KR20140142491A - Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus - Google Patents

Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus Download PDF

Info

Publication number
KR20140142491A
KR20140142491A KR1020130063930A KR20130063930A KR20140142491A KR 20140142491 A KR20140142491 A KR 20140142491A KR 1020130063930 A KR1020130063930 A KR 1020130063930A KR 20130063930 A KR20130063930 A KR 20130063930A KR 20140142491 A KR20140142491 A KR 20140142491A
Authority
KR
South Korea
Prior art keywords
water quality
unit
treatment plant
artificial intelligence
sewage
Prior art date
Application number
KR1020130063930A
Other languages
Korean (ko)
Other versions
KR101629240B1 (en
Inventor
백병천
권중천
Original Assignee
전남대학교산학협력단
주식회사 에코다임
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 전남대학교산학협력단, 주식회사 에코다임 filed Critical 전남대학교산학협력단
Priority to KR1020130063930A priority Critical patent/KR101629240B1/en
Publication of KR20140142491A publication Critical patent/KR20140142491A/en
Application granted granted Critical
Publication of KR101629240B1 publication Critical patent/KR101629240B1/en

Links

Images

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00Water conservation; Efficient water supply; Efficient water use
    • Y02A20/152Water filtration
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02WCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W10/00Technologies for wastewater treatment
    • Y02W10/10Biological treatment of water, waste water, or sewage

Landscapes

  • Feedback Control In General (AREA)
  • Activated Sludge Processes (AREA)

Abstract

The present invention relates to an integrated control system for a sewage and wastewater treatment facility for processing sewage, sludge and wastewater, which comprises (A) a sensor unit for measuring the introducing water quality, the introducing water quantity, the driving factors of unit processes in the treatment facility, the discharged water quality and the discharged water quantity in real time; (B) a memory unit for storing the data collected by the sensor unit; (C) a predictive model producing unit employing an artificial intelligence program producing an evolutionary predictive model for building a predictive model of the discharged water quality of the sewage and wastewater treatment facility in reference to the data; (D) a calculation output unit for calculating an introducing water quantity and driving factors by predicting the discharged water quality after t-time by applying the introducing water quality, the introducing water quantity and the driving factors in the treatment facility collected by the sensor unit to the predictive model, and virtually changing the introducing water quantity and the driving factors when the predicted discharged water quality is out of a reference range of the discharged water quality so that the predicted discharged water quality by applying the predictive model is within the reference range of the discharged water quality; and (E) a process control unit for controlling each unit process on a basis of the calculated introducing water quantity and driving factors. According to the present invention, a mathematical process predictive model to a targeting sewage and wastewater treatment facility can be easily built, automation of operation of sewage and wastewater treatment facility is possible through the information about the discharged water predicted by the process predictive model, and the sewage and wastewater treatment facility can be effectively operated and controlled in normal and dynamic states. Furthermore, professionals in respective fields (environment, mechanics, electrics, etc.) are not required to stay, thereby drastically reducing the operation and management costs of the treatment facility.

Description

진화적 예측모델 생성 인공지능 프로그램이 결합된 수처리장의 인공지능 통합 제어시스템{Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus}Technical Field [0001] The present invention relates to an artificial intelligence integrated control system for a water treatment plant combined with an artificial intelligence program,

본 발명은 오수, 폐수, 하수 등을 처리하는 수처리장의 통합 제어시스템에 관한 것이다.
The present invention relates to an integrated control system of a water treatment plant for treating sewage, wastewater, sewage, and the like.

엄격해지고 있는 수질기준을 충족시키기 위해 수처리장의 고도처리공정이 증가하고 있으며, 이에 따라 고려해야 할 운전인자들도 늘어나게 되었다. 이에 수처리장의 효율적인 제어를 위해 PLC(Programmable Logic Controller)를 적용하는 사례가 늘고 있다.In order to meet stringent water quality standards, the water treatment plant's advanced treatment process has been increasing, and driving factors to consider have also increased. In order to control the water treatment plant efficiently, PLC (Programmable Logic Controller) is applied more and more.

현재 수처리장에서 운전되고 있는 PLC는 단위공정에서 수집된 자료를 바탕으로 운전되고 있는데, 운전인자는 DO와 pH정도로서 실제 현장에서 매우 중요한 운전인자인 유량과 수질(BOD, COD, SS, T-N 등) 인자들에 대한 고려는 전혀 되지 않고 있는 실정이다. 또한 기존 PLC 시스템의 경우, 기술적인 한계로 인해 복잡하고 다양한 운전인자를 반영할 수 있는 예측모델에 의한 최적운전은 거의 불가능하다. 따라서 현장에서는 실제로 실무 엔지니어들의 경험에 전적으로 의존하고 있다. 일예로, 방류수질 기준초과 같은 문제가 발생 했을 때 방류수질기준에 적합하도록 PLC가 운전인자를 조정해 주는 것이 아니고, 오직 운전자의 경험에 따라 PLC 조정이 이루어진다.The operation parameters are DO and pH, and the flow and water quality (BOD, COD, SS, TN, etc.), which are very important operating factors in actual field, There is no consideration of factors at all. In addition, in the case of existing PLC systems, it is almost impossible to optimally operate by a predictive model that can reflect complicated and various operating factors due to technical limitations. Therefore, the field actually depends entirely on the experience of the working engineers. For example, if a problem such as exceeding the discharge water quality criteria occurs, the PLC does not adjust the operating parameters to meet the discharge water quality standards, but only the PLC experience is adjusted according to the driver's experience.

설령 예측모델에 의해 운전되는 PLC이더라도 매우 복잡한 수식들로 표현된 공정모델을 근거로 하기 때문에, 유입수, 반응조, 그리고 방류수의 수질인자에 관한 방대한 자료를 확보한 후, 공정모델들의 복잡하고도 많은 모델 변수들을 특정 하ㆍ폐수 처리장에 맞게 보정해 주어야 한다. 그러나 이러한 작업은 소요시간과 비용소모가 많기 때문에 대부분의 하ㆍ폐수 처리장에서는 오직 현장 운전자(엔지니어)의 경험에 의존하는 운영을 하고 있다.
Even PLCs driven by predictive models are based on process models represented by very complex mathematical expressions, so after obtaining vast data on water quality factors of influent, reaction tank, and effluent, complex and many models of process models Variables should be specified and adjusted to match the wastewater treatment plant. However, most of the waste water and wastewater treatment plants depend on the experience of the field engineers (engineers) because they take a lot of time and cost.

