TW202414321A - Operation method of waste liquid treatment facility, method for predicting property of waste liquid after treatment, operation system, and prediction system - Google Patents

Abstract

To provide an operation method or the like of a waste liquid treatment facility capable of flexibly responding to fluctuation in property of waste liquid. According to one aspect of the present invention, an operation method of a waste liquid treatment facility for treating waste liquid from a product production process is provided. The operation method includes a data acquisition process, a waste liquid prediction value output process, and an operation condition setting process. In the data acquisition process, first data including product production process data in a product production process at a first time is acquired. In the waste liquid prediction value output process, a predicted value with respect to property of waste liquid from the product production process at a second time after the first time is output based on the first data and a prediction model for predicting property of waste liquid. Here, the prediction model is a model created by associating past product production process data in the product production process with data on property of waste liquid discharged at that time. In the operation condition setting process, an operation condition parameter of the waste liquid treatment facility is set based on the predicted value with respect to property of waste liquid output in the waste liquid prediction value output process.

Description

Operation method of waste liquid treatment equipment, method for predicting properties of treated waste liquid, operation system and prediction system

The present invention relates to an operating method of a waste liquid treatment facility, a method for predicting the properties of the treated waste liquid, an operating system, and a prediction system.

In the production process of factories, water is used for various purposes such as dissolving raw materials, cleaning and cooling of production lines, etc. These waters are usually subjected to specific treatment when they are discarded. Here, the properties of the water to be treated change with the changes in the raw materials, product types or production volume, so sometimes it is necessary to make efforts in the drainage treatment steps.

As a technology related to this, the technology disclosed in Patent Document 1 is known. Patent document 1 discloses a method for predicting a monitoring object quantity, which is characterized in that it comprises: a primary prediction step, which uses a plurality of different prediction models, the operating performance data (Data) of the factory equipment, data related to the current operating status, meteorological observation data, and data related to the weather forecast to multiple-calculate the primary prediction value of the monitoring object quantity of the factory equipment; a secondary prediction step, which assigns a weight corresponding to the execution time point of the secondary prediction step to each primary prediction value predicted in the aforementioned primary prediction step, and uses the plurality of primary prediction values assigned with the weights to calculate the secondary prediction value of the monitoring object quantity of the factory equipment as the predicted value of the monitoring object quantity of the factory equipment.

[Prior technical literature] [Patent literature] [Patent literature 1] Japanese Patent Publication No. 2013-161336

[Problems to be solved by the invention] However, the research of the inventors shows that there is still room for improvement in optimizing wastewater treatment conditions.

The present invention is completed in view of the above situation, and its purpose is to provide an operation method of waste liquid treatment equipment that can flexibly cope with changes in the properties of waste liquid.

