outflow portion 103 is a pipe or a waterway through which the treated water 101 that has been treated in the biological reaction tank 10 flows out to the outside of the biological reaction tank 10.

[0029] The diffuser plate 11 is disposed at the bottom of the biological reaction tank 10, and supplies air to the treated water in the biological reaction tank 10. Here, the case of supplying air is exemplified, but any gas containing oxygen like air is acceptable.

[0030] The air blower 12 is connected to the pipe via the diffuser plate 11, and supplies air to the diffuser plate 11. The air volume adjustment portion 13 adjusts the air volume from the air blower 12 to the diffuser plate 11. In one example, the air volume adjustment portion 13 is an air volume adjustment valve provided on the pipe connecting the air blower 12 and the diffuser plate 11. In this case, the air supply amount to the diffuser plate 11 is adjusted by adjusting the opening degree of the air volume adjustment valve. The air volume adjustment portion 13 adjusts the air volume in accordance with the target value of the air supply amount from the air supply amount control device 30.

[0031] The treated water ammonia concentration sensor 14 measures the ammonia concentration of the treated water 101 in the biological reaction tank 10. The treated water 101 is obtained by biologically treating the treated water in the biological reaction tank 10. In one example, by being disposed in the vicinity of or in the outflow portion 103 of the biological reaction tank 10, the ammonia concentration of the treated water 101 that has been treated by the activated sludge in the biological reaction tank 10 can be appropriately measured. The treated water ammonia concentration sensor 14 is connected to the target air supply amount calculation portion 33 of the air supply amount control device 30 via a signal line, and transmits the measurement data of the measured ammonia concentration of the treated water 101 to the target air supply amount calculation portion 33.

[0032] The conductivity sensor 15 measures the conductivity of the treated water, that is, the electric conductivity. In one example, the conductivity sensor 15 is disposed in the inflow portion 102. The measurement method of the conductivity includes an electrode method, an electromagnetic induction method, and the like. The conductivity sensor 15 is connected to the first estimation portion 32 and the database update portion 34 of the air supply amount control device 30 via a signal line, and transmits the measurement data of the measured conductivity of the treated water, that is, the conductivity value, to the first estimation portion 32 and the database update portion 34.

[0033] The aeration amount control device 30 controls the amount of air, i.e., the aeration amount, supplied to the biological reaction tank 10, based on the difference between the ammonia concentration value of the treated water and the ammonia concentration value of the treated water 101. The aeration amount control device 30 has a database 31, a first estimation section 32, a target aeration amount calculation section 33, and a database update section 34.

[0034] The database 31 stores information, i.e., conductivity concentration correlation information, indicating the correlation between the conductivity of the treated water and the ammonia concentration of the treated water. The conductivity concentration correlation information is information indicating the correlation between the conductivity of the treated water and the ammonia concentration, but can also be information indicating the correlation between the change amount of the conductivity of the treated water and the ammonia concentration. In addition, the conductivity concentration correlation information can also be information indicating the correlation between the conductivity of the treated water and the ammonia concentration of the treated water, and other plant data related to the treated water. The other plant data related to the treated water is the measurement result of the concentration of other ions such as chloride ions contained in the treated water, the flow rate of the treated water, the measurement date and time, and the like. The database 31 is connected to the database update section 34 and the first estimation section 32. The database 31 corresponds to a conductivity concentration correlation information storage section.

[0035] The first estimation section 32 estimates, from the conductivity concentration correlation information of the database 31, a first ammonia concentration estimation value of the treated water based on at least the conductivity value of the treated water measured by the conductivity sensor 15, and outputs the estimated first ammonia concentration estimation value of the treated water to the target aeration amount calculation section 33. The measurement result of the conductivity used for the estimation is not particularly limited, and is a momentary value, an average value for a prescribed period, a change amount, or the like. In addition, in the case where the conductivity concentration correlation information of the database 31 is information indicating the correlation between the measurement result of the conductivity, other plant data related to the treated water, and the ammonia concentration of the treated water, the first estimation section 32 can also estimate the first ammonia concentration estimation value of the treated water from the conductivity concentration correlation information based on the measurement result of the conductivity and the other plant data related to the treated water. The first estimation section 32 is connected to the conductivity sensor 15, the database 31, the target aeration amount calculation section 33, and the database update section 34.

[0036] The target aeration amount calculation section 33 calculates a target value of the aeration amount supplied to the biological reaction tank 10 from the blower 12 every arbitrary period, and transmits the target value of the aeration amount to the air volume adjustment section 13 via a signal line. Specifically, the target aeration amount calculation section 33 calculates a target value of the aeration amount supplied to the biological reaction tank 10, based on the first ammonia concentration estimation value of the treated water transmitted from the first estimation section 32 and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 measured by the treated water ammonia concentration sensor 14. The period for calculating the target value of the aeration amount is preferably in the range of 1 second or more and 5 minutes or less, but can be arbitrarily set according to the characteristics of the installation site. The air volume adjustment section 13 adjusts the aeration amount so that the aeration amount supplied to the diffuser plate 11 is equal to the target value of the aeration amount calculated by the target aeration amount calculation section 33. The number of the diffuser plate 11, the air volume adjustment section 13, and the target aeration amount calculation section 33 can be arbitrarily changed according to the scale of the biological reaction tank 10 or the characteristics of the installation site.

[0037] The database update section 34 updates the conductivity concentration correlation information stored in the database 31. As described above, it is known that there is a correlation between the conductivity and the ammonia concentration in the treated water. In addition, it is known that this correlation is affected by the concentration of coexisting substances such as other ions in the treated water. Therefore, in Embodiment 1, the database update section 34 updates the conductivity concentration correlation information in the case where it is judged that the concentration of the coexisting substances in the treated water has changed and the conductivity concentration correlation information needs to be updated. The database update section 34 corresponds to a conductivity concentration correlation information update section.

[0038] Figure 2 is a block diagram schematically showing one example of the structure of the database update section of the aeration amount control device according to Embodiment 1. The database update section 34 includes an acceptance section 341 and an update processing section 342.

