KR102767670B1 - Apparatus for managing optimization of chemical injection in water treatment plant and method therefor - Google Patents

Abstract

A device for managing chemical injection optimization includes a chemical injection management unit which, when receiving real-time data including operating data and status data, analyzes the real-time data to determine whether the status of a water treatment plant is normal, and, based on a result of the determination, applies a control value to the water treatment control device so as to minimize the amount of chemical injection while maintaining the status of treated water of the water treatment plant within a normal range, and an optimization unit which performs chemical injection optimization according to the control mode of the chemical injection optimization.

Description

{Apparatus for managing optimization of chemical injection in water treatment plant and method therefor}

The present invention relates to a technology for managing optimization, and more specifically, to a device for managing optimization of chemical injection in a water treatment plant and a method therefor.

In the case of pretreatment of seawater desalination plants, chemicals such as pH adjusters and coagulants are used before the DAF (Dissolved Air Flotation) process to remove suspended substances such as solid substances. However, in the existing method, sampling experiments and operator know-how were relied on to inject appropriate chemicals. However, it is difficult to control the process by reflecting real-time changes in the status of influent water such as seawater and wastewater.

Korean Patent Publication No. 2016-0027815 (published on March 10, 2016)

The purpose of the present invention is to provide a device and method for managing optimization of chemical injection in a water treatment plant.

In order to achieve the above-described purpose, a device for managing chemical injection optimization according to a preferred embodiment of the present invention includes a chemical injection management unit which, when receiving real-time data including operation data and status data, analyzes the real-time data to determine whether the status of a water treatment plant is normal, and, based on a result of the determination, applies a control value to the water treatment control device so as to minimize the amount of chemical injection while maintaining the status of treated water of the water treatment plant within a normal range, and an optimization unit which performs chemical injection optimization according to the control mode of the chemical injection optimization.

The above chemical injection management unit includes a data analysis-based processing unit that provides a first judgment result for determining whether the state of the water treatment plant is normal by using a learning model or analyzing data patterns to determine whether the real-time data is normal data.

The above chemical injection management unit includes a state recognition-based processing unit that provides a second judgment result for determining whether the state of the water treatment plant is normal based on whether data indicating an abnormal state of the water treatment plant is detected from data indicating the state of the water treatment plant among the real-time data.

The above chemical injection management unit includes a knowledge-based processing unit that compares knowledge-based data indicating an abnormal state of the water treatment plant with post-process data including operation data and state data of a post-process among the real-time data, and provides a third judgment result for determining whether the state of the water treatment plant is normal based on whether post-process data matching the knowledge-based data exists.

The above chemical injection management unit includes an optimization decision unit that determines the control mode of the chemical injection optimization to an automatic mode in which the control value is automatically applied to the water treatment control device when all of the first judgment result, the second judgment result, and the third judgment result determine that the state of the water treatment plant is normal.

The above chemical injection management unit includes an optimization decision unit that determines the control mode of the chemical injection optimization as a guide mode in which application of the control value is determined by the water treatment control device if the first judgment result determines that the state of the water treatment plant is normal and at least one of the second judgment result and the third judgment result determines that the state of the water treatment plant is abnormal.

The above chemical injection management unit includes an optimization decision unit that determines the control mode of the chemical injection optimization as a stop mode that does not provide the control value if the state of the water treatment plant is abnormal as a result of the first judgment.

In order to achieve the above-described object, a method for managing chemical injection optimization according to a preferred embodiment of the present invention comprises the steps of: allowing a chemical injection management unit to receive real-time data including operation data and status data; allowing the chemical injection management unit to analyze the real-time data to determine whether the state of a water treatment plant is normal; allowing the chemical injection management unit to determine a control mode of chemical injection optimization indicating a method of applying a control value to the water treatment control device so as to minimize the amount of chemical injection while maintaining the state of treated water of the water treatment plant within a normal range according to a result of the determination; and allowing the chemical injection management unit to generate a management command to perform the chemical injection optimization according to the control mode of chemical injection optimization and provide the management command to the optimization unit.

The step of determining whether the state of the water treatment plant is normal includes a step of providing a first determination result for determining whether the state of the water treatment plant is normal by having a data analysis-based processing unit use a learning model or analyze data patterns to determine whether the real-time data is normal data.

The step of determining whether the state of the water treatment plant is normal includes a step of providing a second determination result for determining whether the state of the water treatment plant is normal based on whether the state recognition-based processing unit detects data indicating an abnormal state of the water treatment plant from data indicating the state of the water treatment plant among the real-time data.

The step of determining whether the state of the water treatment plant is normal includes a step of a knowledge-based processing unit comparing knowledge-based data indicating an abnormal state of the water treatment plant with post-process data including operation data and state data of a post-process among the real-time data, and providing a third judgment result for determining whether the state of the water treatment plant is normal based on whether post-process data matching the knowledge-based data exists.

The step of determining the control mode of the chemical injection optimization is characterized in that, if the state of the water treatment plant is determined to be normal based on all of the first judgment result, the second judgment result, and the third judgment result, the optimization decision unit determines the control mode of the chemical injection optimization to be an automatic mode in which the control value is automatically applied to the water treatment control device.

The step of determining the control mode of the chemical injection optimization is characterized in that, if the first judgment result determines that the state of the water treatment plant is normal, and at least one of the second judgment result and the third judgment result determines that the state of the water treatment plant is abnormal, the optimization decision unit determines the control mode of the chemical injection optimization as a guide mode in which the application of the control value is determined by the water treatment control device.

The step of determining the control mode of the above chemical injection optimization is characterized in that, if the state of the water treatment plant is abnormal as a result of the first judgment, the optimization decision unit determines the control mode of the chemical injection optimization to a stop mode that does not provide the control value.

According to the present invention, by analyzing real-time data to check for abnormalities in the water treatment control device, optimization control is performed only when optimization control is possible, thereby preventing driving accidents in advance. In addition, even when optimization control is not performed, the optimal control value for optimization is continuously generated through calculation, so that optimization control can be resumed immediately when necessary.