[Technical means for solving the problem] Specifically, the present invention is provided in the following manner. (1) A method for operating a waste liquid treatment facility for treating waste liquid from a product production process, comprising: a data acquisition step, a waste liquid prediction value output step, and an operation condition setting step; in the data acquisition step, first data including product production process data in the product production process at a first time is acquired, in the waste liquid prediction value output step, based on the first data and a prediction model for predicting the properties of the waste liquid, a prediction value related to the properties of the waste liquid from the product production process at a second time after the first time is output, here, the prediction model is a model created by associating the past product production process data in the product production process with data related to the properties of the waste liquid discharged at this time, In the aforementioned operation condition setting step, the operation condition parameters of the aforementioned waste liquid treatment equipment are set based on the predicted value related to the property of the aforementioned waste liquid output in the aforementioned waste liquid predicted value output step. (2) The operation method of the waste liquid treatment equipment as described in (1), wherein the aforementioned prediction model is constructed as a model that can be updated before executing the aforementioned waste liquid predicted value output step. (3) The operation method of the waste liquid treatment equipment as described in (1) or (2), wherein the aforementioned prediction model is a model created by further associating the predetermined parameters of the product produced in the aforementioned product production process, The aforementioned first data obtained in the aforementioned data acquisition step also includes information related to the predetermined parameters of the aforementioned product. (4) A method for predicting the properties of waste liquid after treatment by a waste liquid treatment device that treats waste liquid from a product production process, comprising: a data acquisition step and a step of outputting a predicted value of the treated waste liquid; in the data acquisition step, second data including product production process data in the product production process at a first time and operating condition parameters to be executed by the waste liquid treatment device are acquired; in the step of outputting the predicted value of the treated waste liquid, a predicted value related to the properties of the waste liquid after treatment by the waste liquid treatment device at a second time after the first time is output based on the second data and a prediction model for predicting the properties of the treated waste liquid; Here, the prediction model is a model created by associating the past product production process data in the product production process, the data related to the properties of the waste liquid discharged at this time, the operating condition parameters of the waste liquid treatment equipment for treating the discharged waste liquid at this time, and the properties of the waste liquid after treatment. (5) The method for predicting the properties of treated waste liquid as described in (4) further comprises: a data re-acquisition step and a treated waste liquid predicted value re-output step, in the aforementioned data re-acquisition step, when the predicted value related to the properties of the aforementioned treated waste liquid output in the aforementioned treated waste liquid predicted value output step does not fall within the predetermined range, the aforementioned second data is acquired on the basis of re-setting the operating condition parameters to be executed by the aforementioned waste liquid treatment equipment, In the aforementioned treated waste liquid predicted value re-output step, based on the aforementioned second data obtained in the aforementioned data re-acquisition step and the aforementioned prediction model for predicting the properties of the treated waste liquid, the predicted value related to the properties of the treated waste liquid of the aforementioned waste liquid treatment equipment at the aforementioned second time is re-output. (6) A method for predicting the properties of treated waste liquid as described in (4) or (5), wherein the aforementioned prediction model is constructed as a model that can be updated before executing the aforementioned treated waste liquid predicted value output step. (7) A method for predicting the properties of treated wastewater as described in any one of (4) to (6), wherein the prediction model is a model created by further associating the temperature and/or temperature transition of the wastewater with the corresponding biological treatment capacity, and the second data obtained in the data acquisition step also includes information related to the temperature and/or temperature transition of the wastewater. (8) A method for predicting the properties of treated wastewater as described in any one of (4) to (7), wherein the data acquisition step is configured to set limiting conditions for a portion of the operating condition parameters to be executed by the wastewater treatment equipment. (9) A method for predicting the properties of treated wastewater as described in any one of (4) to (7), wherein the prediction model is a model created by further associating predetermined parameters of a product produced in the product production process, and the second data obtained in the data acquisition step further includes information related to the predetermined parameters of the product. (10) An operation system of a waste liquid treatment facility for treating waste liquid from a product production process, comprising: a data acquisition unit, a waste liquid prediction value output unit, and an operation condition setting unit; the data acquisition unit acquires first data including product production process data in the product production process at a first time, the waste liquid prediction value output unit outputs a prediction value related to the property of the waste liquid from the product production process at a second time after the first time based on the first data and a prediction model for predicting the property of the waste liquid, here, the prediction model is a model created by associating the past product production process data in the product production process with data related to the property of the waste liquid discharged at this time, The operating condition setting unit sets the operating condition parameters of the waste liquid treatment equipment based on the predicted value related to the property of the waste liquid output by the waste liquid predicted value output unit. (11) A prediction system for predicting the properties of waste liquid after treatment by a waste liquid treatment facility that treats waste liquid from a product production process, comprising: a data acquisition unit and a treated waste liquid prediction value output unit; the data acquisition unit acquires second data including product production process data in the product production process at a first time and operating condition parameters to be executed by the waste liquid treatment facility; the treated waste liquid prediction value output unit outputs a prediction value related to the properties of the waste liquid after treatment by the waste liquid treatment facility at a second time after the first time based on the second data and a prediction model for predicting the properties of the treated waste liquid; Here, the prediction model is a model created by associating the past product production process data in the product production process, the data related to the properties of the waste liquid discharged at this time, the operating condition parameters of the waste liquid treatment equipment when treating the discharged waste liquid at this time, and the properties of the waste liquid after treatment.

The technology disclosed in the aforementioned patent document 1 only focuses on the operating conditions of the plant itself that performs wastewater treatment. In contrast, in the operation method of the wastewater treatment equipment of the present application, data related to the product production process located upstream of the wastewater generation can be used to optimize the operating conditions of the wastewater treatment equipment. More specifically, by associating the product production process data with the wastewater treatment data, changes in the properties of the wastewater can be predicted, and the operating conditions of the wastewater treatment equipment can be optimized. In addition, the operating cost or environmental load of the wastewater treatment equipment can be minimized. In addition, even within the limited processing capacity of wastewater treatment equipment, by adjusting the parameters related to wastewater treatment data associated with the product production process, the target wastewater properties (wastewater quality benchmark, etc.) can be achieved without additional equipment investment, etc.

Therefore, according to the above aspect, it is possible to provide a method for operating a waste liquid treatment facility that can flexibly cope with changes in the properties of waste liquid.

The following drawings are used to illustrate the implementation of the present invention. The various features shown in the following implementations can be combined with each other.

However, the computer program used to implement the software appearing in this embodiment may be provided as a non-transitory computer-readable medium, or downloaded from an external server, or provided as a computer program that is activated on an external computer and implements its functions on a client terminal (i.e., so-called cloud computing).

In addition, in the present embodiment, "unit" may include, for example, a combination of hardware resources implemented by a generalized circuit and software information processing that can be specifically implemented by such hardware resources. Although various information is processed in the present embodiment, such information is represented by a physical value such as a signal value representing a voltage or current, or a signal value of a bit set of a binary number composed of 0 or 1, or by quantum superposition (i.e., a so-called quantum bit), and communication or operation can be performed on a generalized circuit.

In addition, a circuit in a broad sense is a circuit implemented by at least appropriately combining circuits, circuit types, processors, and memories. In other words, it includes application-specific integrated circuits (ASICs), programmable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)).

1. Hardware Structure In this section, the hardware structure of the information processing system 100 of this embodiment will be described. FIG. 1 is a diagram showing the overall structure of the information processing system 100.

The information processing system 100 of the present embodiment is a system that can execute an operation method of a waste liquid treatment facility that treats waste liquid from a product production process (sometimes also referred to as an "operation method") and a method for predicting the properties of waste liquid after treatment by a waste liquid treatment facility that treats waste liquid from a product production process (sometimes also referred to as a "prediction method"). In addition, from such a point of view, the information processing system 100 of the present embodiment is sometimes referred to as an "operation system" or a "prediction system". Here, the information processing system 100 of the present embodiment has an information processing device 1 and a communication line 2. The communication line 2 includes the Internet, etc., and mediates data exchange between devices connected to this line. In addition, in the information processing system 100 of this embodiment, the information processing device 1 is connected to the factory PL1 and the factory PL2 via the communication line 2. The system exemplified in the information processing system 100 includes one or more devices or components. Therefore, even if the information processing device 1 is a single unit, it is also an example of a system.

