WO2022139326A1 - Distributed edge computing-based autonomous factory operating system - Google Patents
Distributed edge computing-based autonomous factory operating system Download PDFInfo
- Publication number
- WO2022139326A1 WO2022139326A1 PCT/KR2021/019195 KR2021019195W WO2022139326A1 WO 2022139326 A1 WO2022139326 A1 WO 2022139326A1 KR 2021019195 W KR2021019195 W KR 2021019195W WO 2022139326 A1 WO2022139326 A1 WO 2022139326A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- edge computing
- optimal control
- intelligent
- factory
- operating system
- Prior art date
Links
- 238000000034 method Methods 0.000 claims abstract description 73
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 18
- 238000005457 optimization Methods 0.000 claims abstract description 17
- 238000004519 manufacturing process Methods 0.000 description 24
- 230000004044 response Effects 0.000 description 8
- 238000013136 deep learning model Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000007792 addition Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000009958 sewing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
- G05B19/4187—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow by tool management
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Definitions
- the present invention relates to an autonomous factory operating system based on distributed edge computing that enables small-quantity production in response to market demand.
- the conventional manufacturing process is a manufacturing system suitable for a supplier-oriented market.
- the supplier understands the market demand, manufactures the product by mass production, and supplies it to an agency or retail store, which is composed of a business model based on sales revenue.
- a personalized product eg, each individual's body size, weight, waist circumference, taste, etc.
- the conventional manufacturing system is composed of supplier-oriented product planning-development-manufacturing-logistics-sales, so it is difficult to build a multi-variety small-volume production system in response to the personalized market.
- the present invention has been derived to solve the above-mentioned problems, and aims to provide an autonomous factory operating system based on distributed edge computing that enables small-quantity production of various types in response to market demand.
- the autonomous factory operating system based on distributed edge computing can be applied to a factory including a plurality of process facilities.
- the autonomous factory operating system based on distributed edge computing is connected to each of the plurality of process equipment, collects process basic data related to the process equipment, and is defined based on the collected process basic data.
- a plurality of intelligent edge computing devices (AI-sons) that generate and apply optimal control conditions to process equipment according to an artificial intelligence algorithm; and each of the plurality of intelligent edge computing devices in a cloud environment to check the optimal control conditions for each of the plurality of process facilities, and according to a predefined artificial intelligence algorithm based on the identified optimal control conditions, the factory and an intelligent center computing device (AI-mother), which generates an optimization condition.
- AI-mother intelligent center computing device
- the autonomous factory operating system may further include a database for collecting and storing market demand information for products produced in the factory.
- the market demand information may include individual demand information for the product.
- the intelligent center computing device responds to the individual market demand of the product according to a predefined artificial intelligence algorithm based on the identified optimal control condition and the market demand information stored in the database It is possible to create factory optimization conditions for
- the intelligent center computing device may generate an optimal control condition for each of the plurality of intelligent edge computing devices (AI-son) based on the generated factory optimization condition .
- the intelligent center computing device provides the generated optimal control condition to each of the plurality of intelligent edge computing devices (AI-son), and the plurality of intelligent edge computing devices (AI-mother) -son) may update the pre-stored optimum control condition to the provided optimum control condition, and apply the updated optimum control condition to each process facility.
- the intelligent center computing device (AI-mother) generates the optimal control condition for each predefined time unit and provides it to each of the plurality of intelligent edge computing devices (AI-son), and the plurality of Each of the intelligent edge computing devices (AI-son) may update the pre-stored optimum control condition to the provided optimum control condition, and apply the updated optimum control condition to each process facility.
- the present invention relates to a plurality of intelligent edge computing devices (AI-son) that are connected to each of a plurality of process equipment to generate optimal control conditions according to an artificial intelligence algorithm and apply to the process equipment, and a plurality of intelligent edge computing devices ( It is composed of an intelligent center computing device (AI-mother) that interworks with AI-son) in a cloud environment to create factory optimization conditions according to an artificial intelligence algorithm, but the intelligent center computing device (AI-mother) Based on the optimal control conditions and the collected market demand information, factory optimization conditions are created and operated to provide these to a plurality of intelligent edge computing devices (AI-sons), thereby enabling small-volume production of individual products in response to market demand. do.
- AI-son intelligent edge computing devices
- 1 is a reference diagram for explaining a conventional manufacturing process.
- FIG. 2 is a reference diagram for explaining a manufacturing process according to the present invention.
- FIG. 3 is a reference diagram for explaining an autonomous factory operating system based on distributed edge computing according to the present invention.
- FIG. 2 is a reference diagram for explaining a manufacturing process according to the present invention.
- the conventional manufacturing process consists of supplier-oriented product planning-development-manufacturing-logistics-sales, so it is difficult to establish a multi-variety small-volume production system in response to a personalized market.
- the present invention has been devised to solve the problems of the conventional manufacturing process, and stores personalized specifications that meet the needs of the market in real time in a database, and utilizes artificial intelligence algorithms based on the stored data to optimize product production. By deriving the process specifications and applying the derived process specifications to each process facility, it is possible to produce small amounts of individually tailored multi-variety in response to market demand.
- FIG. 3 is a reference diagram for explaining an autonomous factory operating system based on distributed edge computing according to the present invention.
- the distributed edge computing-based autonomous factory operating system 10 (hereinafter, autonomous factory operating system) according to the present invention includes a plurality of process facilities 100 and a plurality of intelligent edge computing devices 200 and AI- son, hereinafter edge computing device), the intelligent center computing device (300, AI-mother, hereinafter center computing device) and may be configured to include a database (400).
- autonomous factory operating system includes a plurality of process facilities 100 and a plurality of intelligent edge computing devices 200 and AI- son, hereinafter edge computing device), the intelligent center computing device (300, AI-mother, hereinafter center computing device) and may be configured to include a database (400).
- the plurality of process facilities 100 are provided in a specific factory and correspond to facilities for performing a defined process, respectively.
- the first process equipment 100A corresponds to the fabric processing equipment
- the second process equipment 100B corresponds to the sewing process equipment
- the third process equipment 100C corresponds to the quality equipment. It may correspond to an inspection facility.
- these examples are not intended to limit the scope of the present invention, of course, the process equipment according to the present invention may correspond to various process equipment for producing a specific product.
- each of the plurality of process facilities 100 may be configured to include a control device 110 for performing a defined operation.
- each of the control devices 110A, 110B, 110C, ... may output a control signal for operating each of the process equipment 100A, 100B, 100C, ..., and the control signal is the process equipment 100A , 100B, 100C, (7) may include operation parameters for each.
- the edge computing device 200 is a computing device connected to each of the plurality of process facilities 100 .
