System and method for artificial intelligence hydraulic centrifugal dehydration

Abstract

An artificial intelligence hydraulic centrifugal separation system and method, and a program stored on a computer-readable recording medium to perform the same are provided. The artificial intelligence hydraulic centrifugal separation system receives sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information, generates PID (Proportional-Integral-Differential) control information using the sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information, and controls the rotational speed and hydraulic pressure of the concentrator and dewatering machine using the PID control information.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence hydraulic centrifugal separation system and method, and more specifically, to an artificial intelligence hydraulic centrifugal separation system and method capable of constructing big data for statistical analysis, prediction, and classification by building big data in accordance with seasonal sludge characteristics and concentration changes, monitoring data on the performance of the coagulant input amount relative to the sludge input amount, moisture content, and solid recovery rate, storing accurate data values ​​through information collection, and setting target determination values ​​through an analysis type system. Background Technology

[0002] In belt or filter press type concentration or dewatering operations among concentration and dewatering facilities, problems such as increased unnecessary operating time, increased cake processing costs due to inaccurate operating data, reduced operational efficiency, and excessive use of chemicals occur because the operator currently measures changes in the characteristics and concentration of the incoming sludge, as well as the amount of sludge or coagulant added, visually or manually.

[0003] Although automated systems are being established for centrifugal concentrators and centrifugal dewaterers, operational convenience is degraded due to a lack of data on various conditions, and issues such as increased cake processing costs resulting from higher moisture content and discharge water quality problems are occurring.

[0004] Existing technologies, which rely on the technical expertise of operators of concentration and dewatering facilities, are currently being operated based on inaccurate data that makes it difficult to cope with real-time changes in sludge concentration and characteristics caused by irregular seasonal changes.

[0005] Consequently, the reduced ability to cope with external changes, such as sludge changes, leads to increased chemical usage or reduced processing capacity, and increased unnecessary operating time, which causes problems such as excessive processing costs due to increased cake moisture content.

[0006] Due to these problems, there is a need to develop artificial intelligence (AI) centrifugal concentrator and centrifugal dewatering technology that automatically operates chemical dosage, concentrator operating conditions, and dewatering operating conditions by analyzing big data such as influent sludge concentration, characteristics, and flow rate, and transmitting optimal data values ​​to concentration and dewatering facilities through PID (Proportional-Integral-Differential) control in response to the rapidly changing climate crisis. The problem to be solved

[0007] The present invention aims to address these technical challenges by providing an artificial intelligence hydraulic centrifugal separation system and method capable of generating PID control information using sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and separated liquid information.

[0008] Another technical objective of the present invention is to provide an artificial intelligence hydraulic centrifugal separation system and method capable of controlling the rotational speed and hydraulic pressure of a concentrator and a dehydrator using PID control information. means of solving the problem

[0009] As a means to achieve the above-mentioned purpose, the configuration of the present invention comprises: one or more processors; and one or more memories in which instructions are stored to cause the one or more processors to perform calculations when executed by the one or more processors, wherein the one or more processors receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information, generate PID (Proportional-Integral-Differential) control information using the sludge information, the coagulant information, the concentrator information, the dewatering machine information, the cake information, and the dewatering liquid information, and control the rotational speed and hydraulic pressure of the dewatering machine using the PID control information.

[0010] The configuration of the present invention is such that the sludge information includes at least one of sludge concentration, sludge input amount, and sludge characteristics; the coagulant information includes at least one of coagulant dissolution rate, coagulant input amount, and coagulant coagulation state; the concentrator information includes at least one of bowl rotation speed, scroll rotation speed, and hydraulic pressure; the dewatering machine information includes at least one of cake moisture content, inflow rate, and solid recovery rate; the cake information includes at least one of cake moisture content and cake generation amount information; and the separated liquid information may include at least one of suspended solids information and separated liquid recovery rate information.

[0011] The configuration of the present invention is such that one or more processors transmit sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information to a generative artificial intelligence model server, and receive PID control information from the generative artificial intelligence model server; the generative artificial intelligence model server analyzes data on sludge condition, hydraulic pressure, temperature, and coagulant concentration using a generative artificial intelligence model, and thereby predicts key future variables such as energy consumption, machine load, sludge characteristics, and concentration; based on the predicted future data, pre-calculates PID parameters (Kp, Ki, Kd); each PID parameter is directly output by the generative artificial intelligence model server by reflecting the expected error and system operation pattern; while the predicted PID value is applied, the difference between the actual data and the predicted value is monitored, and the generative artificial intelligence model server can immediately generate a new PID value according to the difference.

[0012] The configuration of the present invention is such that the one or more processors measure a first concentration of sludge at a first time, measure a second concentration of sludge at a second time after a predetermined time has elapsed from the first time, measure a third concentration of sludge at a third time after a predetermined time has elapsed from the second time, calculate an average concentration by averaging the first to third concentrations, calculate a first difference value between the average concentration and the first concentration, calculate a second difference value between the average concentration and the second concentration, calculate a third difference value between the average concentration and the third concentration, and if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, the amount of coagulant added is reduced by the difference between the third difference value and the second difference value, and if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, the amount of coagulant added is increased by the difference between the third difference value and the second difference value, and the first If the difference value is smaller than the second difference value and the second difference value is larger than the third difference value, the amount of coagulant added is maintained; and if the first difference value is larger than the second difference value and the second difference value is smaller than the third difference value, the amount of coagulant added can be increased by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value.