Here, plant PL1 is a plant that performs product production processes, and plant PL2 is a plant that functions as a waste liquid treatment facility that treats waste liquid from the product production process. That is, as for the flow of waste liquid, plant PL1 is located upstream relative to plant PL2, and typically, waste liquid generated in plant PL1 is transferred to plant PL2 via liquid pipeline LL1. The machines and the like configured in plant PL2 can be appropriately set according to the type of waste liquid. For example, if the waste liquid is water, a biological treatment device and the like can also be provided in plant PL2. In addition, the biological treatment device can also apply microorganisms that can purify waste water and the like. Although not shown in FIG. 1 , a sensor may be installed for the liquid line LL1, and the sensor and the information processing device 1 may be connected via a communication line 2.

Fig. 2 is a diagram showing the hardware structure of the information processing device 1. The information processing device 1 includes a control unit 11, a memory unit 12, an input unit 13, a display unit 14, and a communication unit 15, and the above-mentioned units are electrically connected via a communication bus 10. The following describes the units of the information processing device 1.

(Control unit 11) The control unit 11 is, for example, a central processing unit (CPU, not shown). The control unit 11 implements various functions related to the information processing device 1 by reading a predetermined computer program stored in the memory unit 12. That is, information processing is specifically implemented by the software (stored in the memory unit 12) through the control unit 11 as an example of hardware, so that it can be executed as each functional unit included in the control unit 11. These will be explained in detail in the next section. Although the control unit 11 is described as a single unit, it is not limited to this, and it can be implemented as a plurality of control units 11 according to each function. In addition, these can also be implemented in combination.

(Memory unit 12) The memory unit 12 stores various information defined in the above description. It can be implemented, for example, as a memory device such as a solid state drive (SSD) for storing various computer programs related to the information processing device 1 executed by the control unit 11, or as a memory such as a random access memory (RAM) for storing temporary necessary information (parameters, arrays, etc.) related to computer program operations. The memory unit 12 stores various computer programs or variables related to the information processing device 1 executed by the control unit 11.

(Input unit 13) The input unit 13 may be included in the housing of the information processing device 1 or may be externally connected. For example, the input unit 13 may be integrated with the display unit 14 and implemented as a touch panel. If it is a touch panel, the user can input tapping operations, sliding operations, etc. Of course, a switch button, a mouse, a QWERTY keyboard, etc. may also be used instead of the touch panel. That is, the input unit 13 receives the operation input performed by the user. The input is transmitted to the control unit 11 as a command signal via the communication bus 10, and the control unit 11 can perform predetermined control or calculation as needed.

(Display unit 14) The display unit 14 may be included in the housing of the information processing device 1 or may be externally connected. The display unit 14 displays a graphical user interface (GUI) screen that can be operated by the user. It is preferred to distinguish and implement display devices such as CRT (Cathode Ray Tube) display, liquid crystal display, organic electroluminescence display (OLED) and plasma display according to the type of information processing device 1.

(Communication unit 15) The communication unit 15 is configured to be able to send various electrical signals from the information processing device 1 to external components. In addition, the communication unit 15 is configured to be able to receive various electrical signals sent from external components to the information processing device 1. In addition, the communication unit 15 may have a network communication function, thereby being able to transmit various information between the information processing device 1 and an external device via the communication line 2.

In addition, although not shown, the factory PL1 and the factory PL2 connected to the information processing device 1 via the communication line 2 may also have devices having the same hardware structure as the aforementioned information processing device 1.

2. Functional Structure In this section, the functional structure of this embodiment is described. FIG. 3 is a functional block diagram showing the functions of the information processing device 1. As described above, the information processing implemented by the software (stored in the memory unit 12) is specifically implemented by the hardware (control unit 11), so that it can be executed as each functional unit included in the control unit 11.

Specifically, the information processing device 1 (control unit 11) may include, as each functional unit, a data acquisition unit 111, a waste liquid predicted value output unit 112, an operation condition setting unit 113, a treated waste liquid predicted value output unit 114, a data re-acquisition unit 115, a treated waste liquid predicted value re-output unit 116, a prediction model creation unit 117, and a memory management unit 118. In addition, each of these functional units may be appropriately added or omitted according to the purpose of the information processing device 1.

(Data acquisition unit 111) The data acquisition unit 111 is configured to execute a data acquisition step. In the data acquisition step, the data acquisition unit 111 acquires first data, which includes product production process data in a product production process at a first time. In addition, in the data acquisition step, the data acquisition unit 111 acquires second data including product production step data in a product production step at a first time and operating condition parameters to be executed by the waste liquid treatment equipment. When acquiring the information, the data acquisition unit 111 is configured to acquire various information (analysis data, etc.) from sensors or instruments configured in the factory PL1 through the communication unit 15, for example.