본 발명은, 수처리장의 PLC 제어시스템을 획기적으로 개선하기 위한 것으로서, ① steady 및 dynamic 상태에 대한 운전이 가능하며 ② 방류수질 예측이 가능하며 ③ 처리장의 기존 운전자료 활용이 가능하며 ④ 별도의 모델선정 등 전처리 과정이 없이도 수학적 모델 구축이 가능하며 ⑤ 처리장 운전의 자동화 및 최적운전이 가능하며 ⑥ 처리장 운영ㆍ관리비용 등의 문제가 자연스럽게 해소될 수 있는 새로운 PLC 제어시스템을 제공하는데 목적이 있다.
The present invention is intended to drastically improve the PLC control system of a water treatment plant. It is capable of operating in steady and dynamic states, predicting the discharge water quality, utilizing the existing operation data of the treatment plant, It is possible to construct a mathematical model without a preprocessing process such as selection, ⑤ to automate and optimize operation of the treatment plant, and ⑥ to provide a new PLC control system that can solve problems such as the cost of operation and management of the treatment plant naturally.

본 발명은 (A) 유입수질, 유입수량과 처리장 내 단위공정들의 운전인자, 방류수질 및 방류수량을 실시간으로 측정하는 센서부; (B) 상기 센서부에 의해 수집된 데이터를 저장하는 기억부; (C) 상기 데이터를 참조하여 수처리장의 방류수질 예측모델을 구축하는 진화적 예측모델 생성 인공지능 프로그램이 결합된 예측모델생성부; (D) 상기 센서부에 의해 수집된 현재 유입수질, 유입수량과 처리장 내 운전인자를 상기 예측모델에 적용하여 t시간 후의 방류수질을 예측하고, 예측된 방류수질이 기준 방류수질 범위 밖인 경우 유입수량과 운전인자를 가상으로 변경하고 상기 예측모델을 적용하여 예측된 방류수질이 기준 방류수질 범위 내가 되도록 하는 유입수량과 운전인자를 추출하는 계산출력부; (E) 상기 추출된 유입수량과 운전인자를 근거로 각 단위공정을 제어하는 공정제어부;를 포함하는 수처리장의 인공지능 통합 제어시스템에 관한 것이다.
(A) a sensor unit for measuring an incoming water quality, an influent water quantity, an operation factor of unit processes in a treatment plant, a discharged water quality and a discharge water quantity in real time; (B) a storage unit for storing data collected by the sensor unit; (C) a prediction model generation unit coupled with an evolutionary prediction model generation artificial intelligence program for constructing a discharge water quality prediction model of a water treatment plant by referring to the data; (D) estimating the discharged water quality after time t by applying the present influent water quality, the influent water quantity and the operation factor in the treatment plant collected by the sensor unit to the prediction model, and if the predicted discharged water quality is out of the reference discharge water quality range, And a calculation output unit for extracting an influent water quantity and an operation factor for virtually changing the operation factor and applying the prediction model so that the predicted discharged water quality is within the reference discharge water quality range; (E) a process control unit for controlling each unit process based on the extracted influent water quantity and operating factor.

이상과 같이 구성되는 본 발명에 의한 수처리장의 인공지능 통합 제어시스템을 하ㆍ폐수처리장에 적용할 경우, 현장 엔지니어가 가지고 있는 공정지식과 경험은 물론, 수처리장이 가지고 있는 독특한 공정과 지역적 특성들을 반영할 수 있는 수학적 공정예측모델 구성이 가능하며 이를 이용하여 방류수의 수질정보를 예측할 수 있고 효율적으로 처리장 제어가 가능하다. When the artificial intelligence integrated control system of the water treatment plant according to the present invention is applied to the wastewater treatment plant, the process knowledge and experience of the field engineer as well as the unique process and local characteristics of the water treatment plant It is possible to construct the mathematical process prediction model that can reflect the water quality information of the discharged water using this, and it is possible to control the treatment plant efficiently.

또한 본 발명에 의하면, 대상 하ㆍ폐수처리장에 대한 수학적 공정예측모델을 쉽게 구축할 수 있고, 공정예측모델에서 예측한 방류수의 정보를 통해 수처리장 운전의 자동화가 가능하며, 정상 및 동적 상태에서도 수처리장을 효과적으로 운영 및 제어가 가능하며, 분야별(환경, 기계, 전기 등) 전문인력이 상주할 필요가 없어져서 처리장 운영ㆍ관리비용이 상당히 감소될 수 있다. According to the present invention, it is possible to easily construct a mathematical process prediction model for the target wastewater treatment plant, automate the operation of the water treatment plant through information of the effluent water predicted by the process prediction model, It is possible to effectively operate and control the treatment plant, and there is no need to reside in a specialized workforce (environment, machine, electric power, etc.) for each field, so that the operation and management cost of the treatment plant can be reduced considerably.

또한 본 발명에 의하면 방류수질 예측을 통해 문제점을 초기에 진단하고 제어할 수 있어 수처리장을 안정적으로 운영할 수 있고, 방류수 수질을 기준치 이하로 운전할 수 있어 처리장의 처리효율 또한 극대화시킬 수 있다.
In addition, according to the present invention, it is possible to diagnose and control problems early on by predicting effluent water quality, to stably operate the water treatment plant, and to operate the water quality below the reference value, thereby maximizing the treatment efficiency of the treatment plant.

도 1은 본 발명에 의한 수처리장의 인공지능 통합 제어시스템의 개념도.
도 2는 본 발명에 의한 수처리장의 인공지능 통합 제어시스템이 적용된 수처리장의 간략예를 보여주는 구성도.
도 3a는 본 발명에 의한 수처리장의 인공지능 통합 제어시스템에서 예측모델생성부에 의한 자동 수학적 공정모델 생성과정을 보여주는 흐름도.
도 3b는 수학적 공정모델 생성과정을 통해 최종적으로 생성된 수학적 공정모델과 그에 따른 예측결과를 나타낸 예시도.
도 4는 진화적 모델 생성을 위한 유전자연산과정의 예를 보여주는 도면.
1 is a conceptual diagram of an artificial intelligence integrated control system of a water treatment plant according to the present invention.
BACKGROUND OF THE INVENTION Field of the Invention [0001] The present invention relates to an artificial intelligence integrated control system for a water treatment plant.
FIG. 3A is a flowchart showing an automatic mathematical process model generation process by a predictive model generation unit in an artificial intelligence integrated control system of a water treatment plant according to the present invention. FIG.
FIG. 3B is an exemplary diagram showing a mathematical process model finally generated through a process of generating a mathematical process model and prediction results therefrom. FIG.
FIG. 4 is a diagram showing an example of a genetic algorithm process for evolutionary model generation; FIG.