[0013] The configuration of the present invention is such that the one or more processors measure a first cake moisture content at a first time, measure a second cake moisture content at a second time after a predetermined time has elapsed from the first time, measure a third cake moisture content at a third time after a predetermined time has elapsed from the second time, calculate an average moisture content by averaging the first to third cake moisture contents, calculate a first difference value between the average moisture content and the first cake moisture content, calculate a second difference value between the average moisture content and the second cake moisture content, calculate a third difference value between the average moisture content and the third cake moisture content, and if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, the rotational speed of the dehydrator is reduced by the difference between the third difference value and the second difference value, and if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, the rotational speed of the dehydrator is increased by the difference between the third difference value and the second difference value. If the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value, the rotation speed of the dehydrator is maintained; and if the first difference value is larger than the second difference value and the second difference value is smaller than the third difference value, the rotation speed of the dehydrator can be increased by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value.

[0014] As another configuration of the present invention, an artificial intelligence hydraulic centrifugal dewatering method using an artificial intelligence hydraulic centrifugal separation system comprising: one or more processors; and one or more memories in which instructions are stored to cause the one or more processors to perform calculations when executed by the one or more processors, may include the steps of: receiving sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information by the one or more processors; generating PID (Proportional-Integral-Differential) control information by the one or more processors using the sludge information, the coagulant information, the concentrator information, the dewatering machine information, the cake information, and the dewatering liquid information; and controlling the rotational speed and hydraulic pressure of the dewatering machine by the one or more processors using the PID control information.

[0015] The composition of the present invention comprises: a step of measuring a first concentration of sludge at a first time; a step of measuring a second concentration of sludge at a second time after a predetermined time has elapsed from the first time; a step of measuring a third concentration of sludge at a third time after a predetermined time has elapsed from the second time; a step of averaging the first to third concentrations to calculate an average concentration; a step of calculating a first difference value between the average concentration and the first concentration; a step of calculating a second difference value between the average concentration and the second concentration; a step of calculating a third difference value between the average concentration and the third concentration; a step of, if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, reducing the amount of coagulant added by the difference between the third difference value and the second difference value; and, if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, increasing the amount of coagulant added by the difference between the third difference value and the second difference value. The method may further include a step of maintaining the amount of coagulant injected when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value; and a step of increasing the amount of coagulant injected by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value when the first difference value is larger than the second difference value and the second difference value is smaller than the third difference value.

[0016] The configuration of the present invention comprises: a step of measuring a first cake moisture content at a first time; a step of measuring a second cake moisture content at a second time after a predetermined time has elapsed from the first time; a step of measuring a third cake moisture content at a third time after a predetermined time has elapsed from the second time; a step of averaging the first to third cake moisture contents to calculate an average moisture content; a step of calculating a first difference value between the average moisture content and the first cake moisture content; a step of calculating a second difference value between the average moisture content and the second cake moisture content; a step of calculating a third difference value between the average moisture content and the third cake moisture content; a step of, if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, decreasing the rotational speed of the dehydrator by the difference between the third difference value and the second difference value; and, if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, increasing the rotational speed of the dehydrator by the difference between the third difference value and the second difference value. The method may further include the step of maintaining the rotation speed of the dehydrator when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value; and the step of increasing the rotation speed of the dehydrator by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value when the first difference value is larger than the second difference value and the second difference value is smaller than the third difference value.

[0017] As another configuration of the present invention, a computer program stored in a computer-readable recording medium that can be executed in a computer comprising: one or more processors; and one or more memories in which instructions are stored to cause the one or more processors to perform calculations when executed by the one or more processors, may be stored in a computer-readable recording medium that enables the following steps to be performed by the one or more processors: receiving sludge information, coagulant information, dewatering machine information, cake information, and dewatering liquid information; generating PID (Proportional-Integral-Differential) control information using the sludge information, the coagulant information, the dewatering machine information, the cake information, and the dewatering liquid information by the one or more processors; and controlling the rotational speed and hydraulic pressure of the dewatering machine using the PID control information by the one or more processors. Effects of the invention

[0018] The present invention has the effect of collecting and analyzing dewatering machine operation data, sludge flow rate data, chemical flow rate data, and sludge polymer coagulation reaction data.

[0019] In addition, the present invention has the effect of performing real-time analysis of dehydrator operation status data from a dehydrator control panel, a PLC CONTROLLER, and a CVC 650 CONTROLLER, and transmitting dehydrator operation control data.

[0020] In addition, the present invention has the effect of being able to perform analysis of moisture content measurement data and extraction liquid measurement data. Brief explanation of the drawing

[0021] FIG. 1 is a configuration diagram of an AI cloud server control panel according to an embodiment of the present invention. FIGS. 2a and 2b are exemplary diagrams showing the pyramidal correlation of parameters according to an embodiment of the present invention. FIG. 3 is an operation flow diagram of an artificial intelligence hydraulic centrifugal separation system according to an embodiment of the present invention. FIG. 4 is an exemplary diagram showing the configuration of an artificial intelligence hydraulic centrifugal separation system according to an embodiment of the present invention. FIG. 5 is an exemplary diagram showing the configuration of an artificial intelligence hydraulic centrifugal separation system according to an embodiment of the present invention. FIG. 6 is an exemplary diagram showing the configuration of a server according to an embodiment of the present invention. FIG. 7 is a diagram illustrating the learning of a neural network according to an embodiment of the present invention. FIG. 8 is a flowchart showing the procedure of an artificial intelligence hydraulic centrifugal dehydration method according to an embodiment of the present invention. Specific details for implementing the invention

[0022] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. However, the technical concept of the present invention is not limited to the embodiments described herein and may be embodied in other forms. The embodiments introduced herein are provided to ensure that the disclosed content is thorough and complete, and to ensure that the concept of the present invention is sufficiently conveyed to those skilled in the art.

[0023] In this specification, when a component is mentioned as being on another component, it means that it may be formed directly on the other component or that a third component may be interposed between them.

