WO2024117330A1 - Artificial intelligence-based method for predicting optimal operation points of fluid machine - Google Patents

Artificial intelligence-based method for predicting optimal operation points of fluid machine Download PDF

Info

Publication number
WO2024117330A1
WO2024117330A1 PCT/KR2022/019442 KR2022019442W WO2024117330A1 WO 2024117330 A1 WO2024117330 A1 WO 2024117330A1 KR 2022019442 W KR2022019442 W KR 2022019442W WO 2024117330 A1 WO2024117330 A1 WO 2024117330A1
Authority
WO
WIPO (PCT)
Prior art keywords
operating point
unit
fluid machine
efficiency
prediction unit
Prior art date
Application number
PCT/KR2022/019442
Other languages
French (fr)
Korean (ko)
Inventor
신용우
김래은
양성진
최종락
남지수
Original Assignee
한국전자기술연구원
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 한국전자기술연구원 filed Critical 한국전자기술연구원
Publication of WO2024117330A1 publication Critical patent/WO2024117330A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
    • F04D—NON-POSITIVE-DISPLACEMENT PUMPS
    • F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0286—Modifications to the monitored process, e.g. stopping operation or adapting control
    • G05B23/0294—Optimizing process, e.g. process efficiency, product quality

Definitions

  • the present invention relates to fluid machine control, and more specifically, to a system and method for predicting and controlling the optimal operating point of fluid machines (pumps, blowers, compressors).
  • a fluid machine is a general term for a machine that transmits and exchanges power using fluid as a moving material or medium. These fluid machines can be divided into powered and non-powered fluid machines depending on their purpose and characteristics.
  • a power fluid machine that is attached to an electric motor and transmits power to the fluid through an impeller or propeller, it is controlled so that it can be operated at the operating point with the highest system efficiency among the operating points that satisfy the target flow level for efficient control of energy. I'm doing it.
  • the present invention was created to solve the above problems, and the purpose of the present invention is to provide a system and method for predicting the optimal operating point of a fluid machine based on artificial intelligence based on various criteria.
  • a fluid machine control system for achieving the above object includes a setting unit that sets a target flow rate; a selection unit that selects an operating point prediction standard; and an operating point prediction unit that predicts the optimal operating point of the fluid machine based on the target flow rate set by the setting unit and the operating point prediction standard selected by the selection unit.
  • the operating point prediction criteria include maximum efficiency and minimum energy
  • the operating point prediction unit includes: a first operating point prediction unit, which is an artificial intelligence model learned to predict the optimal operating point that can maximize efficiency from the target flow rate; It may include a second operating point prediction unit, which is an artificial intelligence model learned to predict the optimal operating point that can minimize input power from the target flow rate.
  • the optimal operating point may include fluid pressure, rotational speed, input power, and impeller pitch of the fluid machine.
  • the fluid machine control system may further include a control unit that controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit.
  • the fluid machine control system includes a collection unit that collects data on the operation characteristics of the fluid machine; It may further include an efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine from the operation characteristic data collected by the collection unit.
  • Operating characteristic data may include fluid pressure, flow rate, rotational speed, and input power.
  • the efficiency prediction unit includes an operating unit efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine operating unit from fluid pressure, flow rate, and rotation speed;
  • a drive unit efficiency prediction unit which is an artificial intelligence model learned to predict the efficiency of the fluid machine drive unit from input power; It may include a calculation unit that calculates the overall efficiency of the fluid machine from the efficiency of the operating unit and the efficiency of the driving unit.
  • the fluid machine control system further includes a characteristic prediction unit, which is an artificial intelligence model learned to predict the remaining operation characteristic data from some of the operation characteristic data collected by the collection unit and the efficiency predicted by the efficiency prediction unit. It can be included.
  • a characteristic prediction unit which is an artificial intelligence model learned to predict the remaining operation characteristic data from some of the operation characteristic data collected by the collection unit and the efficiency predicted by the efficiency prediction unit. It can be included.
  • the fluid machine control system may further include an output unit that displays the optimal operating point predicted by the operating point prediction unit, the efficiency predicted by the efficiency prediction unit, and the operating characteristic data predicted by the characteristic prediction unit. You can.
  • setting a target flow rate Selecting an operating point prediction standard; and an operating point prediction step of predicting the optimal operating point of the fluid machine based on the set target flow rate and the selected operating point prediction standard.
  • an operating point prediction unit that predicts the optimal operating point of the fluid machine based on the target flow rate and the operating point prediction standard in the selection unit; and a control unit that controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit.
  • a fluid machine control system comprising a.
  • a fluid machine control method comprising a.
  • the optimal operating point that can maximize efficiency and the optimal operating point that can minimize input power are predicted based on artificial intelligence, thereby predicting the optimal operating point of the fluid machine. can be controlled based on various criteria.
  • FIG. 1 is a diagram showing the configuration of an artificial intelligence-based fluid machine control system according to an embodiment of the present invention
  • FIG. 2 is a diagram showing the detailed structure of the efficiency prediction unit of Figure 1;
  • Figure 3 is a diagram showing the detailed structure of the characteristic prediction unit of Figure 1;
  • FIG. 4 is a diagram showing the detailed structure of the operating point prediction unit of FIG. 1.
  • An embodiment of the present invention presents a method for predicting the optimal operating point of an artificial intelligence-based fluid machine.
  • This is a technology that uses artificial intelligence models for fluid machines (pumps, blowers, compressors) to predict optimal operating points based on various criteria and control fluid machines accordingly.
  • Figure 1 is a diagram showing the configuration of an artificial intelligence-based fluid machine control system according to an embodiment of the present invention.
  • the fluid machine control system utilizes an artificial intelligence model to predict the efficiency, characteristics, and optimal operating point of the fluid machine, and controls the fluid machine according to the predicted optimal operating point.
