Search | Korea Science

Manufacturing Data Aggregation System Design for Applying Supply Chain Optimization Technology (공급망 최적화 기술 적용을 위한 제조 데이터 수집 시스템)

Hwang, Jae-Yong;Shin, Seong-Yoon;Kang, Sun-Kyoung
- Journal of the Korea Institute of Information and Communication Engineering
- /
- v.25 no.11
- /
- pp.1525-1530
- /
- 2021
By applying AI-based efficient inventory management and logistics optimization technology using the smart factory's production plan and manufacturing data, the company's productivity improvement and customer satisfaction can be expected to increase. In this paper, we proposed a system that collects data from the factory's production process, stores it in the cloud, and uses the manufacturing data stored there to apply AI-based supply chain optimization technology later. While the existing system supported approximately 10 to 20 data types, the proposed system is designed and developed to support more than 100 data types. In addition, in the case of the collection cycle, data can be collected 1-2 times per second, and data collection in TB units is possible. Therefore This system is designed to be applied to the existing factory of past in addition to the smart factory.
https://doi.org/10.6109/jkiice.2021.25.11.1525 인용 PDF KSCI

Optimization of γ-Aminobutyric Acid Production by Enterococcus faecium JK29 Isolated from a Traditional Fermented Foods (전통발효식품 유래 Enterococcus faecium JK29에 의한 γ-aminobutyric acid의 생산 최적화)

Lim, Hee Seon;Cha, In-Tae;Lee, Hyunjin;Seo, Myung-Ji
- Microbiology and Biotechnology Letters
- /
- v.44 no.1
- /
- pp.26-33
- /
- 2016
Dominant lactic acid bacteria (LAB) strains were isolated from traditional fermented foods to obtain rare ${\gamma}$-aminobutyric acid (GABA)-producing LAB. Out of 147 isolates, 23 strains that could produce GABA with 1% (w/v) L-monosodium glutamate (MSG) were first isolated. After further screening of these rare GABA-producing LAB by analysis of the glutamate decarboxylase and 16S rRNA gene sequences, Enterococcus faecium JK29 was isolated, and 1.56 mM of GABA was produced after 48 h cultivation in basic de Man, Rogosa, and Sharpe (MRS) medium. To enhance GABA production by E. faecium JK29, the culture conditions were optimized. When E. faecium JK29 was cultivated in optimized MRS medium containing 0.5% (w/v) sucrose and 2% (w/v) yeast extract with 0.5% (w/v) MSG, GABA production reached 14.86 mM after 48 h cultivation at initial conditions of pH 7.5 and $30^{\circ}C$.
https://doi.org/10.4014/mbl.1512.12004 인용 PDF KSCI KPUBS HTML

Development of Well Placement Optimization Model using Artificial Neural Network and Simulated Annealing (인공신경망과 SA 알고리즘을 이용한 지능형 생산정 위치 최적화 전산 모델 개발)

Kwak, Tae-Sung;Jung, Ji-Hun;Han, Dong-Kwon;Kwon, Sun-Il
- Journal of the Korean Institute of Gas
- /
- v.19 no.1
- /
- pp.28-37
- /
- 2015
This study presents the development of a well placement optimization model, combining an artificial neural network, which enables high-speed calculation, with a simulated annealing algorithm. The conventional FDM simulator takes excessive time when used to perform a field scale reservoir simulation. In order to solve this problem, an artificial neural network was applied to the model to allow the simulation to be executed within a short time. Also by using the given result, the optimization method, SA algorithm, was implemented to automatically select the optimal location without taking any subjective experiences into consideration. By comparing the result of the developed model with the eclipse simulator, it was found that the prediction performance of the developed model has become favorable, and the speed of calculation performance has also been improved. Especially, the optimum value was estimated by performing a sensitivity analysis for the cooling rate and the initial temperature, which is the control parameter of SA algorithm. From this result, it was verified that the calculation performance has been improved, as well. Lastly, an optimization for the well placement was performed using the model, and it concluded the optimized place for the well by selecting regions with great productivity.
https://doi.org/10.7842/kigas.2015.19.1.28 인용 PDF KSCI

Material Topology Optimization Design of Structures using SIMP Approach Part II : Initial Design Domain with Topology of Partial Solids (SIMP를 이용한 구조물의 재료 위상 최적설계 Part II : 부분적인 솔리드 위상을 가지는 초기 설계영역)

Lee, Dong-Kyu;Park, Sung-Soo;Shin, Soo-Mi
- Journal of the Computational Structural Engineering Institute of Korea
- /
- v.20 no.1
- /
- pp.19-28
- /
- 2007
Discrete topology optimization processes of structures start from an initial design domain which is described by the topology of constant material densities. During optimization procedures, the structural topology changes in order to satisfy optimization problems in the fixed design domain, and finally, the optimization produces material density distributions with optimal topology. An introduction of initial holes in a design domain presented by Eschenauer et at. has been utilized in order to improve the optimization convergence of boundary-based shape optimization methods by generating finite changes of design variables. This means that an optimal topology depends on an initial topology with respect to topology optimization problems. In this study, it is investigated that various optimal topologies can be yielded under constraints of usable material, when partial solid phases are deposited in an initial design domain and thus initial topology is finitely changed. As a numerical application, structural topology optimization of a simple MBB-Beam is carried out, applying partial circular solid phases with varying sizes to an initial design domain.
PDF KSCI