FIG. 1 is a drawing for explaining the configuration of a water treatment system according to an embodiment of the present invention.
FIG. 2 is a block diagram for explaining the configuration of a chemical injection optimization device according to an embodiment of the present invention.
FIG. 3 is a block diagram illustrating the configuration of a device for managing chemical injection optimization according to an embodiment of the present invention.
FIG. 4 is a drawing for explaining the configuration of a device for controlling output for optimizing chemical injection of a water treatment plant according to an embodiment of the present invention.
FIG. 5 is a flow chart illustrating a method for generating a water treatment model for optimization of chemical injection in a water treatment plant according to an embodiment of the present invention.
FIG. 6 is a flow chart for explaining a method for optimizing chemical injection in a water treatment plant according to an embodiment of the present invention.
FIG. 7 is a flowchart for explaining a method for optimizing water treatment optimization management according to an embodiment of the present invention.
FIG. 8 is a flow chart for explaining a method for controlling output for optimization of chemical injection of a water treatment plant according to an embodiment of the present invention.
FIG. 9 is a drawing showing a computing device according to an embodiment of the present invention.

The present invention can be modified in various ways and has various embodiments, and specific embodiments are illustrated and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, but should be understood to include all modifications, equivalents, or substitutes included in the spirit and technical scope of the present invention.

The terminology used herein is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In the present invention, it should be understood that the terms "comprise" or "have" and the like are intended to specify that a feature, number, step, operation, component, part or combination thereof described in the specification is present, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. At this time, it should be noted that the same components in the attached drawings are indicated by the same symbols as much as possible. In addition, detailed descriptions of well-known functions and configurations that may obscure the gist of the present invention will be omitted. For the same reason, some components in the attached drawings are exaggerated, omitted, or schematically illustrated.

First, a water treatment system according to an embodiment of the present invention will be described. Fig. 1 is a drawing for explaining the configuration of a water treatment system according to an embodiment of the present invention. Referring to Fig. 1, a water treatment system according to an embodiment of the present invention includes a water treatment plant (1), a water treatment control device (2), and a chemical injection optimization device (3).

A water treatment plant (1) is for water treatment that treats the influent ① flowing into the water treatment plant (1) to suit the purpose and discharges the treated water ④. Such water treatment may include water treatment, wastewater treatment, seawater desalination treatment, etc. The water treatment plant (1) includes a dissolved air flotation (DAF) device, an automatic strainer (AS), an ultrafiltration (UF) device, and a reverse osmosis (RO) device.

The dissolved air flotation (DAF) device treats the influent ② according to the dissolved air flotation method. The automatic filtration (AS) removes solids remaining in the influent ③ treated by the dissolved air flotation (DAF) device to prevent foreign substances from flowing in. The ultrafiltration (UF) device includes a plurality of ultrafiltration units, each having an ultrafiltration membrane. The ultrafiltration (UF) device performs an ultrafiltration process to filter impurities remaining in the influent ③ using the ultrafiltration membranes of the plurality of ultrafiltration units. The ultrafiltration (UF) device can filter impurities remaining in the treated water by passing the treated water through the ultrafiltration membranes of the plurality of ultrafiltration units. The reverse osmosis (RO) device includes multiple trains, each having a reverse osmosis membrane. The reverse osmosis (RO) device performs a reverse osmosis process that filters out impurities remaining in the influent ③ using the reverse osmosis membranes of the multiple trains. The reverse osmosis (RO) device passes treated water through the reverse osmosis membranes of the multiple trains, filters out impurities remaining in the influent ③ according to the reverse osmosis principle, and then discharges the treated water ④.

The water treatment control device (2) is basically for controlling the water treatment plant (1). In particular, a chemical agent is injected (⑤) in the upstream process of the water treatment plant (1), and the water treatment control device (2) can control the injection amount of the chemical agent. More specifically, during the upstream process of the water treatment plant (1), for example, a chemical agent such as a hydrogen ion concentration (pH) regulator (e.g., H2SO4) and a coagulant (e.g., FeCl3) is injected. The water treatment control device (2) can control the injection and injection amount of such chemical agents.

The chemical injection optimization device (3) is for chemical injection optimization. As described above, the water treatment control device (2) controls the chemical injection and the injection amount of the water treatment plant (1). At this time, chemical injection optimization is required so that the minimum amount of chemical injection can be used for the influent water while the state of the treated water by the water treatment is maintained within a normal range. However, since the amount of chemical injection also affects the differential pressure (DP: Differential Pressure) of the automatic filtration device (AS), ultrafiltration device (UF), and reverse osmosis device (RO) that perform the subsequent process, the chemical injection optimization must be performed by considering this differential pressure. The chemical injection optimization device (3) is for performing this chemical injection optimization by controlling or guiding the water treatment control device (2).

Next, the configuration of a chemical injection optimization device (3) according to an embodiment of the present invention will be described. FIG. 2 is a block diagram for explaining the configuration of a chemical injection optimization device according to an embodiment of the present invention. Referring to FIG. 2, the chemical injection optimization device (3) according to an embodiment of the present invention includes a chemical injection management unit (100, DAF Chemical Dosing Management), a data pre-processing unit (200, Data Pre-Processing), an optimization unit (10, Chemical Dosing Optimization), a model generation management unit (20, DAF Model Generation and Management), and a post-process protection unit (800, Post Process Protection Logic). In addition, the optimization unit (10) includes a chemical injection optimization unit (300, Chemical Dosing Optimization Algorithm) and a chemical injection output control unit (400, Chemical Dosing Output Controller). And the model generation management unit (20) includes an automatic modeling processing unit (500, Auto Modeling Processor for DAF Model), a model generation unit (600, DAF Model Candidate Generator), and a model selection unit (700, DAF Model Selection & Management Processor).

The chemical injection management unit (100) is for managing the chemical injection optimization process. The chemical injection management unit (100) receives real-time data including operation data and status data from at least one of the water treatment plant (1) and the water treatment control device (2), and analyzes the same to determine whether to perform the chemical injection optimization process. Real-time data refers to operation data and status data measured or derived in real time. In the embodiment of the present invention, the operation data refers to all data including values input for controlling the process by the dissolved air flotation device (DAF), the automatic filtration device (AS), the ultrafiltration device (UF), and the reverse osmosis device (RO), or values measured for the process, that is, a set value (SV: Set Value, or target value SP: Set Point), a measured value (PV: Process Variable, or CV: Current Value), and a manipulated variable (MV). Here, the setpoint (SV or SP) is a value that sets the control target of the control object, the measured value (PV or CV) is a sensing value that measures the control object, and the manipulated value (MV) means a control value that manipulates the control object to change from the measured value to the setpoint. The setpoint and measured values can be exemplified by flow rate, pressure, water level, temperature, etc. The manipulated values can be exemplified by opening amount, motor RPM speed, voltage, current, etc. The operating data can be processed for analysis according to each purpose. In the embodiment of the present invention, the data derived or processed for analysis of the operating data is referred to as state data. For example, the data measured by the differential pressure of the input and output terminals of the ultrafiltration (UF) and reverse osmosis (RO) device can be exemplified by values processed through logic derived through operating know-how.