이하 첨부된 도면을 참조하여 본 발명을 보다 상세히 설명한다. 그러나 첨부된 도면은 본 발명의 기술적 사상의 내용과 범위를 쉽게 설명하기 위한 예시일 뿐, 이에 의해 본 발명의 기술적 범위가 한정되거나 변경되는 것은 아니다. 또한 이러한 예시에 기초하여 본 발명의 기술적 사상의 범위 안에서 다양한 변형과 변경이 가능함은 당업자에게는 당연할 것이다.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail with reference to the accompanying drawings. It should be understood, however, that the appended drawings illustrate only the contents and scope of technology of the present invention, and the technical scope of the present invention is not limited thereto. It will be apparent to those skilled in the art that various changes and modifications can be made within the scope of the technical idea of the present invention based on these examples.

설명하였듯이, 본 발명은 센서부, 기억부, 예측모델생성부, 계산출력부 및 공정제어부를 포함하는 수처리장의 인공지능 통합 제어시스템이다. 도 1과 2에 각각 본 발명에 의한 수처리장의 인공지능 통합 제어시스템의 개념도와, 본 발명이 적용된 수처리장의 간략예를 보여주는 구성도를 도시하였다.As described above, the present invention is an artificial intelligence integrated control system of a water treatment plant including a sensor unit, a storage unit, a predictive model generation unit, a calculation output unit, and a process control unit. FIGS. 1 and 2 show a conceptual diagram of an artificial intelligence integrated control system of a water treatment plant according to the present invention, and a schematic diagram showing a simplified example of a water treatment plant to which the present invention is applied.

본 발명에서 센서부는 유입수질, 유입수량과 처리장 내 단위공정들의 운전인자, 방류수질 및 방류수량을 실시간으로 측정하여 상기 기억부로 전송한다. 수질측정을 위한 센서부는 유입수와 방류수의 유량과 수질(온도, BOD, COD, SS, TN, TP 등)을 측정할 수 있는 센서들과, 처리장 단위공정의 운전인자(DO, MLSS, 슬러지반송유량, 내부반송유량, 온도 등)를 측정할 수 있는 센서로 되어 있다. In the present invention, the sensor unit measures the influent water quality, the influent water quantity, the operation factors of the unit processes in the treatment plant, the discharge water quality and the discharge water quantity in real time and transmits them to the storage unit. The sensors for measuring water quality are sensors that can measure flow rate and water quality (influenced by temperature, BOD, COD, SS, TN, TP, etc.) of influent and discharge water, operation factors (DO, MLSS, , Internal transport flow rate, temperature, etc.).

기억부는 상기 센서부에 의해 수집된 데이터를 저장하고 필요시 상기 예측모델생성부에 전달하며, 당연히 작업자의 조작에 의해 소정의 출력물로 출력하는 기능을 한다. 기억부에는 기존 처리장 운전자료(처리장 운전인자 및 유입ㆍ방류수질)가 저장되어 있다.The storage unit stores the data collected by the sensor unit and transmits the data to the prediction model generation unit when necessary, and outputs the data to a predetermined output by an operator's operation. Existing treatment plant operation data (treatment plant operation factor and inflow / outflow water quality) are stored in the storage unit.

예측모델생성부는 상기 기억부 저장된 과거의 유입수질, 유입수량과 처리장 내 단위공정들의 운전인자, 방류수질 및 방류수량에 대한 데이터를 참조하여 수처리장의 방류수질 예측모델을 구축하는 역할을 하는 것으로서 진화적 예측모델 생성 인공지능 프로그램이 결합되어 있다.The predictive model generation unit constructs a water quality prediction model of the water treatment plant by referring to data on the past influent water quality, the influent water quantity, the operation factors of the unit processes in the treatment plant, the discharge water quality and the discharge water quantity, And predictive model generation artificial intelligence programs are combined.

계산출력부는 상기 센서부에 의해 수집된 현재 유입수질, 유입수량과 처리장 내 운전인자를 상기 예측모델에 적용하여 t시간 후의 방류수질을 예측한다. 그 결과 예측된 방류수질이 기준 방류수질 범위 밖인 경우 유입수량과 운전인자 들을 가상으로 변경하고 상기 예측모델을 적용하여 예측된 방류수질이 기준 방류수질 범위 내가 되도록 하는 유입수량과 운전인자를 추출하여 상기 공정제어부로 전송한다. The calculation output unit predicts the discharged water quality after time t by applying the present influent water quality, the influent water quantity and the operation factor in the treatment plant collected by the sensor unit to the prediction model. As a result, if the predicted discharged water quality is out of the reference discharge water quality range, the influent water and operating factors are virtually changed and the predicted model is applied to extract the influent water and the operation factor, To the process control unit.

공정제어부는 상기 계산출력부에서 전달받은 유입수량과 운전인자를 각 단위공정에 적용하여 공정을 제어하는 기능을 한다.The process control unit controls the process by applying the influent quantity and operation factor received from the calculation output unit to each unit process.

이렇게 구성된 본 발명에 의한 수처리장의 인공지능 통합 제어시스템에서는 통합적으로 다음과 같은 과정이 이루어진다. : 수처리장으로 유입되는 유입수질(유량, 온도, 강우, BOD, COD, SS, TN, TP 등)과 처리장 내의 운전인자(DO, MLSS, 슬러지반송유량, 내부반송유량, 온도) 등이 센서부에 의해 수집되어 기억부에 저장된다. 기억부에 저장되어 있던 데이터를 예측모델생성부로 전송하면 인공지능 프로그램이 유입수질과 처리장 내 운전인자, 기존 처리장 운전자료 등의 데이터를 이용하여 방류수질을 예측한다. 일반적인 방류수질기준의 수질뿐만 아니라 자료수집과 측정이 가능하다면, 암모니아, 질산성 질소 등 다양한 수질 또한 예측이 가능하다. 특히, 지역적인 요소(유입수 성상, 기온, 강우 등)를 반영한 각각의 처리장에 맞춤형 공정모델을 수립할 수가 있다. 예측한 방류수질을 기반으로 수질기준 이하(혹은 운전자가 설정한 기준)로 운전될 수 있는 인자와 기계적 제어신호를 도출하여 공정제어부(예를 들면 PLC)로 전송하면 공정제어부가 방류수질 기준으로 하ㆍ폐수처리장의 각 단위공정을 제어하게 된다.
In the artificial intelligence integrated control system of the water treatment plant according to the present invention configured as described above, the following process is integrally performed. (DO, MLSS, sludge transport flow rate, internal transport flow rate, temperature) and the like in the treatment plant are inputted to the sensor section And stored in the storage unit. When the data stored in the storage unit is transferred to the predictive model generator, the artificial intelligence program predicts the discharge water quality using data such as influent water quality, operating factors in the treatment plant, and operation data of the existing treatment plant. Various water quality such as ammonia and nitrate nitrogen can be predicted if it is possible to collect and measure data as well as the quality of general discharge water quality standard. In particular, customized process models can be established for each treatment site that reflects local factors (influent, temperature, rainfall, etc.). Based on the predicted effluent quality, factors and mechanical control signals that can be operated below the water quality standard (or the standard set by the driver) are derived and transmitted to the process control unit (PLC for example) ㆍ Each unit process of wastewater treatment plant is controlled.