[0024] In addition, in describing the present invention below, if it is determined that a detailed description of related known functions or configurations could unnecessarily obscure the essence of the invention, such detailed description will be omitted.

[0025] According to the present invention, big data can be constructed in accordance with seasonal changes in sludge characteristics and concentration, and data on the performance of the coagulant input amount, moisture content, and solid recovery rate relative to the sludge input amount can be monitored. Accurate data values ​​are stored through information collection, and target determination values ​​are set through an analysis TYPE SYSTEM to construct big data for statistical analysis, prediction, and classification.

[0026] According to the present invention, the amount of chemical input is automatically adjusted to match the sludge characteristics and concentration that change in real time through a determined value based on big data, and further advanced, the rotation speed of the dewatering machine is automatically adjusted to achieve optimal operational efficiency.

[0027] According to the present invention, by utilizing rapid and high-accuracy data and operating automatically with artificial intelligence (AI), it is possible to reduce cake processing costs by reducing moisture content, reduce coagulant chemical purchase costs, and minimize maintenance costs by reducing power consumption through the elimination of unnecessary operating situations, while improving the quality of discharged water.

[0028] The following table shows the subjects of analysis according to the embodiments of the present invention.

[0029]

[0030] According to the present invention, data is stored on a daily basis for data analysis, and all data can be performed on a basis of a concentrator and a dehydrator.

[0031] FIG. 1 is a configuration diagram of an AI cloud server according to an embodiment of the present invention.

[0032] As illustrated in FIG. 1, the AI ​​cloud server may include an AI cloud server panel, an AI-dedicated workstation server and data logger, an AI-dedicated PLC controller, an AI-dedicated data analysis collection program, and an uninterruptible power supply (UPS).

[0033] The values ​​of the major and minor categories in Table 1 can be collected through the AI ​​cloud server.

[0034] The AI ​​cloud server stores three years of sub-category data subject to analysis at the water treatment plant and can calculate monthly average values. For example, it can calculate the average sludge concentration value from January to December. Daily sub-category values ​​can be collected through trial operation after applying dewatering machine data using the initial collected data mentioned above. Target values ​​can be set after calculating the average value during the initial collection stage.

[0035] The AI ​​cloud server can set a target moisture content of 95% for the concentrator and 77% for the dewatering machine. The moisture content is determined by the rotational speed and hydraulic pressure of the concentrator and dewatering machine, and external factors such as the input sludge concentration and input amount, as well as the coagulation state and input amount of the coagulant, can be indicated. At the target moisture content, the suspended solids in the separated liquid will be low, and the solid recovery rate can be high.

[0036] FIGS. 2a and 2b are exemplary diagrams showing the pyramidal correlation of parameters according to an embodiment of the present invention.

[0037] As illustrated in FIGS. 2a and 2b, a pyramid-shaped correlation can be constructed starting with the cake moisture content or the concentrated moisture content. For the process from the concentration, flow rate, and characteristics of the initial input sludge to the moisture content of the dewatered cake, parameters must be specified for each element.

[0038] In computer programming, a parameter is a special type of variable that is one of several data provided as input to a subroutine, such as a function. Here, the various data provided as input to a subroutine are called arguments.

[0039] FIG. 3 is an operation flow diagram of an artificial intelligence hydraulic centrifugal separation system according to an embodiment of the present invention.

[0040] As illustrated in FIG. 3, the artificial intelligence hydraulic centrifugal separation system can collect and analyze sludge storage tank concentration and chemical dissolution concentration data from the AI ​​cloud server. Additionally, the AI ​​cloud server can collect and analyze dewatering machine operation data, sludge flow rate data, chemical flow rate data, and sludge polymer coagulation reaction data. Furthermore, the AI ​​cloud server can perform real-time analysis of dewatering machine operation status data from the dewatering machine control panel, PLC CONTROLLER, and CVC 650 CONTROLLER, and transmit dewatering machine operation control data. The AI ​​cloud server can also analyze moisture content measurement data and leachate measurement data.

[0041] FIG. 4 is an exemplary diagram showing the configuration of an artificial intelligence hydraulic centrifugal separation system according to an embodiment of the present invention.

[0042] As illustrated in FIG. 4, the artificial intelligence hydraulic centrifugal separation system may include a big data analysis program, a chemical stock solution tank, a sludge storage tank, a sludge supply pump, a PID automatic control program, an AI centrifugal concentrator, a concentration tank, an AI centrifugal dewatering machine, a PLC, a CVC650 concentration control program, etc.

[0043] FIG. 5 is an exemplary diagram showing the configuration of an artificial intelligence hydraulic centrifugal separation system according to an embodiment of the present invention.

[0044] As illustrated in FIG. 5, an artificial intelligence hydraulic centrifugal separation system (100) according to an embodiment of the present invention may include a plurality of devices (110-1, ..., 110-n), a server (120), and a database (130). According to one embodiment, the database (130) is shown as being configured separately from the server (120), but is not limited thereto, and the database (130) may be provided within the server (120). For example, the server (120) may include a plurality of artificial intelligence models for performing machine learning algorithms. According to one embodiment, the plurality of devices (110-1, ..., 110-n), the server (120), and the database (130) may be connected to communicate with each other through a network (N).

[0045] According to one embodiment, a plurality of devices (110-1,…,110-n) may include a sludge storage tank, a chemical stock tank, a sludge supply pump, a chemical dissolution & supply pump, an AI centrifugal concentrator, an AI centrifugal dewatering machine, a cake storage tank, a PID controller, a dewatering controller, etc.

