• Title/Summary/Keyword: 제조 데이터 수집

Search Result 195, Processing Time 0.025 seconds

A Study on the Experimental Application of the Artificial Neural Network for the Process Improvement (공정개선을 위한 인공신경망의 실험적 적용에 관한 연구)

  • 한우철
    • Journal of the Korea Society of Computer and Information
    • /
    • v.7 no.1
    • /
    • pp.174-183
    • /
    • 2002
  • In this paper a control chart pattern recognition methodology based on the back propagation algorithm and Multi layer perceptron, a neural computing theory, is presented. This pattern recognition algorithm, suitable for real time statistical process control. evaluates observations routinely collected for control charting to determine whether a Pattern, such as a cycle. trend or shift, which is exists in the data. This approach is promising because of its flexible training and high speed computation with low-end workstation. The artificial neural network methodology is developed utilizing the delta learning rule, sigmoid activation function with two hidden layers. In a computer integrated manufacturing environment, the operator need not routinely monitor the control chart but, rather, can be alerted to patterns by a computer signal generated by the proposed system.

  • PDF

Research on the Relationship between Player Type and MMORPG "Grinding" Type (플레이어 유형과 MMORPG "Grinding" 유형과의 관계 연구)

  • Yang, Dan;Cho, Dong-Min
    • Journal of Korea Game Society
    • /
    • v.21 no.5
    • /
    • pp.49-62
    • /
    • 2021
  • In the middle and late period of MMORPG, as more and more time and energies are repeatedly consumed due to Grinding, it is easy for the players to feel bored and quit the game. This paper mainly studies the differences in preferences of four types of players for MMORPG grinding types. Apart from that, SPSS software is used to make descriptive analysis, credibility analysis, and one-way analysis of variance on the 200 survey sample data. Based on the content of the experimental results, this study proposes an optimized design plan for MMORPG grinding from the perspective of player tendency.

Implement Automobile Black Box System for Proving Cause of Sudden Unintended Acceleration (급발진 사고원인을 증명하기 위한 자동차 블랙박스 시스템 개발)

  • Kim, Minyoung;Jang, Jong-Wook
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.18 no.6
    • /
    • pp.1429-1434
    • /
    • 2014
  • Recently, SUA(Sudden Unintended Acceleration) are increasingly occurred. However, all the responsibilities of SUA are accepted by an innocent driver despite of painful results due to mystery of accurate cause. If a driver raises this kind of trouble to the corresponding manufacturer, the automaker collects EDR installed in that vehicle and provides the result of their analysis as it turns out most of the analysis results were diagnosed "there is nothing wrong with the car". In this trend, the technology to protect drivers' position from SUA should be developed. In this study, the researchers aimed to develop a black box system that collects additional data from throttle valve which is considered as one of major causes of SUA accidents, in order to explain cause of SUA and defend innocent drivers.

Development of a Portable and Disposable pH Sensor Based on Titanium Wire with High Electrochemical Sensing Performance (우수한 전기화학적 센싱 성능을 지닌 티타늄 와이어 기반의 휴대 및 일회용 pH 센서 개발)

  • Yoon, Eun Seop;Yoon, Jo Hee;Son, Seon Gyu;Kim, Seo Jin;Choi, Bong Gill
    • Applied Chemistry for Engineering
    • /
    • v.32 no.6
    • /
    • pp.700-705
    • /
    • 2021
  • A portable and disposable pH sensor based on Ti wire was successfully developed for monitoring hydronium ion concentrations. A sensing electrode was prepared by electrochemically depositing iridium oxide onto a Ti wire, while a reference electrode was fabricated by coating Ag/AgCl ink on a Ti wire. Combining the two electrodes in the pH sensor enabled the collection of open circuit potential signals when the sensor was immersed in solutions of various pH values. The pH sensor exhibited excellent electrochemical sensing performance in terms of sensitivity, response time, repeatability, selectivity, and stability. To demonstrate point-of-measurement applications, the pH sensor was integrated with a wireless electronic module that could communicate with a mobile application. The portable pH sensor accurately measured pH changes in real samples. The results obtained were consistent with those of using a commercial pH meter.

Efficiency Improvement Research in Proton Exchange Membrane Fuel Cell (고분자전해질형 연료전지의 효율향상에 대한 연구)

  • Jang, Haer-Yong;Kim, Jun-Bom
    • Journal of the Korean Electrochemical Society
    • /
    • v.8 no.4
    • /
    • pp.149-154
    • /
    • 2005
  • Fuel cell performance evaluation logic was developed using G-language (LabVIEW) to measure performance stability. Degree of stability and reliability of performance data were improved with averaged value and standard deviation method. Water injection system was introduced and the performance using this method was comparable to that of conventional humidification method. Water injection system has advantage of lowering operation energy consumption, reducing the number of parts needed in humidification, therefore increasing efficiency of fuel cell system. Fuel cell performance was decreased in case of low temperature operation such as sub freezing condition. Air purge method was tested to reduce the water content in cell fixture before sub freezing condition. The performance degradation due to low temperature operation was minimized by air purge method in medium size cell fixture ($25cm^2$) case.