본 발명에서는 하ㆍ폐수 처리장 유입수 및 반응조의 정보 또는 기존 운전자료를 이용해서 방류수의 수질분석 항목인 BOD, COD, SS, T-N, T-P 등을 자동적으로 예측할 수 있는 수학적 공정모델을 생성한다.
In the present invention, a mathematical process model capable of automatically predicting BOD, COD, SS, TN, and TP, which are water quality analysis items of discharged water, is generated by using information of inflow water of a wastewater treatment plant and reaction tank or existing operation data.

본 발명에서 상기 인공지능 프로그램은 그램마-유전자프로그래밍(Grammar-based Genetic Programming, GBGP) 기술에 의하여 수학적으로 표현되는 진화적 공정모델시스템(evolutionary process induction system)인 것이 바람직하다. 도 3a에 본 발명에 의한 수처리장의 인공지능 통합 제어시스템에서 예측모델생성부에 의한 자동 수학적 공정모델 생성과정을 보여주는 흐름도를 도시하였다.In the present invention, the artificial intelligence program is preferably an evolutionary process induction system mathematically represented by Grammar-based Genetic Programming (GBGP) technology. 3A is a flowchart showing an automatic mathematical process model generation process by the predictive model generation unit in the artificial intelligence integrated control system of the water treatment plant according to the present invention.

진화적 공정모델시스템은 context-free grammar(도 3에서 304)라 불리우는 그램마를 이용하여 공정모델들의 초기 개체군을 생성시킨다(305). Context-free grammar은 아래 그림과 같이 4개 요소인 Start와 N(nonterminal symbol), P(production set), T(terminal symbol)로 구성된다. 이 context-free grammar는 진화적 공정모델 시스템내에서 공정모델들을 생성하는 방법을 제어한다. The evolutionary process modeling system generates an initial population of process models (305) using a grammar called a context-free grammar (304 in FIG. 3). Context-free grammar consists of four elements, Start and N (nonterminal symbol), P (production set) and T (terminal symbol) as shown below. This context-free grammar controls how to generate process models within an evolutionary process model system.

Figure pat00001
Figure pat00001

위와 같이 grammar을 통해 진화적 공정모델시스템은 수학적 함수집합과 종단 노드집합에서 임의의 원소를 선택하여 다음과 같이 나뭇가지 형태의 구조로 공정모델의 수학적 모델구조를 생성한다. 다음은 그램마와 x, y, z이라고 불리우는 공정모델의 변수와 +, -, *, /와 같은 수학적 함수집합을 이용해서 Z*(X+4.5Y)라는 형태를 가진 공정모델을 만든 예이다. Through the grammar, the evolutionary process model system selects a mathematical function set and an arbitrary element from the set of end nodes to generate a mathematical model structure of the process model as follows: The following is an example of a process model with the form of Z * (X + 4.5Y) using the variables of the process model called grammar and x, y, z and mathematical function set such as +, -, *, / .

Figure pat00002
Figure pat00002

초기에 새로운 공정모델이 생성될 때, Start를 가지는 하나의 노드로 시작한다. 다음에 Nonterminal (N)이라고 불리우는 심볼과 공정모델의 변수와 +, -, *, / 와 같은 수학적 함수집합으로 구성된 Terminal (T)과의 혼합을 통해서 앞에서 보여준 나무가지의 형태로 표현되는 공정모델의 수학적 구조를 생성해 낸다. 그리고 진화연산(evolutionary computation) 과정을 통해서 나뭇가지형태의 구조로된 공정모델의 수학적 구조를 반복적으로 변형해 나감으로써 최종적으로 가장 우수하게 방류수의 정보를 예측할 수 있는 최적의 공정모델들을 도출해낸다. 진화적 공정모델시스템에서 최적의 공정모델들을 진화시키는 단계는 다음과 같이 4단계로 구분해서 설명할 수 있다.Initially, when a new process model is created, it starts with one node with Start. Next, a process model, represented by the tree branch shown above, is generated by mixing a symbol called Nonterminal (N) with a Terminal (T) composed of variables of the process model and a set of mathematical functions such as +, -, *, and / Create a mathematical structure. Through the evolutionary computation process, the mathematical structure of the process model with the tree branch structure is repeatedly modified to derive optimal process models that can predict the information of the effluent water finally. The evolution of the optimal process models in the evolutionary process modeling system can be divided into four stages as follows.

i) 초기화: context-free grammar(304)을 이용하여 공정모델의 초기 개체군 (initial population)생성 : K(세대)=0 (도3에서 305)i) Initialization: Generate initial population of process model using context-free grammar 304: K (generation) = 0 (305 in FIG. 3)

ii) 각각의 개체군에 속한 공정모델들에 포함된 모델상수들의 최적화 (도3에서 306)ii) optimization of the model constants included in the process models belonging to each population (306 in Figure 3)

iii) 각각의 공정모델들에 대한 적합도 (fitness) 실행 및 평가 (도3에서 307)iii) fitness execution and evaluation (307 in FIG. 3) for each process model;

iv) 유전자 루프 : K=Kmax까지 실행 (도3에서 308)iv) Run the gene loop: K = Kmax (308 in FIG. 3)

a. 교차연산 (crossover), 돌연변이 연산을 통해 새로운 개체군 생성   a. Create new population through crossover and mutation operations

a-1 다음 세대 모델진화를 위해 적합한 두 공정모델(부모) 선정      a-1 Selection of two process models (parents) suitable for the next generation model evolution

a-2 부모모델(parents)과 자녀모델(child)의 무작위 교차연산 수행      a-2 Perform random crossover of parent and child models

a-3 각각의 자녀 모델 sub-tree를 무작위를 변형시키는 돌연변이(mutation) 연산 수행      a-3 Perform a mutation operation that randomly transforms each child model sub-tree.