[0046] The server (120) can receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information. According to one embodiment, the server (120) can receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information from a plurality of devices (110-1, ..., 110-n) through a network (N). For example, the sludge information may include at least one of sludge concentration, sludge input amount, and sludge characteristics; the coagulant information may include at least one of coagulant dissolution rate, coagulant input amount, and coagulant coagulation state; the concentrator information may include at least one of bowl rotation speed, scroll rotation speed, and hydraulic pressure; the dewatering machine information may include at least one of cake moisture content, inflow rate, and solid recovery rate; the cake information may include at least one of cake moisture content and cake generation amount information; and the dewatering liquid information may include at least one of suspended solids information and dewatering liquid recovery rate information.

[0047] The server (120) can generate PID (Proportional-Integral-Differential) control information using sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information. According to one embodiment, the server (120) can build big data in accordance with the received seasonal sludge characteristics and concentration changes, monitor data on the moisture content of the coagulant input amount relative to the sludge input amount and the solid recovery rate performance, store accurate data values ​​through information collection, and build big data for statistical analysis, prediction, and classification by setting target decision values.

[0048] The server (120) can control the rotational speed and hydraulic pressure of the concentrator and dewatering machine using the generated PID (Proportional-Integral-Differential) control information.

[0049] The server (120) automatically adjusts the amount of chemical input according to the sludge characteristics and concentration that change in real time through big data determination values, and further develops it to automatically adjust the rotation speed of the concentrator and dewatering machine to achieve optimal operational efficiency. In addition, the server (120) is automatically operated by artificial intelligence (AI) using rapid and high-accuracy data, thereby reducing cake processing costs by reducing moisture content, reducing coagulant chemical purchase costs, and reducing power consumption by eliminating unnecessary operating conditions, thereby minimizing maintenance costs and improving the discharge water quality.

[0050] The server (120) can transmit sludge information, coagulant information, concentrator information, dewatering machine information, cake information and dewatering liquid information received from a plurality of devices (110-1,…,110-n) to a generative artificial intelligence model server through a network (N).

[0051] The above-mentioned generative artificial intelligence model server analyzes data such as sludge condition, hydraulic pressure, temperature, and coagulant concentration using a generative artificial intelligence model, and through this, predicts key future variables such as energy consumption, machine load, sludge characteristics, and concentration, and pre-calculates PID parameters (Kp, Ki, Kd) based on the predicted future data, and each PID parameter is directly output by the generative artificial intelligence model server by reflecting the expected error and system operation pattern, and while the predicted PID value is applied, the difference between the actual data and the predicted value is monitored, and the generative artificial intelligence model server immediately generates a new PID (Proportional-Integral-Differential) value according to the difference.

[0052] The server (120) receives PID (Proportional-Integral-Differential) control information from the generative artificial intelligence model server through the network (N).

[0053] Additionally, the server (120) can measure the first concentration of sludge at the first time. A sludge storage tank (e.g., 110-1), which is one of the plurality of devices (110-1, ..., 110-n), can measure the first concentration of sludge at any first time and transmit it to the server (120).

[0054] The server (120) can measure the second concentration of sludge at a second time after a predetermined time has elapsed from the first time. A sludge storage tank (e.g., 110-1), which is one of a plurality of devices (110-1, ..., 110-n), can measure the second concentration of sludge at a second time after a predetermined time has elapsed from the first time and transmit it to the server (120).

[0055] The server (120) can measure the third concentration of sludge at the third time, which is the time elapsed from the second time. A sludge storage tank (110-1), which is one of a plurality of devices (110-1,…,110-n), can measure the third concentration of sludge at the third time, which is the time elapsed from the second time, and transmit it to the server (120).

[0056] The server (120) can calculate the average concentration by averaging the first to third concentrations using the following mathematical formula 1.

[0057] [Mathematical Formula 1]

[0058]

[0059] The server (120) can calculate the first difference value between the average concentration and the first concentration using the following mathematical formula 2.

[0060] [Mathematical Formula 2]

[0061]

[0062] The server (120) can calculate the second difference value between the average concentration and the second concentration using the following mathematical formula 2.

[0063] [Mathematical Formula 3]

[0064]

[0065] The server (120) can calculate the third difference value between the average concentration and the third concentration using the following mathematical formula 4.

[0066] [Mathematical Formula 4]

[0067]

[0068] The server (120) can reduce the amount of coagulant added by the difference between the third difference value and the second difference value when the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, that is, when the sludge concentration tends to decrease.

[0069] The server (120) can increase the amount of coagulant added by the difference between the third difference value and the second difference value when the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, that is, when the sludge concentration tends to increase.

[0070] The server (120) can maintain the amount of coagulant added when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value, that is, when the sludge concentration tends to increase and then decrease.

[0071] The server (120) can increase the amount of coagulant added by the difference between the first difference value and the second difference value when the first difference value is greater than the second difference value and the second difference value is smaller than the third difference value, that is, when the sludge concentration tends to decrease and then increase.

[0072] Therefore, the amount of coagulant added can be increased less than the tendency for the sludge concentration to continuously increase.

[0073] Additionally, the server (120) can measure the first cake moisture content at a first time. A cake reservoir (e.g., 110-n), which is one of the plurality of devices (110-1, ..., 110-n), can measure the first cake moisture content at any first time and transmit it to the server (120).

[0074] The server (120) can measure the second cake moisture content at a second time after a predetermined time has elapsed from the first time. A cake reservoir (e.g., 110-n), which is one of a plurality of devices (110-1, ..., 110-n), can measure the second cake moisture content at a second time after a predetermined time has elapsed from the first time and transmit it to the server (120).

[0075] The server (120) can measure the third cake moisture content at the third time after a predetermined time has elapsed from the second time. A cake reservoir (e.g., 110-n), which is one of the plurality of devices (110-1, ..., 110-n), can measure the third cake moisture content at the third time after a predetermined time has elapsed from the second time and transmit it to the server (120).

