KR20240067165A - A ststem for fault detection and failure prediction in manufacturing processes using sensor data and explanable AI model - Google Patents
A ststem for fault detection and failure prediction in manufacturing processes using sensor data and explanable AI model Download PDFInfo
- Publication number
- KR20240067165A KR20240067165A KR1020220146944A KR20220146944A KR20240067165A KR 20240067165 A KR20240067165 A KR 20240067165A KR 1020220146944 A KR1020220146944 A KR 1020220146944A KR 20220146944 A KR20220146944 A KR 20220146944A KR 20240067165 A KR20240067165 A KR 20240067165A
- Authority
- KR
- South Korea
- Prior art keywords
- artificial intelligence
- intelligence model
- sensor data
- manufacturing
- model
- Prior art date
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims description 9
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 30
- 230000007547 defect Effects 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 abstract 1
- 238000000034 method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
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
- 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
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- 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]
- G05B19/41875—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 quality surveillance of production
-
- 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
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- 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
- G05B23/0267—Fault communication, e.g. human machine interface [HMI]
- G05B23/0272—Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user
-
- 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
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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]
Abstract
본 발명은 제조 환경의 센서 데이터를 이용한 통합 모니터링 서비스에 관한 것이다. 본 발명은, 제조 현장에 직접 센서를 부착하여 얻을 수 있는 데이터를 분석하여 제조 관련자가 제조 현장에서 식별, 진단, 예측 등 의사 결정을 도와줄 수 있는 인공지능 플랫폼으로서, 설명 가능한 인공지능 모델을 이용하여 제조 지식 기반 설비 제어를 가능하게하는 시스템을 제공하고자 한다. The present invention relates to an integrated monitoring service using sensor data from a manufacturing environment. The present invention is an artificial intelligence platform that can help manufacturing personnel make decisions such as identification, diagnosis, and prediction at the manufacturing site by analyzing data that can be obtained by attaching sensors directly to the manufacturing site, using an explainable artificial intelligence model. We aim to provide a system that enables manufacturing knowledge-based facility control.
Description
본 발명은 인공지능 기반의 제조 공정 관리 시스템에 관한 것으로서, 보다 상세하게는 제조 환경에 센서를 부착해 제조 시스템의 상태를 기 획득된 데이터를 학습한 인공지능 모델을 이용하여 제조 공정의 이상을 모니터링 하고 설비 기간을 분석하는 시스템에 관한 것이다. The present invention relates to an artificial intelligence-based manufacturing process management system. More specifically, the present invention relates to an artificial intelligence-based manufacturing process management system. More specifically, it attaches sensors to the manufacturing environment and monitors abnormalities in the manufacturing process using an artificial intelligence model that learns the state of the manufacturing system from previously acquired data. It is about a system that analyzes the facility period.
제조 공정의 센서 데이터를 이용한 결함 탐지 및 고장 예지 연구는 증가하는 추세이나, 결과가 도출되는 과정을 알 수 없는 인공지능 모델을 사용하여 출력된 결과의 원인을 분석하기 쉽지 않은 어려움이 있다. 따라서 이와 같은 문제점들을 해결하기 위한 방법이 요구된다.Research on defect detection and failure prediction using sensor data from the manufacturing process is increasing, but it is difficult to analyze the cause of the output results using an artificial intelligence model whose process by which the results are derived is unknown. Therefore, a method to solve these problems is required.
본 발명은 종래의 문제점을 해결하기 위해 안출된 발명으로서, 제조 공정에서 발생한 문제의 분석이 가능한 인공지능 모델을 활용하고 결과에 따라 고장 예지 및 설비 기간 분석 등을 가능하게 하는 목적을 가진다. The present invention is an invention made to solve conventional problems, and its purpose is to utilize an artificial intelligence model capable of analyzing problems occurring in the manufacturing process and to enable failure prediction and facility period analysis based on the results.
본 발명은 이상에서 언급한 과제들로 제한되지 않으며, 명시되지 않은 과제들 또한 당업자에게 이해될 수 있다.The present invention is not limited to the tasks mentioned above, and tasks not specified can also be understood by those skilled in the art.
상기의 기술적 과제를 해결하기 위해 본 발명은 In order to solve the above technical problems, the present invention
제조 환경에서 센서를 부착해 실시간 데이터를 획득하는 (a) 단계; Step (a) of acquiring real-time data by attaching a sensor in a manufacturing environment;
상기 획득한 실시간 데이터를 인공지능 모델에 입력하는 (b) 단계;Step (b) of inputting the acquired real-time data into an artificial intelligence model;
상기 인공지능 모델에서 실시간 결과를 출력하는 (c) 단계;Step (c) of outputting real-time results from the artificial intelligence model;
상기 인공지능 모델에서 출력된 결과를 해석하는 (d) 단계; 를 포함한다. 또한 설명 가능한 인공지능 모델을 사용함으로써 출력된 결과를 역으로 추적하여 설비의 이상 원인을 파악하고 고장을 예지하는 단계를 포함할 수 있다. Step (d) of interpreting the results output from the artificial intelligence model; Includes. In addition, by using an explainable artificial intelligence model, the output results can be traced back to identify the cause of equipment abnormalities and predict failures.
센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템은 기존에 설명 불가능한 인공지능 모델을 사용하여 결과가 도출된 과정이 불투명한 단점을 보완할 수 있다. Using sensor data and explainable artificial intelligence models, a defect detection and prediction system in the manufacturing process can compensate for the disadvantage of using existing unexplainable artificial intelligence models, where the process of deriving the results is unclear.