[0039] The acceptance section 341 accepts from the outside a value of the ammonia concentration of the treated water, i.e., a second ammonia concentration estimation value. The second ammonia concentration estimation value is a value of the ammonia concentration of the treated water that is measured or estimated by a method different from the method of estimating the first ammonia concentration estimation value from the measured value of the conductivity of the treated water. At this time, the acceptance section 341 can also accept the date and time of the second ammonia concentration estimation value of the treated water accepted from the outside. In one example, the acceptance section 341 can also measure the ammonia concentration of the treated water collected by the worker using an analysis device such as an ion chromatograph analysis device, and accept the measured result as the second ammonia concentration estimation value. In addition, in another example, the acceptance section 341 can accept the estimation value of an estimation device of the ammonia concentration of the treated water as the second ammonia concentration estimation value. Examples of the estimation device of the ammonia concentration of the treated water are described in Embodiment 2. In addition, the acceptance section 341 can accept a data set in which a plurality of date and times of the second ammonia concentration estimation value are input. The acceptance section 341 transmits the accepted second ammonia concentration estimation value of the treated water to the update processing section 342.

[0040] The update processing section 342 is connected to the first estimation section 32, the conductivity sensor 15, and the database 31. The update processing section 342 determines whether or not the conductivity concentration-related information of the database 31 needs to be updated, based on the difference between the first ammonia concentration estimation value estimated by the first estimation section 32 and the second ammonia concentration estimation value accepted by the acceptance section 341. In one example, the update processing section 342 determines that the conductivity concentration-related information does not need to be updated when the difference between the first ammonia concentration estimation value estimated by the first estimation section 32 and the second ammonia concentration estimation value accepted by the acceptance section 341 at the same time is less than a predetermined determination value, and determines that the conductivity concentration-related information needs to be updated when the difference is greater than the determination value. When the difference is equal to the determination value, it can be determined that the conductivity concentration-related information does not need to be updated, or it can be determined that the conductivity concentration-related information needs to be updated.

[0041] In one example, the determination value is a threshold value that can determine that the first ammonia concentration estimation value and the second ammonia concentration estimation value are consistent within an error range. The determination of whether or not the conductivity concentration-related information needs to be updated can also be made based on a predetermined ratio or the like. The same time can not be the same time in units of seconds, but can be a prescribed range of time. The prescribed range of time can be within 1 hour in one example. However, from the viewpoint of being able to improve the accuracy of the determination, it is preferable that the prescribed range of time be short.

[0042] When it is determined that the conductivity concentration-related information needs to be updated, the update processing section 342 newly constructs the conductivity concentration-related information of the treated water based on the second ammonia concentration estimation value of the treated water accepted by the acceptance section 341 and the conductivity value measured by the conductivity sensor 15, and updates the conductivity concentration-related information in the database 31. At this time, the update processing section 342 newly constructs the conductivity concentration-related information of the treated water using a plurality of data composed of a group including the second ammonia concentration estimation value of the treated water at the same time and the conductivity.

[0043] Therefore, in Embodiment 1, the database update section 34 updates the conductivity concentration-related information at an appropriate timing in the case where the correlation between the conductivity and the ammonia concentration of the treated water has changed with respect to the conductivity concentration-related information stored in the database 31 due to a change in the concentration of the coexisting substance that affects the conductivity. Therefore, the first estimation section 32 estimates the first ammonia concentration estimation value of the treated water with reference to the conductivity concentration-related information updated at an appropriate timing, and the target aeration amount calculation section 33 calculates the target value of the aeration amount using the first ammonia concentration estimation value. As a result, an appropriate amount of air can be supplied to the biological reaction tank 10 in response to a change in the load of the inflowing ammonia.

[0044] Next, the aeration amount control method in the aeration amount control device 30 and the updating method of the conductivity concentration-related information will be described in order. The updating method of the conductivity concentration-related information is performed when the aeration amount control method is executed, and is a part of the aeration amount control method. That is, the aeration amount control method includes the updating method of the conductivity concentration-related information.

[0045] Figure 3 is a flowchart showing one example of the processing steps of the aeration amount control method according to Embodiment 1. When the aeration amount control is started, the conductivity sensor 15 measures the conductivity of the treated water at a certain time t (step Sll). The conductivity sensor 15 outputs the measurement result to the first estimation section 32.

[0046] Next, the first estimation section 32 estimates the first ammonia concentration estimation value of the treated water from the conductivity concentration-related information of the database 31 based on the measured conductivity value (step S12). The first estimation section 32 outputs the first ammonia concentration estimation value of the treated water to the target aeration amount calculation section 33.

[0047] In addition, at the time t, in parallel with steps Sll and S12, the treated water ammonia concentration sensor 14 measures the ammonia concentration of the treated water 101 (step S13). The treated water ammonia concentration sensor 14 outputs the measurement result to the target aeration amount calculation section 33.

[0048] After the step S12 and the step S13, the target aeration amount calculation section 33 calculates a target value of the aeration amount supplied to the biological reaction tank 10, based on the first ammonia concentration estimated value of the treated water acquired from the first estimation section 32 and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 acquired from the treated water ammonia concentration sensor 14 (step S14). In one example, the target aeration amount calculation section 33 calculates the target value of the aeration amount with the difference between the first ammonia concentration estimated value and the ammonia concentration value of the treated water 101 as an index. The target aeration amount calculation section 33 outputs the calculated target value of the aeration amount to the air volume adjustment section 13.

[0049] After that, the air volume adjustment section 13 adjusts the air volume and supplies air to the biological reaction tank 10 to achieve the target value of the aeration amount (step S15).

[0050] The above processes of the steps S11 to S15 are repeated at a certain time interval At1. Here, At1 is preferably in the range of 1 second to 1 hour or so. However, a time longer than the time required for the entire processes from the step S11 to the step S15 is set as At1.