  • the fluid machine control system that performs this function includes a collection unit 110, an efficiency prediction unit 120, a characteristic prediction unit 130, a goal setting unit 140, and a standard selection unit. It is configured to include (150), an operating point prediction unit (160), an output unit (170), and a control unit (180).
  • the collection unit 110 collects data on the operation characteristics of the fluid machine.
  • the operating characteristic data collected by the collection unit 110 includes fluid pressure (P), flow rate (Q), rotation speed (RPM), and input power (E).
  • the efficiency prediction unit 120 is an artificial intelligence model learned to predict the efficiency (Eff.) of the fluid machine from the operation characteristic data collected by the collection unit 110.
  • Figure 2 shows the detailed structure of the efficiency prediction unit 120.
  • the efficiency prediction unit 120 includes an operation unit efficiency prediction unit 121, a drive unit efficiency prediction unit 122, and an overall efficiency calculation unit 123.
  • the operating unit efficiency prediction unit 121 is an artificial intelligence model learned to predict the efficiency of the fluid machine operating unit (impeller) from fluid pressure (P), flow rate (Q), and rotation speed (RPM).
  • the efficiency of the fluid machine operating unit is predicted from the fluid pressure (P), flow rate (Q), and rotation speed (RPM) by the operating unit efficiency prediction unit 121.
  • the drive unit efficiency prediction unit 122 is an artificial intelligence model learned to predict the efficiency of the fluid machine drive unit (electric motor) from the input power (E).
  • the efficiency of the fluid machine drive unit is predicted from the input power (E) by the drive unit efficiency prediction unit 122.
  • the overall efficiency calculation unit 123 calculates the overall efficiency of the fluid machine by multiplying the efficiency of the operating unit predicted by the operating unit efficiency prediction unit 121 and the efficiency of the driving unit predicted by the driving unit efficiency prediction unit 122.
  • the characteristic prediction unit 130 is configured to predict operation characteristic data of the fluid machine handled by the collection unit 110. It can be used when some driving characteristic data is lost when constructing a learning dataset.
  • Figure 3 shows the detailed structure of the characteristic prediction unit 130.
  • the characteristics prediction unit 130 includes a fluid pressure prediction unit 131, a flow rate prediction unit 132, a rotation speed prediction unit 133, and an input power prediction unit 134.
  • the fluid pressure prediction unit 131 is an artificial intelligence model learned to predict fluid pressure (P) from flow rate (Q), rotation speed (RPM), input power (E), and efficiency (Eff.).
  • the flow rate prediction unit 132 is an artificial intelligence model learned to predict flow rate (Q) from fluid pressure (P), rotation speed (RPM), input power (E), and efficiency (Eff.).
  • the rotation speed prediction unit 133 is an artificial intelligence model learned to predict the rotation speed (RPM) from fluid pressure (P), flow rate (Q), input power (E), and efficiency (Eff.).
  • the input power prediction unit 134 is an artificial intelligence model learned to predict input power (E) from fluid pressure (P), flow rate (Q), rotation speed (RPM), and efficiency (Eff.).
  • the target setting unit 140 is a means for setting the target flow rate (Q)
  • the standard selection unit 150 is a means for selecting a standard for operating point prediction.
  • the standards for operating point prediction are divided into two categories. One is to predict the operating point based on maximum efficiency, and the other is to predict the operating point based on minimum energy.
  • the operating point prediction unit 160 predicts the optimal operating point of the fluid machine based on the target flow rate (Q) set by the target setting unit 140 and the standard selected by the reference selection unit 150.
  • Figure 4 shows the detailed structure of the operating point prediction unit 160.
  • the operating point prediction unit 160 includes an optimal operating point prediction unit 161 based on maximum efficiency and an optimal operating point prediction unit 162 based on minimum energy.
  • the optimal operating point prediction unit 161 based on maximum efficiency operates when the maximum efficiency is selected as the standard in the standard selection unit 150.
  • the optimal operating point prediction unit 161 based on maximum efficiency is an artificial intelligence model learned to predict the optimal operating point that can maximize efficiency from the target flow rate (Q) set by the goal setting unit 140.
  • the optimal operating point prediction unit 162 based on minimum energy operates when the minimum energy is selected as the standard in the standard selection unit 150.
  • the minimum energy-based optimal operating point prediction unit 162 is an artificial intelligence model learned to predict the optimal operating point that can minimize the input power (E) from the target flow rate (Q) set by the goal setting unit 140. .
  • the optimal operating point predicted by the optimal operating point prediction units 161 and 162 includes fluid pressure (P), rotational speed (RPM), input power (E), and impeller pitch (p) of the fluid machine.
  • the output unit 170 displays the efficiency predicted by the efficiency prediction unit 120, the operating characteristic data predicted by the characteristic prediction unit 130, and the optimal operating point predicted by the operating point prediction unit 160. am.
  • the control unit 180 controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit 160.
  • the learning dataset can be obtained while operating the fluid machine.
  • the optimal operating point that can maximize efficiency and the optimal operating point that can minimize input power are predicted based on artificial intelligence, allowing the optimal operating point of the fluid machine to be controlled using various standards.
  • a computer-readable recording medium can be any data storage device that can be read by a computer and store data.
  • computer-readable recording media can be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, etc.
  • computer-readable codes or programs stored on a computer-readable recording medium may be transmitted through a network connected between computers.

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Feedback Control In General (AREA)
  • Mathematical Physics (AREA)
  • Control Of Positive-Displacement Air Blowers (AREA)

Abstract

Provided is an artificial intelligence-based method for predicting optimal operation points of a fluid machine. A fluid machine control system according to an embodiment of the present invention comprises: a setting unit for setting a target fluid amount; a selection unit for selecting operation point prediction criteria; and an operation point prediction unit which predicts an optimal operation point of a fluid machine on the basis of the target fluid amount set by the setting unit and the operation point prediction criteria selected in the selection unit. Accordingly, the optimal operation point at which efficiency is maximized and the optimal operation point at which input power is minimized can be predicted on the basis of artificial intelligence to control the optimal operation points of the fluid machine on the basis of various criteria.