a-4 'a-1'~'a-2'를 새로운 자손모델(offspring)이 생성될 때까지 수행      a-4 'a-1' to 'a-2' are performed until a new offspring is generated

a-5 부모 개체군의 구 모델은 새로운 공정모델로 대체      a-5 Old model of parent population replaced with new process model

b. 다음 세대 진행 : K+1   b. Next Generation: K + 1

보다 자세히 설명하면, 이와 같은 진화적 공정모델시스템은 진화연산(evolutionary computation) 또는 진화알고리즘(evolutionary algorithm)이라 불리는 인공지능 기술에 기반을 두고 있다. 진화적 공정모델시스템은 적자생존과 같은 생태계의 진화현상과 유전자학에 근거로 해서 개발된 계산 알고리즘으로서 주어진 하ㆍ폐수 처리장의 유입수 및 반응조 정보를 가지고 방류수의 정보를 예측할 수 있는 최적의 공정모델 수학식을 자동으로 생성해주는 기술이다. 본 발명에서 개발한 진화적 공정모델시스템은 첫 번째 단계에서 context-free grammar라고 불리우는 그램마를 이용해서 공정모델을 표현하는데 필요한 방법을 정의한 후 수학적 함수집합과 종단 노드집합에서 임의의 원소를 선택하여 수학적으로 초기 공정모델의 개체군 (population)을 형성한다. 두 번째 단계에서는 개체군에 속한 모든 공정모델을 실행시켜서 개체군에 속한 각 공정모델들이 방류수 수질를 얼마나 잘 예측 할 수 있는가에 대한 적합도(fitness) 검사를 시행한다. 세 번째 단계에서는 이 적합도 결과에 따라서 좋은 적합도를 가진 공정모델들은 살아남고, 유전연산자 (genetic operator)를 이용해서 다음세대 (next generation)를 위한 공정모델들의 새로운 개체군 (population)를 형성한다. 즉, 이 단계에서 주로 우수한 적합도를 가진 공정모델들의 복제 (reproduction), 두 개의 우수한 공정모델들의 일부분을 서로 교환하는 교차연산(crossover), 그리고 공정모델들의 일부를 변형하는 돌연변이(mutation)과정을 통해서 좀 더 나은 수학적 공정모델의 개체군 (population)를 형성한다. 이러한 반복과정을 통해 최종적으로 가장 우수하게 방류수 정보를 예측할 수 있는 최적의 공정모델 수학식들을 생성한다.
More specifically, such an evolutionary process model system is based on artificial intelligence techniques called evolutionary computation or evolutionary algorithms. The evolutionary process modeling system is a computational algorithm developed on the basis of evolutionary phenomena and genomics of ecosystems such as survival of the fittest. It is an optimal process model that can predict the information of effluent water with influent and reaction tank information of a given wastewater treatment plant. Is automatically generated. The evolutionary process model system developed in the present invention firstly defines a method for expressing a process model using a grammar called a context-free grammar, selects mathematical function sets and arbitrary elements from the set of end nodes, Form a population of initial process models. The second step is to run all the process models belonging to the population and conduct a fitness test on how well each process model in the population can predict the effluent quality. In the third step, the process models with good fit survive this fitness result and use a genetic operator to form a new population of process models for the next generation. That is, at this stage, mainly through reproduction of process models with good fit, crossovers exchanging portions of two superior process models, and mutation processes modifying some of the process models To form a population of better mathematical process models. Through such an iterative process, optimal process model mathematical expressions are generated that can predict the discharge water information at the final best.

다음은 이러한 과정을 통해 최종적으로 생성된 수학적 공정모델과 그에 따른 예측결과를 나타낸 예이다(도 3b 참조).The following is an example of the finally generated mathematical process model through the above process and the predicted result thereof (see FIG. 3B).

여기서, Flow : 유량Here, Flow: Flow

RAS(Return Activated Sludge) : 반송율Return Activated Sludge (RAS): Return Rate

SVI(Sludge Volume Index) : 슬러지용량지표 SVI (Sludge Volume Index): Sludge capacity indicator

MLSS(Mixed Liquor Suspended Sludge) : 슬러지 농도 MLSS (Mixed Liquor Suspended Sludge): Sludge concentration

BODeff(effluent of Biochemical Oxygen Demand) : 유출수의 생물학적 산소요구량BOD eff (effluent of Biochemical Oxygen Demand): Biological oxygen demand of effluent

SRT(Sludge Retention Time) : 슬러지체류시간SRT (Sludge Retention Time): Sludge residence time

pH : 수소이온농도pH: hydrogen ion concentration

temp(temperature) : 온도를 의미하며,temp (temperature) means temperature,

현재의 시간을 t라고 가정할 때, Flow(t-2)는 t-2시간에서의 유량 값을 의미한다.
Assuming that the current time is t, Flow (t-2) means the flow rate value at time t-2.

진화적 수학적 공정모델을 통해 하ㆍ폐수처리장의 방류수질에 대한 수학식을 도출할 수 있으며, 이에 따른 수학식의 산정을 통해 각 방류수질 항목에 대한 수질을 예측할 수 있으며, 아래 그래프와 같이 예측수질을 시계열로 나타낼 수 있다. 그래프에서 나타난 것처럼 진화적 공정모델시스템을 통해 예측된 방류수질은 실제 측정한 방류수질과 거의 비슷한 것을 알 수 있다.
The evolutionary mathematical process model can be used to derive mathematical equations for the effluent quality of sewage and wastewater treatment plants. The estimation of the water quality of each effluent water quality item can be estimated through the calculation of mathematical formulas. Can be expressed in a time series. As shown in the graph, the predicted effluent quality through the evolutionary process model system is almost similar to the actual effluent quality.

도 4에 본 발명에 의한 수처리장의 인공지능 통합 제어시스템에서 예측모델생성부에 채택되는 인공지능 프로그램의 일예로서 GBGP의 유전자 연산과정의 예를 보여주는 도면을 도시하였다.FIG. 4 is a diagram showing an example of a genetic algorithm process of GBGP as an example of an artificial intelligence program adopted in a predictive model generation unit in an artificial intelligence integrated control system of a water treatment plant according to the present invention.