- the edge computing devices 200A, 200B, 200C, ... are implemented as separate hardware and disposed or attached to the vicinity of the process facilities 100A, 100B, 100C, ... and interconnected through a wired/wireless network, or A plurality of process equipment (100A, 100B, 100C, ...) may be implemented by being included in the interior.
- the edge computing devices 200A, 200B, 200C, ... may collect process basic data associated with each of the process facilities 100A, 100B, 100C, ....
- the process basic data is data related to the operation of the process equipment 100 , and includes control signals, operating parameters, environmental conditions, operating conditions, process amounts, and control signals for each of the process facilities 100A, 100B, 100C, ... It may include failure events and the like.
- Each of the edge computing devices 200A, 200B, 200C, ... generates optimal control conditions for each of the process facilities 100A, 100B, 100C, ... according to a predefined artificial intelligence algorithm based on the collected process basic data. can do.
- the optimal control condition may mean a control signal capable of optimizing each process facility.
- each of the edge computing devices 200A, 200B, 200C, . can be analyzed using a predefined deep learning model to create optimal control conditions that can show the best process efficiency.
- the artificial intelligence algorithm may correspond to various well-known artificial intelligence models, for example, it may correspond to a deep learning-based learning model.
- a method for learning a deep learning model using various process basic data as input data and deriving an optimal control condition that is intended output information using the learned deep learning model is a well-known technology and is a core technology of the present invention. Since it is not an idea, a detailed description thereof will be omitted.
- Each of the edge computing devices 200A, 200B, 200C, ... may apply the generated optimal control condition to each of the process facilities 100A, 100B, 100C, .... That is, when the edge computing device 200 transmits the optimum control condition to the process facility 100 , the process facility 100 applies the optimum control condition to each control device 110 to operate according to the optimum control condition. have.
- the center computing device 300 may be linked with each of the edge computing devices 200A, 200B, 200C, ... in a cloud environment.
- the center computing device 300 may be implemented as a cloud server, and may be interconnected with each of the edge computing devices 200A, 200B, 200C, ... through a network to transmit and receive data.
- the center computing device 300 identifies optimal control conditions for each of the plurality of process facilities 100A, 100B, 100C, ..., and factory optimization conditions according to a predefined artificial intelligence algorithm based on the identified optimal control conditions can create
- the factory optimization condition may mean a condition for optimizing the entire factory including each process facility.
- the factory optimization condition may include product production by specification, operation time for each process facility, environmental conditions in the factory, etc., and also the optimum for each of the plurality of process facilities 100A, 100B, 100C, ... Control conditions may be included.
- the artificial intelligence algorithm may correspond to various well-known artificial intelligence models, for example, it may correspond to a deep learning-based learning model.
- the method of learning a deep learning model using the optimal control condition as input data and deriving the factory optimization condition, which is the intended output information, using the learned deep learning model is a well-known technology and is a core technical idea of the present invention. Since this is not the case, a detailed description thereof will be omitted.
- the database 400 may collect and store market demand information for products produced in a corresponding factory.
- the market demand information may mean information indicating product demand for each individual consumer, and may include individual demand information for each consumer.
- the market demand information may include clothing order information or an order quantity for each clothing model, size, and period.
- the database 400 may be connected to an external information providing device that provides market demand information through a network, and for example, the information providing device corresponds to a server of a sales company that sells products produced in a corresponding factory. can do.
- the market demand information may be processed according to a predefined format and stored in the database 400 .
- order information for each individual consumer is stored as raw data in the database 400 , or the raw data is processed in the form of an order quantity for each clothing model, size, and period through a quantitative analysis process and stored in the database 400 . it might be
- the center computing device 300 checks the optimal control conditions for each of the plurality of process facilities 100A, 100B, 100C, ... and the market demand information stored in the database 400, and the identified optimal control Based on the conditions and market demand information, it is possible to create factory optimization conditions according to a predefined artificial intelligence algorithm.
- the factory optimization condition according to this embodiment is an optimization condition for responding to individual market demand for products produced in the factory, and may include product production by specification according to product demand, operation time for each process facility, environmental conditions in the factory, etc. can
- the center computing device 300 may generate an optimal control condition for each of the plurality of process facilities 100A, 100B, 100C, ..., based on the generated factory optimization condition.
- the center computing device 300 may provide the generated optimal control condition to each of the edge computing devices 200A, 200B, 200C, .... Thereafter, each of the edge computing devices 200A, 200B, 200C, ... updates the optimal control conditions provided with the pre-stored optimal control conditions, and updates the updated optimal control conditions to the process facilities 100A, 100B, 100C, ... can be applied to each.
- the center computing device 300 generates an optimal control condition for each predefined time unit (eg, 2 minutes or 10 minutes, etc.) to provide to each of the edge computing devices 200A, 200B, 200C, ...
- each of the edge computing devices 200A, 200B, 200C, ... may update pre-stored information immediately upon receiving the optimal control condition.
- the center computing device (AI-mother) generates factory optimization conditions based on the optimal control conditions for each process facility and the collected market demand information, and uses the It is provided to computing devices (AI-son) so that each process facility operates optimally in response to the individual needs of each consumer, thereby enabling small-volume production of individually tailored multi-products in response to market demand.
- the operation of the autonomous factory operating system according to the present invention described above may be implemented as computer-readable codes on a computer-readable recording medium.
- the computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device.
- the computer-readable recording medium is distributed in network-connected computer systems, and computer-readable codes can be stored and executed in a distributed manner.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
A distributed edge computing-based autonomous factory operating system according to the present invention comprises: a plurality of intelligent edge computing devices which are connected to each of a plurality of process facilities to collect basic process data related to the process facilities, generate an optimal control condition according to a predefined artificial intelligence algorithm on the basis of the collected basic process data, and apply same to the process facilities; and an intelligent center computing device which is linked to each of the plurality of intelligent edge computing devices in a cloud environment to identify optimal control conditions for each of the plurality of process facilities, and generates factory optimization conditions according to a predefined artificial intelligence algorithm on the basis of the identified optimal control conditions.
Description
본 발명은 시장 수요에 대응한 다품종 소량 생산을 가능케하는 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템에 관한 것이다. The present invention relates to an autonomous factory operating system based on distributed edge computing that enables small-quantity production in response to market demand.