Description

인공지능 기반 유체기계의 최적 운전점 예측 방법Optimal operating point prediction method for artificial intelligence-based fluid machines
본 발명은 유체기계 제어에 관한 것으로, 더욱 상세하게는 유체기계(펌프, 송풍기, 압축기)의 최적 운전점을 예측하여 제어하는 시스템 및 방법에 관한 것이다.The present invention relates to fluid machine control, and more specifically, to a system and method for predicting and controlling the optimal operating point of fluid machines (pumps, blowers, compressors).
유체기계란 유체를 동작 물질 혹은 매개로 하여 동력의 전달 및 교환을 수행하는 기계를 통칭한다. 이러한 유체기계는 사용 목적과 특성에 따라 동력 및 무동력 유체기계로 구분될 수 있다.A fluid machine is a general term for a machine that transmits and exchanges power using fluid as a moving material or medium. These fluid machines can be divided into powered and non-powered fluid machines depending on their purpose and characteristics.
전동기가 부착되어 임펠러나 프로펠러를 통해 유체로 동력을 전달시키는 동력 유체기계의 경우, 에너지의 효율적 제어를 위해 목표 유량 수준을 만족시키는 운전점들 중 시스템 효율이 가장 뛰어난 운전점에서 운용될 수 있도록 제어하고 있다.In the case of a power fluid machine that is attached to an electric motor and transmits power to the fluid through an impeller or propeller, it is controlled so that it can be operated at the operating point with the highest system efficiency among the operating points that satisfy the target flow level for efficient control of energy. I'm doing it.
하지만 유체기계의 효율은 입력 에너지와 선형적 비례 관계를 만족하지 않으므로, 최대 효율 운전점은 최소 에너지 운전점과는 일치하지 않으며, 따라서 시스템 효율 기반의 제어 알고리즘은 에너지 절감 측면에서 최적 운전 상태임을 보장할 수 없다는 불확실성을 내포한다.However, since the efficiency of fluid machines does not satisfy a linear proportional relationship with input energy, the maximum efficiency operating point does not coincide with the minimum energy operating point, and therefore the system efficiency-based control algorithm ensures the optimal operating state in terms of energy saving. It implies uncertainty that it cannot be done.
본 발명은 상기와 같은 문제점을 해결하기 위하여 안출된 것으로서, 본 발명의 목적은, 인공지능 기반으로 유체기계의 최적 운전점을 다양한 기준으로 예측하는 시스템 및 방법을 제공함에 있다.The present invention was created to solve the above problems, and the purpose of the present invention is to provide a system and method for predicting the optimal operating point of a fluid machine based on artificial intelligence based on various criteria.
상기 목적을 달성하기 위한 본 발명의 일 실시예에 따른 유체기계 제어 시스템은 목표 유량을 설정받는 설정부; 운전점 예측 기준을 선택받는 선택부; 및 설정부에 의해 설정된 목표 유량과 선택부에서 선택된 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측부;를 포함한다. A fluid machine control system according to an embodiment of the present invention for achieving the above object includes a setting unit that sets a target flow rate; a selection unit that selects an operating point prediction standard; and an operating point prediction unit that predicts the optimal operating point of the fluid machine based on the target flow rate set by the setting unit and the operating point prediction standard selected by the selection unit.
운전점 예측 기준은, 최대효율과 최소에너지를 포함하고, 운전점 예측부는, 목표 유량으로부터 효율을 최대로 할 수 있는 최적 운전점을 예측하도록 학습된 인공지능 모델인 제1 운전점 예측부; 목표 유량으로부터 입력 전력을 최소로 할 수 있는 최적 운전점을 예측하도록 학습된 인공지능 모델인 제2 운전점 예측부;를 포함할 수 있다. The operating point prediction criteria include maximum efficiency and minimum energy, and the operating point prediction unit includes: a first operating point prediction unit, which is an artificial intelligence model learned to predict the optimal operating point that can maximize efficiency from the target flow rate; It may include a second operating point prediction unit, which is an artificial intelligence model learned to predict the optimal operating point that can minimize input power from the target flow rate.
최적 운전점은, 유체기계의 유체 압력, 회전수, 입력 전력 및 임펠러 피치를 포함할 수 있다.The optimal operating point may include fluid pressure, rotational speed, input power, and impeller pitch of the fluid machine.
본 발명에 따른 유체기계 제어 시스템은 운전점 예측부에 의해 예측된 최적 운전점에 따라 유체기계를 제어하는 제어부를 더 포함할 수 있다.The fluid machine control system according to the present invention may further include a control unit that controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit.
본 발명에 따른 유체기계 제어 시스템은 유체기계의 운전 특성 데이터들을 수집하는 수집부; 수집부에 의해 수집되는 운전 특성 데이터들로부터 유체기계의 효율을 예측하도록 학습된 인공지능 모델인 효율 예측부;를 더 포함할 수 있다.The fluid machine control system according to the present invention includes a collection unit that collects data on the operation characteristics of the fluid machine; It may further include an efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine from the operation characteristic data collected by the collection unit.
운전 특성 데이터들은, 유체 압력, 유량, 회전수 및 입력 전력을 포함할 수 있다.Operating characteristic data may include fluid pressure, flow rate, rotational speed, and input power.
효율 예측부는, 유체 압력, 유량, 회전수로부터 유체기계 작동부의 효율을 예측하도록 학습된 인공지능 모델인 작동부 효율 예측부; 입력 전력으로부터 유체기계 구동부의 효율을 예측하도록 학습된 인공지능 모델인 구동부 효율 예측부; 작동부의 효율과 구동부의 효율로부터 유체기계의 전체 효율을 계산하는 계산부;를 포함할 수 있다.The efficiency prediction unit includes an operating unit efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine operating unit from fluid pressure, flow rate, and rotation speed; A drive unit efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine drive unit from input power; It may include a calculation unit that calculates the overall efficiency of the fluid machine from the efficiency of the operating unit and the efficiency of the driving unit.
본 발명에 따른 유체기계 제어 시스템은 수집부에 의해 수집된 일부의 운전 특성 데이터들과 효율 예측부에 의해 예측된 효율로부터 나머지 운전 특성 데이터를 예측하도록 학습된 인공지능 모델인 특성 예측부;를 더 포함할 수 있다.The fluid machine control system according to the present invention further includes a characteristic prediction unit, which is an artificial intelligence model learned to predict the remaining operation characteristic data from some of the operation characteristic data collected by the collection unit and the efficiency predicted by the efficiency prediction unit. It can be included.