[0076] The server (120) can calculate the average moisture content by averaging the first to third cake moisture contents using the following mathematical formula 5.

[0077] [Mathematical Formula 5]

[0078]

[0079] The server (120) can calculate the first difference value between the average moisture content and the first cake moisture content using the following mathematical formula 6.

[0080] [Mathematical Formula 6]

[0081]

[0082] The server (120) can calculate the second difference value between the average moisture content and the second cake moisture content using the following mathematical formula 7.

[0083] [Mathematical Formula 7]

[0084]

[0085] The server (120) can calculate the third difference value between the average moisture content and the third cake moisture content using the following mathematical formula 8.

[0086] [Mathematical Formula 8]

[0087]

[0088] The server (120) can reduce the rotation speed of the dehydrator by the difference between the third difference value and the second difference value when the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, that is, when the cake moisture content tends to decrease.

[0089] The server (120) can increase the rotation speed of the dehydrator by the difference between the third difference value and the second difference value when the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, that is, when the cake moisture content tends to increase.

[0090] The server (120) can maintain the rotation speed of the dehydrator when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value, that is, when the cake moisture content tends to increase and then decrease.

[0091] When the first difference value is greater than the second difference value and the second difference value is smaller than the third difference value, that is, when the cake moisture content tends to decrease and then increase, the server (120) can increase the rotation speed of the dehydrator by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value.

[0092] Therefore, the rotation speed of the dehydrator can be increased less than the tendency for the cake moisture content to continuously increase.

[0093] A network (N) can perform wireless or wired communication between multiple devices (110-1, ..., 110-n), a server (120), a database (130), etc. For example, the network (N) can perform wireless communication according to methods such as LTE (long-term evolution), LTE-A (LTE Advanced), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (Wireless BroadBand), WiFi (wireless fidelity), Bluetooth, NFC (near field communication), GPS (Global Positioning System), or GNSS (global navigation satellite system). For example, the network (N) can perform wired communication according to methods such as USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), or POTS (plain old telephone service).

[0094] The database (130) can store various data. Data stored in the database (130) may include software (e.g., programs) as data acquired, processed, or used by at least one component of a plurality of devices (110-1, ..., 110-n) and a server (120). The database (130) may include volatile and / or non-volatile memory. In one embodiment, the database (130) may store sludge information, coagulant information, dewatering machine information, cake information, dewatering liquid information, etc.

[0095] In the present invention, Artificial Intelligence (AI) refers to a technology that imitates human learning ability, reasoning ability, and perceptual ability, and implements them on a computer, and may include concepts such as machine learning and symbolic logic. Machine Learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. AI technology can analyze input data as a machine learning algorithm, learn from the results of the analysis, and make judgments or predictions based on the results of the learning. Furthermore, technologies that mimic the functions of the human brain, such as cognition and judgment, by utilizing machine learning algorithms can also be understood as falling within the category of AI. For example, technological fields such as linguistic understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control may be included.

[0096] Machine learning can refer to the process of training neural network models using experience in processing data. It implies that through machine learning, computer software improves its own data processing capabilities. A neural network model is constructed by modeling the correlations between data, and these correlations can be expressed by multiple parameters. A neural network model extracts and analyzes features from given data to derive correlations between them; machine learning can be defined as the process of optimizing the model's parameters by repeating this process. For example, a neural network model can learn the mapping (correlation) between inputs and outputs for data given as input-output pairs. Alternatively, even when only input data is provided, a neural network model can derive regularities between the given data and learn those relationships.

[0097] An artificial intelligence learning model or neural network model can be designed to implement the structure of the human brain on a computer and may include multiple network nodes that have weights and simulate neurons of a human neural network. The multiple network nodes may have interconnected relationships by simulating the synaptic activity of neurons, where neurons exchange signals through synapses. In an artificial intelligence learning model, multiple network nodes may be located in layers of different depths and exchange data according to convolutional connections. The artificial intelligence learning model may be, for example, an Artificial Neural Network (ANN) or a Convolutional Neural Network (CNN). As an embodiment, the artificial intelligence learning model may be machine learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning may include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, Ada-boost, Perceptron, Genetic Programming, and Clustering.

[0098] Among these, CNNs are a type of multilayer perceptron designed to use minimal preprocessing. CNNs consist of one or more convolutional layers and standard artificial neural network layers stacked on top, additionally utilizing weights and pooling layers. Thanks to this structure, CNNs can fully utilize two-dimensional input data. Compared to other deep learning architectures, CNNs demonstrate good performance in both image and audio fields. CNNs can also be trained using standard backpropagation. CNNs have the advantage of being easier to train than other feedforward artificial neural network techniques and using a small number of parameters.

[0099] Convolutional networks are neural networks comprising sets of nodes with bounded parameters. Many computer vision tasks have been significantly improved, driven by the increased size of available training data and the availability of computational power, combined with algorithmic advancements such as discriminative linear units and dropout training. In the case of massive datasets, such as those available for many tasks today, outfitting is not critical, and increasing the network size improves test accuracy. Optimal utilization of computing resources becomes a limiting factor. To address this, distributed, scalable implementations of deep neural networks can be employed.

[0100] FIG. 6 is an exemplary diagram showing the configuration of a server according to an embodiment of the present invention.

[0101] As illustrated in FIG. 6, the server (120) may include one or more processors (122), one or more memories (124), and a transceiver (126). In one embodiment, at least one of these components of the server (120) may be omitted, or other components may be added to the server (120). Additionally or alternatively, some components may be implemented as a single or multiple entities. At least some of the components inside and outside the server (120) may be connected to each other via a system bus, GPIO (general purpose input / output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface), etc., to exchange data and / or signals.