종래의 제조공정은 공급자 중심의 시장에 적합한 제조시스템이다. 도 1을 참조하면, 종래의 제조 공정의 경우, 공급자가 시장의 수요를 파악하여 대량생산으로 제품을 제조하고, 이를 대리점이나 소매점에 공급하여 제품을 판매한 판매수익을 기반으로 한 비즈니스 모델로 구성되어 있다. 이러한 종래의 제조 공정에 따르면, 제조 시스템에 피드백이 이루어지지 않아, 개인맞춤형 제품(예 : 의류 제조시 개인 각각의 신체사이즈, 몸무게, 허리둘레, 취향 등)을 생산하는데 한계가 있다.The conventional manufacturing process is a manufacturing system suitable for a supplier-oriented market. Referring to Figure 1, in the case of the conventional manufacturing process, the supplier understands the market demand, manufactures the product by mass production, and supplies it to an agency or retail store, which is composed of a business model based on sales revenue. has been According to this conventional manufacturing process, there is no feedback to the manufacturing system, so there is a limit in producing a personalized product (eg, each individual's body size, weight, waist circumference, taste, etc.) when manufacturing clothes.
즉, 종래 제조시스템은 공급자 중심의 제품기획-개발-제조-물류-판매의 형태로 구성되어 있어 개인맞춤형 시장에 대응한 다품종 소량 생산 시스템을 구축하는데 어려움이 있다. That is, the conventional manufacturing system is composed of supplier-oriented product planning-development-manufacturing-logistics-sales, so it is difficult to build a multi-variety small-volume production system in response to the personalized market.
현재, 이러한 종래의 제조 공정에 따른 문제점을 해결하기 위한 기술 개발이 절실한 실정이다.Currently, there is an urgent need to develop a technology to solve the problems according to the conventional manufacturing process.
본 발명은 상술된 문제점을 해결하기 위해 도출된 것으로, 시장 수요에 대응한 다품종 소량 생산을 가능케하는, 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템을 제공하고자 한다.The present invention has been derived to solve the above-mentioned problems, and aims to provide an autonomous factory operating system based on distributed edge computing that enables small-quantity production of various types in response to market demand.
본 발명에 따른 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템은 복수의 공정 설비들을 포함하는 공장에 적용될 수 있다. 여기에서, 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템은, 상기 복수의 공정 설비들 각각과 연결되어, 공정 설비와 연관되는 공정 기초 데이터를 수집하며, 상기 수집된 공정 기초 데이터를 기반으로 기정의된 인공지능 알고리즘에 따라 최적 제어 조건을 생성하여 공정 설비에 적용하는, 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들; 및 상기 복수의 지능형 엣지 컴퓨팅 디바이스들 각각과 클라우드 환경에서 연동되어, 상기 복수의 공정 설비들 각각에 대한 최적 제어 조건을 확인하고, 확인된 최적 제어 조건을 기반으로 기정의된 인공지능 알고리즘에 따라 공장 최적화 조건을 생성하는, 지능형 센터 컴퓨팅 디바이스(AI-mother);를 포함한다.The autonomous factory operating system based on distributed edge computing according to the present invention can be applied to a factory including a plurality of process facilities. Here, the autonomous factory operating system based on distributed edge computing is connected to each of the plurality of process equipment, collects process basic data related to the process equipment, and is defined based on the collected process basic data. a plurality of intelligent edge computing devices (AI-sons) that generate and apply optimal control conditions to process equipment according to an artificial intelligence algorithm; and each of the plurality of intelligent edge computing devices in a cloud environment to check the optimal control conditions for each of the plurality of process facilities, and according to a predefined artificial intelligence algorithm based on the identified optimal control conditions, the factory and an intelligent center computing device (AI-mother), which generates an optimization condition.
일 실시예에서, 상기 자율화 공장 운영 시스템은, 상기 공장에서 생산하는 제품에 대한 시장 수요 정보를 수집하여 저장하는 데이터베이스를 더 포함할 수 있다.In an embodiment, the autonomous factory operating system may further include a database for collecting and storing market demand information for products produced in the factory.
일 실시예에서, 상기 시장 수요 정보는, 상기 제품에 대한 수요자 개인별 요구 정보를 포함할 수 있다.In an embodiment, the market demand information may include individual demand information for the product.
일 실시예에서, 상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는 상기 확인된 최적 제어 조건과 상기 데이터베이스에 저장된 시장 수요 정보를 기반으로 기정의된 인공지능 알고리즘에 따라, 상기 제품의 개인별 시장 수요에 대응하기 위한 공장 최적화 조건을 생성할 수 있다.In one embodiment, the intelligent center computing device (AI-mother) responds to the individual market demand of the product according to a predefined artificial intelligence algorithm based on the identified optimal control condition and the market demand information stored in the database It is possible to create factory optimization conditions for
일 실시예에서, 상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는 상기 생성된 공장 최적화 조건을 기초로, 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각에 대한 최적 제어 조건을 생성할 수 있다. In one embodiment, the intelligent center computing device (AI-mother) may generate an optimal control condition for each of the plurality of intelligent edge computing devices (AI-son) based on the generated factory optimization condition .
일 실시예에서, 상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는 상기 생성된 최적 제어 조건을 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각에 제공하고, 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각은, 기저장된 최적 제어 조건을 제공받은 최적 제어 조건으로 갱신하고, 갱신된 최적 제어 조건을 공정 설비 각각에 적용할 수 있다. In an embodiment, the intelligent center computing device (AI-mother) provides the generated optimal control condition to each of the plurality of intelligent edge computing devices (AI-son), and the plurality of intelligent edge computing devices (AI-mother) -son) may update the pre-stored optimum control condition to the provided optimum control condition, and apply the updated optimum control condition to each process facility.
일 실시예에서, 상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는 기정의된 시간 단위마다 상기 최적 제어 조건을 생성하여 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각에 제공하며, 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각은, 기저장된 최적 제어 조건을 제공받은 최적 제어 조건으로 갱신하고, 갱신된 최적 제어 조건을 공정 설비 각각에 적용할 수 있다.In one embodiment, the intelligent center computing device (AI-mother) generates the optimal control condition for each predefined time unit and provides it to each of the plurality of intelligent edge computing devices (AI-son), and the plurality of Each of the intelligent edge computing devices (AI-son) may update the pre-stored optimum control condition to the provided optimum control condition, and apply the updated optimum control condition to each process facility.
본 발명은, 복수의 공정 설비들 각각과 연결되어 인공지능 알고리즘에 따라 최적 제어 조건을 생성하여 공정 설비에 적용하는 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들과, 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들과 클라우드 환경에서 연동되어 인공지능 알고리즘에 따라 공장 최적화 조건을 생성하는 지능형 센터 컴퓨팅 디바이스(AI-mother)로 구성되되, 지능형 센터 컴퓨팅 디바이스(AI-mother)가 공정 설비 각각에 대한 최적 제어 조건 및 수집된 시장 수요 정보를 기초로 공장 최적화 조건을 생성하고, 이를 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들에게 제공하도록 동작함으로써, 시장 수요에 대응한 개인 맞춤형 다품종 소량 생산을 가능케 한다.The present invention relates to a plurality of intelligent edge computing devices (AI-son) that are connected to each of a plurality of process equipment to generate optimal control conditions according to an artificial intelligence algorithm and apply to the process equipment, and a plurality of intelligent edge computing devices ( It is composed of an intelligent center computing device (AI-mother) that interworks with AI-son) in a cloud environment to create factory optimization conditions according to an artificial intelligence algorithm, but the intelligent center computing device (AI-mother) Based on the optimal control conditions and the collected market demand information, factory optimization conditions are created and operated to provide these to a plurality of intelligent edge computing devices (AI-sons), thereby enabling small-volume production of individual products in response to market demand. do.