(Waste liquid predicted value output unit 112) The waste liquid predicted value output unit 112 is configured to be able to execute a waste liquid predicted value output step. In the waste liquid predicted value output step, the waste liquid predicted value output unit 112 outputs a predicted value related to the properties of waste liquid from the product production process at a second time after the first time based on the aforementioned first data and a prediction model for predicting the properties of the waste liquid. Here, the prediction model is a model created by associating the past product production process data in the product production process with the data related to the properties of the waste liquid discharged at this time. The details of the information processing will be described later.

(Operation condition setting unit 113) The operation condition setting unit 113 is configured to execute an operation condition setting step. In the operation condition setting step, the operation condition setting unit 113 sets the operation condition parameters of the waste liquid treatment equipment based on the predicted value related to the property of the waste liquid output by the waste liquid predicted value output unit. When setting the operation condition, the operation condition setting unit 113 is typically configured to send various information (signals, etc.) to various machines configured in the factory PL2 through the communication unit 15.

(Treatment waste liquid prediction value output unit 114) The treatment waste liquid prediction value output unit 114 is configured to be able to perform a treatment waste liquid prediction value output step. In the treatment waste liquid prediction value output step, the treatment waste liquid prediction value output unit 114 outputs a prediction value related to the property of the treated waste liquid of the waste liquid treatment equipment at a second time after the first time based on the aforementioned second data and a prediction model for predicting the property of the treated waste liquid. Here, the prediction model is created by associating the past product production process data in the product production process, the data related to the properties of the waste liquid discharged at that time, the operating condition parameters when the waste liquid treatment equipment treats the discharged waste liquid at that time, and the properties of the waste liquid after treatment. The details of this information processing will be explained later.

(Data re-acquisition unit 115) The data re-acquisition unit 115 is configured to execute a data re-acquisition step. In the data re-acquisition step, when the predicted value related to the property of the treated waste liquid output in the treated waste liquid predicted value output step does not fall within the predetermined range, the data re-acquisition unit 115 acquires the second data based on resetting the operating condition parameters to be executed by the waste liquid treatment equipment. The specific aspects will be described later.

(Predicted value re-output unit 116 for treated waste liquid) The predicted value re-output unit 116 for treated waste liquid is configured to be able to perform a predicted value re-output step for treated waste liquid. In the predicted value re-output step for treated waste liquid, the predicted value re-output unit 116 for treated waste liquid re-outputs a predicted value related to the property of the treated waste liquid of the waste liquid treatment equipment at the second time based on the second data acquired in the data re-acquisition step and the prediction model for predicting the property of the treated waste liquid.

(Prediction model creation unit 117) The prediction model creation unit 117 is configured to be able to execute a prediction model creation step. In the prediction model creation step, the prediction model creation unit 117 creates or updates a prediction model used in the aforementioned waste liquid prediction value output step or the treated waste liquid prediction value output step, etc.

(Memory management unit 118) The memory management unit 118 is configured to execute a memory management step. In the memory management step, the memory management unit 118 is configured to manage various information that needs to be stored and is associated with the information processing system 100 of this embodiment. Typically, the memory management unit 118 is configured to store information input from the factory PL1 or the factory PL2 to the information processing device 1 in a memory area. The memory area is exemplified by the memory unit 12 of the information processing device 1 or the memory units of various terminals, but the memory area is not necessarily within the information processing system 100, and the memory management unit 118 can also manage to store various information in an external memory device, etc.

3. Details of information processing In Section 3, the information processing method performed by the information processing device 1 etc. is described with reference to an activity diagram etc.

(Applicable objects) First, the applicable objects of the information processing device 1 of this embodiment will be described. As described above, the information processing system 100 (information processing device 1) of this embodiment is used for the operation method of the waste liquid treatment equipment or the method of predicting the waste liquid after treatment of the waste liquid treatment equipment, but the type of waste liquid described here can be appropriately set. That is, the waste liquid supplied from the product production process corresponds to the type of the product production process, which can be water-based waste liquid or oil-based waste liquid. That is, regarding the factory PL1 that executes the product production process in this embodiment, the types of products produced are not limited, and it can be assumed that it is a paper mill, a steel mill, a power plant, an oil plant, a chemical plant, and other well-known factories. In the following, assuming that the waste liquid from the product production process is a water system, the operation method of the waste liquid treatment equipment and the method of predicting the waste liquid after treatment by the waste liquid treatment equipment are described.

(Information processing flow (operation method of waste liquid treatment equipment)) The following uses FIG. 4 and the like to explain the flow of information processing performed by the information processing device 1 and the like of this embodiment. FIG. 4 is an activity diagram showing the information processing flow using the information processing device 1 and the like.

First, in the operating method of this embodiment, the data acquisition unit 111 acquires first data including product production process data in a product production process at a first time (activity A101).

The first data here includes the product production process data of the product production process in the first time, and the product production process data includes the production volume of the product, the product type, the drugs used and their amounts, the amount of waste liquid treated, the control parameters in the factory PL1, etc.

The data is obtained by, for example, the communication unit 15 obtaining various information (analysis data, etc.) from sensors or instruments configured in the factory PL1. That is, if it is the production volume of the product, the data acquisition unit 111 obtains the weight of the produced product when weighing as at least a part of the first data to achieve the activity. The data (data group) constituting the first data can be quantitative data or qualitative data. When using qualitative parameters, numerical values can also be assigned and treated as quantitative data.

Regarding such product production process data, the following describes specific examples of various parameters in the papermaking process using a water system in the product production process. Examples of these various parameters include water quality parameters, control parameters, and result parameters.