[0051] Figure 4 is a flowchart showing one example of the steps of the method of updating the conductivity concentration-related information in the aeration amount control device according to Embodiment 1. First, at a certain time t, the acceptance section 341 of the database updating section 34 accepts from the outside a data set of the second ammonia concentration estimated value of the treated water for one or more date and time (step S31). As described above, the second ammonia concentration estimated value of the treated water is a value of the ammonia concentration of the treated water measured or estimated by a method different from the method of estimating the first ammonia concentration estimated value from the conductivity of the treated water. In one example, a value of the ammonia concentration of the treated water collected analyzed by an analysis device is used as the second ammonia concentration estimated value, or a value estimated by an estimation device of the ammonia concentration of the treated water is used as the second ammonia concentration estimated value. The acceptance section 341 outputs the accepted data set to the update processing section 342. The process of the step S31 corresponds to the second ammonia concentration estimated value acceptance process.

[0052] In addition, at the time t, in parallel with the step S31, the conductivity sensor 15 measures the conductivity of the treated water (step S32). The conductivity sensor 15 outputs the measurement result to the first estimation section 32. The process of the step S32 corresponds to the conductivity acquisition process. In addition, the first estimation section 32 estimates the first ammonia concentration estimated value of the treated water from the conductivity-related information of the database 31 based on the measured conductivity value (step S33). The first estimation section 32 outputs the estimation result, that is, the first ammonia concentration estimated value, to the update processing section 342. The process of the step S33 corresponds to the first ammonia concentration estimated value estimation process.

[0053] After the step S31 and the step S33, the update processing section 342 determines whether or not the conductivity concentration correlation information of the database 31 needs to be updated, based on the first ammonia concentration estimation value estimated by the first estimation section 32 and the second ammonia concentration estimation value accepted by the acceptance section 341 (step S34). In one example, the update processing section 342 determines whether or not the difference between the first ammonia concentration estimation value and the second ammonia concentration estimation value at the same time is less than a predetermined determination value. If the difference is less than the determination value, the update processing section 342 determines that the conductivity concentration correlation information does not need to be updated. In addition, the update processing section 342 determines that the conductivity concentration correlation information needs to be updated in a case where the difference is greater than the determination value. The processing of the step S34 corresponds to the determination process.

[0054] In a case where it is determined that the conductivity concentration correlation information does not need to be updated (the case where "No" in the step S34), the processing returns to the step S31 and the step S32. In addition, in a case where it is determined that the conductivity concentration correlation information needs to be updated (the case where "Yes" in the step S34), the update processing section 342 newly constructs the correlation between the conductivity and the ammonia concentration of the treated water, based on the second ammonia concentration estimation value of the treated water accepted by the acceptance section 341 and the conductivity value measured by the conductivity sensor 15, and updates the conductivity concentration correlation information of the database 31 (step S35). In a case where the data group accepted in the step S31 is the second ammonia concentration estimation value of the treated water at one date and time, the new conductivity concentration correlation information is constructed using the second ammonia concentration estimation value and the conductivity value of the treated water at the same time in the past. The processing of the step S35 corresponds to the update processing process.

[0055] The processing of the above steps S31 to S35 is repeatedly performed at a certain time interval At2.

[0056] As described above, in the embodiment 1, in a case where the correlation between the conductivity and the ammonia concentration of the treated water is changed with respect to the conductivity concentration correlation information stored in the database 31 due to the variation in the concentration of the coexisting substance that affects the conductivity of the treated water, the database update section 34 determines whether or not the conductivity concentration correlation information needs to be updated, based on the difference between the first ammonia concentration estimation value and the second ammonia concentration estimation value. In a case where the conductivity concentration correlation information needs to be updated, the database update section 34 updates the conductivity concentration correlation information of the treated water stored in the database 31 using the second ammonia concentration estimation value and the conductivity value of the treated water. That is, the conductivity concentration correlation information is updated at an appropriate timing. Therefore, even in a case where the concentration of the coexisting substance in the treated water is varied, an appropriate amount of air can be supplied to the biological reaction tank 10 in accordance with the variation in the ammonia load of the treated water that flows in.

[0057] Embodiment 2.

[0058] The aeration volume control device 30 involved in Embodiment 2 is the same as that in Embodiment 1. Figure 1 The structure is the same, but the structure of the database update section 34 is different. Figure 5 This is a block diagram illustrating an example of the structure of the database update unit of the aeration volume control device according to Embodiment 2. The same symbols are used to denote structural elements identical to those in Embodiment 1, and their descriptions are omitted; only the different parts are described. The database update unit 34 of the aeration volume control device 30 according to Embodiment 2 includes a second estimation unit 343, a receiving unit 341, and an update processing unit 342.

[0059] The second estimation unit 343 estimates a second ammonia concentration of the treated water based on plant data including the inflow rate of the treated water into the bioreactor 10, the aeration rate of the blower 12, and the ammonia concentration of the treated water 101 in the bioreactor 10. The second estimation unit 343 outputs the estimated second ammonia concentration of the treated water to the receiving unit 341. In one example, the second estimation unit 343 is equipped with a completion learning model that uses an estimation algorithm to estimate the ammonia concentration of the treated water. That is, the second estimation unit 343 inputs plant data including the inflow rate of the treated water into the bioreactor 10, the aeration rate of the blower 12, and the ammonia concentration of the treated water 101 in the bioreactor 10 into the completion learning model, and uses the obtained result as the estimated second ammonia concentration of the treated water. The completed learning model only needs to employ a method that can estimate the ammonia concentration of the treated water based on plant data, including the inflow rate of the treated water into the bioreactor 10, the aeration rate of the blower 12, and the ammonia concentration of the treated water 101 within the bioreactor 10. In the estimation algorithm used in the second estimation unit 343, the following can be used: an activated sludge model (ASM) modeling the bioreactor, a linear regression model, a nonlinear regression model, machine learning, reinforcement learning, deep reinforcement learning, deep learning, random forests, neural networks, and other prediction methods using artificial intelligence.