도 1은 종래 제조 공정을 설명하기 위한 참조도이다. 1 is a reference diagram for explaining a conventional manufacturing process.
도 2는 본 발명에 따른 제조 공정을 설명하기 위한 참조도이다. 2 is a reference diagram for explaining a manufacturing process according to the present invention.
도 3은 본 발명에 따른 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템을 설명하기 위한 참조도이다.3 is a reference diagram for explaining an autonomous factory operating system based on distributed edge computing according to the present invention.
본 발명은 다양한 변환을 가할 수 있고 여러 가지 실시예를 가질 수 있는 바, 특정 실시예들을 도면에 예시하고 상세한 설명에 상세하게 설명하고자 한다. 그러나, 이는 본 발명을 특정한 실시 형태에 대해 한정하려는 것이 아니며, 본 발명의 사상 및 기술 범위에 포함되는 모든 변환, 균등물 내지 대체물을 포함하는 것으로 이해되어야 한다. 본 발명을 설명함에 있어서 관련된 공지 기술에 대한 구체적인 설명이 본 발명의 요지를 흐릴 수 있다고 판단되는 경우 그 상세한 설명을 생략한다.Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.
제1, 제2 등의 용어는 다양한 구성요소들을 설명하는데 사용될 수 있지만, 상기 구성요소들은 상기 용어들에 의해 한정되어서는 안 된다. 상기 용어들은 하나의 구성요소를 다른 구성요소로부터 구별하는 목적으로만 사용된다. Terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.
본 출원에서 사용한 용어는 단지 특정한 실시예를 설명하기 위해 사용된 것으로, 본 발명을 한정하려는 의도가 아니다. 단수의 표현은 문맥상 명백하게 다르게 뜻하지 않는 한, 복수의 표현을 포함한다. 본 출원에서, "포함하다" 또는 "가지다" 등의 용어는 명세서상에 기재된 특징, 숫자, 단계, 동작, 구성요소, 부품 또는 이들을 조합한 것이 존재함을 지정하려는 것이지, 하나 또는 그 이상의 다른 특징들이나 숫자, 단계, 동작, 구성요소, 부품 또는 이들을 조합한 것들의 존재 또는 부가 가능성을 미리 배제하지 않는 것으로 이해되어야 한다. 이하, 본 발명의 실시예를 첨부한 도면들을 참조하여 상세히 설명하기로 한다. The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof. Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
도 2는 본 발명에 따른 제조 공정을 설명하기 위한 참조도이다. 2 is a reference diagram for explaining a manufacturing process according to the present invention.
상술한 바와 같이, 종래의 제조공정은 공급자 중심의 제품기획-개발-제조-물류-판매의 형태로 구성되어, 개인맞춤형 시장에 대응한 다품종 소량 생산 시스템을 구축하는데 어려움이 있다. 본 발명은 이러한 종래 제조 공정의 문제점을 해결하기 위하여 안출된 것으로, 시장의 요구에 맞는 개인맞춤형 스펙을 실시간으로 데이터베이스에 저장하고, 저장된 데이터를 기반으로 인공지능 알고리즘을 활용하여 제품 생산을 위한 최적화된 공정 사양을 도출하며, 도출된 공정 사양을 각 공정 설비에 적용함으로써, 시장 수요에 대응한 개인 맞춤형 다품종 소량 생산을 가능케 한다. As described above, the conventional manufacturing process consists of supplier-oriented product planning-development-manufacturing-logistics-sales, so it is difficult to establish a multi-variety small-volume production system in response to a personalized market. The present invention has been devised to solve the problems of the conventional manufacturing process, and stores personalized specifications that meet the needs of the market in real time in a database, and utilizes artificial intelligence algorithms based on the stored data to optimize product production. By deriving the process specifications and applying the derived process specifications to each process facility, it is possible to produce small amounts of individually tailored multi-variety in response to market demand.
이하에서는, 본 발명이 제안하는 제조 공정을 구현하기 위한 자율화 공장 운영 시스템에 대하여 보다 상세하게 설명한다. Hereinafter, an autonomous factory operating system for implementing the manufacturing process proposed by the present invention will be described in more detail.
도 3은 본 발명에 따른 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템을 설명하기 위한 참조도이다.3 is a reference diagram for explaining an autonomous factory operating system based on distributed edge computing according to the present invention.
도 3을 참조하면, 본 발명에 따른 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템(10, 이하 자율화 공장 운영 시스템)은 복수의 공정 설비들(100), 복수의 지능형 엣지 컴퓨팅 디바이스(200, AI-son, 이하 엣지 컴퓨팅 디바이스), 지능형 센터 컴퓨팅 디바이스(300, AI-mother, 이하 센터 컴퓨팅 디바이스) 및 데이터베이스(400)를 포함하여 구성될 수 있다.Referring to FIG. 3 , the distributed edge computing-based autonomous factory operating system 10 (hereinafter, autonomous factory operating system) according to the present invention includes a plurality of process facilities 100 and a plurality of intelligent edge computing devices 200 and AI- son, hereinafter edge computing device), the intelligent center computing device (300, AI-mother, hereinafter center computing device) and may be configured to include a database (400).
복수의 공정 설비들(100)은 특정 공장에 구비되며 각각 정의된 공정을 수행하는 설비에 해당한다. 의류 공장에 구비되는 공정 설비들을 예로 들면, 제1 공정 설비(100A)는 원단 가공 설비에 해당하고, 제2 공정 설비(100B)는 제봉 공정 설비에 해당하고, 제3 공정 설비(100C)는 품질 검사 설비에 해당할 수 있다. 한편, 이러한 예시는 본 발명의 권리범위를 한정하고자 하는 것은 아니며, 본 발명에 따른 공정 설비는 특정 제품을 생산하기 위한 다양한 공정 설비에 해당할 수 있음은 물론이다.The plurality of process facilities 100 are provided in a specific factory and correspond to facilities for performing a defined process, respectively. For example, the first process equipment 100A corresponds to the fabric processing equipment, the second process equipment 100B corresponds to the sewing process equipment, and the third process equipment 100C corresponds to the quality equipment. It may correspond to an inspection facility. On the other hand, these examples are not intended to limit the scope of the present invention, of course, the process equipment according to the present invention may correspond to various process equipment for producing a specific product.