도시된 예에 하면, 다음과 같이 공정모델이 생성, 변형하게 된다. : 적합도 검사를 통해서 적합도가 높은 모델을 선택(selection)하여 다음 세대로의 생존 분포(모델 복제)를 결정한다. 선택된 부모모델과 자녀모델의 교차연산(crossover)을 통해 각각의 공정모델의 위치에 작은 변화가 생기는 것을 알 수 있으며, 이를 통해 개체군내의 공정모델들을 진화적으로 변형해서, 좀 더 나은 공정모델들을 생성해낸다. 돌연변이(mutation) 연산은 단일 공정모델를 선택한 후 새롭게 생성한 공정모델의 한 나뭇가지 (sub-tree)를 선택하여 교체함으로써 새로운 개체군의 공정모델들을 변형해 나간다. In the illustrated example, a process model is created and modified as follows. : The selection of a model with high fitness is selected through the fitness test to determine the survival distribution (model replica) to the next generation. A crossover of the selected parent and child models reveals a small change in the location of each process model, evolving the process models in the population to evolve into better process models I'll do it. The mutation operation modifies the process models of the new population by selecting a single process model and then selecting and replacing a single sub-tree of the newly created process model.

한편, 일반적으로 하,폐수처리장 운영수질에 가장 많은 영향을 주는 것은 유입수 유량이다. 따라서, 인공지능프로그램으로 예측한 수질이 방류수 수질기준 혹은 사용자가 원하는 수질을 초과하였을 경우, 예시적으로, 다음과 같이 유량을 제어하는 방법으로 수질이 초과하지 않도록 조치할 수 있다(도 2 참조).On the other hand, influent water flow rate is the most influential factor in the operating water quality of wastewater treatment plants in general. Therefore, when the water quality predicted by the artificial intelligence program exceeds the discharged water quality standard or the user desired water quality, the water quality can be prevented from being exceeded by controlling the flow rate as an example (refer to FIG. 2) .

유입유량계 혹은 수위센서 등의 센서부를 통해 현재 유입되는 유입유량을 예측모델생성부로 전송한다. 이후 예측모델생성부의 인공지능프로그램을 통해 방류수질을 수질기준 항목별로 예측할 수 있으며, 예측된 수질이 수질기준 혹은 사용자 기준에 부합한지를 판단할 수 있다. 만약 그렇지 않는다면, 계산출력부가 수질기준 혹은 사용자 기준을 만족시키는 유입유량을 계산하여 공정제어부로 전송한다. 공정제어부는 도 2에 예시적으로 도시된 바와 같이 각 단위공정의 인버터를 제어하여 유입유량을 감소시키고, 감소된 유량만큼을 내부반송과 슬러지반송에 각각 1:1로 배분하여 인버터 유량을 기존보다 증가시킨다. 이러한 기작이 즉각적으로 일어남으로서 간편하게 소정의 방류수 수질기준을 충족하는 방류수를 방출하게 된다.And the inflow flow rate currently flowing through the sensor unit such as an inflow flow meter or a water level sensor is transmitted to the prediction model generation unit. Thereafter, the artificial intelligence program of the predictive model generation unit predicts the discharge water quality by the water quality standard item, and it can be judged whether the predicted water quality meets the water quality standard or the user standard. If not, the calculation output calculates an influent flow rate that meets water quality or user criteria and sends it to the process control. The process control unit controls the inverter of each unit process as shown in FIG. 2 to reduce the inflow flow rate, and distributes the reduced flow rate to the internal transfer and the sludge transport at a ratio of 1: 1, . Such a mechanism immediately occurs, thereby discharging discharged water satisfying predetermined water quality standards.

실제 현장에서 KNR 공법에 따라 운전 중인 수처리장에서 유입유량 및 수질 변동(설계대비)에 대한 대응방안의 예를 아래 표에 나타내었다. 이 방안은 인공지능프로그램과 결합되지 않은 제어방법이지만, 현장 운전 및 제어에 매우 효과적이며, 처리수질 또한 안정적이다. 따라서, 인공지능프로그램과 결부된 본 발명에 의한 수처리장의 인공지능 통합 제어시스템에 의하면 유량에 따른 방류수질기준 혹은 사용자 기준에 부합할 수 있는 운전모드를 더욱 더 세분화할 수 있어 최적처리장 운전이 가능하게 될 것이다.Examples of countermeasures against influent flow rate and water quality fluctuation (compared with design) at a water treatment plant in operation in accordance with the KNR method are shown in the table below. This method is a control method that is not combined with an AI program, but is very effective for on-site operation and control, and the quality of the treated water is also stable. Therefore, according to the artificial intelligence integrated control system of the water treatment plant according to the present invention combined with the artificial intelligence program, the operation mode capable of meeting the discharged water quality standard or the user standard according to the flow rate can be further subdivided, .

Figure pat00003
Figure pat00003

본 발명에 의한 수처리장의 인공지능 통합 제어시스템은 하ㆍ폐수처리장 무인 및 자동화를 위한 운영 및 제어시스템에 적용 가능하다. 유럽을 비롯한 선진국에서는 STAR, STAC 등의 제어시스템을 개발하였으나, 단순 인자만을 반영한 시스템으로 다양한 인자 반영이 필요한 하ㆍ폐수처리장 시스템 구현에 많은 어려움이 있다. 따라서, 본 발명에서 구현한 인공지능 통합 제어시스템은 인공지능에 장착된 진화적 공정모델시스템을 이용해서 다양한 운영인자를 반영한 방류수질을 예측할 수 있는 수학적 공정모델구축이 가능해지고, 효과적인 운영 및 제어 시스템 구현이 가능할 것이다. 이로 인해 본 발명에 대한 환경산업의 수요가 증가될 것이며, 인공지능통합 PLC 제어시스템은 다양한 산업분야 전반에서 응용 및 접목이 가능한 기술이 될 것이다.The artificial intelligence integrated control system of the water treatment plant according to the present invention is applicable to an operation and control system for unmanned and wastewater treatment plant unmanned and automated. In Europe and other advanced countries, STAR and STAC have developed control systems. However, there are many difficulties in implementing a sewage and wastewater treatment plant system that reflects various factors with a system that reflects only simple factors. Accordingly, the artificial intelligence integrated control system implemented in the present invention can construct a mathematical process model that can predict the discharged water quality reflecting various operating factors by using an evolutionary process model system installed in artificial intelligence, Implementation will be possible. As a result, the demand of the environment industry for the present invention will be increased, and the artificial intelligence integrated PLC control system will be applied and applied in various industrial fields.