The data preprocessing unit (200) receives raw data. At this time, the raw data includes operation data and status data received from at least one of the water treatment plant (1) and the water treatment control device (2). The raw data is operation data and status data collected from the water treatment plant (1) and the water treatment control device (2) accumulated and stored. Therefore, the raw data may include real-time data including operation data and status data collected in real time. In addition, the raw data includes a plurality of types of data having different attributes. The raw data is continuously received from the water treatment plant (1) or the water treatment control device (2) over time. In particular, the raw data includes input attribute data having input attributes and output attribute data having output attributes. The input attribute data includes operation data and status data related to influent flowing into the water treatment plant (1), particularly, a dissolved air flotation device (DAF). The input attribute data may include, for example, the flow rate, temperature, conductivity, acidity (or hydrogen ion concentration), turbidity, flow rate, treatment amount for the influent (per unit time), chemical injection amount for the influent, chemical injection concentration, etc. The output attribute data includes operating data and status data related to the treated water treated by the dissolved air flotation device (DAF). The output attribute data may include, for example, the acidity (or hydrogen ion concentration, pH) or acidity change amount, turbidity or turbidity change amount, residual iron, etc. When the raw data is collected, the preprocessing unit (200) preprocesses the raw data to generate learning data. The learning data is classified by purpose and includes learning data and verification data. In addition, the learning data includes input data and output data in accordance with the attribute. The learning data is provided to the model generation management unit (20). In addition, the data preprocessing unit (200) may preprocess real-time data and provide the preprocessed real-time data to the optimization unit (10). The data preprocessing unit (200) performs preprocessing by analyzing raw data including real-time data using tags indicating data properties. This preprocessing removes noise through signal processing, normal data processing (based on knowledge/based on data), outlier removal, etc., or removes noise in the data, or removes data that may have a negative effect on creating a DAF model or designing a controller.

The optimization unit (10) analyzes real-time data to derive control values for optimizing the chemical injection amount. As described above, the optimization unit (10) includes a chemical injection optimization unit (300) and a chemical injection output control unit (400).

The chemical injection optimization unit (300) analyzes the current data, selects an optimal controller from among multiple controllers created previously based on the results, and searches for an optimal chemical injection control value. Optimization design information, i.e., an objective function, constraints, moderator variables, and a search range, are required to search for an optimal control value. At this time, the chemical injection optimization unit (300) analyzes real-time data through one or more water treatment models to derive a predicted value that predicts the state of the treated water of the water treatment plant (1) (e.g., turbidity, pH, etc.). In addition, the chemical injection optimization unit (300) derives a control value that injects a minimum amount of chemical while maintaining the state of the treated water of the water treatment plant (1) within a normal range based on the predicted value through one or more controllers.

The chemical injection/output control unit (400) basically provides or makes a final decision not to provide the control value derived by the chemical injection optimization unit (300) based on at least one of the management command and current status of the chemical injection management unit (100). The control value provided to the chemical injection/output control unit (400) from the chemical injection optimization unit (300) is derived by the chemical injection optimization unit (300) using real-time data, but when the time processed by the chemical injection/output control unit (400) is defined as the present, it is past data, for example, 1 minute or 5 minutes ago, at which the chemical injection optimization unit (300) searches for the control value. Accordingly, the chemical injection/output control unit (400) can compare the operation data and status data that are the basis for calculating the control value with the current operation data and status data, and if the difference is greater than or equal to a reference value, correct the control value, hold (HOLD) or stop (STOP) the output of the control value. When the chemical injection/output control unit (400) provides the control value, it can provide the control value in a guide manner so that the water treatment control device (2) automatically applies the control value according to the management command of the chemical injection management unit (100), or provide the control value in a guide format so that whether to apply the control value is determined by the water treatment control device (2). In addition, the chemical injection/output control unit (400) can correct the control value by using the correction bias value derived from the post-process protection unit (800) according to the post-process protection logic. In particular, the chemical injection/output control unit (400) converts the control value according to the control cycle and control range of the water treatment control device (2) so that the water treatment control device (2) can operate stably, and provides the converted control value to the water treatment control device (2). According to an embodiment of the present invention, the chemical injection/output control unit (400) converts the control value according to the range applicable to the water treatment control device (2). That is, the chemical injection/output control unit (400) converts the control value according to the control cycle and control range of the water treatment control device (2) compared to the control value derivation cycle by the chemical injection optimization unit (300). For example, if the time period for providing the control value of the chemical injection optimization unit (300), i.e., the control period of the control value is 1 minute, the control period of the water treatment control device (2) is 10 seconds, and the control range is ±4, then the control value with a control period of 1 minute is converted to match the control period of the water treatment control device (2) at 10-second intervals and the control range of ±4. Specifically, in the case where the control value is to increase by 20 from the existing value, the control value is converted to increase by 4 every 10 seconds to become +4, +8, +12, +16, +20, and +20.

The model generation management unit (20) is for automatically generating one or more water treatment models through learning. The water treatment model is an algorithm including at least one artificial neural network, and simulates a water treatment plant (1) that generates treated water through water treatment (e.g., DAF) of influent water. Accordingly, the water treatment model receives various types of information indicating the state of the influent water, performs calculations on the state of the influent water according to what has been learned, and produces a predicted value predicting the state of the treated water. Here, the state of the influent water can be exemplified by, for example, the flow rate, temperature, conductivity, acidity (or hydrogen ion concentration), turbidity, flow rate, treatment amount for the influent water (per unit time), chemical injection amount for the influent water, chemical injection concentration, etc. In addition, the state of the treated water can be exemplified by, for example, the acidity or acidity change amount of the treated water, turbidity or turbidity change amount, residual iron, etc.

As described above, the model generation management unit (20) includes an automatic modeling processing unit (500), a model generation unit (600), and a model selection unit (700).

The automatic modeling processing unit (500) designs a new water treatment model to generate model design information. The automatic modeling processing unit (500) designs the format, structure, input/output, variables, etc. of the water treatment model. According to one embodiment, the automatic modeling processing unit (500) can receive and determine model design information such as the format, structure, input/output, variables, etc. of the water treatment model. According to another embodiment, the automatic modeling processing unit (500) can extract model design information from any one of a plurality of previously stored seed models and design the water treatment model according to the extracted model design information. The seed model is a model generated by an expert among water treatment models. The automatic modeling processing unit (500) extracts model design information including at least one of the format, structure, input/output, and variables of the seed model to be applied to the new water treatment model. The extracted model design information is applied to the new water treatment model.

