• 대한기계학회논문집A
• /
• 제21권5호
• /
• pp.727-734
• /
• 1997

In practice, the design of forging processes is performed based on an experience-oriented technology, that is designer's experience and expensive trial and errors. Using the finite element simulation and the artificial neural network, we propose an optimal die geometry satisfying the design conditions of final product. A three-layer neural network is used and the back propagation algorithm is employed to train the network. An optimal die geometry that satisfied the same between inner extruded rib and outer extruded one is determined by applying the ability of function approximation of neural network. The neural networks may reduce the number of finite element simulation for determine the optimal die geometry of forging products and further they are usefully applied to physical modelling for the forging design.

• 한국산업정보학회논문지
• /
• 제28권5호
• /
• pp.77-87
• /
• 2023

재생 에너지 생성에서 중요한 역할을 하는 풍력 터빈은 작동 상태를 정확하게 평가하는 것이 에너지 생산을 극대화하고 가동 중지 시간을 최소화하는 데 매우 중요하다. 이 연구는 풍력 터빈 상태 진단을 위한 다양한 신경망 모델의 비교 분석을 수행하고 센서 측정 및 과거 터빈 데이터가 포함된 데이터 세트를 사용하여 효율성을 평가하였다. 분석을 위해 2MW 이중 여자 유도 발전기 기반 풍력 터빈 시스템(모델 HQ2000)에서 수집된 감시 제어 및 데이터 수집 데이터를 활용했다. 활성화함수, 은닉층 등을 고려하여 인공신경망, 장단기기억, 순환신경망 등 다양한 신경망 모델을 구축하였다. 대칭 평균 절대 백분율 오류는 모델의 성능을 평가하는 데 사용되었다. 평가를 바탕으로 풍력 터빈 상태 진단을 위한 신경망 모델의 상대적 효율성에 관한 결론이 도출되었다. 본 연구결과는 풍력발전기의 상태진단을 위한 모델선정의 길잡이가 되며, 고도의 신경망 기반 기법을 통한 신뢰성 및 효율성 향상에 기여하고, 향후 관련연구의 방향을 제시하는데 기여한다.

• 정보보호학회논문지
• /
• 제28권2호
• /
• pp.449-456
• /
• 2018

불필요한 트래픽의 송수신을 통한 분리된 조직/부서 간의 내부 자료 유출을 방지하기 위해 많은 조직에서 네트워크를 분할하여 망을 관리한다. 물리적으로 별도의 장비를 기반으로 하는 것이 가장 근본적인 네트워크 분할 방식이나 이보다 적은 비용으로 구축이 가능한 가상랜(Virtual LAN, VLAN) 네트워크 접근 제어 기능을 활용하여 논리적으로 네트워크를 분할 운영하는 사례가 존재한다. 본 연구에서는 VLAN ID값을 검색하는 스캐닝 기법과 Double Encapsulation VLAN Hopping 공격기법을 활용해 VLAN을 이용하여 분할된 네트워크 간 통신 우회 가능성을 제시한 후, 스캐닝을 통해 획득한 VLAN ID 정보를 이용한 자료 유출 시나리오를 제시한다. 또한 이 공격을 탐지 및 차단하기 위한 기법을 제안하고 구현을 통해 제시된 기법의 효과에 대해 검증한다. 본 연구는 궁극적으로 VLAN으로 분리된 네트워크 취약점을 활용한 자료 유출 또는 외부 사이버 공격을 차단함으로써 VLAN 이용 환경의 보안성 향상에 기여할 것으로 기대한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2164-2168
• /
• 2003

Real time control system such as in factory automation fields, defense field, aerospace, railway industries, financial trading and so forth, includes multiple computers on multiple nodes, and share data to process various actions and functions. This is similar to multitasking in a multiprocessor computer system. The task processing efficiency of such system is proportionally increased by process speed of each process computer. And also it is greatly influenced by communication latencies of each node. To provide proper operation of such real time system, a network that can guarantee deterministic exchange of certain amount of data within a limited time is required. Such network is called as a real time network. As for modern distributed control system, the timeliness of data exchange gives important factor for the dynamics of entire control system. In a real time network system, exchanged data are determined by off-line design process to provide the timeliness of data. In other word, designer of network makes up a network data table that describes the specification of data exchanged between control equipments. And by this off-line design result, the network data are exchanged by predetermined schedule. First, this paper explains international standard real time network TCN (Train Communication Network) applied to the KHST (Korean High Speed Train) project. And then it explains the computer program developed for design tool of network data table of TCN.