또한 본 발명에 따른 설명 가능한 인공지능 모델을 활용하여 실무자가 제조 프로세스에 활용가능한 인사이트를 도출 할 수 있다. Additionally, by using the explainable artificial intelligence model according to the present invention, practitioners can derive insights that can be used in the manufacturing process.
또한 제조 숙련자가 아니어도 설비의 예지 보전이 가능하게 한다.In addition, it enables predictive maintenance of equipment even if you are not skilled in manufacturing.
또한 경험으로만 얻을 수 있는 고장 예지 및 설비 기간 분석 등을 설명 가능한 인공지능 모델을 이용해 생산성 향상을 가져올 수 있다.In addition, productivity can be improved by using an artificial intelligence model that can explain failure prediction and facility period analysis that can only be obtained through experience.
도 1 은, 본 발명에 따른 센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템의 순서를 설명하는 도면이다. 1 is a diagram illustrating the sequence of a defect detection and prediction system in a manufacturing process using sensor data and an explainable artificial intelligence model according to the present invention.
도 1은 본 발명의 센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템을 나타낸 순서도이다. 1 is a flowchart showing a defect detection and prediction system in a manufacturing process using sensor data and an explainable artificial intelligence model of the present invention.
도1에 도시된 바와 같이, 센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템에서 사용되는 센서로부터 실시간 데이터를 획득하는 (a) 단계 기 학습 데이터를 학습한 설명가능한 인공지능 모델에 입력하는 (b)단계 상기 설명 가능한 인공지능 모델에서 출력된 결과를 모니터링하는 (c) 단계 상기 인공지능 모델에서 출력된 결과를 해석하여 설비 공정에 이상 원인과 고장 예지하는 (d) 단계를 포함한다. As shown in Figure 1, in step (a), real-time data is acquired from sensors used in a defect detection and prediction system in the manufacturing process using sensor data and an explainable artificial intelligence model. Step (b) of inputting into the intelligence model Step (c) of monitoring the results output from the explainable artificial intelligence model Step (d) of interpreting the results output from the artificial intelligence model to predict the cause of abnormalities and failures in the equipment process Includes.
Claims (3)
상기 획득한 실시간 데이터를 인공지능 모델에 입력하는 (b) 단계;
상기 인공지능 모델에서 실시간 결과를 출력하는 (c) 단계;
상기 인공지능 모델에서 출력된 결과를 해석하는 (d) 단계;
를 포함하는 센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템
Step (a) of acquiring real-time data by attaching a sensor in a manufacturing environment;
Step (b) of inputting the obtained real-time data into an artificial intelligence model;
Step (c) of outputting real-time results from the artificial intelligence model;
Step (d) of interpreting the results output from the artificial intelligence model;
A defect detection and prediction system in the manufacturing process using sensor data and explainable artificial intelligence models including
상기 인공지능 모델은 설명 가능한 인공지능 모델로 제조 환경의 이상 유무를 분석 가능하게하는 센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템
According to claim 1,
The artificial intelligence model is an explainable artificial intelligence model. It is a defect detection and prediction system in the manufacturing process using sensor data that enables analysis of abnormalities in the manufacturing environment and an explainable artificial intelligence model.
상기 인공지능 모델은 기 획득된 학습 데이터를 통해 학습된 인공지능 모델로서, 결함의 종류와 설비 기간 분석 등을 결과로 출력하는,
센서 데이터와 설명가능한 인공지능 모델을 이용하여 제조 공정의 결함 탐지 및 예측 시스템
According to claim 2,
The artificial intelligence model is an artificial intelligence model learned through previously acquired learning data, and outputs results such as type of defect and analysis of equipment period, etc.
Manufacturing process defect detection and prediction system using sensor data and explainable artificial intelligence model
Publications (1)
Publication Number | Publication Date |
---|---|
KR20240067165A true KR20240067165A (en) | 2024-05-16 |
Family
ID=
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6999635B2 (en) | Image-based maintenance prediction and operation error detection | |
CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
CN106598791B (en) | Industrial equipment fault preventive identification method based on machine learning | |
US20170074250A1 (en) | Wind turbine condition monitoring method and system | |
CN115657617A (en) | Implementation method of intelligent monitoring alarm system for thermal power plant | |
CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
CN112858804A (en) | Power supply screen fault diagnosis method and device for railway vehicle | |
CN117151649B (en) | Construction method management and control system and method based on big data analysis | |
CN110597235A (en) | Universal intelligent fault diagnosis method | |
CN117055502A (en) | Intelligent control system based on Internet of things and big data analysis | |
Massaro et al. | Production optimization monitoring system implementing artificial intelligence and big data | |
CN113962308A (en) | Aviation equipment fault prediction method | |
CN117193222A (en) | Intelligent quality control system based on industrial Internet of things and big data and control method thereof | |
US11900223B2 (en) | Device and method for monitoring a system | |
CN114002597A (en) | Motor fault diagnosis method and system based on GRU network stator current analysis | |
CN116092014A (en) | Intelligent inspection control method and system based on Internet of things equipment | |
CN110765633A (en) | Intelligent management method and device for power device | |
KR20240067165A (en) | A ststem for fault detection and failure prediction in manufacturing processes using sensor data and explanable AI model | |
CN117215940A (en) | Intelligent operation and maintenance emergency processing system | |
CN115600695B (en) | Fault diagnosis method for metering equipment | |
CN116277001A (en) | Continuous casting robot management method and system based on digital twin | |
KR20200002433A (en) | Statistical quality control system and method using big data analysis | |
RU2735296C1 (en) | Method for multi-parameter monitoring of complex electrotechnical objects state | |
Tabit et al. | Machine Learning: Strategies for industrial defect detection | |
JP7202248B2 (en) | PLANT CONDITION MONITORING SYSTEM AND PLANT CONDITION MONITORING METHOD |