[0060] In a case where the ammonia load, which is represented by the product of the ammonia concentration of the treated water and the inflow water amount, is large, the aeration amount to be supplied to the biological reaction tank 10 needs to be increased in order to treat the ammonia load, and if the aeration amount is insufficient, the ammonia concentration value of the treated water 101 detected by the treated water ammonia concentration sensor 14 increases. In contrast, in a case where the ammonia load of the treated water is small, the aeration amount to be supplied to the biological reaction tank 10 needs to be decreased in order to treat the ammonia load, and if the aeration amount is sufficient, the ammonia concentration value of the treated water 101 detected by the treated water ammonia concentration sensor 14 decreases. Thus, there is a correlation between the ammonia load, the aeration amount, and the ammonia concentration value of the treated water 101, and more specifically, between the ammonia concentration of the treated water and the inflow water amount of the treated water, the aeration amount, and the ammonia concentration value of the treated water 101. That is, the correlation between the ammonia concentration of the treated water and the plant data including the inflow water amount of the treated water to the biological reaction tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 can be expressed using a completed learning model. The completed learning model is generated using the above-described estimation algorithm. Then, the second estimation section 343 can estimate the ammonia concentration of the treated water from the plant data using the completed learning model. The second estimation section 343 is one example of the ammonia concentration estimation device of the treated water of Embodiment 1.

[0061] One example of generating the completed learning model used by the second estimation section 343 through machine learning will be described. Figure 6 is a diagram illustrating one example of the structure of a learning device that generates a completed learning model in the aeration amount control device according to Embodiment 2. The learning device 50 includes a data acquisition section 51, a model generation section 52, and a completed learning model storage section 53.

[0062] The data acquisition unit 51 acquires, as learning data, plant data including the inflow amount of the treated water into the biological reaction tank 10, the aeration amount of the blower 12, the ammonia concentration value of the treated water 101 in the biological reaction tank 10, and the ammonia concentration value of the treated water. The ammonia concentration value of the treated water can be, in one example, a value obtained by analyzing the ammonia concentration of the treated water collected by an operator using an ion chromatography analyzer or the like. In addition, in the biological reaction tank 10, the treated water flowing from the inflow portion 102 slowly flows toward the outflow portion 103. Therefore, in the case where the ammonia concentration of the treated water at the inflow portion 102 changes, the aeration amount required in the biological reaction tank 10 changes, and a time lag corresponding to the flow-down time occurs before the ammonia concentration value of the treated water 101 changes. Therefore, the data of the aeration amount of the blower 12 for estimating the ammonia concentration of the treated water at the time T and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 are preferably data at the time T+ΔT after the flow-down time ΔT from the inflow portion 102 to each measurement point. If the flow-down time of the treated water from the inflow portion 102 to the position where the aeration treatment is performed is set to ΔT1, and the flow-down time of the treated water 101 from the inflow portion 102 to the treated water ammonia concentration sensor 14 is set to ΔT2, it is preferable to use, as the plant data, plant data including the inflow amount of the treated water into the biological reaction tank 10 at the time T, the aeration amount of the blower 12 at the time T+ΔT1, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 at the time T+ΔT2.

[0063] The model generation unit 52 learns the estimated value of the ammonia concentration of the treated water on the basis of learning data generated from a combination of the plant data and the ammonia concentration value of the treated water output from the data acquisition unit 51. That is, a completed learning model for inferring the optimal estimated value of the ammonia concentration of the treated water is generated on the basis of the plant data of the aeration amount control system 1 and the ammonia concentration value of the treated water. Here, the learning data is data in which the plant data and the ammonia concentration value of the treated water are associated with each other.

[0064] The learning device 50 is a device for learning the estimated value of the ammonia concentration of the treated water of the aeration amount control system 1, but can be, for example, a device connected to the aeration amount control system 1 via a network and independent of the aeration amount control system 1. In addition, the learning device 50 can be built into the aeration amount control system 1, particularly the aeration amount control device 30, or can exist on a cloud server.

[0065] The completed learning model used by the model generation unit 52 can use a known algorithm such as supervised learning, reinforcement learning, or the like. As one example, a case where a neural network is applied will be described.

[0066] The model generation unit 52 learns the estimated value of the ammonia concentration of the treated water by so-called supervised learning, for example, according to a neural network model. Here, supervised learning refers to a method of learning features possessed in learning data by providing the learning device 50 with sets of input and result label data, and inferring the result from the input.

[0067] The neural network is composed of an input layer composed of a plurality of neurons, an intermediate layer composed of a plurality of neurons, and an output layer composed of a plurality of neurons. The intermediate layer is also referred to as a hidden layer, and can be one layer or two or more layers.

[0068] Figure 7 is a diagram schematically showing one example of a neural network used by the model generation unit Figure 6 For example, if it is a three-layer neural network as shown in Figure 7 When a plurality of inputs are input to the input layer X1 to the input layer X3, the values are multiplied by weights represented by w11 to w16 and input to the intermediate layer Y1 to the intermediate layer Y2. In the case where the weights w11 to w16 are not distinguished separately, it is referred to as a weight w1. In addition, the result from the intermediate layer Y1 to the intermediate layer Y2 is multiplied again by weights represented by w21 to w26, and output from the output layer Z1 to the output layer Z3. In the case where the weights w21 to w26 are not distinguished separately, it is referred to as a weight w2. The output result of the output layer Z1 to the output layer Z3 varies depending on the values of the weights w1, w2.

[0069] In Embodiment 1, the neural network learns the estimated value of the ammonia concentration of the treated water by so-called supervised learning, based on learning data generated based on a combination of the plant data acquired by the data acquisition unit 51 and the ammonia concentration value of the treated water.

[0070] That is, the neural network learns by adjusting the weights w1, w2 so that the result of inputting the plant data to the input layer and outputting from the output layer approaches the ammonia concentration value of the treated water.

[0071] The model generation unit 52 generates and outputs a completed learning model by performing the learning described above.

[0072] The completed learning model storage unit 53 stores the completed learning model output from the model generation unit 52.

[0073] Next, the processing in which the learning device 50 learns will be described. Figure 8 is a flowchart showing one example of the steps of the learning processing performed by the learning device. Figure 8

[0074] ​The data acquisition unit 51 acquires the plant data and the ammonia concentration value of the treated water (step S51). The plant data and the ammonia concentration value of the treated water are acquired at the same time, but as long as the plant data and the ammonia concentration value of the treated water can be associated and input, the plant data and the ammonia concentration value of the treated water can be acquired at different timings.

[0075] Next, the model generation unit 52 learns the estimated value of the ammonia concentration of the treated water by so-called supervised learning based on learning data generated based on the combination of the plant data and the ammonia concentration value of the treated water acquired by the data acquisition unit 51, and generates a completed learning model using an estimation algorithm that represents the correlation between the plant data including the inflow amount of the treated water into the biological reactor tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reactor tank 10 and the ammonia concentration value of the treated water (step S52).