[0102] One or more processors (122) can control at least one component of a server (120) connected to the processor (122) by running software (e.g., instructions, programs, etc.). Additionally, the processor (122) can perform various operations related to the present invention, such as computation, processing, data generation, and processing. Furthermore, the processor (122) can load data, etc. from one or more memories (124) or store it in one or more memories (124).

[0103] One or more processors (122) can receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information. According to one embodiment, the processor (122) can receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information from a plurality of devices (110-1,…,110-n) through a transceiver (126). For example, sludge information may include at least one of sludge concentration, sludge input amount, and sludge characteristics; coagulant information may include at least one of coagulant dissolution rate, coagulant input amount, and coagulant coagulation state; concentrator information may include at least one of bowl rotation speed, scroll rotation speed, and hydraulic pressure; dewatering machine information may include at least one of cake moisture content, inflow rate, and solid recovery rate; cake information may include at least one of cake moisture content and cake generation amount information; and dewatering liquid information may include at least one of suspended solids information and dewatering liquid recovery rate information.

[0104] One or more processors (122) can generate PID (Proportional-Integral-Differential) control information using sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and dewatering liquid information. According to one embodiment, the processor (122) can build big data in accordance with the received seasonal sludge characteristics and concentration changes, monitor data on the moisture content and solid recovery rate performance of the coagulant input amount relative to the sludge input amount, store accurate data values ​​through information collection, and build big data for statistical analysis, prediction, and classification by setting target determination values. In addition, the processor (122) can automatically adjust the amount of chemical input in accordance with the sludge characteristics and concentration changing in real time through the determination values ​​from the big data, and further advance it to automatically adjust the rotation speed of the centrifugal dewatering machine to achieve optimal operational efficiency. In addition, the processor (122) can be automatically operated by artificial intelligence (AI) using rapid and high-accuracy data to reduce cake processing costs by reducing moisture content, reduce coagulant chemical purchase costs, reduce power consumption by eliminating unnecessary operating conditions, minimize maintenance costs, and improve discharge water quality.

[0105] One or more processors (122) can control the rotational speed and hydraulic pressure of the dehydrator using PID control information. According to one embodiment, the processor (122) can control the rotational speed and hydraulic pressure of the dehydrator using generated PID information.

[0106] One or more memories (124) can store the above-described sludge information, coagulant information, concentrator information, dewatering machine information, cake information, dewatering liquid information, etc. Additionally, one or more memories (124) can store commands that cause one or more processors (122) to perform calculations when executed by one or more processors (122).

[0107] According to one embodiment, the server (120) may further include a transceiver (126). The transceiver (126) can perform wireless or wired communication between the server (120) and various external servers, databases, client devices and / or other devices. For example, the transceiver (126) can perform wireless communication according to methods such as eMBB (enhanced Mobile Broadband), URLLC (Ultra Reliable Low-Latency Communications), MMTC (Massive Machine Type Communications), LTE (long-term evolution), LTE-A (LTE Advance), UMTS (Universal Mobile Telecommunications System), GSM (Global System for Mobile communications), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (Wireless Broadband), WiFi (wireless fidelity), Bluetooth, NFC (near field communication), GPS (Global Positioning System), or GNSS (global navigation satellite system). For example, the transceiver (126) may perform wired communication according to methods such as USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232) or POTS (plain old telephone service).

[0108] According to one embodiment, one or more processors (122) can control a transceiver (126) to obtain information from various external servers and databases (130). The information obtained from various external servers and databases (130) can be stored in one or more memories (124).

[0109] According to one embodiment, the server (120) may be a device of various forms. For example, the server (120) may be a portable communication device, a computer device, or a device according to one or more of the devices described above. The server (120) of the present invention is not limited to the devices described above.

[0110] Various embodiments of the server (120) according to the present invention may be combined with one another. Each embodiment may be combined according to the number of cases, and the embodiment of the server (120) created by combining them also falls within the scope of the present invention. In addition, the internal / external components of the server (120) according to the present invention described above may be added, changed, replaced, or deleted depending on the embodiment. Furthermore, the internal / external components of the server (120) described above may be implemented as hardware components.

[0111] FIG. 7 is a diagram illustrating the learning of a neural network according to an embodiment of the present invention.

[0112] As illustrated in FIG. 7, the learning device can train a neural network (128) to generate PID control information from sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and leachate information. According to one embodiment, the learning device may be a separate entity from the server (120), but is not limited thereto.

[0113] The neural network (128) includes an input layer (127) into which training samples are input and an output layer (129) that outputs training outputs, and can be trained based on the difference between the training outputs and the labels. Here, the labels can be defined based on PID control information corresponding to sludge information, coagulant information, dewatering machine information, cake information, and dewatering liquid information. The neural network (128) is connected in groups of multiple nodes and is defined by weights between the connected nodes and an activation function that activates the nodes.

[0114] The learning device can train the neural network (128) using the Gradient Descent (GD) technique or the Stochastic Gradient Descent (SGD) technique. The learning device can use a loss function designed by the outputs and labels of the neural network.

[0115] The learning device can calculate the training error using a predefined loss function. The loss function can be predefined with labels, outputs, and parameters as input variables, where the parameters can be set by weights within the neural network (128). For example, the loss function can be designed in the form of Mean Square Error (MSE), entropy, etc., and various techniques or methods may be employed in the embodiments in which the loss function is designed.

[0116] The learning device can find weights that affect the training error using the backpropagation technique. Here, the weights are relationships between nodes within the neural network (128). The learning device can use the SGD technique with labels and outputs to optimize the weights found through the backpropagation technique. For example, the learning device can update the weights of a loss function defined based on labels, outputs, and weights using the SGD technique.