일 실시예에서, 복수의 공정 설비들(100) 각각은 정의된 동작을 수행하기 위한 제어 장치(110)를 포함하여 구성될 수 있다. 여기에서, 각각의 제어 장치(110A, 110B, 110C, …)는 공정 설비들(100A, 100B, 100C, …) 각각을 동작시키기 위한 제어 신호를 출력할 수 있으며, 제어 신호는 공정 설비들(100A, 100B, 100C, …) 각각에 대한 동작 파라미터를 포함할 수 있다. In one embodiment, each of the plurality of process facilities 100 may be configured to include a control device 110 for performing a defined operation. Here, each of the control devices 110A, 110B, 110C, … may output a control signal for operating each of the process equipment 100A, 100B, 100C, …, and the control signal is the process equipment 100A , 100B, 100C, ...) may include operation parameters for each.
엣지 컴퓨팅 디바이스(200)는 복수의 공정 설비들(100) 각각과 연결된 컴퓨팅 장치이다. 여기에서, 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …)는 별도의 하드웨어로 구현되고 공정 설비들(100A, 100B, 100C, …)의 인근에 배치 또는 부착되어 유무선 네트워크를 통해 상호 연결되거나, 또는 복수의 공정 설비들(100A, 100B, 100C, …)의 내부에 포함되어 구현될 수 있다. The edge computing device 200 is a computing device connected to each of the plurality of process facilities 100 . Here, the edge computing devices 200A, 200B, 200C, ... are implemented as separate hardware and disposed or attached to the vicinity of the process facilities 100A, 100B, 100C, ... and interconnected through a wired/wireless network, or A plurality of process equipment (100A, 100B, 100C, ...) may be implemented by being included in the interior.
엣지 컴퓨팅 디바이스(200A, 200B, 200C, …)는 공정 설비들(100A, 100B, 100C, …) 각각과 연관되는 공정 기초 데이터를 수집할 수 있다. 여기에서, 공정 기초 데이터는 공정 설비(100)의 동작과 연관되는 데이터로서, 공정 설비들(100A, 100B, 100C, …) 각각에 대한 제어 신호, 동작 파라미터, 환경 조건, 동작 조건, 공정량, 고장 이벤트 등을 포함할 수 있다. The edge computing devices 200A, 200B, 200C, ... may collect process basic data associated with each of the process facilities 100A, 100B, 100C, .... Here, the process basic data is data related to the operation of the process equipment 100 , and includes control signals, operating parameters, environmental conditions, operating conditions, process amounts, and control signals for each of the process facilities 100A, 100B, 100C, ... It may include failure events and the like.
엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각은 수집된 공정 기초 데이터를 기반으로 기정의된 인공지능 알고리즘에 따라 공정 설비들(100A, 100B, 100C, …) 각각에 대한 최적 제어 조건을 생성할 수 있다. 여기에서, 최적 제어 조건은 각 공정 설비들을 최적화할 수 있는 제어 신호를 의미할 수 있다. 예를 들어, 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각은 공정 설비들(100A, 100B, 100C, …) 각각에 대한 제어 신호, 동작 파라미터, 환경 조건, 동작 조건, 공정량, 고장 이벤트를 기정의된 딥러닝 모델을 이용해 분석하여 최고의 공정 효율을 나타낼 수 있는 최적 제어 조건을 생성할 수 있다. Each of the edge computing devices 200A, 200B, 200C, … generates optimal control conditions for each of the process facilities 100A, 100B, 100C, … according to a predefined artificial intelligence algorithm based on the collected process basic data. can do. Here, the optimal control condition may mean a control signal capable of optimizing each process facility. For example, each of the edge computing devices 200A, 200B, 200C, . can be analyzed using a predefined deep learning model to create optimal control conditions that can show the best process efficiency.
일 실시예에서, 인공지능 알고리즘은 공지의 다양한 인공지능 모델에 해당할 수 있으며, 예를 들어, 딥러닝 기반의 학습 모델에 해당할 수 있다. 한편, 다양한 공정 기초 데이터를 입력 데이터로 하여 딥러닝 모델을 학습시키고, 학습된 딥러닝 모델을 이용하여 의도하는 출력 정보인 최적 제어 조건을 도출하는 방법론은, 공지의 기술이며 본 발명의 핵심적인 기술적 사상이 아니므로 이에 대한 상세한 설명은 생략한다. In an embodiment, the artificial intelligence algorithm may correspond to various well-known artificial intelligence models, for example, it may correspond to a deep learning-based learning model. On the other hand, a method for learning a deep learning model using various process basic data as input data and deriving an optimal control condition that is intended output information using the learned deep learning model is a well-known technology and is a core technology of the present invention. Since it is not an idea, a detailed description thereof will be omitted.
엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각은 생성된 최적 제어 조건을 공정 설비들(100A, 100B, 100C, …) 각각에 적용할 수 있다. 즉, 엣지 컴퓨팅 디바이스(200)가 공정 설비(100)에 최적 제어 조건을 전달하면, 공정 설비(100)는 최적 제어 조건을 각각의 제어 장치(110)에 적용하여 최적 제어 조건에 따라 동작할 수 있다. Each of the edge computing devices 200A, 200B, 200C, ... may apply the generated optimal control condition to each of the process facilities 100A, 100B, 100C, .... That is, when the edge computing device 200 transmits the optimum control condition to the process facility 100 , the process facility 100 applies the optimum control condition to each control device 110 to operate according to the optimum control condition. have.
센터 컴퓨팅 디바이스(300)는 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각과 클라우드 환경에서 연동될 수 있다. 예를 들어, 센터 컴퓨팅 디바이스(300)는 클라우드 서버로 구현될 수 있으며, 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각과 네트워크를 통해 상호 연결되어 데이터를 송수신하도록 구성될 수 있다. The center computing device 300 may be linked with each of the edge computing devices 200A, 200B, 200C, ... in a cloud environment. For example, the center computing device 300 may be implemented as a cloud server, and may be interconnected with each of the edge computing devices 200A, 200B, 200C, ... through a network to transmit and receive data.