[0076] Then, the completed learning model storage unit 53 stores the completed learning model generated by the model generation unit 52 (step S53). At this point, the process ends.

[0077] Next, the details of the second estimation unit 343 will be described. Figure 9 is a diagram schematically showing one example of the structure of the second estimation unit of the aeration amount control device according to Embodiment 2. The second estimation unit 343, as described above, is an inference device that inputs plant data including the inflow amount of the treated water into the biological reactor tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reactor tank 10 into the completed learning model, and outputs the obtained result as a second ammonia concentration estimated value. The second estimation unit 343 includes a data acquisition unit 3431 and an inference unit 3432.

[0078] The data acquisition section 3431 acquires plant data including the inflow amount of the treated water into the biological reaction tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10. As described for the data acquisition section 51 of the learning device 50, in the biological reaction tank 10, the treated water flowing from the inflow section 102 slowly flows toward the outflow section 103, and thus, in the case where the ammonia concentration of the treated water at the inflow section 102 changes, the aeration amount required in the biological reaction tank 10 changes, and a time lag corresponding to the flowing time occurs before the ammonia concentration value of the treated water 101 changes. Therefore, if the flowing time of the treated water from the inflow section 102 to the position where the aeration treatment is performed is set to ΔΤ1, and the flowing time of the treated water 101 from the inflow section 102 to the treated water ammonia concentration sensor 14 is set to ΔΤ2, the data acquisition section 3431 preferably uses, as the plant data, plant data including the inflow amount of the treated water into the biological reaction tank 10 at time T, the aeration amount of the blower 12 at time T + ΔΤ1, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 at time T + ΔΤ2.

[0079] The inference section 3432 infers the second ammonia concentration estimated value of the treated water using the completed learning model. That is, by inputting the plant data acquired by the data acquisition section 3431 to the completed learning model, the second ammonia concentration estimated value of the treated water inferred from the plant data can be output.

[0080] In Embodiment 2, the completed learning model learned using the plant data and the ammonia concentration value of the treated water according to the aeration amount control system 1 is described. However, a completed learning model learned using the plant data and the ammonia concentration value of the treated water according to another aeration amount control system 1 can be acquired from the outside, and the second ammonia concentration estimated value of the treated water can be output according to the completed learning model.

[0081] Next, the second ammonia concentration estimated value of the treated water is obtained using the second estimation section 343. Figure 10 The process of obtaining the second ammonia concentration estimated value of the treated water using the second estimation section 343 is described. Figure 10 is a flowchart showing one example of the steps of the estimation process performed by the second estimation section of the aeration amount control device according to Embodiment 2.

[0082] First, the data acquisition section 3431 acquires the plant data (step S71). The plant data is data including the inflow amount of the treated water into the biological reaction tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10.

[0083] Next, the inference section 3432 inputs the plant data to the completed learning model stored in the completed learning model storage section 53, and obtains the second ammonia concentration estimated value of the treated water (step S72).

[0084] Thereafter, the inference unit 3432 outputs the second ammonia concentration estimation value of the treated water obtained by completing the learning model to the aeration amount control system 1, specifically, to the acceptance unit 341 of the database update unit 34 of the aeration amount control device 30 (step S73).

[0085] Then, the acceptance unit 341 outputs the output second ammonia concentration estimation value of the treated water to the update processing unit 342, which, as will be described later, uses the second ammonia concentration estimation value of the treated water and the first ammonia concentration estimation value of the treated water output from the first estimation unit 32 to determine the deviation of the first ammonia concentration estimation value of the treated water from the actual ammonia concentration value (step S74). The second ammonia concentration estimation value inferred by the inference unit 3432 is calculated by removing the influence of the concentration variation of the coexisting substance, and thus is a value closer to the actual ammonia concentration value of the treated water than the first ammonia concentration estimation value. Thus, it is possible to distinguish whether the change in the conductivity of the treated water is caused by the ammonia concentration or by the influence of the coexisting substance of the treated water. Up to this point, the processing ends.

[0086] In Embodiment 2, a case where supervised learning is applied in the learning algorithm used by the model generation unit 52 is described, but the present technology is not limited to this. For the learning algorithm, reinforcement learning or semi-supervised learning or the like can be applied in addition to supervised learning.

[0087] In addition, the model generation unit 52 can also learn the estimation value of the ammonia concentration of the treated water from the learning data generated by a plurality of aeration amount control systems 1. The model generation unit 52 can acquire learning data from a plurality of aeration amount control systems 1 used in the same region, or can learn the estimation value of the ammonia concentration of the treated water using learning data collected from a plurality of aeration amount control systems 1 independently operating in different regions. In addition, the aeration amount control system 1 that collects learning data can be added to the target or removed from the target in the middle. Furthermore, the learning device 50 that has learned the estimation value of the ammonia concentration of the treated water with respect to a certain aeration amount control system 1 can be applied to a different aeration amount control system 1, with respect to which the estimation value of the ammonia concentration of the treated water is relearned and updated.

[0088] In addition, as the learning algorithm used in the model generation unit 52, deep learning that extracts learning features itself can be used, or machine learning can be performed according to other publicly known methods such as genetic programming, functional logic programming, support vector machines, and the like.

[0089] As described above, in order for the second estimation section 343 to estimate the second ammonia concentration estimation value of the treated water, it is necessary to use the plant data including the aeration amount of the blower 12 at the time T+ΔT1 after the flow-down time ΔT1 of the treated water from the inflow section 102 to the position where the aeration treatment is performed, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 at the time T+ΔT2 after the flow-down time ΔT2 of the treated water 101 from the inflow section 102 to the treated water ammonia concentration sensor 14. Therefore, the ammonia concentration of the treated water cannot be estimated in real time. However, it can be considered that the ammonia concentration of the treated water 101 when the treated water with a certain aeration amount is biologically treated with a certain inflow water amount is mainly affected by the ammonia concentration in the treated water. That is, it is not easily affected by the concentration variation of the coexisting substance such as other ions, which is a problem when the ammonia concentration is estimated using the conductivity of the treated water. As a result, it can be considered that the estimation value of the ammonia concentration of the treated water estimated by the second estimation section 343 represents the ammonia concentration in the presence of the coexisting substance in the treated water. Therefore, it is possible to use as a reference when the deviation of the first ammonia concentration estimation value of the treated water from the actual ammonia concentration of the treated water is determined when the first ammonia concentration estimation value of the treated water is estimated by the first estimation section 32 based on the conductivity of the treated water measured by the conductivity sensor 15, and the conductivity concentration correlation information.