As water quality parameters, there can be listed the pH (acidity and alkalinity) of the water system, electrical conductivity, redox potential, zeta potential, turbidity, temperature, foam height, biochemical oxygen demand (BOD), chemical oxygen demand (COD (e.g. COD _Mn , COD _Cr )), absorbance (e.g. UV (ultraviolet) absorbance), color (e.g. RGB value), drug residue concentration, particle size distribution, degree of agglomeration, amount of foreign matter, foaming area on the water surface, stain area in the water, amount of bubbles, amount of glucose, amount of organic acid, amount of starch, amount of calcium, total chlorine, amount of free chlorine, amount of dissolved oxygen, cation demand, amount of hydrogen sulfide, amount of hydrogen peroxide, and microbial respiration rate.

As control parameters, there can be listed the operating speed of the papermaking machine (papermaking speed), the filter cloth rotation speed of the raw material dehydrator, the filter cloth rotation speed of the washing machine, the amount of chemical addition relative to the water system, the amount of chemical addition relative to the raw materials added in the water system, the amount of chemical addition relative to the water system related equipment, the amount of steam for heating, the temperature of steam for heating, the steam pressure for heating, the flow from the seed box, the pressing pressure of the pressing part, the felt vacuum pressure of the pressing part, the mixing ratio of papermaking raw materials, the amount of damaged paper in papermaking raw materials, the mesh of the screen of papermaking raw materials, the gap distance between the rotor and the stator of the pulping machine, the freeness and the pulping degree, etc. Examples of "water-related equipment" include papermaking machine threads or felts to which chemicals are directly added.

As result parameters, there can be cited white water concentration, steam amount in the equipment for manufacturing paper products, steam temperature in the equipment for manufacturing paper products, steam pressure in the equipment for manufacturing paper products, paper break period in the step, freeness, beating degree, air exposure, etc. Among them, as the steam amount in the equipment for manufacturing paper products, for example, the steam amount of the paper machine dryer, the steam amount of the kraft pulp black liquor evaporator, the steam amount of the black liquor heater of the kraft pulp digestion kettle, and the steam amount blown into the pulp raw material or for heating white water can be used.

The first data may further include information related to predetermined parameters of the product. Here, the predetermined parameters of the product are typically analytical values related to the product, such as the completion status or quality of the product (such as product purity, impurities contained, analytical values from machines, etc.). Such predetermined parameters of the product can be obtained from various sensors configured in the factory PL1 through the communication unit 15, or can be obtained based on the content of the quality guarantee issued by the factory PL1.

In accordance with the above description, if we explain specific examples of various parameters of the papermaking process using a water system in the product production process, as predetermined parameters of such products, we can cite the unit weight of the paper product (basis weight), yield rate, moisture content of the paper product, thickness of the paper product, ash concentration in the paper product, type of defects in the paper product, number of defects in the paper product, etc.

In the operation method of this embodiment, after the first data is obtained in this manner, a predicted value related to the property of the waste liquid from the product production process at a second time after the first time is output based on the first data and a prediction model for predicting the property of the waste liquid (activity A102).

In this activity, the prediction model is a model created by associating the past product production process data in the product production process with the data related to the properties of the waste liquid discharged at that time. Here, this prediction model is a model that models the relationship between the performance of the product production process and the properties of the waste liquid discharged at that time in advance, but as this model, for example, it can be a function or a lookup table that represents the relationship between the two, or it can be a learned model that has learned the relationship between the two.

Such a prediction model can be analyzed based on known analytical methods for the relationship between past product production process data and data related to the properties of wastewater discharged at that time in the product production process. Typically, regression analysis methods (linear model, generalized linear model, generalized linear mixed model, ridge regression, LASSO (least absolute shrinkage and selection operator) regression, elastic net, support vector regression, projection pursuit regression, etc.), time series analysis (VAR (vector autoregression model) model, SVAR (structural VAR) model, ARIMAX model, SARIMAX model, state space model, etc.), decision trees (decision tree, regression tree, random forest, XGBoost, etc.), neural networks (simple perceptron, multi-layer perceptron, DNN (Deep Neural Network), CNN (Convolution Neural Network), RNN (Recurrent Neural Network) can be used. Network; recurrent neural network), LSTM (Long Short-Term Memory), Bayes (naive Bayes), clustering (k-means, k-means++, etc.), comprehensive learning (Boosting, AdaBoost, etc.), etc. are analyzed to obtain the desired prediction model. In addition, although the prediction model creation is performed by the prediction model creation unit 117, it is not limited to this. Such a prediction model can also be created outside the information processing system 100, and the operation method of this embodiment can be executed by installing the creation in the information processing device 1, etc. In addition, the prediction model can also be configured as a model that can be updated before executing the waste liquid prediction value output step. In this case, the prediction model creation unit 117 may also be configured to sequentially update the prediction model in accordance with the accumulation of wastewater treatment performance.

In addition, the prediction model outputs a prediction value related to the properties of the waste liquid at a second time after the first time, but the prediction model can also be configured to predict the change (deterioration) of the waste liquid over time. In addition, when predicting such a change (deterioration) over time, the environment (temperature, weather) in which the information processing system 100 exists can also be considered as reference information to improve the prediction accuracy. According to the use of the information processing system 100 of this embodiment, the first time and the second time can also be basically simultaneous.