센터 컴퓨팅 디바이스(300)는 복수의 공정 설비들(100A, 100B, 100C, …) 각각에 대한 최적 제어 조건을 확인하고, 확인된 최적 제어 조건을 기반으로 기정의된 인공지능 알고리즘에 따라 공장 최적화 조건을 생성할 수 있다. 여기에서, 공장 최적화 조건은 각 공정 설비들을 포함한 공장 전체의 최적화를 위한 조건을 의미할 수 있다. 예를 들어, 공장 최적화 조건은 스펙별 제품 생산량, 공정 설비별 동작 시간, 공장 내 환경 조건 등을 포함할 수 있으며, 또한, 복수의 공정 설비들(100A, 100B, 100C, …) 각각에 대한 최적 제어 조건을 포함할 수 있다.The center computing device 300 identifies optimal control conditions for each of the plurality of process facilities 100A, 100B, 100C, ..., and factory optimization conditions according to a predefined artificial intelligence algorithm based on the identified optimal control conditions can create Here, the factory optimization condition may mean a condition for optimizing the entire factory including each process facility. For example, the factory optimization condition may include product production by specification, operation time for each process facility, environmental conditions in the factory, etc., and also the optimum for each of the plurality of process facilities 100A, 100B, 100C, ... Control conditions may be included.
일 실시예에서, 인공지능 알고리즘은 공지의 다양한 인공지능 모델에 해당할 수 있으며, 예를 들어, 딥러닝 기반의 학습 모델에 해당할 수 있다. 한편, 최적 제어 조건을 입력 데이터로 하여 딥러닝 모델을 학습시키고, 학습된 딥러닝 모델을 이용하여 의도하는 출력 정보인 공장 최적화 조건을 도출하는 방법론은, 공지의 기술이며 본 발명의 핵심적인 기술적 사상이 아니므로 이에 대한 상세한 설명은 생략한다. In an embodiment, the artificial intelligence algorithm may correspond to various well-known artificial intelligence models, for example, it may correspond to a deep learning-based learning model. On the other hand, the method of learning a deep learning model using the optimal control condition as input data and deriving the factory optimization condition, which is the intended output information, using the learned deep learning model, is a well-known technology and is a core technical idea of the present invention. Since this is not the case, a detailed description thereof will be omitted.
데이터베이스(400)는 해당 공장에서 생산하는 제품에 대한 시장 수요 정보를 수집하여 저장할 수 있다. 여기에서, 시장 수요 정보는 수요자 개인별 제품 수요를 나타내는 정보를 의미할 수 있으며, 수요자 개인별 요구 정보를 포함할 수 있다. 예를 들어, 시장 수요 정보는 의류 주문 정보, 또는 의류 모델별, 사이즈별, 시기별 주문량 등을 포함할 수 있다. The database 400 may collect and store market demand information for products produced in a corresponding factory. Here, the market demand information may mean information indicating product demand for each individual consumer, and may include individual demand information for each consumer. For example, the market demand information may include clothing order information or an order quantity for each clothing model, size, and period.
일 실시예에서, 데이터베이스(400)는 시장 수요 정보를 제공하는 외부의 정보 제공 장치와 네트워크를 통해 연결될 수 있으며, 예를 들어, 정보 제공 장치는 해당 공장에서 생산하는 제품을 판매하는 판매사 서버에 해당할 수 있다. In an embodiment, the database 400 may be connected to an external information providing device that provides market demand information through a network, and for example, the information providing device corresponds to a server of a sales company that sells products produced in a corresponding factory. can do.
일 실시예에서, 시장 수요 정보는 기정의된 포멧에 따라 가공되어 데이터베이스(400)에 저장될 수 있다. 예를 들어, 수요자 개인별 주문 정보가 데이터베이스(400)에 로데이터로서 저장되거나, 해당 로데이터가 정량 분석 프로세스를 통해 의류 모델별, 사이즈별, 시기별 주문량의 형태로 가공되어 데이터베이스(400)에 저장될 수도 있다. In an embodiment, the market demand information may be processed according to a predefined format and stored in the database 400 . For example, order information for each individual consumer is stored as raw data in the database 400 , or the raw data is processed in the form of an order quantity for each clothing model, size, and period through a quantitative analysis process and stored in the database 400 . it might be
일 실시예에서, 센터 컴퓨팅 디바이스(300)는 복수의 공정 설비들(100A, 100B, 100C, …) 각각에 대한 최적 제어 조건과 데이터베이스(400)에 저장된 시장 수요 정보를 확인하고, 확인된 최적 제어 조건 및 시장 수요 정보를 기반으로 기정의된 인공지능 알고리즘에 따라 공장 최적화 조건을 생성할 수 있다. 본 실시예에 따른 공장 최적화 조건은 해당 공장에서 생산되는 제품의 개인별 시장 수요에 대응하기 위한 최적화 조건으로서, 제품 수요에 따른 스펙별 제품 생산량, 공정 설비별 동작 시간, 공장 내 환경 조건 등을 포함할 수 있다.In one embodiment, the center computing device 300 checks the optimal control conditions for each of the plurality of process facilities 100A, 100B, 100C, ... and the market demand information stored in the database 400, and the identified optimal control Based on the conditions and market demand information, it is possible to create factory optimization conditions according to a predefined artificial intelligence algorithm. The factory optimization condition according to this embodiment is an optimization condition for responding to individual market demand for products produced in the factory, and may include product production by specification according to product demand, operation time for each process facility, environmental conditions in the factory, etc. can
일 실시예에서, 센터 컴퓨팅 디바이스(300)는 생성된 공장 최적화 조건을 기초로, 복수의 공정 설비들(100A, 100B, 100C, …) 각각에 대한 최적 제어 조건을 생성할 수 있다. 여기에서, 센터 컴퓨팅 디바이스(300)는 생성된 최적 제어 조건을 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각에 제공할 수 있다. 이 후, 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각은 기저장된 최적 제어 조건을 제공받은 최적 제어 조건으로 갱신하고, 갱신된 최적 제어 조건을 공정 설비들(100A, 100B, 100C, …) 각각에 적용할 수 있다. In an embodiment, the center computing device 300 may generate an optimal control condition for each of the plurality of process facilities 100A, 100B, 100C, ..., based on the generated factory optimization condition. Here, the center computing device 300 may provide the generated optimal control condition to each of the edge computing devices 200A, 200B, 200C, .... Thereafter, each of the edge computing devices 200A, 200B, 200C, ... updates the optimal control conditions provided with the pre-stored optimal control conditions, and updates the updated optimal control conditions to the process facilities 100A, 100B, 100C, ... can be applied to each.
일 실시예에서, 센터 컴퓨팅 디바이스(300)는 기정의된 시간 단위(예 : 2분 또는 10분 등)마다 최적 제어 조건을 생성하여 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각에 제공할 수 있으며, 엣지 컴퓨팅 디바이스(200A, 200B, 200C, …) 각각은 최적 제어 조건을 전달받는 즉시 기저장된 정보를 갱신할 수 있다. In one embodiment, the center computing device 300 generates an optimal control condition for each predefined time unit (eg, 2 minutes or 10 minutes, etc.) to provide to each of the edge computing devices 200A, 200B, 200C, ... In addition, each of the edge computing devices 200A, 200B, 200C, ... may update pre-stored information immediately upon receiving the optimal control condition.