[0117] According to one embodiment, the learning device acquires sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and leachate information, and can generate PID control information from the sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and leachate information. The learning device can acquire pre-labeled information (first labels) for each of the training sludge information, training coagulant information, training concentrator information, training dewatering machine information, training cake information, and training leachate information, and can acquire first labels representing pre-defined PID control information for the training sludge information, training coagulant information, training concentrator information, training dewatering machine information, training cake information, and training leachate information.

[0118] According to one embodiment, the learning device can generate first training feature vectors based on the constituent features, pattern features, and numeric features of training sludge information, training coagulant information, training concentrator information, training dewatering machine information, training cake information, and training leachate information. Various methods may be employed to extract features of training sludge information, training coagulant information, training concentrator information, training dewatering machine information, training cake information, and training leachate information.

[0119] According to one embodiment, the learning device can obtain training outputs by applying first training feature vectors to the neural network (128). The learning device can train the neural network (128) based on the training outputs and first labels. The learning device can train the neural network (128) by calculating training errors corresponding to the training outputs and optimizing the connection relationships of nodes within the neural network (128) to minimize the training errors. The server (120) can generate PID control information from sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and leachate information using the trained neural network (128).

[0120] FIG. 8 is a flowchart illustrating the procedure of an artificial intelligence hydraulic centrifugal dehydration method according to an embodiment of the present invention. Although process steps, method steps, algorithms, etc. are described in a sequential order in the flowchart of FIG. 8, such processes, methods, and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods, and algorithms described in various embodiments of the present invention do not need to be performed in the order described in the present invention. Furthermore, even if some steps are described as being performed asynchronously, in other embodiments, such steps may be performed simultaneously. Also, the example of a process by the depiction in the drawings does not imply that the illustrated process excludes other variations and modifications thereof, does not imply that any of the illustrated process or any of its steps is essential to one or more of the various embodiments of the present invention, and does not imply that the illustrated process is preferred.

[0121] As illustrated in FIG. 8, various information is received in step (S810). For example, referring to FIGS. 1 to 7, the server (110) of the artificial intelligence hydraulic centrifugal separation system (100) can receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and separation liquid information from a plurality of devices (110-1,…,110-n) through a network (N). For example, sludge information may include at least one of sludge concentration, sludge input amount, and sludge characteristics; coagulant information may include at least one of coagulant dissolution rate, coagulant input amount, and coagulant coagulation state; concentrator information may include at least one of bowl rotation speed, scroll rotation speed, and hydraulic pressure; dewatering machine information may include at least one of cake moisture content, inflow rate, and solid recovery rate; cake information may include at least one of cake moisture content and cake generation amount information; and dewatering liquid information may include at least one of suspended solids information and dewatering liquid recovery rate information.

[0122] In step (S820), PID control information is generated. For example, referring to FIGS. 1 to 7, the server (110) of the artificial intelligence hydraulic centrifugal separation system (100) can generate PID (Proportional-Integral-Differential) control information using the sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and separated liquid information received in step S810. According to one embodiment, the server (120) can build big data in accordance with the received seasonal sludge characteristics and concentration changes, monitor data on the moisture content of the coagulant input amount relative to the sludge input amount and the solid recovery rate performance, store accurate data values ​​through information collection, and determine target decision values ​​to build big data for statistical analysis, prediction, and classification. In addition, the server (120) automatically adjusts the amount of chemical input according to the sludge characteristics and concentration that change in real time through big data, and further develops it to automatically adjust the rotation speed of the centrifugal dewatering machine to achieve optimal operational efficiency. Furthermore, the server (120) is automatically operated by artificial intelligence (AI) using rapid and high-accuracy data, thereby reducing cake processing costs by reducing moisture content, reducing coagulant chemical purchase costs, and reducing power consumption by eliminating unnecessary operating conditions, thereby minimizing maintenance costs and improving the discharge water quality.

[0123] In step (S830), the rotational speed and hydraulic pressure of the concentrator and dehydrator are controlled. For example, referring to FIGS. 1 to 7, the server (110) of the artificial intelligence hydraulic centrifugal separation system (100) can control the rotational speed and hydraulic pressure of the concentrator and dehydrator using PID control information generated in step S820.

[0124] Although the above method has been described through specific embodiments, the above method can also be implemented as computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. Additionally, the computer-readable recording medium may be distributed across networked computer systems so that computer-readable code can be stored and executed in a distributed manner. Furthermore, functional programs, codes, and code segments for implementing the above embodiments can be easily inferred by programmers skilled in the art to which the present invention pertains. Explanation of the symbols

[0125] 100: Artificial intelligence hydraulic centrifugal separation system 110-1, 110-n: Multiple devices 120: Server 130: Database 122: Processor 124: Memory 126: Transmitter / Receiver 127: Input Layer 128: Neural Network 129: Output Layer