본 발명에 따른 유체기계 제어 시스템은 운전점 예측부에 의해 예측된 최적 운전점, 효율 예측부에 의해 예측된 효율 및 특성 예측부에 의해 예측된 운전 특성 데이터를 표시하는 출력부;를 더 포함할 수 있다.The fluid machine control system according to the present invention may further include an output unit that displays the optimal operating point predicted by the operating point prediction unit, the efficiency predicted by the efficiency prediction unit, and the operating characteristic data predicted by the characteristic prediction unit. You can.
본 발명의 다른 측면에 따르면, 목표 유량을 설정받는 단계; 운전점 예측 기준을 선택받는 단계; 및 설정된 목표 유량과 선택된 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측단계;를 포함하는 것을 특징으로 하는 유체기계 제어 방법이 제공된다.According to another aspect of the present invention, setting a target flow rate; Selecting an operating point prediction standard; and an operating point prediction step of predicting the optimal operating point of the fluid machine based on the set target flow rate and the selected operating point prediction standard.
본 발명의 또다른 측면에 따르면, 목표 유량과 선택부에서 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측부; 및 운전점 예측부에 의해 예측된 최적 운전점에 따라 유체기계를 제어하는 제어부;를 포함하는 것을 특징으로 하는 유체기계 제어 시스템이 제공된다.According to another aspect of the present invention, an operating point prediction unit that predicts the optimal operating point of the fluid machine based on the target flow rate and the operating point prediction standard in the selection unit; and a control unit that controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit. A fluid machine control system is provided, comprising a.
본 발명의 또다른 측면에 따르면, 목표 유량과 선택부에서 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측단계; 및 운전점 예측단계에 의해 예측된 최적 운전점에 따라 유체기계를 제어하는 단계;를 포함하는 것을 특징으로 하는 유체기계 제어 방법이 제공된다.According to another aspect of the present invention, an operating point prediction step of predicting the optimal operating point of the fluid machine based on the target flow rate and the operating point prediction standard in the selection unit; and controlling the fluid machine according to the optimal operating point predicted by the operating point prediction step. A fluid machine control method comprising a.
이상 설명한 바와 같이, 본 발명의 실시예들에 따르면, 인공지능 기반으로 효율을 최대로 할 수 있는 최적 운전점과 입력 전력을 최소로 할 수 있는 최적 운전점을 예측하여, 유체기계의 최적 운전점을 다양한 기준으로 제어할 수 있게 된다.As described above, according to the embodiments of the present invention, the optimal operating point that can maximize efficiency and the optimal operating point that can minimize input power are predicted based on artificial intelligence, thereby predicting the optimal operating point of the fluid machine. can be controlled based on various criteria.
도 1은 본 발명의 일 실시예에 따른 인공지능 기반 유체기계 제어 시스템의 구성을 도시한 도면,1 is a diagram showing the configuration of an artificial intelligence-based fluid machine control system according to an embodiment of the present invention;
도 2는 도 1의 효율 예측부의 상세 구조를 나타낸 도면,Figure 2 is a diagram showing the detailed structure of the efficiency prediction unit of Figure 1;
도 3은 도 1의 특성 예측부의 상세 구조를 나타낸 도면,Figure 3 is a diagram showing the detailed structure of the characteristic prediction unit of Figure 1;
도 4는 도 1의 운전점 예측부의 상세 구조를 나타낸 도면이다.FIG. 4 is a diagram showing the detailed structure of the operating point prediction unit of FIG. 1.
이하에서는 도면을 참조하여 본 발명을 보다 상세하게 설명한다.Hereinafter, the present invention will be described in more detail with reference to the drawings.
본 발명의 실시예에서는 인공지능 기반 유체기계의 최적 운전점 예측 방법을 제시한다. 유체기계(펌프, 송풍기, 압축기)를 대상으로 인공지능 모델을 이용하여 다양한 기준의 최적 운전점들을 예측하고 그에 따라 유체기계를 제어하는 기술이다.An embodiment of the present invention presents a method for predicting the optimal operating point of an artificial intelligence-based fluid machine. This is a technology that uses artificial intelligence models for fluid machines (pumps, blowers, compressors) to predict optimal operating points based on various criteria and control fluid machines accordingly.
도 1은 본 발명의 일 실시예에 따른 인공지능 기반 유체기계 제어 시스템의 구성을 도시한 도면이다.Figure 1 is a diagram showing the configuration of an artificial intelligence-based fluid machine control system according to an embodiment of the present invention.
본 발명의 실시예에 따른 유체기계 제어 시스템은 인공지능 모델을 활용하여, 유체기계의 효율, 특성 및 최적 운전점을 예측하고, 예측한 최적 운전점에 따라 유체기기를 제어한다.The fluid machine control system according to an embodiment of the present invention utilizes an artificial intelligence model to predict the efficiency, characteristics, and optimal operating point of the fluid machine, and controls the fluid machine according to the predicted optimal operating point.
이와 같은 기능을 수행하는 유체기계 제어 시스템은, 도 1에 도시된 바와 같이, 수집부(110), 효율 예측부(120), 특성 예측부(130), 목표 설정부(140), 기준 선택부(150), 운전점 예측부(160), 출력부(170) 및 제어부(180)를 포함하여 구성된다.As shown in FIG. 1, the fluid machine control system that performs this function includes a collection unit 110, an efficiency prediction unit 120, a characteristic prediction unit 130, a goal setting unit 140, and a standard selection unit. It is configured to include (150), an operating point prediction unit (160), an output unit (170), and a control unit (180).
수집부(110)는 유체기계의 운전 특성 데이터들을 수집한다. 수집부(110)에 의해 수집되는 운전 특성 데이터들에는, 유체 압력(P), 유량(Q), 회전수(RPM), 입력 전력(E)이 포함된다.The collection unit 110 collects data on the operation characteristics of the fluid machine. The operating characteristic data collected by the collection unit 110 includes fluid pressure (P), flow rate (Q), rotation speed (RPM), and input power (E).