또한, 측정 및 계측기술이 한 단계 더 진보한다면, 본 발명에서 제시한 내용의 정보보다 더 많은 정보의 수질을 예측할 수 있으며, 처리장에 따라 최적운전이 가능할 수 있는 제어시스템 보급이 가능할 것이다.
Further, if the measurement and measurement technology advances one step further, it is possible to predict the quality of water more than the information provided by the present invention and to spread the control system capable of optimum operation according to the treatment site.

304...context-free grammar, 305...개체군 생성단계, 306...모델 최적화 단계,
307...모델 적합도 평가단계, 308....유전자 루프
304 ... context-free grammar, 305 ... population generation step, 306 ... model optimization step,
307 ... model fitness evaluation step, 308 .... gene loop

Claims (4)

(A) 유입수질, 유입수량과 처리장 내 단위공정들의 운전인자, 방류수질 및 방류수량을 실시간으로 측정하는 센서부;
(B) 상기 센서부에 의해 수집된 데이터를 저장하는 기억부;
(C) 상기 데이터를 참조하여 수처리장의 방류수질 예측모델을 구축하는 진화적 예측모델 생성 인공지능 프로그램이 결합된 예측모델생성부;
(D) 상기 센서부에 의해 수집된 현재 유입수질, 유입수량과 처리장 내 운전인자를 상기 예측모델에 적용하여 t시간 후의 방류수질을 예측하고, 예측된 방류수질이 기준 방류수질 범위 밖인 경우 유입수량과 운전인자를 가상으로 변경하고 상기 예측모델을 적용하여 예측된 방류수질이 기준 방류수질 범위 내가 되도록 하는 유입수량과 운전인자를 추출하는 계산출력부;
(E) 상기 추출된 유입수량과 운전인자를 근거로 각 단위공정을 제어하는 공정제어부;
를 포함하는 것을 특징으로 하는 수처리장의 인공지능 통합 제어시스템.
(A) a sensor unit for measuring the influent water quality, the influent water quantity, the operation factors of the unit processes in the treatment plant, the discharge water quality and the discharge water quantity in real time;
(B) a storage unit for storing data collected by the sensor unit;
(C) a prediction model generation unit coupled with an evolutionary prediction model generation artificial intelligence program for constructing a discharge water quality prediction model of a water treatment plant by referring to the data;
(D) estimating the discharged water quality after time t by applying the present influent water quality, the influent water quantity and the operation factor in the treatment plant collected by the sensor unit to the prediction model, and if the predicted discharged water quality is out of the reference discharge water quality range, And a calculation output unit for extracting an influent water quantity and an operation factor for virtually changing the operation factor and applying the prediction model so that the predicted discharged water quality is within the reference discharge water quality range;
(E) a process control unit for controlling each unit process based on the extracted influent water quantity and operating factor;
And an integrated control system for artificial intelligence of a water treatment plant.
제 1 항에 있어서,
상기 인공지능 프로그램은 그램마-유전자프로그래밍(Grammar-based Genetic Programming, GBGP) 기술에 의하여 수학적으로 표현되는 진화적 공정모델시스템(evolutionary process induction system)인 것을 특징으로 하는 수처리장의 인공지능 통합 제어시스템.
The method according to claim 1,
Wherein said artificial intelligence program is an evolutionary process induction system mathematically represented by Grammar-based Genetic Programming (GBGP) technology. .
제 1 항 또는 제 2 항에 있어서,
상기 공정제어부는 PLC(Programmable Logic Controller) 형태인 것을 특징으로 하는 수처리장의 인공지능 통합 제어시스템.
3. The method according to claim 1 or 2,
Wherein the process control unit is in the form of PLC (Programmable Logic Controller).
제 1 항 또는 제 2 항에 있어서,
상기 유입수질 및 방출수질 항목은 수질분석 항목인 온도, BOD, COD, SS, T-N, T-P를 포함하며, 내부인자는 DO, MLSS, 슬러지반송유량, 내부반송유량, 온도를 포함하는 것을 특징으로 하는 수처리장의 인공지능 통합 제어시스템.
3. The method according to claim 1 or 2,
Wherein the influent water quality and the discharged water quality item include temperature, BOD, COD, SS, TN and TP which are water quality analysis items and the internal factors include DO, MLSS, sludge conveying flow rate, internal conveying flow rate, Integrated control system of artificial intelligence of water treatment plant.
KR1020130063930A 2013-06-04 2013-06-04 Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus KR101629240B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020130063930A KR101629240B1 (en) 2013-06-04 2013-06-04 Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020130063930A KR101629240B1 (en) 2013-06-04 2013-06-04 Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus

Publications (2)

Publication Number Publication Date
KR20140142491A true KR20140142491A (en) 2014-12-12
KR101629240B1 KR101629240B1 (en) 2016-06-10

Family

ID=52459959

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020130063930A KR101629240B1 (en) 2013-06-04 2013-06-04 Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus

Country Status (1)

Country Link
KR (1) KR101629240B1 (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016167513A1 (en) * 2015-04-17 2016-10-20 주식회사 부강테크 Oxygen supply device for wastewater/sewage treatment device capable of adjusting oxygen concentration
CN110357236A (en) * 2019-08-16 2019-10-22 江苏如是数学研究院有限公司 A kind of sewage plant wisdom control method based on mutation inverting water outlet prediction model
CN111661884A (en) * 2020-06-15 2020-09-15 上海水成环保科技股份有限公司 Control method and device based on water treatment, terminal and readable storage medium
CN112573641A (en) * 2020-11-20 2021-03-30 中国环境科学研究院 Sewage treatment capacity determining method and device
CN112631221A (en) * 2020-12-16 2021-04-09 四川绿水环保工程有限公司 Sewage treatment remote monitoring system and method thereof
CN112707605A (en) * 2021-01-19 2021-04-27 中鼎特金秦皇岛科技股份有限公司 Intelligent modularized wastewater treatment integrated system
CN115373347A (en) * 2022-03-31 2022-11-22 北京工业大学 Integrated intelligent optimization control method for sewage treatment process
KR20230086850A (en) 2021-12-08 2023-06-16 경희대학교 산학협력단 Data­Driven Hybrid Model for Forecasting Wastewater Infuent Loads Based on Multimodal and Ensemble Deep Learning