Claims

Claim 1 One or more processors; And, when executed by the one or more processors, the method includes one or more memories storing instructions that cause the one or more processors to perform calculations; the one or more processors receive sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and leachate information; generate PID (Proportional-Integral-Differential) control information using the sludge information, the coagulant information, the concentrator information, the dewatering machine information, the cake information, and the leachate information; and control the rotational speed and hydraulic pressure of the concentrator and dewatering machine using the PID control information; the one or more processors measure a first concentration of sludge at a first time; measure a second concentration of sludge at a second time after a predetermined time has elapsed from the first time; measure a third concentration of sludge at a third time after a predetermined time has elapsed from the second time; calculate an average concentration by averaging the first to third concentrations; calculate a first difference value between the average concentration and the first concentration; and the average concentration and the second Calculate a second difference value of the concentration, and calculate a third difference value between the average concentration and the third concentration. If the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, reduce the amount of coagulant added by the difference between the third difference value and the second difference value. If the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, increase the amount of coagulant added by the difference between the third difference value and the second difference value. If the first difference value is smaller than the second difference value and the second difference value is greater than the third difference value, maintain the amount of coagulant added. If the first difference value is greater than the second difference value and the second difference value is smaller than the third difference value, reduce the amount of coagulant added by the first difference value and the second difference value.An artificial intelligence hydraulic centrifugal separation system that increases by the smaller of the difference between the second difference value and the third difference value. Claim 2 An artificial intelligence hydraulic centrifugal separation system according to claim 1, wherein the sludge information includes at least one of sludge concentration, sludge input amount, and sludge characteristics; the coagulant information includes at least one of coagulant dissolution rate, coagulant input amount, and coagulant coagulation state; the concentrator information includes at least one of bowl rotation speed, scroll rotation speed, and hydraulic pressure; the dewatering machine information includes at least one of cake moisture content, inflow rate, and solid recovery rate; the cake information includes at least one of cake moisture content and cake generation amount information; and the separated liquid information includes at least one of suspended solids information and separated liquid recovery rate information. Claim 3 An artificial intelligence hydraulic centrifugal separation system according to claim 1, wherein one or more processors transmit sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and separated liquid information to a generative artificial intelligence model server, receive PID control information from the generative artificial intelligence model server, and the generative artificial intelligence model server analyzes data on sludge condition, hydraulic pressure, temperature, and coagulant concentration using a generative artificial intelligence model, thereby predicting key future variables such as energy consumption, machine load, sludge characteristics, and concentration, pre-calculates PID parameters (Kp, Ki, Kd) based on the predicted future data, and each PID parameter is directly output by the generative artificial intelligence model server by reflecting the expected error and system operation pattern, and while the predicted PID value is applied, monitors the difference between the actual data and the predicted value, and the generative artificial intelligence model server immediately generates a new PID value according to the difference. Claim 4 delete Claim 5 In claim 1, the one or more processors measure a first cake moisture content at a first time, measure a second cake moisture content at a second time after a predetermined time has elapsed from the first time, measure a third cake moisture content at a third time after a predetermined time has elapsed from the second time, calculate an average moisture content by averaging the first to third cake moisture contents, calculate a first difference value between the average moisture content and the first cake moisture content, calculate a second difference value between the average moisture content and the second cake moisture content, calculate a third difference value between the average moisture content and the third cake moisture content, and if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, reduce the rotational speed of the dehydrator by the difference between the third difference value and the second difference value, and if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, reduce the rotational speed of the dehydrator by the difference between the third difference value and the second difference value. An artificial intelligence hydraulic centrifugal separation system that increases, maintains the rotational speed of the dehydrator when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value, and increases the rotational speed of the dehydrator by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value. Claim 6 An artificial intelligence hydraulic centrifugal dewatering method using an artificial intelligence hydraulic centrifugal separation system comprising: one or more processors; and one or more memories storing instructions that cause the one or more processors to perform calculations when executed by the one or more processors, the method comprises the steps of: receiving sludge information, coagulant information, concentrator information, dewatering machine information, cake information, and leachate information by the one or more processors; and generating PID (Proportional-Integral-Differential) control information by the one or more processors using the sludge information, the coagulant information, the concentrator information, the dewatering machine information, the cake information, and the leachate information. The method comprises the step of controlling the rotational speed and hydraulic pressure of a concentrator and a dewatering machine using the PID control information by the above-mentioned one or more processors, wherein the method includes: measuring a first concentration of sludge at a first time; measuring a second concentration of sludge at a second time after a predetermined time has elapsed from the first time; measuring a third concentration of sludge at a third time after a predetermined time has elapsed from the second time; averaging the first to third concentrations to calculate an average concentration; calculating a first difference value between the average concentration and the first concentration; calculating a second difference value between the average concentration and the second concentration; calculating a third difference value between the average concentration and the third concentration; if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, reducing the amount of coagulant added by the difference between the third difference value and the second difference value; if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, the A step of increasing the amount of coagulant added by the difference between the third difference value and the second difference value;An artificial intelligence hydraulic centrifugal dewatering method further comprising: a step of maintaining the amount of coagulant injected when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value; and a step of increasing the amount of coagulant injected by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value when the first difference value is larger than the second difference value and the second difference value is smaller than the third difference value. Claim 7 delete Claim 8 In claim 6, the method comprises: a step of measuring a first cake moisture content at a first time; a step of measuring a second cake moisture content at a second time after a predetermined time has elapsed from the first time; a step of measuring a third cake moisture content at a third time after a predetermined time has elapsed from the second time; a step of averaging the first to third cake moisture contents to calculate an average moisture content; a step of calculating a first difference value between the average moisture content and the first cake moisture content; a step of calculating a second difference value between the average moisture content and the second cake moisture content; a step of calculating a third difference value between the average moisture content and the third cake moisture content; a step of, if the first difference value is greater than the second difference value and the second difference value is greater than the third difference value, decreasing the rotational speed of the dehydrator by the difference between the third difference value and the second difference value; and, if the first difference value is smaller than the second difference value and the second difference value is smaller than the third difference value, increasing the rotational speed of the dehydrator by the difference between the third difference value and the second difference value. A method for artificial intelligence hydraulic centrifugal dehydration, further comprising: a step of maintaining the rotational speed of the dehydrator when the first difference value is smaller than the second difference value and the second difference value is larger than the third difference value; and a step of increasing the rotational speed of the dehydrator by the smaller value among the first difference value, the second difference value, and the difference between the second difference value and the third difference value when the first difference value is larger than the second difference value and the second difference value is smaller than the third difference value. Claim 9 delete

Images