효율 예측부(120)는 수집부(110)에 의해 수집되는 운전 특성 데이터들로부터 유체기계의 효율(Eff.)을 예측하도록 학습된 인공지능 모델이다. 도 2에 효율 예측부(120)의 상세 구조를 나타내었다.The efficiency prediction unit 120 is an artificial intelligence model learned to predict the efficiency (Eff.) of the fluid machine from the operation characteristic data collected by the collection unit 110. Figure 2 shows the detailed structure of the efficiency prediction unit 120.
도시된 바와 같이 효율 예측부(120)는 작동부 효율 예측부(121), 구동부 효율 예측부(122) 및 전체 효율 계산부(123)를 포함하여 구성된다.As shown, the efficiency prediction unit 120 includes an operation unit efficiency prediction unit 121, a drive unit efficiency prediction unit 122, and an overall efficiency calculation unit 123.
작동부 효율 예측부(121)는 유체 압력(P), 유량(Q), 회전수(RPM)로부터 유체기계 작동부(임펠러)의 효율을 예측하도록 학습된 인공지능 모델이다. 작동부 효율 예측부(121)에 의해 유체 압력(P), 유량(Q), 회전수(RPM)로부터 유체기계 작동부의 효율이 예측된다.The operating unit efficiency prediction unit 121 is an artificial intelligence model learned to predict the efficiency of the fluid machine operating unit (impeller) from fluid pressure (P), flow rate (Q), and rotation speed (RPM). The efficiency of the fluid machine operating unit is predicted from the fluid pressure (P), flow rate (Q), and rotation speed (RPM) by the operating unit efficiency prediction unit 121.
구동부 효율 예측부(122)는 입력 전력(E)으로부터 유체기계 구동부(전동기)의 효율을 예측하도록 학습된 인공지능 모델이다. 구동부 효율 예측부(122)에 의해 입력 전력(E)으로부터 유체기계 구동부의 효율이 예측된다.The drive unit efficiency prediction unit 122 is an artificial intelligence model learned to predict the efficiency of the fluid machine drive unit (electric motor) from the input power (E). The efficiency of the fluid machine drive unit is predicted from the input power (E) by the drive unit efficiency prediction unit 122.
전체 효율 계산부(123)는 작동부 효율 예측부(121)에 의해 예측된 작동부의 효율과 구동부 효율 예측부(122)에 의해 예측된 구동부의 효율을 곱하여, 유체기계의 전체 효율을 계산한다.The overall efficiency calculation unit 123 calculates the overall efficiency of the fluid machine by multiplying the efficiency of the operating unit predicted by the operating unit efficiency prediction unit 121 and the efficiency of the driving unit predicted by the driving unit efficiency prediction unit 122.
다시 도 1을 참조하여 설명한다. 특성 예측부(130)는 수집부(110)에서 취급하는 유체기계의 운전 특성 데이터들을 예측하기 위한 구성이다. 학습 데이터셋을 구성함에 있어 운전 특성 데이터 일부가 유실된 경우에 활용될 수 있다.Description will be made again with reference to FIG. 1 . The characteristic prediction unit 130 is configured to predict operation characteristic data of the fluid machine handled by the collection unit 110. It can be used when some driving characteristic data is lost when constructing a learning dataset.
도 3에 특성 예측부(130)의 상세 구조를 나타내었다. 도시된 바와 같이 특성 예측부(130)는 유체 압력 예측부(131), 유량 예측부(132), 회전수 예측부(133) 및 입력 전력 예측부(134)를 포함하여 구성된다.Figure 3 shows the detailed structure of the characteristic prediction unit 130. As shown, the characteristics prediction unit 130 includes a fluid pressure prediction unit 131, a flow rate prediction unit 132, a rotation speed prediction unit 133, and an input power prediction unit 134.
유체 압력 예측부(131)는 유량(Q), 회전수(RPM), 입력 전력(E), 효율(Eff.)로부터 유체 압력(P)을 예측하도록 학습된 인공지능 모델이다.The fluid pressure prediction unit 131 is an artificial intelligence model learned to predict fluid pressure (P) from flow rate (Q), rotation speed (RPM), input power (E), and efficiency (Eff.).
유량 예측부(132)는 유체 압력(P), 회전수(RPM), 입력 전력(E), 효율(Eff.)로부터 유량(Q)을 예측하도록 학습된 인공지능 모델이다.The flow rate prediction unit 132 is an artificial intelligence model learned to predict flow rate (Q) from fluid pressure (P), rotation speed (RPM), input power (E), and efficiency (Eff.).
회전수 예측부(133)는 유체 압력(P), 유량(Q), 입력 전력(E), 효율(Eff.)로부터 회전수(RPM)를 예측하도록 학습된 인공지능 모델이다.The rotation speed prediction unit 133 is an artificial intelligence model learned to predict the rotation speed (RPM) from fluid pressure (P), flow rate (Q), input power (E), and efficiency (Eff.).
입력 전력 예측부(134)는 유체 압력(P), 유량(Q), 회전수(RPM), 효율(Eff.)로부터 입력 전력(E)을 예측하도록 학습된 인공지능 모델이다.The input power prediction unit 134 is an artificial intelligence model learned to predict input power (E) from fluid pressure (P), flow rate (Q), rotation speed (RPM), and efficiency (Eff.).
다시 도 1을 참조하여 설명한다. 목표 설정부(140)는 목표 유량(Q)을 설정하기 위한 수단이고, 기준 선택부(150)는 운전점 예측의 기준을 선택하기 위한 수단이다.Description will be made again with reference to FIG. 1 . The target setting unit 140 is a means for setting the target flow rate (Q), and the standard selection unit 150 is a means for selecting a standard for operating point prediction.
운전점 예측의 기준은 2가지로 분류된다. 하나는 최대효율을 기준으로 운전점을 예측하는 것이고, 다른 하나는 최소 에너지를 기준으로 운전점을 예측하는 것이다.The standards for operating point prediction are divided into two categories. One is to predict the operating point based on maximum efficiency, and the other is to predict the operating point based on minimum energy.
운전점 예측부(160)는 목표 설정부(140)에 의해 설정된 목표 유량(Q)과 기준 선택부(150)에서 선택된 기준으로 유체기계의 최적 운전점을 예측한다. 도 4에 운전점 예측부(160)의 상세 구조를 나타내었다. 도시된 바와 같이 운전점 예측부(160)는 최대효율 기준 최적 운전점 예측부(161)와 최소에너지 기준 최적 운전점 예측부(162)를 포함하여 구성된다.The operating point prediction unit 160 predicts the optimal operating point of the fluid machine based on the target flow rate (Q) set by the target setting unit 140 and the standard selected by the reference selection unit 150. Figure 4 shows the detailed structure of the operating point prediction unit 160. As shown, the operating point prediction unit 160 includes an optimal operating point prediction unit 161 based on maximum efficiency and an optimal operating point prediction unit 162 based on minimum energy.