Here, the properties of the discharged wastewater associated with the prediction model can be appropriately set. When the wastewater is a water system, various items of the aforementioned water quality parameters can be cited.

In addition, the prediction model may be a model created by further associating the predetermined parameters of the product produced in the product production process. That is, in addition to the past product production process data in the product production process and the data related to the properties of the waste liquid discharged at this time, the predetermined parameters of the product produced in the product production process may be further associated to create the prediction model. When the first data acquired by the data acquisition unit 111 includes the predetermined parameters of the product, by applying the prediction model associated with the predetermined parameters of the product, it can contribute to the improvement of the prediction accuracy of this activity.

Next, in the operation method of this embodiment, the operation condition parameters of the waste liquid treatment equipment are set based on the predicted value related to the property of the waste liquid output in the waste liquid predicted value output step (activity A103).

In a typical implementation, the operation condition setting unit 113 of the information processing device 1 transmits various information (signals, etc.) to various machines configured in the plant PL2 via the communication unit 15, thereby achieving the activity. More specifically, the operation condition setting unit 113 sets the property of the waste liquid to a level that can be discharged from the plant PL2, and controls so that the plant PL2 operates under the condition. For example, if the pH of the waste liquid supplied from the plant PL1 is predicted to be different from the normal value, the amount of the neutralizer used in the plant PL2 can be adjusted to an appropriate amount. Similarly, when it is predicted that the chemical oxygen demand (COD) value of the wastewater supplied from plant PL1 will become higher than usual, the dissolved oxygen concentration and sludge management concentration in the biological treatment step performed in plant PL2 can be set to an appropriate range. In addition, the operating condition setting unit 113 can set various conditions such as the treatment temperature conditions in plant PL2, the humidity conditions in the plant, and the stirring conditions of the stirring tank.

The waste liquid treated in this way is appropriately discharged from the plant PL2. For example, if the waste liquid treated in the plant PL2 is water, it can be discharged into a river etc. after a final inspection of the water quality etc.

(Information processing flow (method for predicting the properties of wastewater after treatment)) The following uses FIG. 5 and the like to explain the flow of information processing performed by the information processing device 1 and the like of this embodiment. FIG. 5 is an activity diagram showing the flow of information processing using the information processing device 1 and the like. In addition, since this prediction method also has some overlaps with the description of the aforementioned operation method, the following description will focus on the differences.

First, in the prediction method of this embodiment, the data acquisition unit 111 acquires second data, which includes product production process data in the product production process at a first time and operating condition parameters to be executed by the waste liquid treatment equipment (activity A201).

The product production process data included in the second data may be the same as the product production process data in the aforementioned prediction method, and thus the description thereof is omitted here. In addition, the operating condition parameters included in the second data may also be the same as the operating condition parameters in the aforementioned prediction method, and thus the description thereof is omitted here.

In the prediction method of this embodiment, the data acquisition unit 111 can also be configured to set restrictive conditions for a part of the operating condition parameters to be executed by the waste liquid treatment equipment. If combined with a typical example, the restrictive conditions can cite the operating limit value, cost, environmental load limit and other conditions of the waste liquid treatment equipment. It can be said that the prediction method of this embodiment can propose the best treatment specifications while being subject to such certain restrictions. Specifically, when setting the operating condition parameters consistent with the target value, as a cost condition, such as the amount of drug used and the environmental load condition, the restrictive conditions such as the amount of dilution water used, the amount of drug used, the pump operating conditions, the aeration amount, etc. can be set, so that the best operating conditions can be proposed within the restriction range.

The second data may also include information related to predetermined parameters of the product. The predetermined parameters of the product that can be included in the second data may be the same as the predetermined parameters of the product in the aforementioned prediction method, so the description thereof is omitted here.

The second data may also include information related to the temperature of the waste liquid and/or the change in temperature. That is, by increasing the number of parameters that can be included in the second data in this way, the accuracy of predicting the properties of the waste liquid after treatment can be improved. The details of the treatment will be described later.

In the prediction method of this embodiment, after the second data is obtained, the treated waste liquid prediction value output unit 114 outputs a prediction value related to the property of the treated waste liquid of the waste liquid treatment equipment at a second time after the first time based on the second data and the prediction model for predicting the property of the treated waste liquid (activity A202).

In this activity, the prediction model is created by associating the past product production process data, the data related to the properties of the waste liquid discharged at that time, the operating condition parameters of the waste liquid treatment equipment for treating the discharged waste liquid at that time, and the properties of the waste liquid after treatment.

To explain the difference from the aforementioned operation method, the prediction model used in this embodiment is characterized in that, in addition to the past product production process data in the product production process and the data related to the properties of the waste liquid discharged at that time, it is also related to the operating condition parameters for treating the waste liquid discharged by the waste liquid treatment equipment and the properties of the waste liquid after treatment.

That is, in such a prediction model, since it is a model created by associating at least these four parameters, it can be said that after the waste liquid treatment equipment actually treats the waste liquid, it is easy to predict the properties of the treated waste liquid with high accuracy. In addition, the prediction model can also be configured to be a model that can be updated before executing the step of outputting the predicted value of the treated waste liquid.

As with the aforementioned operation method, the model may be a model created by further associating predetermined parameters of the product produced in the product production process. In this case, it is easy to predict the properties of the treated wastewater with higher accuracy.