The model generation unit (600) receives model design information from the automatic modeling processing unit (500), and generates a water treatment model through learning using learning data based on the model design information. That is, the model generation unit (600) generates a plurality of water treatment models that simulate a water treatment plant through learning using learning data including learning data and verification data and predict the state of treated water according to the state of influent water to the water treatment plant. The learning data including learning data and verification data includes input data and output data corresponding to the input data. For example, the input data may exemplify the flow rate, temperature, conductivity, acidity (or hydrogen ion concentration), turbidity, flow rate, treatment amount for influent water (per unit time), and injection concentration for influent water. In addition, the output data may exemplify the acidity or acidity change amount of the treated water, turbidity or turbidity change amount, and the like. Here, during learning, the output data is used as a target value corresponding to the input data.

The model selection unit (700) compares and evaluates the water treatment model generated by the model generation unit (600) with the previously stored water treatment models to select the optimal water treatment model. To this end, the evaluation of multiple water treatment models is performed using evaluation data indicating the water treatment device (1) at the evaluation time. The evaluation data, like learning data and verification data, includes input data and output data corresponding to the input data. That is, the model selection unit (700) generates evaluation data using data collected from the water treatment device (1) at the evaluation time, and performs evaluation using the generated evaluation data. That is, the model selection unit (700) performs evaluation of multiple water treatment models using evaluation data collected from the water treatment device at the evaluation time. Then, the model selection unit (700) selects the water treatment model having the highest degree of similarity with the water treatment device (1) at the evaluation time among the multiple water treatment models as a result of the evaluation. Then, the model selection unit (700) provides the selected water treatment model to the chemical injection optimization unit (300). In addition, the model selection unit (700) sorts the water treatment models in the order in which they were created each time an evaluation is completed, and if the storage space for storing the water treatment models is insufficient, the water treatment models that were not selected can be sequentially deleted in the order in which they were created.

The post-process protection unit (800) receives post-process data including operation data and status data of the post-process of the water treatment plant (1), i.e., the process by the automatic filtration unit (AS), the ultrafiltration unit (UF), and the reverse osmosis unit (RO), analyzes the received post-process data, and derives a correction bias value for protecting the post-process according to the post-process protection logic for preventing damage to the post-process, such as fouling, from occurring. Here, fouling refers to a phenomenon in which a membrane is clogged by contaminants in the influent. The correction bias value is provided to the chemical input/output control unit (400).

Next, a device for managing chemical injection optimization according to an embodiment of the present invention will be described. Fig. 3 is a block diagram for explaining the configuration of a device for managing chemical injection optimization according to an embodiment of the present invention.

Referring to FIG. 3, the chemical injection management unit (100) according to the embodiment of the present invention includes a data analysis-based processing unit (110), a state recognition-based processing unit (120), a knowledge-based processing unit (130), and an optimization decision unit (140).

The chemical injection management unit (100) receives real-time data including operation data and status data, and determines whether to perform and the mode of performing a chemical injection optimization process for optimizing the amount of chemical injected in the upstream process of the water treatment plant (1). Here, optimization means that the state of the treated water of the water treatment plant (1) is maintained within a normal range, while the amount of chemical injected is minimized, which is an optimized state. To this end, real-time data is input into the data analysis-based processing unit (110), the status recognition-based processing unit (120), and the knowledge-based processing unit (130), and each of the data analysis-based processing unit (110), the status recognition-based processing unit (120), and the knowledge-based processing unit (130) determines conditions for determining whether to perform. In addition, the optimization decision unit (140) determines whether to perform and the mode of performing by combining the conditions. This will be described in detail as follows.

The data analysis-based processing unit (110) analyzes the operation data of the water treatment plant (1) through the learning model to determine whether the water treatment plant is in an optimized state, thereby determining the first condition for starting the chemical injection optimization process. Here, the learning model may be a pattern recognition model or a machine learning model that determines whether the water treatment plant is in an optimized state or not. Accordingly, the learning model analyzes the operation data to determine whether the water treatment plant is in an optimized state, and if not in an optimized state, determines that the first condition is satisfied.

The status recognition-based processing unit (120) analyzes the status data of the water treatment plant (1) to detect an abnormal state of the water treatment plant, thereby determining the second condition for determining whether to perform the chemical injection optimization process. Here, the abnormal state may be, for example, green algae inflow, overflow inflow exceeding the treatment capacity of the water treatment plant, a system abnormality of the water treatment plant (1), a sensor abnormality, etc. The status recognition-based processing unit (120) analyzes the status data, and if an abnormal state is detected, it determines that the second condition is satisfied.

The knowledge-based processing unit (130) analyzes the operation data and status data of the downstream process of the water treatment plant (1), i.e., the process by the automatic filtration device (AS), the ultrafiltration device (UF), and the reverse osmosis device (RO), among the real-time data based on the previously stored knowledge-based data, and detects whether it matches the previously stored knowledge-based data, thereby determining the third condition for determining whether the chemical injection optimization process is performed. That is, the knowledge-based data stores data indicating a situation in which the chemical injection optimization process is required based on existing empirical rules, and the knowledge-based processing unit (130) determines that the third condition is satisfied if it matches the knowledge-based data.

The optimization decision unit (140) determines whether to perform the chemical injection optimization process and the manner in which it is performed based on whether the first, second, and third conditions are satisfied. That is, if the first condition, the second condition, and the third condition are all satisfied, the optimization decision unit (140) controls the optimization unit (10) to perform the chemical injection optimization process to obtain an optimized state, derive a control value, and provide the derived control value to the water treatment control device. In addition, if the first condition is satisfied and at least one of the second condition and the third condition is not satisfied, the optimization decision unit (140) controls the optimization unit (10) to provide the control value in a guide format. In this case, since performing the chemical injection optimization process may worsen the state of the water treatment plant (1) or the water treatment control device (2), the control value is provided in a guide format and the chemical injection optimization process is not forced. The control value provided in a guide format is provided through an operation screen or the like so that the plant operator can view it. On the other hand, the optimization decision unit (140) controls the chemical injection optimization process not to be performed even if the second and third conditions are satisfied if the first condition is not satisfied. In this case, the chemical injection optimization process is not performed because performing the chemical injection optimization process may further worsen the condition of the water treatment plant (1) or the water treatment control device (2).