최대효율 기준 최적 운전점 예측부(161)는 기준 선택부(150)에서 최대효율이 기준으로 선택된 경우에 동작한다. 최대효율 기준 최적 운전점 예측부(161)는 목표 설정부(140)에 의해 설정된 목표 유량(Q)으로부터 효율을 최대로 할 수 있는 최적 운전점을 예측하도록 학습된 인공지능 모델이다.The optimal operating point prediction unit 161 based on maximum efficiency operates when the maximum efficiency is selected as the standard in the standard selection unit 150. The optimal operating point prediction unit 161 based on maximum efficiency is an artificial intelligence model learned to predict the optimal operating point that can maximize efficiency from the target flow rate (Q) set by the goal setting unit 140.
최소에너지 기준 최적 운전점 예측부(162)는 기준 선택부(150)에서 최소에너지가 기준으로 선택된 경우에 동작한다. 최소에너지 기준 최적 운전점 예측부(162)는 목표 설정부(140)에 의해 설정된 목표 유량(Q)으로부터 입력 전력(E)을 최소로 할 수 있는 최적 운전점을 예측하도록 학습된 인공지능 모델이다.The optimal operating point prediction unit 162 based on minimum energy operates when the minimum energy is selected as the standard in the standard selection unit 150. The minimum energy-based optimal operating point prediction unit 162 is an artificial intelligence model learned to predict the optimal operating point that can minimize the input power (E) from the target flow rate (Q) set by the goal setting unit 140. .
최적 운전점 예측부들(161,162)에서 예측하는 최적 운전점에는 유체기계의 유체 압력(P), 회전수(RPM), 입력 전력(E), 임펠러 피치(p)가 포함된다.The optimal operating point predicted by the optimal operating point prediction units 161 and 162 includes fluid pressure (P), rotational speed (RPM), input power (E), and impeller pitch (p) of the fluid machine.
출력부(170)는 효율 예측부(120)에 의해 예측된 효율, 특성 예측부(130)에 의해 예측된 운전 특성 데이터, 운전점 예측부(160)에 의해 예측된 최적 운전점을 표시하는 디스플레이이다.The output unit 170 displays the efficiency predicted by the efficiency prediction unit 120, the operating characteristic data predicted by the characteristic prediction unit 130, and the optimal operating point predicted by the operating point prediction unit 160. am.
제어부(180)는 운전점 예측부(160)에 의해 예측된 최적 운전점에 따라 유체기계를 제어한다.The control unit 180 controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit 160.
한편 효율 예측부(120), 특성 예측부(130), 운전점 예측부(160)를 학습시킴에 있어, 학습 데이터셋은 유체기계를 운전하는 동안 획득할 수 있다.Meanwhile, when training the efficiency prediction unit 120, the characteristic prediction unit 130, and the operating point prediction unit 160, the learning dataset can be obtained while operating the fluid machine.
이 때, 유체기계의 전 운전 영역이 아닌 특정 운전 속도에서의 운전 특성 데이터만을 활용하는 것이 적정하다. 이는 특성 데이터 취합하기 위해서는 많은 운용 시간이 소모되어 초기 기동이 지연될 수 있다는 문제를 배제할 수 있다.At this time, it is appropriate to utilize only the operation characteristic data at a specific operation speed rather than the entire operation range of the fluid machine. This can rule out the problem that initial startup may be delayed because a lot of operating time is consumed to collect characteristic data.
나아가 취득된 특성 데이터를 데이터 증분(data augmentation) 하여 모조 특성 데이터를 생성하여 학습데이터셋에 추가하는 것도 가능하다.Furthermore, it is also possible to generate fake characteristic data by performing data augmentation on the acquired characteristic data and add it to the learning dataset.
지금까지 인공지능 기반 유체기계 제어 시스템 및 방법에 대해 바람직한 실시예를 들어 상세히 설명하였다.So far, the artificial intelligence-based fluid machine control system and method has been described in detail with preferred embodiments.
위 실시예에서는 인공지능 기반으로 효율을 최대로 할 수 있는 최적 운전점과 입력 전력을 최소로 할 수 있는 최적 운전점을 예측하여, 유체기계의 최적 운전점을 다양한 기준으로 제어할 수 있도록 하였다.In the above example, the optimal operating point that can maximize efficiency and the optimal operating point that can minimize input power are predicted based on artificial intelligence, allowing the optimal operating point of the fluid machine to be controlled using various standards.
한편, 본 실시예에 따른 장치와 방법의 기능을 수행하게 하는 컴퓨터 프로그램을 수록한 컴퓨터로 읽을 수 있는 기록매체에도 본 발명의 기술적 사상이 적용될 수 있음은 물론이다. 또한, 본 발명의 다양한 실시예에 따른 기술적 사상은 컴퓨터로 읽을 수 있는 기록매체에 기록된 컴퓨터로 읽을 수 있는 코드 형태로 구현될 수도 있다. 컴퓨터로 읽을 수 있는 기록매체는 컴퓨터에 의해 읽을 수 있고 데이터를 저장할 수 있는 어떤 데이터 저장 장치이더라도 가능하다. 예를 들어, 컴퓨터로 읽을 수 있는 기록매체는 ROM, RAM, CD-ROM, 자기 테이프, 플로피 디스크, 광디스크, 하드 디스크 드라이브, 등이 될 수 있음은 물론이다. 또한, 컴퓨터로 읽을 수 있는 기록매체에 저장된 컴퓨터로 읽을 수 있는 코드 또는 프로그램은 컴퓨터간에 연결된 네트워크를 통해 전송될 수도 있다.Meanwhile, of course, the technical idea of the present invention can be applied to a computer-readable recording medium containing a computer program that performs the functions of the device and method according to this embodiment. Additionally, the technical ideas according to various embodiments of the present invention may be implemented in the form of computer-readable code recorded on a computer-readable recording medium. A computer-readable recording medium can be any data storage device that can be read by a computer and store data. For example, of course, computer-readable recording media can be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, etc. Additionally, computer-readable codes or programs stored on a computer-readable recording medium may be transmitted through a network connected between computers.
또한, 이상에서는 본 발명의 바람직한 실시예에 대하여 도시하고 설명하였지만, 본 발명은 상술한 특정의 실시예에 한정되지 아니하며, 청구범위에서 청구하는 본 발명의 요지를 벗어남이 없이 당해 발명이 속하는 기술분야에서 통상의 지식을 가진자에 의해 다양한 변형실시가 가능한 것은 물론이고, 이러한 변형실시들은 본 발명의 기술적 사상이나 전망으로부터 개별적으로 이해되어져서는 안될 것이다.In addition, although preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the invention pertains without departing from the gist of the present invention as claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be understood individually from the technical idea or perspective of the present invention.