Furthermore, the prediction model can also be a model created by further associating the temperature and/or temperature transition of the wastewater with the corresponding biological treatment capacity. That is, since the aforementioned second data can include information related to the temperature and/or temperature transition of the wastewater, by using such a prediction model, it is possible to perform a prediction that takes into account the changes in biological treatment capacity in each season. In a typical example, in summer, due to the increase in wastewater temperature (especially water temperature), the operation status of the biological treatment device sometimes becomes insufficient, but considering the transition of the wastewater temperature (especially water temperature) at this time or the operating conditions of the temperature management equipment before and after, etc., it is possible to set the optimal operating condition parameters for the biological treatment device. In addition, the data of the temperature of the waste liquid (waste water) associated with the prediction model can be based on the temperature of the waste liquid in the plant PL1 and/or the plant PL2, the temperature of the waste liquid in the biological treatment device (and the steps before and after it), or the meteorological data.

By outputting the above-mentioned predicted value of the treated wastewater, the wastewater treated in Plant PL2 can be managed. As described in the above operation method, the treated wastewater can also be discharged from Plant PL2 as appropriate. For example, if the treated wastewater treated in Plant PL2 is water, it can be discharged into a river after a final inspection of the water quality.

In addition, in the prediction method of this embodiment, the data re-acquisition unit 115 can also be configured to obtain second data based on re-setting the operating condition parameters to be executed by the waste liquid treatment equipment when the predicted value related to the property of the treated waste liquid output in the treated waste liquid predicted value output step does not fall within the predetermined range (this step can also be called a "data re-acquisition step"). In addition, the treated waste liquid predicted value re-output unit 116 may also be configured to re-output a predicted value related to the property of the treated waste liquid of the waste liquid treatment equipment at the second time based on the second data acquired in the data re-acquisition step and the prediction model for predicting the property of the treated waste liquid (this step may also be referred to as a "treated waste liquid predicted value re-output step").

As shown in the activity diagram of FIG5 , it is possible to configure such that, when a certain parameter is not within a predetermined range (for example, a value that is not suitable for discharge into a river, etc.) while temporarily outputting the predicted value of the treated wastewater, the second data is re-acquired. That is, it is possible to configure such that the same operation as the aforementioned activity A201 is performed, but for convenience, this operation is referred to as a "data re-acquisition step" in this specification. As described above, based on the second data obtained in the data re-acquisition step, the predicted value of the treated wastewater can be output, and the repetition of this processing can be repeated until the managed parameter is within a predetermined range. Typically, the data re-acquisition step can be performed while changing the operating condition parameters related to the wastewater treatment. That is, repeating the process until the managed parameters are within the predetermined range essentially has the ability to rationalize the operating condition parameters related to the wastewater treatment.

As examples of parameters that do not fall within the predetermined range, the aforementioned water quality parameters are illustrated, but they can be appropriately set according to the type of waste liquid.

As described above, according to this embodiment, a method of operating a waste liquid treatment facility that can flexibly cope with changes in the properties of waste liquid can be provided. According to such an embodiment, the investment level in waste liquid treatment facilities can be reduced, and effects such as reduction in environmental load can also be expected.

4. Variations In Section 4, variations of the information processing method of the aforementioned information processing device 1, etc. will be described.

The above-mentioned implementation is described as the structure of the information processing device 1, but a computer program can also be provided to enable the computer to function as each part of the information processing device 1.

In the above-mentioned embodiment, the information processing device 1 is applied to the factory PL1 and the factory PL2 connected by the liquid line LL1, but the two factories do not necessarily need to be connected by the liquid line LL1, and the waste liquid can be transferred from the factory PL1 to the factory PL2 by rotation, etc. In addition, the business entity that owns the factory PL1 and the business entity that owns the factory PL2 can be the same or different.

Although the above-mentioned embodiments illustrate an operation method or a prediction method using a prediction model, the information associated with creating a prediction model is not limited thereto. That is, the prediction model used in the present embodiment can be associated with various other conditions, such as meteorological conditions, conditions related to the region, conditions related to the age of the equipment, etc.

In summary, the present invention meets the requirements for invention patents, and a patent application is filed in accordance with the law. However, although the present invention has been described above with various implementations, it is not intended to limit the present invention. Any person with ordinary knowledge in the relevant technical field can make various omissions, substitutions and changes without departing from the spirit and scope of the present invention. The implementations and their variations are included in the scope and purpose of the invention, and are included in the invention described in the scope of the invention patent application and its equivalent.

1: Information processing device 2: Communication line 10: Communication bus 11: Control unit 12: Memory unit 13: Input unit 14: Display unit 15: Communication unit 100: Information processing system 111: Data acquisition unit 112: Waste liquid prediction value output unit 113: Operation condition setting unit 114: Treated waste liquid prediction value output unit 115: Data re-acquisition unit 116: Treated waste liquid prediction value re-output unit 117: Prediction model creation unit 118: Memory management unit LL1: Liquid line PL1: Factory PL2: Factory

FIG1 is a diagram showing the overall structure of the information processing system 100. FIG2 is a diagram showing the hardware structure of the information processing device 1. FIG3 is a functional block diagram showing the functions of the information processing device 1. FIG4 is an activity diagram showing the process of performing information processing using the information processing device 1, etc. FIG5 is an activity diagram showing the process of performing information processing using the information processing device 1, etc.