Next, a device for controlling output for optimizing chemical injection of a water treatment plant according to an embodiment of the present invention will be described. FIG. 4 is a drawing for explaining the configuration of a device for controlling output for optimizing chemical injection of a water treatment plant according to an embodiment of the present invention.

Referring to FIG. 4, the chemical injection/output control unit (400) includes a control value correction unit (410), a control mode management unit (420), and an output processing unit (430).

The control value correction unit (410) can correct the control value received from the chemical injection optimization unit (300) according to a predetermined control cycle (e.g., 1 minute) using the correction bias value received from the post-process protection unit (800).

The chemical injection optimization unit (300) analyzes real-time data received during a control period (e.g., 1 minute) through one or more water treatment models to derive a predicted value predicting the state of the treated water of the water treatment plant (1) (i.e., the state in ③ of FIG. 1), derives a control value to inject a minimum amount of chemical agent while maintaining the state of the treated water of the water treatment plant within a normal range based on the predicted value through the controller, and provides the derived control value to the chemical injection/output control unit (400). In addition, the post-process protection unit (800) analyzes post-process data including operation data and state data of the process by the post-process received during the control period (e.g., 1 minute) to derive a correction bias value to prevent damage to the post-process (i.e., damage occurring between ③ and ④ of FIG. 1), and provides the derived correction bias value to the chemical injection/output control unit (400). Accordingly, the control value correction unit (410) can correct the control value using the correction bias value. For example, if the control value is a target value of the injection amount of sulfuric acid and iron chloride, the control value can be corrected as in the following mathematical expression 1.

<Mathematical formula 1>

Sulfuric Acid Target = Sulfuric Acid Target + AFCS × Sulfuric Acid Bias

Ferric Chloride Target=Ferric Chloride Target + AFCS × Ferric Chloride Bias

Here, Sulfuric Acid Target and Ferric Chloride Target are the target values of the injection amounts of sulfuric acid and ferric chloride, AFCS (Anti-Fouling Controller Switch) is 0 or 1, and Sulfuric Acid Bias and Ferric Chloride Bias are the correction bias values of the injection amounts of sulfuric acid and ferric chloride.

The control mode management unit (420) is for resetting the control mode. The control mode includes an AUTO mode, a GUIDE mode, a HOLD mode, and a STOP mode. The AUTO mode means that the output processing unit (430) provides a control value to the water treatment control device (2) so that the control value is automatically applied to the water treatment control device (2). In the AUTO mode, the water treatment control device (2) automatically reflects the control value and controls the water treatment plant (1). The GUIDE mode is a mode in which the output processing unit (430) provides a control value to the water treatment control device (2), but provides the control value in a viewable state so that the application of the control value is determined by the water treatment control device (2). The STANDBY mode is a mode in which the output processing unit (430) converts the control value according to the control cycle of the water treatment control device and the control range in each control cycle, but does not provide the converted control value to the water treatment control device. The control mode management unit (420) does not provide a control value to the output processing unit (430) in the interrupt mode. Therefore, the output processing unit (430) cannot provide a control value to the water treatment control device (2) in the interrupt mode.

As described in FIG. 3, the chemical injection management unit (100) analyzes real-time data to determine the control mode of chemical injection optimization and transmits the determined control mode as a management command. Then, the control mode management unit (420) considers the control mode of the previous cycle in a predetermined control cycle (e.g., 1 minute), and checks whether the control value is normally updated for each cycle according to the predetermined control cycle (e.g., 1 minute), and can reset the control mode. If the input of the control value must be updated for each control cycle (continuous input even if it is the same A), but the control cycle in which the control value is not input continues for a predetermined cycle or longer, it is determined that an abnormal situation has occurred, and the control mode of the previous cycle can be considered to be switched to the HOLD mode or the STOP mode.

In addition, the control mode management unit (420) can compare real-time data of the previous control cycle and the current control cycle according to a predetermined control cycle, and if a difference exceeding a preset threshold occurs, the control mode can be reset to a standby mode. The control value calculated by the chemical injection optimization unit (300) is derived using real-time data of the previous cycle in the control cycle, but if there is a significant difference between the real-time data of the current control cycle and the real-time data of the previous cycle, the reliability of the control value is determined to be low and the control value is switched to a standby mode.

The output processing unit (430) provides a control value to the water treatment control device (2) according to the control of the control mode management unit (420), that is, the control mode reset by the control mode management unit (420). In particular, when the output processing unit (430) receives a control value for each control period from the control mode management unit (420), it can convert the control value according to the control period of the water treatment control device (2) and the control range of the water treatment control device (2) in each control period, and provide the converted control value to the water treatment control device (2). It is assumed that the control period of the chemical injection optimization device (3) is 1 minute, and the control period of the water treatment control device (2) is 10 seconds. In addition, it is assumed that the control range of the water treatment control device (2) in each control period is ±4. Then, the chemical injection optimization unit (300) will calculate the control value at one-minute intervals, the control value correction unit (410) of the chemical injection output control unit (400) will correct the control value at one-minute intervals, and the control mode management unit (420) will transmit the control value to the output processing unit (430) at one-minute intervals. At this time, the transmitted control value is a target value, and is assumed to be +20. Then, the output processing unit (430) changes the control value and provides the water treatment control device (2) with control values (target values) of +4, +8, +12, +16, +20, and +20 in 10-second units according to the control cycle and control range of the water treatment control device (2).

Next, a method for generating a water treatment model for chemical injection optimization in a water treatment plant according to an embodiment of the present invention will be described. FIG. 5 is a flowchart for explaining a method for generating a water treatment model for chemical injection optimization in a water treatment plant according to an embodiment of the present invention.

Referring to FIG. 5, the preprocessing unit (200) receives raw data at step S110. At this time, the raw data includes operation data and status data from at least one of the water treatment plant (1) and the water treatment control device (2). The raw data is operation data and status data collected from the water treatment plant (1) and the water treatment control device (2) over time and accumulated and stored. Therefore, the raw data may include real-time data including operation data and status data collected in real time. In particular, the raw data also includes a plurality of types of data having different attributes. The raw data is continuously received over time from the water treatment plant (1) or the water treatment control device (2). In particular, the raw data includes input attribute data having input attributes and output attribute data having output attributes. The input attribute data includes operation data and status data related to influent flowing into the water treatment plant (1), particularly, a dissolved air flotation device (DAF). Such input attribute data may include, for example, flow rate, temperature, conductivity, acidity (or hydrogen ion concentration), turbidity, flow rate, treatment amount for influent (per unit time), chemical injection amount for influent, chemical injection concentration, etc. The output attribute data includes operating data and status data related to treated water by the dissolved air flotation device (DAF). The output attribute data may include, for example, acidity (or hydrogen ion concentration, pH) or acidity change, turbidity or turbidity change, residual iron, etc. of treated water.