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102131847B1 (en) * 2020-04-09 2020-07-09 현시스메틱 주식회사 System and method for automatically control of water treatment using machine learning
KR102403493B1 (en) * 2021-03-12 2022-05-30 환경시설관리 주식회사 Integrated management system of sewage and wastewater treatment plants using artificial intelligence
KR102440371B1 (en) * 2021-11-26 2022-09-05 니브스코리아 주식회사 Providing method, apparatus and computer-readable medium of managing effluent environmental information of sewage treatment facilities based on big data and artificial intelligence
KR20230086849A (en) 2021-12-08 2023-06-16 경희대학교 산학협력단 Dual­objective optimization for energy­saving and fouling mitigation in MBR plants using AI­based influent prediction and an integrated biological­physical model
KR20230086851A (en) 2021-12-08 2023-06-16 경희대학교 산학협력단 A hybrid machine learningebased multi­objective supervisory control strategy of a full­scale wastewater treatment for cost­effective and sustainable operation under varying infuent conditions
KR20230128190A (en) 2022-02-25 2023-09-04 경희대학교 산학협력단 An intelligent protocol of multi-agent reinforcement learning- based autonomous model calibration for ASM-type model of membrane bioreactor
KR20230128191A (en) 2022-02-25 2023-09-04 경희대학교 산학협력단 An auto-adaptive controller tuning system for wastewater treatment process using data-driven smart decisions of offline reinforcement learning
KR102587787B1 (en) * 2022-11-28 2023-10-13 금강엔지니어링 주식회사 Intelligent control system of mbr wastewater treatment device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20070070647A (en) * 2005-12-29 2007-07-04 (주)대우건설 United managing system for waste treatment facility using the quality of water simulator and statistical analysis method
KR100920522B1 (en) * 2009-05-21 2009-10-09 대양바이오테크 주식회사 Device and method for diagnosing and controlling wastewater treatment process
KR20110137164A (en) * 2010-06-16 2011-12-22 한국바이오시스템(주) Method and system for controlling waste water treatment process

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20070070647A (en) * 2005-12-29 2007-07-04 (주)대우건설 United managing system for waste treatment facility using the quality of water simulator and statistical analysis method
KR100920522B1 (en) * 2009-05-21 2009-10-09 대양바이오테크 주식회사 Device and method for diagnosing and controlling wastewater treatment process
KR20110137164A (en) * 2010-06-16 2011-12-22 한국바이오시스템(주) Method and system for controlling waste water treatment process

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JOURNAL OF ENVIRONMENTAL ENGINEERING VOLUME 133, ISSUE 12 (DECEMBER 2007 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016167513A1 (en) * 2015-04-17 2016-10-20 주식회사 부강테크 Oxygen supply device for wastewater/sewage treatment device capable of adjusting oxygen concentration
CN110357236A (en) * 2019-08-16 2019-10-22 江苏如是数学研究院有限公司 A kind of sewage plant wisdom control method based on mutation inverting water outlet prediction model
CN110357236B (en) * 2019-08-16 2022-01-25 江苏如是数学研究院有限公司 Sewage plant intelligent control method based on mutation inversion effluent prediction model
CN111661884A (en) * 2020-06-15 2020-09-15 上海水成环保科技股份有限公司 Control method and device based on water treatment, terminal and readable storage medium
CN112573641A (en) * 2020-11-20 2021-03-30 中国环境科学研究院 Sewage treatment capacity determining method and device
CN112631221A (en) * 2020-12-16 2021-04-09 四川绿水环保工程有限公司 Sewage treatment remote monitoring system and method thereof
CN112707605A (en) * 2021-01-19 2021-04-27 中鼎特金秦皇岛科技股份有限公司 Intelligent modularized wastewater treatment integrated system
KR20230086850A (en) 2021-12-08 2023-06-16 경희대학교 산학협력단 Data­Driven Hybrid Model for Forecasting Wastewater Infuent Loads Based on Multimodal and Ensemble Deep Learning
CN115373347A (en) * 2022-03-31 2022-11-22 北京工业大学 Integrated intelligent optimization control method for sewage treatment process

Also Published As

Publication number Publication date
KR101629240B1 (en) 2016-06-10

Similar Documents

Publication Publication Date Title
KR101629240B1 (en) Artificial Intelligence Programmable Logic Controller System for a Sewage and Wastewater Treatment Apparatus
Bernardelli et al. Real-time model predictive control of a wastewater treatment plant based on machine learning
KR940005029B1 (en) Supporting method and system for process control
KR102440371B1 (en) Providing method, apparatus and computer-readable medium of managing effluent environmental information of sewage treatment facilities based on big data and artificial intelligence
KR102440372B1 (en) Providing method, apparatus and computer-readable medium of managing influent environmental information of sewage treatment facilities based on big data and artificial intelligence
CN109879410A (en) Sewage treatment aeration control system
Behandish et al. Concurrent pump scheduling and storage level optimization using meta-models and evolutionary algorithms
CN102902257A (en) Sewage treatment process optimization and energy-saving control system and method
CN103632032A (en) Effluent index online soft measurement prediction method in urban sewage treatment process
JP2013064245A (en) Water intake/conveyance operation controller
Tejaswini et al. Multi-objective optimization based controller design for improved wastewater treatment plant operation
JP3790129B2 (en) Process simulator application control apparatus and method
Perendeci et al. Prediction of effluent quality of an anaerobic treatment plant under unsteady state through ANFIS modeling with on-line input variables
Nawaz et al. Intelligent human–machine interface: An agile operation and decision support for an ANAMMOX SBR system at a pilot-scale wastewater treatment plant
CN116088450A (en) Intelligent terminal control system of sewage treatment plant, construction method and control method
Ortiz-Martínez et al. Multiplicity of solutions in model-based multiobjective optimization of wastewater treatment plants
Han et al. Robust optimal control for anaerobic-anoxic-oxic reactors
Li et al. Real-time predictive control for chemical distribution in sewer networks using improved elephant herding optimization
Salles et al. Dynamic setpoint optimization using metaheuristic algorithms for wastewater treatment plants
Liu et al. Multi-objective optimization of cascade controller in combined biological nitrogen and phosphorus removal wastewater treatment plant
Le Quiniou et al. Optimization of drinking water and sewer hydraulic management: Coupling of a genetic algorithm and two network hydraulic tools
JP2009294731A (en) Plant controller automatically extracting operation know-how
Fernández-Arévalo et al. Diagnosis and optimization of WWTPs using the PWM library: full-scale experiences
Beraud et al. Multiobjective genetic algorithms for the optimisation of wastewater treatment processes
CN101794117B (en) Method for optimizing and controlling operation of membrane bioreactor based on mechanism model

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E601 Decision to refuse application
AMND Amendment
X701 Decision to grant (after re-examination)
GRNT Written decision to grant