상기에서 설명한 본 발명의 다양한 실시예에 따르면, 센터 컴퓨팅 디바이스(AI-mother)가 공정 설비 각각에 대한 최적 제어 조건과, 수집된 시장 수요 정보를 기초로 공장 최적화 조건을 생성하고, 이를 복수의 엣지 컴퓨팅 디바이스(AI-son)들에게 제공하여 공정 설비 각각이 수요자 개인별 요구에 대응하여 최적으로 동작하도록 함으로써, 시장 수요에 대응한 개인 맞춤형 다품종 소량 생산을 가능케 한다. According to various embodiments of the present invention described above, the center computing device (AI-mother) generates factory optimization conditions based on the optimal control conditions for each process facility and the collected market demand information, and uses the It is provided to computing devices (AI-son) so that each process facility operates optimally in response to the individual needs of each consumer, thereby enabling small-volume production of individually tailored multi-products in response to market demand.
이상에서 설명한 본 발명에 따른 자율화 공장 운영 시스템의 동작은 컴퓨터로 읽을 수 있는 기록매체에 컴퓨터가 읽을 수 있는 코드로서 구현될 수 있다. 컴퓨터가 읽을 수 있는 기록매체는 컴퓨터 시스템에 의하여 읽혀질 수 있는 데이터가 저장되는 모든 종류의 기록장치를 포함한다. 컴퓨터가 읽을 수 있는 기록매체의 예로는 ROM, RAM, CD-ROM, 자기 테이프, 플로피 디스크, 광 데이터 저장장치 등이 있다. 또한 컴퓨터가 읽을 수 있는 기록매체는 네트워크로 연결된 컴퓨터 시스템에 분산되어, 분산방식으로 컴퓨터가 읽을 수 있는 코드가 저장되고 실행될 수 있다.The operation of the autonomous factory operating system according to the present invention described above may be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. In addition, the computer-readable recording medium is distributed in network-connected computer systems, and computer-readable codes can be stored and executed in a distributed manner.
상기한 본 발명의 바람직한 실시예는 예시의 목적을 위해 개시된 것이고, 본 발명에 대해 통상의 지식을 가진 당업자라면 본 발명의 사상과 범위 안에서 다양한 수정, 변경, 부가가 가능할 것이며, 이러한 수정, 변경 및 부가는 하기의 특허청구범위에 속하는 것으로 보아야 할 것이다.The above-described preferred embodiments of the present invention have been disclosed for purposes of illustration, and various modifications, changes, and additions will be possible within the spirit and scope of the present invention by those of ordinary skill in the art with respect to the present invention, and such modifications, changes and Additions should be considered to fall within the scope of the following claims.
Claims (7)
- 복수의 공정 설비들을 포함하는 공장에 적용될 수 있는, 분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템에 있어서, In an autonomous factory operating system based on distributed edge computing that can be applied to a factory including a plurality of process facilities,상기 복수의 공정 설비들 각각과 연결되어, 공정 설비와 연관되는 공정 기초 데이터를 수집하며, 상기 수집된 공정 기초 데이터를 기반으로 기정의된 인공지능 알고리즘에 따라 최적 제어 조건을 생성하여 공정 설비에 적용하는, 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들; 및It is connected to each of the plurality of process equipment to collect process basic data related to the process equipment, and based on the collected process basic data, an optimal control condition is generated according to a predefined artificial intelligence algorithm and applied to the process equipment a plurality of intelligent edge computing devices (AI-son); and상기 복수의 지능형 엣지 컴퓨팅 디바이스들 각각과 클라우드 환경에서 연동되어, 상기 복수의 공정 설비들 각각에 대한 최적 제어 조건을 확인하고, 확인된 최적 제어 조건을 기반으로 기정의된 인공지능 알고리즘에 따라 공장 최적화 조건을 생성하는, 지능형 센터 컴퓨팅 디바이스(AI-mother);를 포함하는,Each of the plurality of intelligent edge computing devices is linked in a cloud environment, the optimal control conditions for each of the plurality of process facilities are checked, and the factory is optimized according to a predefined artificial intelligence algorithm based on the identified optimal control conditions An intelligent center computing device (AI-mother) that generates a condition; including;분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
- 제1항에 있어서, 상기 자율화 공장 운영 시스템은,According to claim 1, wherein the autonomous factory operating system,상기 공장에서 생산하는 제품에 대한 시장 수요 정보를 수집하여 저장하는 데이터베이스를 더 포함하는 것을 특징으로 하는, Characterized in that it further comprises a database for collecting and storing market demand information for products produced in the factory,분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
- 제2항에 있어서, 상기 시장 수요 정보는,According to claim 2, wherein the market demand information,상기 제품에 대한 수요자 개인별 요구 정보를 포함하는 것을 특징으로 하는,Characterized in that it includes information required for each individual consumer for the product,분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
- 제3항에 있어서, 상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는According to claim 3, wherein the intelligent center computing device (AI-mother) is상기 확인된 최적 제어 조건과 상기 데이터베이스에 저장된 시장 수요 정보를 기반으로 기정의된 인공지능 알고리즘에 따라, 상기 제품의 개인별 시장 수요에 대응하기 위한 공장 최적화 조건을 생성하는 것을 특징으로 하는, Based on the identified optimal control conditions and market demand information stored in the database, according to a predefined artificial intelligence algorithm, factory optimization conditions for responding to individual market demands of the product are generated, characterized in that분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
- 제4항에 있어서, 상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는According to claim 4, wherein the intelligent center computing device (AI-mother)상기 생성된 공장 최적화 조건을 기초로, 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각에 대한 최적 제어 조건을 생성하는 것을 특징으로 하는,Characterized in generating an optimal control condition for each of the plurality of intelligent edge computing devices (AI-son) based on the generated factory optimization condition,분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
- 제5항에 있어서, 6. The method of claim 5,상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는The intelligent center computing device (AI-mother) is상기 생성된 최적 제어 조건을 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각에 제공하고,providing the generated optimal control condition to each of the plurality of intelligent edge computing devices (AI-son);상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각은,Each of the plurality of intelligent edge computing devices (AI-son),기저장된 최적 제어 조건을 제공받은 최적 제어 조건으로 갱신하고, 갱신된 최적 제어 조건을 공정 설비 각각에 적용하는 것을 특징으로 하는, characterized in that the pre-stored optimal control conditions are updated with the provided optimal control conditions, and the updated optimal control conditions are applied to each process equipment,분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
- 제6항에 있어서, 7. The method of claim 6,상기 지능형 센터 컴퓨팅 디바이스(AI-mother)는The intelligent center computing device (AI-mother) is기정의된 시간 단위마다 상기 최적 제어 조건을 생성하여 상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각에 제공하며, Generates the optimal control condition for each predefined time unit and provides it to each of the plurality of intelligent edge computing devices (AI-son),상기 복수의 지능형 엣지 컴퓨팅 디바이스(AI-son)들 각각은,Each of the plurality of intelligent edge computing devices (AI-son),기저장된 최적 제어 조건을 제공받은 최적 제어 조건으로 갱신하고, 갱신된 최적 제어 조건을 공정 설비 각각에 적용하는 것을 특징으로 하는, characterized in that the pre-stored optimal control conditions are updated with the provided optimal control conditions, and the updated optimal control conditions are applied to each process equipment,분산형 엣지 컴퓨팅 기반의 자율화 공장 운영 시스템.Autonomous factory operating system based on distributed edge computing.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2020-0183793 | 2020-12-24 | ||