When raw data is collected, the preprocessing unit (200) preprocesses the raw data to generate learning data in step S120. The learning data is classified according to its purpose, and includes learning data and verification data. In addition, the learning data is classified according to its attribute, and includes input data and output data. The input data is derived by preprocessing the input attribute data, and the output data is derived by preprocessing the output attribute data. The input data may exemplify the flow rate, temperature, conductivity, acidity (or hydrogen ion concentration), turbidity, flow rate, treatment amount for the influent (per unit time), chemical injection amount for the influent, chemical injection concentration, etc. The output data may exemplify the acidity (or hydrogen ion concentration, pH) or acidity change, turbidity or turbidity change, residual iron, etc. of the treated water.

Then, the model generation management unit (20) including the automatic modeling processing unit (500), the model generation unit (600), and the model selection unit (700) receives learning data, and generates a water treatment model using the learning data at step S130. At step S130, the automatic modeling processing unit (500) designs a water treatment model. Designing a water treatment model means specifying the format of the model, the number of sub-models belonging to one model, inputs, outputs, and variables. Then, the model generation unit (600) performs learning using learning data among the learning data for the designed water treatment model, thereby generating a water treatment model that simulates the water treatment plant (1) and predicts the state of the treated water according to the state of the influent water to the water treatment plant (1). Then, the model selection unit (700) selects the water treatment model having the highest similarity to the water treatment device (2) among the plurality of water treatment models using verification data among the learning data. In this way, the selected water treatment model is provided to the chemical injection optimization unit (300) of the optimization unit (10).

Next, a method for optimizing chemical injection in a water treatment plant according to an embodiment of the present invention will be described. FIG. 6 is a flowchart for explaining a method for optimizing chemical injection in a water treatment plant according to an embodiment of the present invention.

Referring to FIG. 6, the chemical injection management unit (100) receives real-time data including operation data and status data at step S210. Then, the chemical injection management unit (100) analyzes the real-time data at step S220 to determine whether there is an abnormality in the water treatment plant (1) and determines whether to perform chemical injection optimization to optimize the chemical injection amount. If there is no abnormality in the water treatment plant (1) and it is determined to perform chemical injection optimization, the preprocessing unit (200) performs preprocessing on the real-time data at step S230 and provides the preprocessed real-time data to the optimization unit (10) including the chemical injection optimization unit (300) and the chemical injection output control unit (400).

Meanwhile, as described above in FIG. 6, the optimization unit (10) may receive a water treatment model from the model generation management unit (20). Accordingly, the chemical injection optimization unit (300) of the optimization unit (10) analyzes real-time data through one or more water treatment models and one or more controllers in step S240 to derive a control value that allows the minimum chemical injection amount to be injected while the state of the treated water of the water treatment plant is maintained within a normal range. Here, the controller is a search algorithm. In addition, the state of the treated water may include, for example, turbidity, acidity, residual iron, etc. In step S240, one or more water treatment models analyze real-time data according to input from the controller to derive a predicted value that predicts the state of the treated water of the water treatment plant, and one or more controllers search for and derive a control value that allows the predicted value of the water treatment model to be injected while the state of the treated water is maintained within a normal range while the minimum chemical injection amount is injected. That is, the controller can derive an optimal control value by performing a simulation to predict the state of treated water in a water treatment plant through a water treatment model that simulates the water treatment plant.

Meanwhile, the post-process protection unit (800) receives post-process data including operation data and status data of the post-process of the water treatment plant (1), i.e., the process by the automatic filtration unit (AS), the ultrafiltration unit (UF), and the reverse osmosis unit (RO), at step S250, analyzes the post-process data received at step S260, and derives a correction bias value for protecting the post-process according to the post-process protection logic for preventing damage to the post-process, such as fouling, and provides the value to the chemical input/output control unit (400).

The chemical injection/output control unit (400) can modify the control value according to the compensation bias value, the control cycle and the control range of the water treatment control device (2) at step S270. Then, the chemical injection/output control unit (400) provides the control value derived by the chemical injection optimization unit (300) to the water treatment control device (2) according to at least one of the management command and the current status of the chemical injection management unit (100) at step S280. At this time, the chemical injection/output control unit (400) may not provide the control value to the water treatment control device (2) according to at least one of the management command and the current status.

Next, a method for optimizing water treatment optimization management according to an embodiment of the present invention will be described. Fig. 7 is a flowchart for explaining a method for optimizing water treatment optimization management according to an embodiment of the present invention.

Referring to Fig. 7, the chemical injection management unit (100) receives real-time data including operating data and status data at step S310. The real-time data can be provided from at least one of the water treatment plant (1) and the water treatment control device (2).

Accordingly, the chemical injection management unit (100), which includes a data analysis-based processing unit (110), a status recognition-based processing unit (120), a knowledge-based processing unit (130), and a decision unit (140), analyzes real-time data to determine whether the status of the water treatment plant (1) is normal.

To this end, the data analysis-based processing unit (110) determines whether real-time data is normal data by using a learning model or data pattern analysis at step S320, thereby providing a first judgment result for determining whether the state of the water treatment plant is normal. At this time, the data analysis-based processing unit (110) can classify whether the input real-time data is normal data or abnormal data by using a learning model. Alternatively, the data analysis-based processing unit (110) can distinguish whether the input real-time data has a normal pattern or whether the input real-time data deviates from the normal pattern through pattern analysis.

In addition, the status recognition-based processing unit (120) can provide a second judgment result for determining whether the status of the water treatment plant (1) is normal, depending on whether data indicating an abnormal status of the water treatment plant (1) is detected from the data indicating the status of the water treatment plant (1) among the real-time data input at step S330. For example, the status recognition-based processing unit (120) can detect green algae inflow, inflow water overflow, system abnormality, sensor abnormality, etc. through the data indicating the status of the water treatment plant (1).

And the knowledge-based processing unit (130) compares the knowledge-based data already stored in step S340 with the post-process data among the input real-time data, and provides a third judgment result for determining whether the state of the water treatment plant is normal based on whether there is post-process data that matches the knowledge-based data. Here, the knowledge-based data means post-process data that indicates that the water treatment plant (1) is in an abnormal state based on existing empirical rules. In addition, the post-process data includes the operation data and state data of the post-process among the real-time data.