[0090] Return Figure 5 The acceptance section 341 accepts the second ammonia concentration estimation value of the treated water estimated by the second estimation section 343. The acceptance section 341 can also accept the estimation date and time of the accepted second ammonia concentration estimation value of the treated water at the same time.

[0091] The update processing section 342 determines whether or not it is necessary to update the conductivity concentration correlation information of the database 31 based on the difference between the first ammonia concentration estimation value estimated by the first estimation section 32 and the second ammonia concentration estimation value estimated by the second estimation section 343. As described above, since the second ammonia concentration estimation value estimated by the second estimation section 343 can be considered as the actual ammonia concentration value of the treated water, the update processing section 342 determines whether or not it is necessary to update the conductivity concentration correlation information based on the degree of deviation of the first ammonia concentration estimation value estimated by the first estimation section 32 from the second ammonia concentration estimation value.

[0092] In one example, if the difference between the first ammonia concentration estimation value estimated by the first estimation section 32 and the second ammonia concentration estimation value estimated by the second estimation section 343 is smaller than a predetermined determination value at the same time, the updating processing section 342 determines that the electric conductivity concentration correlation information does not need to be updated. In addition, the updating processing section 342 determines that the electric conductivity concentration correlation information needs to be updated in a case where the difference is larger than the determination value. The determination of whether or not the electric conductivity concentration correlation information needs to be updated can also be made based on a predetermined ratio or the like. In addition, in a case where the difference is equal to the determination value, it can be determined that the electric conductivity concentration correlation information does not need to be updated, or it can be determined that the electric conductivity concentration correlation information needs to be updated.

[0093] The updating processing section 342 newly constructs the correlation between the electric conductivity of the treated water and the ammonia concentration of the treated water based on the second ammonia concentration estimation value of the treated water estimated by the second estimation section 343 and the electric conductivity value measured by the electric conductivity sensor 15, and updates the electric conductivity concentration correlation information of the database 31 in a case where it is determined that the database 31 needs to be updated. At this time, a plurality of sets of data of the second ammonia concentration estimation value and the electric conductivity value are preferably data acquired at a plurality of different times.

[0094] Therefore, in Embodiment 2, in a case where the correlation between the electric conductivity of the treated water and the ammonia concentration of the treated water has changed due to the concentration fluctuation of the coexisting substance that affects the electric conductivity, relative to the electric conductivity concentration correlation information stored in the database 31, the second ammonia concentration estimation value of the treated water in the presence of the coexisting substance can be estimated based on the plant data. The estimated second ammonia concentration estimation value of the treated water suppresses the influence of the concentration of the coexisting substance, and thus becomes a value closer to the actual ammonia concentration of the treated water, compared to the first ammonia concentration estimation value calculated based on the electric conductivity of the treated water. By using this second ammonia concentration estimation value of the treated water, the database updating section 34 can update the electric conductivity concentration correlation information of the treated water stored in the database 31 at an appropriate timing. As a result, the appropriate amount of air can be supplied to the biological reaction tank 10, with the influence of the coexisting substance being excluded, in response to the load fluctuation of the inflowing ammonia.

[0095] Next, the method of updating the electric conductivity concentration correlation information in the database updating section 34 of the aeration amount control device 30 of Embodiment 2 will be described. Figure 11 is a flowchart showing one example of the steps of the method of updating the electric conductivity concentration correlation information in the aeration amount control device according to Embodiment 2.

[0096] First, at a certain time t, the second estimation section 343 acquires plant data including the inflow amount of the treated water to the biological reaction tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 (step S91). The processing of step S91 is a plant data acquisition process.

[0097] Next, the second estimation unit 343 estimates a second ammonia concentration estimation value of the treated water, based on the plant data including the inflow amount of the treated water into the biological reaction tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10 (step S92). Specifically, the second estimation unit 343 outputs, as the second ammonia concentration estimation value of the treated water, a value output by inputting the plant data as input data into the completed learning model. The second estimation unit 343 outputs the estimated second ammonia concentration estimation value of the treated water to the acceptance unit 341. The process of step S92 corresponds to a second ammonia concentration estimation value estimation process.

[0098] The acceptance unit 341 accepts the second ammonia concentration estimation value of the treated water estimated by the second estimation unit 343 (step S93). The acceptance unit 341 outputs, to the update processing unit 342, a data set of the accepted second ammonia concentration estimation value of the treated water. The process of step S93 corresponds to a second ammonia concentration estimation value acceptance process.

[0099] In addition, at time t, the conductivity of the treated water is measured by the conductivity sensor 15 in parallel with the processes of steps S91 to S93 (step S94). The conductivity sensor 15 outputs the measurement result to the first estimation unit 32. The process of step S94 corresponds to a conductivity acquisition process.

[0100] Next, the first estimation unit 32 estimates a first ammonia concentration estimation value of the treated water, from the conductivity concentration correlation information of the database 31, based on the measured conductivity value (step S95). The first estimation unit 32 outputs the estimation result, that is, the first ammonia concentration estimation value of the treated water, to the update processing unit 342. The process of step S95 corresponds to a first ammonia concentration estimation value estimation process.

[0101] After steps S93 and S95, the update processing unit 342 determines whether or not the conductivity concentration correlation information of the database 31 needs to be updated, based on the difference between the first ammonia concentration estimation value of the treated water estimated by the first estimation unit 32 and the second ammonia concentration estimation value estimated by the second estimation unit 343 (step S96). In one example, when the difference between the first ammonia concentration estimation value estimated by the first estimation unit 32 and the second ammonia concentration estimation value estimated by the second estimation unit 343 at the same time is less than a predetermined determination value, the update processing unit 342 determines that the conductivity concentration correlation information does not need to be updated. In addition, the update processing unit 342 determines that the conductivity concentration correlation information needs to be updated when the difference is greater than the determination value. The process of step S96 corresponds to a determination process.