• 한국물환경학회지
• /
• 제28권4호
• /
• pp.615-623
• /
• 2012

In this study, we evaluate the corrosion indexes (CI) such as Langelier Index (LI), Larson ratio (LR), Ryznar saturation index (RSI), Aggressiveness index (AI) of water quality for raw water, treated water and water in distribution reservoir at major eight drinking water treatment plants (DWTPs) in Korea. By analyzing secondary contamination of tap water, the variation of secondary contaminants was investigated with regard to pipe materials, aging and corrosion index (CI). In addition, we suggested an appropriate CI applicable water quality and the management plan for CI monitoriing. All CI showed corrosive water quality, and they did not change significantly in the distribution network. However, Copper (Cu), iron (Fe) and zinc (Zn) concentrations as secondary contaminants increased through the distribution network. Among CI, LI was most sensitive to changes in raw water quality and drinking water treatment. Also, it has high correlations with other indexes such as RSI, AI. Therefore, LI is considered as an appropriate CI to the domestic water quality. Based on these result, we propose LI as a drinking water quality standard to control the pipe corrosion from DWTPs.

• Computers and Concrete
• /
• 제32권6호
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.319-323
• /
• 2022

The information research system continues to be developed and directed at leading research National Institute of Technology (ITN) Malang in accordance with the Research Strategic Plan of ITN Malang. One of them is a computer system in a complete integrated facility management activity, such as this research scheme. The purpose of this research is to combine and integrate people, places, product, processes and technology. All of them are integrate existing organizational factors into a more effective, simplifying of complex processes, identifying and scheduling, notes, decision makers and more. This research was conducted in stages by design with a structured model stage for 3 (three) years (focus on humans, products and processes), research on Integration Facility Management: Interface Coordination in human resources and product management have been completed on 2019 and 2020. While the focus of research this year is to obtain an integrated facility management Interface Coordination in Process Management.

• 한국재료학회지
• /
• 제18권3호
• /
• pp.163-168
• /
• 2008

The morphology of three-dimensional (3D) cross-linked electrodeposits of copper and tin was investigated as a function of the content of metal sulfate and acetic acid in a deposition bath. The composition of copper sulfate had little effect on the overall copper network structure, whereas that of tin sulfate produced significant differences in the tin network structure. The effect of the metal sulfate content on the copper and tin network is discussed in terms of whether or not hydrogen evolution occurs on electrodeposits. In addition, the hydrophobic additive, i.e., acetic acid, which suppresses the coalescence of evolved hydrogen bubbles and thereby makes the pore size controllable, proved to be detrimental to the formation of a well-defined network structure. This led to a non-uniform or discontinuous copper network. This implies that acetic acid critically retards the electrodeposition of copper.

• 대한한의학방제학회지
• /
• 제28권3호
• /
• pp.243-254
• /
• 2020

Objectives : Network pharmacology analysis is commonly used to investigate the synergies and potential mechanisms of multiple compounds by analyzing complex, multi-layered networks. We used TCMSP and BATMAN-TCM databases to compare results of network pharmacological analysis between White Ginseng(WG) and Red Ginseng(RG). Methods : WG and RG were compared with components and their target molecules using TCMSP database, and compound-target-pathway/disease networks were compared using BATMAN-TCM database. Results : Through TCMSP, 104 kinds of target molecules were derived from WG and 38 kinds were derived from RG. Using the BATMAN-TCM database, target pathways and diseases were screened, and more target pathways and diseases were screened compared to RG due to the high composition of WG ingredients. Analysis of component-target-pathway/disease network using network analysis tools provided by BATMAN-TCM showed that WG formed more networks than RG. Conclusions : Network pharmacology analysis can be effectively performed using various databases used in system biology research, and although the materials that have been reported in the past can be used efficiently for research on diseases related to targets, the results are unreliable if prior studies are focused on limited or narrow research areas.

• ETRI Journal
• /
• 제40권3호
• /
• pp.355-365
• /
• 2018

The increase in data traffic calls for investment in mobile networks; however, the saturating revenue of mobile broadband and increasing capital expenditure are discouraging mobile operators from investing in next-generation mobile networks. Mobile network sharing is a viable solution for operators and regulators to resolve this dilemma. This research uses a difference-in-differences analysis of 33 operators (including 11 control operators) to empirically evaluate the cost reduction effect of mobile network sharing. The results indicate a reduction in overall operating expenditure and short-term capital expenditure by national roaming. This finding implies that future technology and standards development should focus on flexible network operation and maintenance, energy efficiency, and maximizing economies of scale in radio access networks. Furthermore, mobile network sharing will become more viable and relevant in a 5G network deployment as spectrum bands are likely to increase the total cost of ownership of mobile networks and technical enablers will facilitate network sharing.