The optimization decision unit (140) determines the control mode of chemical injection optimization according to the first, second, and third judgment results in step S350. Chemical injection optimization means applying a control value that minimizes the amount of chemical injection while maintaining the state of the treated water of the water treatment plant within a normal range. The control mode of this chemical injection optimization means a method of applying the control value to the water treatment control device. The control mode includes an automatic mode, a guide mode, and a stop mode. Here, the automatic mode is a method in which the control value is automatically applied to the water treatment control device (2). The guide mode is a method in which the control value is provided to the water treatment control device, but the application of the control value is determined by the water treatment control device. That is, in the guide mode, the control value is provided through an operation screen, etc. so that the operator of the water treatment control device (2) can view it. Accordingly, the operator of the water treatment control device (2) can view the control value, and if it is determined that it can be applied or is necessary, the control value can be applied. The stop mode is a method in which the control value is not provided.

The optimization decision unit (140) generates a management command to optimize chemical injection according to the control mode at step S360 and provides the management command to the optimization unit (10). Then, the optimization unit (10) generates a control value and enables chemical injection optimization by referring to the control mode of chemical injection optimization according to the management command.

Next, a method for controlling output for optimizing chemical injection of a water treatment plant according to an embodiment of the present invention will be described. FIG. 8 is a flowchart for explaining a method for controlling output for optimizing chemical injection of a water treatment plant according to an embodiment of the present invention.

Referring to FIG. 8, the control value correction unit (410) receives a control value from the chemical injection optimization unit (300) according to the control cycle (e.g., 1 minute) of the chemical injection optimization device (3) at step S410. Then, the control value correction unit (410) can correct the control value received at step S420 using the correction bias value received from the post-process protection unit (800). The chemical injection optimization unit (300) analyzes real-time data received during the control cycle (e.g., 1 minute) through one or more water treatment models to derive a predicted value predicting the state of the treated water of the water treatment plant (1) (i.e., the state in ③ of FIG. 1), and derives a control value that allows the minimum chemical injection amount to be injected while the state of the treated water of the water treatment plant is maintained within a normal range based on the predicted value through the controller, and provides the derived control value to the chemical injection/output control unit (400). In addition, the post-process protection unit (800) analyzes the post-process data including the process operation data and status data by the post-process received during the control period (e.g., 1 minute) to derive a correction bias value for preventing damage to the post-process (i.e., damage occurring between ③ and ④ in FIG. 1) and provides the derived correction bias value to the chemical injection/output control unit (400). Accordingly, the control value correction unit (410) can correct the control value using the correction bias value. For example, when the control value is a target value of the injection amount of sulfuric acid and ferric chloride, the control value can be corrected as in the mathematical expression 1 described above.

Next, the control mode management unit (420) resets the control mode at step S430. The chemical injection management unit (100) analyzes real-time data to determine the control mode of chemical injection optimization and transmits the determined control mode as a management command. Then, the control mode management unit (420) can reset the control mode by considering the control mode of the previous control cycle in the control cycle (e.g., 1 minute) of the chemical injection optimization device (3) and checking whether the control value is normally updated for each control cycle. If the input of the control value must be updated for each control cycle (continuous input even if it is the same A), but the control cycle in which the control value is not input continues for a predetermined time or longer, it is determined that an abnormal situation has occurred and the control mode of the previous control cycle can be considered to be switched to the HOLD mode or the STOP mode. In addition, the control mode management unit (420) can compare real-time data of the previous control cycle and the current control cycle according to a predetermined control cycle, and if a difference exceeding a preset threshold occurs, the control mode can be reset to a standby mode. The control value calculated by the chemical injection optimization unit (300) is derived using real-time data received from the previous control cycle in the control cycle, but if there is a significant difference between the real-time data of the current control cycle and the real-time data of the previous control cycle, the control value is judged to be unreliable and the control mode can be switched to a standby mode.

Next, when the output processing unit (430) receives a control value for each control period from the control mode management unit (420) at step S440, it converts the control value according to the control period of the water treatment control device (2) and the control range of the water treatment control device (2) in each control period. It is assumed that the control period of the chemical injection optimization unit (3) is 1 minute and the control period of the water treatment control device (2) is 10 seconds. In addition, it is assumed that the control range of each control period of the water treatment control device (2) is ±4. Then, the chemical injection optimization unit (300) will calculate the control value in a 1-minute period, the control value correction unit (410) of the chemical injection output control unit (400) will correct the control value in a 1-minute period, and the control mode management unit (420) will transmit the control value to the output processing unit (430) in a 1-minute period. At this time, the transmitted control value is a target value and is assumed to be +20. Then, the output processing unit (430) changes the control value and converts the control value (target value) to +4, +8, +12, +16, +20, and +20 in 10-second units in accordance with the control cycle and control range of the water treatment control device (2).

Next, the output processing unit (430) provides the converted control value according to the control mode reset by the control mode management unit (420) at step S450 to the water treatment control device (2). The control mode includes an automatic mode, a guide mode, a standby mode, and a stop mode. The automatic mode means that the output processing unit (430) provides the control value to the water treatment control device (2) so that the control value is automatically applied to the water treatment control device (2). In the automatic mode, the water treatment control device (2) automatically reflects the control value and controls the water treatment plant (1). The guide mode is a mode in which the output processing unit (430) provides the control value to the water treatment control device (2), but provides the control value in a viewable state so that the application of the control value is determined by the water treatment control device (2). The standby mode is a mode in which the output processing unit (430) converts the control value according to the control cycle of the water treatment control device and the control range in each control cycle, but does not provide the converted control value to the water treatment control device. Since the control mode management unit (420) does not provide the control value to the output processing unit (430) in the stop mode, the output processing unit (430) cannot provide the control value to the water treatment control device (2) in the stop mode.

FIG. 9 is a diagram showing a computing device according to an embodiment of the present invention. The computing device (TN100) may be a device described in this specification (e.g., a water treatment control device (2) and a chemical injection optimization device (3), etc.).

In the embodiment of FIG. 9, the computing device (TN100) may include at least one processor (TN110), a transceiver (TN120), and a memory (TN130). In addition, the computing device (TN100) may further include a storage device (TN140), an input interface device (TN150), an output interface device (TN160), etc. The components included in the computing device (TN100) may be connected by a bus (TN170) to communicate with each other.

The processor (TN110) can execute a program command stored in at least one of the memory (TN130) and the storage device (TN140). The processor (TN110) may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. The processor (TN110) may be configured to implement procedures, functions, methods, etc. described in relation to embodiments of the present invention. The processor (TN110) may control each component of the computing device (TN100).