Claims (12)

  1. 목표 유량을 설정받는 설정부;A setting unit that sets the target flow rate;
    운전점 예측 기준을 선택받는 선택부; 및a selection unit that selects an operating point prediction standard; and
    설정부에 의해 설정된 목표 유량과 선택부에서 선택된 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측부;를 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system comprising: an operating point prediction unit that predicts the optimal operating point of the fluid machine based on the target flow rate set by the setting unit and the operating point prediction standard selected by the selection unit.
  2. 청구항 1에 있어서,In claim 1,
    운전점 예측 기준은,The operating point prediction criteria are:
    최대효율과 최소에너지를 포함하고,Includes maximum efficiency and minimum energy,
    운전점 예측부는,Operating point prediction unit,
    목표 유량으로부터 효율을 최대로 할 수 있는 최적 운전점을 예측하도록 학습된 인공지능 모델인 제1 운전점 예측부;A first operating point prediction unit, which is an artificial intelligence model learned to predict the optimal operating point that can maximize efficiency from the target flow rate;
    목표 유량으로부터 입력 전력을 최소로 할 수 있는 최적 운전점을 예측하도록 학습된 인공지능 모델인 제2 운전점 예측부;를 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system comprising a second operating point prediction unit, which is an artificial intelligence model learned to predict the optimal operating point that can minimize input power from the target flow rate.
  3. 청구항 2에 있어서,In claim 2,
    최적 운전점은,The optimal operating point is,
    유체기계의 유체 압력, 회전수, 입력 전력 및 임펠러 피치를 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system comprising fluid pressure, rotation speed, input power, and impeller pitch of the fluid machine.
  4. 청구항 1에 있어서,In claim 1,
    운전점 예측부에 의해 예측된 최적 운전점에 따라 유체기계를 제어하는 제어부를 더 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system further comprising a control unit that controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit.
  5. 청구항 1에 있어서,In claim 1,
    유체기계의 운전 특성 데이터들을 수집하는 수집부;A collection unit that collects data on the operation characteristics of the fluid machine;
    수집부에 의해 수집되는 운전 특성 데이터들로부터 유체기계의 효율을 예측하도록 학습된 인공지능 모델인 효율 예측부;를 더 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system further comprising an efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine from the operation characteristic data collected by the collection unit.
  6. 청구항 5에 있어서.In claim 5.
    운전 특성 데이터들은,The driving characteristic data is,
    유체 압력, 유량, 회전수 및 입력 전력을 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system comprising fluid pressure, flow rate, rotation speed, and input power.
  7. 청구항 6에 있어서,In claim 6,
    효율 예측부는,Efficiency prediction department,
    유체 압력, 유량, 회전수로부터 유체기계 작동부의 효율을 예측하도록 학습된 인공지능 모델인 작동부 효율 예측부;An operating unit efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine operating unit from fluid pressure, flow rate, and rotation speed;
    입력 전력으로부터 유체기계 구동부의 효율을 예측하도록 학습된 인공지능 모델인 구동부 효율 예측부;A drive unit efficiency prediction unit, which is an artificial intelligence model learned to predict the efficiency of the fluid machine drive unit from input power;
    작동부의 효율과 구동부의 효율로부터 유체기계의 전체 효율을 계산하는 계산부;를 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system comprising a calculation unit that calculates the overall efficiency of the fluid machine from the efficiency of the operating unit and the efficiency of the driving unit.
  8. 청구항 5에 있어서,In claim 5,
    수집부에 의해 수집된 일부의 운전 특성 데이터들과 효율 예측부에 의해 예측된 효율로부터 나머지 운전 특성 데이터를 예측하도록 학습된 인공지능 모델인 특성 예측부;를 더 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control further comprising a characteristic prediction unit, which is an artificial intelligence model trained to predict the remaining driving characteristic data from some of the driving characteristic data collected by the collection unit and the efficiency predicted by the efficiency prediction unit. system.
  9. 청구항 8에 있어서,In claim 8,
    운전점 예측부에 의해 예측된 최적 운전점, 효율 예측부에 의해 예측된 효율 및 특성 예측부에 의해 예측된 운전 특성 데이터를 표시하는 출력부;를 더 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system further comprising an output unit that displays the optimal operating point predicted by the operating point prediction unit, the efficiency predicted by the efficiency prediction unit, and the operating characteristic data predicted by the characteristic prediction unit.
  10. 목표 유량을 설정받는 단계;Setting a target flow rate;
    운전점 예측 기준을 선택받는 단계; 및Selecting an operating point prediction standard; and
    설정된 목표 유량과 선택된 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측단계;를 포함하는 것을 특징으로 하는 유체기계 제어 방법.A fluid machine control method comprising a operating point prediction step of predicting the optimal operating point of the fluid machine based on the set target flow rate and the selected operating point prediction standard.
  11. 목표 유량과 선택부에서 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측부; 및An operating point prediction unit that predicts the optimal operating point of the fluid machine based on the target flow rate and the operating point prediction standard in the selection unit; and
    운전점 예측부에 의해 예측된 최적 운전점에 따라 유체기계를 제어하는 제어부;를 포함하는 것을 특징으로 하는 유체기계 제어 시스템.A fluid machine control system comprising a control unit that controls the fluid machine according to the optimal operating point predicted by the operating point prediction unit.
  12. 목표 유량과 선택부에서 운전점 예측 기준을 기초로, 유체기계의 최적 운전점을 예측하는 운전점 예측단계; 및An operating point prediction step of predicting the optimal operating point of the fluid machine based on the target flow rate and the operating point prediction standard in the selection unit; and
    운전점 예측단계에 의해 예측된 최적 운전점에 따라 유체기계를 제어하는 단계;를 포함하는 것을 특징으로 하는 유체기계 제어 방법.A fluid machine control method comprising: controlling the fluid machine according to the optimal operating point predicted by the operating point prediction step.
PCT/KR2022/019442 2022-12-02 2022-12-02 Artificial intelligence-based method for predicting optimal operation points of fluid machine WO2024117330A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2022-0166178 2022-12-02
KR1020220166178A KR20240082492A (en) 2022-12-02 2022-12-02 Artificial Intelligence-based Optimal Operating Point Prediction Method for Fluid Machinery