KR1020200183793A KR20220092227A (en) | 2020-12-24 | 2020-12-24 | Factory automation system based on distributed edge computing |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022139326A1 true WO2022139326A1 (en) | 2022-06-30 |
Family
ID=82159664
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2021/019195 WO2022139326A1 (en) | 2020-12-24 | 2021-12-16 | Distributed edge computing-based autonomous factory operating system |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR20220092227A (en) |
WO (1) | WO2022139326A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111090243A (en) * | 2018-10-23 | 2020-05-01 | 宁波方太厨具有限公司 | Method for realizing intelligent interconnection of kitchen appliances |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102668875B1 (en) * | 2022-09-21 | 2024-06-26 | 농업회사법인 주식회사 솔오토메틱 | IoT-based grain washing process automation monitoring and robotization implementation method and system |
KR20240103510A (en) * | 2022-12-27 | 2024-07-04 | (주)인더스웰 | Smart consumer goods parts manufacturing collaboration platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190106368A (en) * | 2018-03-09 | 2019-09-18 | 타이아(주) | Distributed data acquisition and distributed control command system for factory automation, and Distributed data collection and distributed control method for the same |
KR20200046146A (en) * | 2018-10-15 | 2020-05-07 | 박인철 | Sewing site management system |
KR20200052403A (en) * | 2018-10-23 | 2020-05-15 | 삼성에스디에스 주식회사 | Data analysis system based on edge computing and method thereof |
KR20200125313A (en) * | 2019-04-26 | 2020-11-04 | 박병훈 | Securing High Availability and Providing Customized AI service of Edge AI System for Smart Factory |
US20200393820A1 (en) * | 2019-06-17 | 2020-12-17 | Vms Solutions Co., Ltd. | Reinforcement learning and simulation based dispatching method in a factory, and an apparatus thereof |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20200120980A (en) | 2019-04-08 | 2020-10-23 | 주식회사 컴퓨터메이트 | Smart factory operation system and method thereof |
-
2020
- 2020-12-24 KR KR1020200183793A patent/KR20220092227A/en unknown
-
2021
- 2021-12-16 WO PCT/KR2021/019195 patent/WO2022139326A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190106368A (en) * | 2018-03-09 | 2019-09-18 | 타이아(주) | Distributed data acquisition and distributed control command system for factory automation, and Distributed data collection and distributed control method for the same |
KR20200046146A (en) * | 2018-10-15 | 2020-05-07 | 박인철 | Sewing site management system |
KR20200052403A (en) * | 2018-10-23 | 2020-05-15 | 삼성에스디에스 주식회사 | Data analysis system based on edge computing and method thereof |
KR20200125313A (en) * | 2019-04-26 | 2020-11-04 | 박병훈 | Securing High Availability and Providing Customized AI service of Edge AI System for Smart Factory |
US20200393820A1 (en) * | 2019-06-17 | 2020-12-17 | Vms Solutions Co., Ltd. | Reinforcement learning and simulation based dispatching method in a factory, and an apparatus thereof |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111090243A (en) * | 2018-10-23 | 2020-05-01 | 宁波方太厨具有限公司 | Method for realizing intelligent interconnection of kitchen appliances |
CN111090243B (en) * | 2018-10-23 | 2023-04-14 | 宁波方太厨具有限公司 | Method for realizing intelligent interconnection of kitchen appliances |
Also Published As
Publication number | Publication date |
---|---|
KR20220092227A (en) | 2022-07-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022139326A1 (en) | Distributed edge computing-based autonomous factory operating system | |
CA2449606A1 (en) | Adaptive knowledge management system for vehicle trend monitoring, health management and preventive maintenance | |
WO2021060593A1 (en) | System, method, and computer program for credit assessment by using machine learning | |
WO2019066104A1 (en) | Process control method and system which use history data-based neural network learning | |
Şahinel et al. | Human modeling and interaction in cyber-physical systems: a reference framework | |
WO2020111309A1 (en) | Data parsing and construction method for building automationml-based opc ua environment | |
US20210166468A1 (en) | Information service system and information service method | |
CN105471972A (en) | Internet of things information system | |
CN110379036A (en) | Intelligent substation patrol recognition methods, system, device and storage medium | |
CN113556768A (en) | Sensor data anomaly detection method and system | |
WO2020101196A1 (en) | Artificial intelligence-based module identification and assistant system | |
WO2022154630A1 (en) | Patent evaluation method based on artificial intelligence | |
CN114170041A (en) | Method for establishing intelligent building operation and maintenance management system by applying building subject data | |
CN107610260B (en) | Intelligent attendance system and attendance method based on machine vision | |
CN108145714B (en) | Distributed control system of service type robot | |
US20060059497A1 (en) | Object-oriented system for networking onboard aeronautical equipment items | |
CN106067092A (en) | The student realized based on the Internet asks for leave management method and system | |
Hollingum | Implementing an information strategy in manufacture: a practical approach | |
CN100555126C (en) | The method and apparatus that is used for supervising transmission medium | |
WO2020130169A1 (en) | Method for configuring opc ua-based platform for efficient management of heterogeneous quality data | |
CN114072751A (en) | System and method for simulating industrial processes | |
Niemelä et al. | Practical evaluation of software product family architectures | |
WO2023017953A1 (en) | Method and system for automating standard api specification for data distribution between heterogeneous systems | |
CN108897608A (en) | A kind of intelligent universal task scheduling system that data-driven is expansible | |
Alexakos et al. | Production process adaptation to IoT triggered manufacturing resource failure events |
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: 21911393 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21911393 Country of ref document: EP Kind code of ref document: A1 |