[0102] In a case where it is determined that the conductivity concentration-related information does not need to be updated (the case where "No" in step S96), the process returns to step S91 and step S94. In a case where it is determined that the conductivity concentration-related information needs to be updated (the case where "Yes" in step S96), the database update section 34 newly constructs a correlation between the conductivity and the ammonia concentration of the treated water based on the second ammonia concentration estimation value of the treated water estimated by the second estimation section 343 and the conductivity value measured by the conductivity sensor 15, and updates the conductivity concentration-related information of the database 31 (step S97). In the update process of the conductivity concentration-related information, a plurality of sets of data of the second ammonia concentration estimation value estimated by the second estimation section 343 and the conductivity value measured by the conductivity sensor 15 are used. The process of step S97 corresponds to the update process.

[0103] The processes of steps S91 to S97 described above are repeatedly performed at a certain time interval Δt3.

[0104] As described above, in Embodiment 2, in a case where the correlation between the conductivity and the ammonia concentration of the treated water has changed with respect to the conductivity concentration-related information stored in the database 31 due to a change in the concentration of the coexisting substance that affects the conductivity, the second ammonia concentration estimation value excluding the influence of the coexisting substance of the treated water is estimated based on the plant data including the inflow amount of the treated water to the biological reaction tank 10, the aeration amount of the blower 12, and the ammonia concentration value of the treated water 101 in the biological reaction tank 10. The database update section 34 can appropriately determine the timing of updating the conductivity concentration-related information of the treated water by comparing the first ammonia concentration estimation value with the second ammonia concentration estimation value. In a case where the conductivity concentration-related information is updated, the database update section 34 newly constructs a correlation between the conductivity and the ammonia concentration of the treated water based on the second ammonia concentration estimation value and the conductivity value measured by the conductivity sensor 15, and updates the conductivity concentration-related information. Therefore, an appropriate amount of air can be supplied to the biological reaction tank 10 in response to a change in the load of the inflowing ammonia.

[0105] In the above description, the case where the target aeration amount calculation section 33 outputs the target value of the aeration amount to the air volume adjustment section 13, and the air volume adjustment section 13 adjusts the opening degree of the air volume adjustment valve is exemplified. However, as long as the aeration amount can be finally adjusted, the air volume can also be adjusted by the blower 12 instead of the air volume adjustment section 13. That is, the target aeration amount calculation section 33 can also output the target value of the aeration amount as the output of the blower 12, and adjust the air volume so that the blower 12 reaches the target value of the aeration amount.

[0106] Here, Figure 1The aeration amount control device 30 shown can be configured as a separate circuit or device, and each of the database 31, the first estimation section 32, the target aeration amount calculation section 33, and the database update section 34 can also be configured as one circuit or device. In addition, each part can be realized by a control circuit including a memory and a processor that executes a program stored in the memory, or by a dedicated hardware. Here, a case where the aeration amount control device 30 is realized by a control circuit will be exemplified.

[0107] Figure 12 is a diagram showing one example of a hardware structure of a control circuit. Figure 12 The control circuit 400 shown includes an input section 401, a processor 402, a memory 403, and an output section 404. The parts of the control circuit 400 are connected to each other via a bus 411.

[0108] The input section 401 receives a signal from the outside. The output section 404 outputs a signal generated by the control circuit 400 to the outside. The processor 402 is, for example, a CPU (Central Processing Unit), a central processing device, a processing device, an arithmetic device, a microprocessor, a microcomputer, a DSP (Digital Signal Processor), or the like. The processor 402 executes various processes.

[0109] The memory 403 is, for example, a nonvolatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory), or the like, and a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD (Digital Versatile Disc), or the like. The memory 403 stores a program for causing the aeration amount control device 30 to act, conductivity concentration-related information, and the like.

[0110] The processor 402 reads and executes the program stored in the memory 403 via the bus 411, and governs the processes and control of the entire aeration amount control device 30. Figure 1 The functions of the target aeration amount calculation section 33, the first estimation section 32, and the database update section 34 of the aeration amount control device 30 shown are realized using the processor 402.

[0111] The memory 403 functions as a work area of the processor 402. In addition, programs such as an aeration amount control program that starts up a program, executes the aeration amount control method, and updates the conductivity concentration-related information are stored in the memory 403. In the case where the aeration amount control method shown in Embodiments 1 and 2 is executed, the processor 402 loads the aeration amount control program into the memory 403 to execute various processes.

[0112] In addition, in the case where each processing section that constitutes the aeration amount control device 30, each processing section that constitutes the database update section 34, each processing section that constitutes the second estimation section 343, or each processing section that constitutes the learning device 50 is implemented by a dedicated hardware, the dedicated hardware is, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. In the case where each processing section is implemented by a dedicated hardware, each processing section is connected via a signal line. Then, data is communicated between each processing section via the signal line.

[0113] Further, by causing a computer to execute the above-described aeration amount control program, the computer has the same functions as the aeration amount control device 30.

[0114] In addition, the above-described aeration amount control program is stored in advance in the memory 403, but is not limited thereto. The above-described aeration amount control program can also be provided to a user in a state of being written in a recording medium such as a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc)-ROM, or the like, and installed in the memory 403 by the user. In addition, the above-described aeration amount control program can also be provided to a user via a network such as the Internet.

[0115] The structure shown in the above-described embodiments is indicative of one example, can be combined with other known technologies, can be combined with each other, and can omit or change a part of the structure within a range not departing from the gist.

[0116] Explanation of Reference Signs

[0117] 1 Aeration amount control system, 10 Biological reaction tank, 11 Diffuser plate, 12 Blower, 13 Air volume adjusting section, 14 Treated water ammonia concentration sensor, 15 Conductivity sensor, 30 Aeration amount control device, 31 Database, 32 First estimation section, 33 Target aeration amount calculation section, 34 Database update section, 50 Learning device, 51, 3431 Data acquisition section, 52 Model generation section, 53 Completed learning model storage section, 101 Treated water, 102 Inflow section, 103 Outflow section, 341 Acceptance section, 342 Update processing section, 343 Second estimation section, 400 Control circuit, 401 Input section, 402 Processor, 403 Memory, 404 Output section, 411 Bus, 3432 Inference section.