Development of an FTA origin information management system prototype utilizing private block chain (프라이빗 블록체인 활용 FTA원산지 정보관리 시스템 프로토타입 개발)

  • Cho, Hyung-Min;Kim, Jong-Hyun;Lee, Kyung-Hee
    • The Journal of Bigdata
    • /
    • v.4 no.1
    • /
    • pp.1-10
    • /
    • 2019
  • As FTA is spreading, it is becoming more and more necessary to improve the accuracy and reliability of the country of origin information at the domestic trading stage in preparation for the actual surveys expected to surge in the near future. However, there are many problems in collecting and managing information related to origin. It is pointed out that the shortage of export-oriented profits and the incentive for issuance of FTA-related profits, as well as the lack of information on the distribution and management of origin information of domestic manufacturing companies are also pointed out as important causes. In this paper, we propose a method to improve the efficiency of management and circulation of smooth FTA origin (comprehensive) certificate of Korean companies and to improve reliability through manipulation prevention by building prototype of origin information management system based on private block chain Hyperledger. The block chain, called Distributed Ledger or Trusted Internet, provides a technical infrastructure that enables various related companies to distribute origin information with high reliability and immediate distribution in the supply chain, but research on its application is still in the beginning stage.

  • PDF

Modelling Phase Equilibria of Binary Mixtures for the Direct Synthesis of Dimethyl Carbonate from CO2 (직접 합성법을 이용한 dimethyl carbonate제조공정을 위한 공정 혼합물의 상평형 모델링)

  • Im, Jihoon;Lee, Gangwon;An, Jichul;Kim, Hwayong
    • Clean Technology
    • /
    • v.11 no.4
    • /
    • pp.165-170
    • /
    • 2005
  • The aim of this study is to provide vapor-liquid equilibrium (VLE) information for the study of process which directly synthesize dimethyl carbonate (DMC) from $CO_2$. For this study we collected some necessary VLE systems data of Methanol-Water, Methanol-DMC, $CO_2$-DMC, $CO_2$-Methanol, $CO_2$-Methanol, and performed VLE calculation with Peng-Robinson equation of state, Wong-Sandler mixing rules that widely used in chemical industry. These calculation results relatively agreed with VLE data well. Optimized Parameters of EoS given through this calculation will be used as some valuable information for fundamental study, process development and process optimization of DMC direct synthesis.

  • PDF

A More Storage-Efficient Order-Revealing Encryption Scheme (우수한 공간 효율성을 제공하는 순서노출암호 기법)

  • Kim, Kee Sung
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.29 no.3
    • /
    • pp.503-509
    • /
    • 2019
  • Order-revealing encryption which enables a range query over encrypted data is attracting attention as one of the important security technologies in industry such as IoT, smart manufacturing, and cloud computing. In 2015, an ideally-secure order-revealing encryption whose ciphertexts reveal no additional information beyond the order of the underlying plaintexts has been proposed. However, their construction is too inefficient for practical use and some security analysis of multilinear maps, which their construction relies on, have been proposed. Recently, more practical schemes have been proposed, focusing on achieving practically usable efficiency rather than the ideal security. In this paper, we propose a more storage-efficient order-revealing encryption scheme than the Lewi et al.'s scheme most recently published by presenting an idea that can generate shorter ciphertexts without any security loss.

Interorganizational Information System Asymmetry and Supply Chain Performance (조직간 정보시스템 비대칭과 공급망 성과)

  • Kim, Kyung Kyu;Lee, Ae Ri
    • The Journal of the Korea Contents Association
    • /
    • v.19 no.9
    • /
    • pp.460-475
    • /
    • 2019
  • Notwithstanding the big potential benefits from interorganizational information systems (IOS), not very many companies have realized these benefits. In an attempt to explain this phenomenon, this study proposes a new construct of IOS asymmetry which refers to the asymmetry in information transparency between supply chain (SC) partners. When there is IOS asymmetry in SC relationships, IOS may not facilitate seamless information exchange among SC partners. Instead, IOS asymmetry may result in SC inefficiencies due to a lack of information sharing. The objective of this study is to empirically investigate whether IOS asymmetry exists in practice and whether it influences SC performance negatively. The data was collected from 130 matched pairs of upstream SC partners in manufacturing industries. The results show that IOS asymmetry indeed decreases overall SC performance. Also, the relationship between IOS asymmetry and SC performance is strengthened under the conditions of high environmental uncertainty.

Machine Learning Model for Predicting the Residual Useful Lifetime of the CNC Milling Insert (공작기계의 절삭용 인서트의 잔여 유효 수명 예측 모형)

  • Won-Gun Choi;Heungseob Kim;Bong Jin Ko
    • Journal of Advanced Navigation Technology
    • /
    • v.27 no.1
    • /
    • pp.111-118
    • /
    • 2023
  • For the implementation of a smart factory, it is necessary to collect data by connecting various sensors and devices in the manufacturing environment and to diagnose or predict failures in production facilities through data analysis. In this paper, to predict the residual useful lifetime of milling insert used for machining products in CNC machine, weight k-NN algorithm, Decision Tree, SVR, XGBoost, Random forest, 1D-CNN, and frequency spectrum based on vibration signal are investigated. As the results of the paper, the frequency spectrum does not provide a reliable criterion for an accurate prediction of the residual useful lifetime of an insert. And the weighted k-nearest neighbor algorithm performed best with an MAE of 0.0013, MSE of 0.004, and RMSE of 0.0192. This is an error of 0.001 seconds of the remaining useful lifetime of the insert predicted by the weighted-nearest neighbor algorithm, and it is considered to be a level that can be applied to actual industrial sites.