Each of the memory (TN130) and the storage device (TN140) can store various information related to the operation of the processor (TN110). Each of the memory (TN130) and the storage device (TN140) can be configured with at least one of a volatile storage medium and a nonvolatile storage medium. For example, the memory (TN130) can be configured with at least one of a read-only memory (ROM) and a random access memory (RAM).

The transceiver (TN120) can transmit or receive wired or wireless signals. The transceiver (TN120) can be connected to a network and perform communications.

Meanwhile, various methods according to the embodiments of the present invention described above may be implemented in the form of readable programs through various computer means and recorded on a computer-readable recording medium. Here, the recording medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the recording medium may be those specially designed and configured for the present invention or may be those known to and usable by those skilled in the art of computer software. For example, the recording medium includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program commands may include not only machine language generated by a compiler, but also high-level languages that can be executed by a computer using an interpreter, etc. These hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

Above, one embodiment of the present invention has been described, but those skilled in the art will be able to modify and change the present invention in various ways by adding, changing, deleting or adding components, etc., within the scope that does not depart from the spirit of the present invention described in the claims, and this will also be considered to be included within the scope of the rights of the present invention.

Claims (14)

When real-time data including operation data and status data are received, the real-time data is analyzed to determine whether the status of the water treatment plant is normal, and when a control value is derived to minimize the amount of chemical injection while maintaining the status of the treated water of the water treatment plant within the normal range based on the result of the determination,
A chemical injection management unit that determines a control mode of chemical injection optimization indicating a method of applying the derived control value to a water treatment control device; and
An optimization unit that performs chemical injection optimization according to the control mode of the above chemical injection optimization;
characterized by including
A device for managing chemical injection optimization. In the first paragraph,
The above chemical injection management department
By using learning models or analyzing data patterns
By determining whether the above real-time data is normal data,
A data analysis-based processing unit that provides a first judgment result for determining whether the state of the above water treatment plant is normal;
characterized by including
A device for managing chemical injection optimization. In the second paragraph,
The above chemical injection management department
Depending on whether data indicating an abnormal condition of the water treatment plant is detected from the data indicating the condition of the water treatment plant among the real-time data above.
A status recognition-based processing unit that provides a second judgment result for determining whether the status of the above water treatment plant is normal;
characterized by including
A device for managing chemical injection optimization. In the third paragraph,
The above chemical injection management department
By comparing the knowledge-based data indicating the abnormal state of the water treatment plant with the post-process data including the operation data and status data of the post-process among the real-time data,
Depending on whether there is post-processing data that matches the above knowledge base data.
A knowledge-based processing unit that provides a third judgment result for determining whether the state of the above water treatment plant is normal;
characterized by including
A device for managing chemical injection optimization. In paragraph 4,
The above chemical injection management department
If the state of the water treatment plant is judged to be normal based on the above first judgment result, the above second judgment result, and the above third judgment result,
An optimization decision unit that determines the control mode of the above chemical injection optimization as an automatic mode so that the control value is automatically applied to the water treatment control device;
characterized by including
A device for managing chemical injection optimization. In paragraph 4,
The above chemical injection management department
If the first judgment result above determines that the water treatment plant is in a normal state, and at least one of the second judgment result and the third judgment result determines that the water treatment plant is in an abnormal state,
An optimization decision unit that determines the control mode of the above chemical injection optimization as a guide mode in which the application of the above control value is determined by the water treatment control device;
characterized by including
A device for managing chemical injection optimization. In paragraph 4,
The above chemical injection management department
As a result of the first judgment above, if the water treatment plant is in an abnormal state,
An optimization decision unit that determines the control mode of the above chemical injection optimization as a stop mode that does not provide the above control value;
characterized by including
A device for managing chemical injection optimization. A step for receiving real-time data including driving data and status data by the chemical injection management unit;
A step in which the chemical injection management unit analyzes the real-time data to determine whether the water treatment plant is in normal condition;
When the chemical injection management department derives a control value that minimizes the amount of chemical injection while maintaining the condition of the treated water of the water treatment plant within the normal range based on the results of the judgment,
A step of determining a control mode of chemical injection optimization indicating a method of applying the derived control value to a water treatment control device; and
A step in which the chemical injection management unit generates a management command so that the chemical injection optimization is performed according to the control mode of the chemical injection optimization;
characterized by including
A method for managing chemical injection optimization. In Article 8,
The step for determining whether the above water treatment plant is in normal condition is
Data analysis-based processing department
By using learning models or analyzing data patterns
By determining whether the above real-time data is normal data,
A step of providing a first judgment result for determining whether the state of the water treatment plant is normal;
characterized by including
A method for managing chemical injection optimization. In Article 9,
The step for determining whether the above water treatment plant is in normal condition is
State-aware processing unit
Depending on whether data indicating an abnormal condition of the water treatment plant is detected from the data indicating the condition of the water treatment plant among the real-time data above.
A step of providing a second judgment result for determining whether the state of the water treatment plant is normal;
characterized by including
A method for managing chemical injection optimization. In Article 10,
The step for determining whether the above water treatment plant is in normal condition is
Knowledge-based processing department
By comparing the knowledge-based data indicating the abnormal state of the water treatment plant with the post-process data including the operation data and status data of the post-process among the real-time data,
Depending on whether there is post-processing data that matches the above knowledge base data.
A step of providing a third judgment result for determining whether the state of the water treatment plant is normal;
characterized by including
A method for managing chemical injection optimization. In Article 11,
The step of determining the control mode of the above chemical injection optimization is
If the state of the water treatment plant is judged to be normal based on the above first judgment result, the above second judgment result, and the above third judgment result,
The optimization decision unit is characterized in that the control mode of the chemical injection optimization is determined as an automatic mode in which the control value is automatically applied to the water treatment control device.
A method for managing chemical injection optimization. In Article 11,
The step of determining the control mode of the above chemical injection optimization is
If the first judgment result above determines that the water treatment plant is in a normal state, and at least one of the second judgment result and the third judgment result determines that the water treatment plant is in an abnormal state,
The optimization decision unit is characterized in that the control mode of the chemical injection optimization is determined as a guide mode in which the application of the control value is determined by the water treatment control device.
A method for managing chemical injection optimization. In Article 11,
The step of determining the control mode of the above chemical injection optimization is
As a result of the first judgment above, if the water treatment plant is in an abnormal state,
The optimization decision unit is characterized in that it determines the control mode of the chemical injection optimization as a stop mode that does not provide the control value.
A method for managing chemical injection optimization.