Claims

1. An aeration amount control device that controls an amount of oxygen-containing gas, i.e., an aeration amount, supplied to a biological reaction tank that biologically treats water to be treated, the aeration amount control device characterized by comprising: an ammonia concentration sensor that measures an ammonia concentration of treated water that is the water to be treated after being biologically treated in the biological reaction tank; a conductivity sensor that measures a conductivity of the water to be treated that flows into the biological reaction tank; a conductivity-concentration correlation information storage section that stores conductivity-concentration correlation information that indicates a correlation between the conductivity of the water to be treated and the ammonia concentration of the water to be treated; a first estimation section that estimates, from the conductivity-concentration correlation information, an estimated value of the ammonia concentration of the water to be treated, i.e., a first ammonia concentration estimated value, based on a conductivity value measured by the conductivity sensor; a target aeration amount calculation section that calculates a target value of the aeration amount supplied to the biological reaction tank based on the first ammonia concentration estimated value of the water to be treated and an ammonia concentration value of the treated water measured by the ammonia concentration sensor; and a conductivity-concentration correlation information update section that updates the conductivity-concentration correlation information, the conductivity-concentration correlation information update section having: an acceptance section that accepts a value of the ammonia concentration of the water to be treated, i.e., a second ammonia concentration estimated value, measured or estimated by a method different from a method of estimating the first ammonia concentration estimated value; and an update processing section that updates the conductivity-concentration correlation information based on the second ammonia concentration estimated value accepted by the acceptance section and the conductivity value measured by the conductivity sensor.

2. The aeration amount control device according to claim 1, wherein the conductivity-concentration correlation information update section further includes a second estimation section that outputs the second ammonia concentration estimated value using a completed learning model that reasons the second ammonia concentration estimated value of the water to be treated from plant data including an inflow water amount of the water to be treated to the biological reaction tank, the aeration amount, and an ammonia concentration value of the treated water in the biological reaction tank, the acceptance section accepting the second ammonia concentration estimated value from the second estimation section.

3. The aeration amount control device according to claim 1 or 2, wherein the update processing section determines whether or not the conductivity-concentration correlation information needs to be updated based on the first ammonia concentration estimated value and the second ammonia concentration estimated value, and performs the update of the conductivity-concentration correlation information in a case where the conductivity-concentration correlation information needs to be updated.

4. The aeration amount control device according to claim 3, wherein ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ The update processing section determines that the conductivity concentration correlation information needs to be updated when the difference between the first ammonia concentration estimation value and the second ammonia concentration estimation value is greater than a predetermined determination value, and newly constructs a correlation between the conductivity of the treated water and the ammonia concentration of the treated water using the second ammonia concentration estimation value and the conductivity value at the same time, and updates the conductivity concentration correlation information stored in the conductivity concentration correlation information storage section.

5. The aeration amount control device according to claim 2, wherein In a case where a time from when the treated water flows into the biological reaction tank to when it reaches a position where aeration is performed is set as ΔΤ1, and a time from when the treated water flows into the biological reaction tank to when it reaches a position of the ammonia concentration sensor is set as ΔΤ2, the flow amount of the treated water into the biological reaction tank is data at time T, the aeration amount is data at time T + ΔΤ1, and the ammonia concentration value of the treated water in the biological reaction tank is data at time T + ΔΤ2.

6. The control device for the amount of aeration according to claim 2 or 5, wherein Further comprising a learning device that generates the completed learning model, The learning device has: a data acquisition section that acquires learning data including the plant data and the ammonia concentration value of the treated water, the plant data including the flow amount of the treated water into the biological reaction tank, the aeration amount, and the ammonia concentration value of the treated water in the biological reaction tank; and a model generation section that generates a completed learning model using the learning data, the completed learning model being used to infer the second ammonia concentration estimation value from the plant data including the flow amount of the treated water into the biological reaction tank, the aeration amount, and the ammonia concentration value of the treated water in the biological reaction tank.

7. An aeration amount control method for an aeration amount control device that uses conductivity concentration correlation information to estimate an estimation value of an ammonia concentration of treated water flowing into a biological reaction tank in which biological treatment of the treated water is performed, the estimation value being a first ammonia concentration estimation value, and uses the first ammonia concentration estimation value to control an aeration amount, the aeration amount being an amount of oxygen-containing gas supplied to the biological reaction tank, the aeration amount control method characterized by comprising: a conductivity acquisition process in which the aeration amount control device acquires a conductivity value of the treated water flowing into the biological reaction tank; a second ammonia concentration estimation value acceptance process in which the aeration amount control device externally receives a second ammonia concentration estimation value, the second ammonia concentration estimation value being a value of an ammonia concentration of the treated water that is measured or estimated by a method different from a method of estimating the first ammonia concentration estimation value; and an update processing process in which the aeration amount control device updates the conductivity concentration correlation information of the treated water based on the second ammonia concentration estimation value and the conductivity value.

8. The aeration amount control method according to Claim 7, characterized by, Further comprising: a first ammonia concentration estimation value estimation process in which the aeration amount control device estimates the first ammonia concentration estimation value of the treated water from the conductivity concentration correlation information based on the acquired conductivity value; and a second ammonia concentration estimation value acceptance process in which the aeration amount control device externally receives a second ammonia concentration estimation value, the second ammonia concentration estimation value being a value of an ammonia concentration of the treated water that is measured or estimated by a method different from a method of estimating the first ammonia concentration estimation value; and an update processing process in which the aeration amount control device updates the conductivity concentration correlation information of the treated water based on the second ammonia concentration estimation value and the conductivity value. The aeration amount control device determines whether or not the electric conductivity concentration correlation information needs to be updated based on the first ammonia concentration estimation value and the second ammonia concentration estimation value in a determination step, In a case where it is determined that the electric conductivity concentration correlation information needs to be updated, the update processing step is executed.

Images