1: Information processing device

2: Communication lines

100: Information processing system

LL1: Liquid line

PL1: Factory

PL2: Factory

Claims (11)

A method for operating a waste liquid treatment device for treating waste liquid from a product production process, comprising: a data acquisition step, a waste liquid prediction value output step, and an operation condition setting step; in the data acquisition step, first data including product production process data in the product production process at a first time is acquired, in the waste liquid prediction value output step, based on the first data and a prediction model for predicting the properties of the waste liquid, a prediction value related to the properties of the waste liquid from the product production process at a second time after the first time is output, here, the prediction model is a model created by associating the past product production process data in the product production process with data related to the properties of the waste liquid discharged at this time, In the aforementioned operation condition setting step, the operation condition parameters of the aforementioned waste liquid treatment equipment are set based on the predicted value related to the properties of the aforementioned waste liquid output in the aforementioned waste liquid predicted value output step. The method for operating a waste liquid treatment device as recited in claim 1, wherein the prediction model is configured to be a model that can be updated before executing the waste liquid prediction value output step. The method for operating a waste liquid treatment device as described in claim 1 or 2, wherein the prediction model is a model created by further associating predetermined parameters of a product produced in the product production process, and the first data obtained in the data acquisition step further includes information related to the predetermined parameters of the product. A method for predicting the properties of waste liquid after treatment by a waste liquid treatment device that treats waste liquid from a product production process, comprising: a data acquisition step and a step of outputting a predicted value of the treated waste liquid; in the data acquisition step, second data including product production process data in the product production process at a first time and operating condition parameters to be executed by the waste liquid treatment device are acquired, in the step of outputting the predicted value of the treated waste liquid, based on the second data and a prediction model for predicting the properties of the treated waste liquid, a predicted value related to the properties of the treated waste liquid of the waste liquid treatment device at a second time after the first time is output, Here, the prediction model is a model created by associating the past product production process data in the product production process, the data related to the properties of the waste liquid discharged at this time, the operating condition parameters of the waste liquid treatment equipment for treating the discharged waste liquid at this time, and the properties of the waste liquid after treatment. The method for predicting the properties of treated waste liquid as described in claim 4 also comprises: a data re-acquisition step and a treated waste liquid predicted value re-output step, in the aforementioned data re-acquisition step, when the predicted value related to the properties of the aforementioned treated waste liquid output in the aforementioned treated waste liquid predicted value output step does not fall within the predetermined range, the aforementioned second data is obtained based on re-setting the operating condition parameters to be executed by the aforementioned waste liquid treatment equipment, In the aforementioned step of re-outputting the predicted value of the treated waste liquid, based on the aforementioned second data obtained in the aforementioned step of re-obtaining data and the aforementioned prediction model for predicting the properties of the treated waste liquid, the predicted value related to the properties of the treated waste liquid of the aforementioned waste liquid treatment equipment at the aforementioned second time is re-outputted. A method for predicting properties of treated wastewater as recited in claim 4 or 5, wherein the prediction model is configured to be updateable before executing the step of outputting the predicted value of the treated wastewater. A method for predicting the properties of treated wastewater as recited in any one of claims 4 to 6, wherein the prediction model is a model created by further associating the temperature and/or temperature transition of the wastewater with the corresponding biological treatment capacity, and the second data obtained in the data acquisition step further includes information related to the temperature and/or temperature transition of the wastewater. A method for predicting the properties of treated wastewater as recited in any one of claims 4 to 7, wherein the data acquisition step is configured to set limiting conditions for a portion of the operating condition parameters to be performed by the wastewater treatment equipment. A method for predicting the properties of treated wastewater as recited in any one of claims 4 to 8, wherein the prediction model is a model created by further associating predetermined parameters of a product produced in the product production process, and the second data obtained in the data acquisition step further includes information related to the predetermined parameters of the product. An operation system of a waste liquid treatment equipment for treating waste liquid from a product production process, comprising: a data acquisition unit, a waste liquid prediction value output unit, and an operation condition setting unit; the data acquisition unit acquires first data including product production process data in the product production process at a first time, the waste liquid prediction value output unit outputs a prediction value related to the property of the waste liquid from the product production process at a second time after the first time based on the first data and a prediction model for predicting the property of the waste liquid, here, the prediction model is a model created by associating the past product production process data in the product production process with data related to the property of the waste liquid discharged at this time, The operating condition setting unit sets the operating condition parameters of the waste liquid treatment equipment based on the predicted value related to the property of the waste liquid output by the waste liquid predicted value output unit. A prediction system for predicting the properties of waste liquid after treatment by a waste liquid treatment device that treats waste liquid from a product production process, comprising: a data acquisition unit and a treated waste liquid prediction value output unit; the data acquisition unit acquires second data including product production process data in the product production process at a first time and operating condition parameters to be executed by the waste liquid treatment device; the treated waste liquid prediction value output unit outputs a prediction value related to the properties of the treated waste liquid by the waste liquid treatment device at a second time after the first time based on the second data and a prediction model for predicting the properties of the treated waste liquid; Here, the prediction model is a model created by associating the past product production process data in the product production process, the data related to the properties of the waste liquid discharged at this time, the operating condition parameters of the waste liquid treatment equipment when treating the discharged waste liquid at this time, and the properties of the waste liquid after treatment.