Publications (1)

Publication Number Publication Date
WO2024117330A1 true WO2024117330A1 (en) 2024-06-06

Family

ID=91324258

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/019442 WO2024117330A1 (en) 2022-12-02 2022-12-02 Artificial intelligence-based method for predicting optimal operation points of fluid machine

Country Status (2)

Country Link
KR (2) KR20240082492A (en)
WO (1) WO2024117330A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR19990025431A (en) * 1997-09-12 1999-04-06 이일쇄 How to determine the optimal system of boosting pump type water supply system
KR100419006B1 (en) * 2001-10-05 2004-02-14 이경훈 The optimum selection method of cut-off valves in fluid supply pipe network
US7143016B1 (en) * 2001-03-02 2006-11-28 Rockwell Automation Technologies, Inc. System and method for dynamic multi-objective optimization of pumping system operation and diagnostics
KR102041787B1 (en) * 2017-11-29 2019-11-07 인하대학교 산학협력단 Decision method of optimal Working Fluid mixing ratio for maximizing the efficiency of organic rankine cycle system
JP2022510123A (en) * 2019-11-04 2022-01-26 姚福来 Power saving / optimization operation method of water pump unit and determination method of switching point

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR19990025431A (en) * 1997-09-12 1999-04-06 이일쇄 How to determine the optimal system of boosting pump type water supply system
US7143016B1 (en) * 2001-03-02 2006-11-28 Rockwell Automation Technologies, Inc. System and method for dynamic multi-objective optimization of pumping system operation and diagnostics
KR100419006B1 (en) * 2001-10-05 2004-02-14 이경훈 The optimum selection method of cut-off valves in fluid supply pipe network
KR102041787B1 (en) * 2017-11-29 2019-11-07 인하대학교 산학협력단 Decision method of optimal Working Fluid mixing ratio for maximizing the efficiency of organic rankine cycle system
JP2022510123A (en) * 2019-11-04 2022-01-26 姚福来 Power saving / optimization operation method of water pump unit and determination method of switching point

Also Published As

Publication number Publication date
KR20240082492A (en) 2024-06-11
KR20240083080A (en) 2024-06-11

Similar Documents

Publication Publication Date Title
WO2015023100A1 (en) Apparatus and system for providing energy information
WO2024117330A1 (en) Artificial intelligence-based method for predicting optimal operation points of fluid machine
CN108798997A (en) Control method, device, controller and system of wind generating set
WO2014104698A1 (en) Engine control device for hybrid construction machinery
CN115113814B (en) Neural network model online method and related device
US10539993B2 (en) Integrated energy storage systems in computing facilities
WO2012005391A1 (en) Horsepower control system of a hybrid excavator and control method therefor
CN114061101A (en) Control method and device, air conditioner fresh air equipment and storage medium
WO2017188475A1 (en) Non-contact identification method and system, for energy home appliances, using total power consumption and composite sensor
CN104391736A (en) Method for setting up sleep mode of virtual machine and device
CN112240632B (en) Method and device for controlling dehumidification of air conditioner and air conditioner
WO2021125664A1 (en) Method and system for operating multi-type wind farm controllers
KR20210103609A (en) AHU controlling system using A3C
CN116819191A (en) Remote phase sequence checking method and system for fixed-point detection function of power grid
Kaur et al. Hybrid Approach for Virtual Machine Optimization using BAT Algorithm in cloud
CN101231523B (en) Control system and method for sensibility charge
US20220146989A1 (en) Extension module, industrial equipment, and estimation method
CN212619044U (en) Novel underground ventilation system
WO2022045697A1 (en) Big data-based modular ai engine server and driving method thereof
WO2024090593A1 (en) Lightweight and low-power object recognition device and operation method thereof
CN112510732A (en) Power supply device and method based on high-speed flywheel and related equipment thereof
CN114132808A (en) Projection device and method capable of identifying opening and closing states of elevator door
KR102669930B1 (en) Virtual sensing method and system for variable Inlet Guide Vane control fluid device operating frequency based on metamodel
CN116860029B (en) Digital twinning-based boarding corridor bridge control method and related equipment
WO2021029563A1 (en) Method, system and non-transitory computer-readable recording medium for providing learning information

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22967305

Country of ref document: EP

Kind code of ref document: A1