• Journal of KIBIM
• /
• v.11 no.2
• /
• pp.24-32
• /
• 2021

Recently, starting with smart construction research, interest in technology that automates construction site management using artificial intelligence technology is increasing. In order to automate construction site management, it is necessary to recognize objects such as construction equipment or workers, and automatically analyze the relationship between them. For example, if the relationship between workers and construction equipment at a construction site can be known, various use cases of site management such as work productivity, equipment operation status monitoring, and safety management can be implemented. This study derives a real-time object detection platform architecture that is required when performing construction site management using deep learning technology, which has recently been increasingly used. To this end, deep learning models that support real-time object detection are investigated and analyzed. Based on this, a deep learning model development process required for real-time construction site object detection is defined. Based on the defined process, a prototype that learns and detects construction site objects is developed, and then platform development considerations and architecture are derived from the results.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.664-667
• /
• 1997

For higher component density per chip, it is necessary to identify and control the semiconductor manufacturing process more stringently. Recently, neural networks have been identified as one of the most promising techniques for modeling and control of complicated processes such as plasma etching process. Since wafer states after each run using identical recipe may differ from each other, conventional neural network models utilizing input factors only cannot represent the actual state of process and equipment. In this paper, in addition to the input factors of the recipe, real-time tool data are utilized for modeling of 64M DRAM s-poly plasma etching process to reflect the actual state of process and equipment. For real-time tool data, we collect optical emission spectroscopy (OES) data. Through principal component analysis (PCA), we extract principal components from entire OES data. And then these principal components are included to input parameters of neural network model. Finally neural network model is trained using feed forward error back propagation (FFEBP) algorithm. As a results, simulation results exhibit good wafer state prediction capability after plasma etching process.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.767-770
• /
• 2000

In order to reduce lean-time and cost, recently the technology of Rapid Prototyping and Manufacturing(PR/M) has been used widely. So various RP/M methods have been developed and these systems commercialized several years ago. The machining process is one of these methods. It also offers advantages such as precision and versatility. But there are some considerations during machining. The most important problem among them is the fixturing. So we have to overcome the limitation because the fixturing time is depend on the complexity of geometry to be machined. In this paper, we have developed the fixturing technique using filling process that can be widely useful for rapid products within a short time. So we have carried out some kinds of rapid products such as plastic knob and metal fan using our fixturing process. In fixturing step, the filling material might chosen a resin or a alloy according to wether the work material is plastic or metal respectively. Also we developed the set-up equipment attachable on the table of the milling machine that provided practicable quality during a series of machining operations, named by two step milling process.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.05a
• /
• pp.1112-1113
• /
• 2005

• Journal of Applied Reliability
• /
• v.15 no.4
• /
• pp.248-255
• /
• 2015

Purpose : The purpose of this research is to develop the optimized method and process in the reliability-growth target setting, especially for complex and repairable system (or products) such as vehicle and airplane, construction equipment. Method : A reliability-growth test plan specifies a scenario to achieve the planned reliability value (or reliability target). The major elements in test planning are reliability-growth starting time and reliability level at that time, reliability-growth rate and reliability-growth target. All of them except a reliability target can be referred to the previous development data and reference researches. The reliability target level is directly influencing to test period (or time) which is related to test and warranty cost together. There are a few researches about the reliability target setting method and but showing the limitations to consider the views of engineering, business and customer together. There is no research how to handle the target setting process in detail. Result : We develop the optimized method and systematic process in reliability target setting with considering such views. This research also establish the new concept as production capability which means company (or supplier) capability to product its products. Conclusion : In this research result, we apply the new method to a few projects and can set the reasonable test planning. The developing results is showing the good balance between the developing cost and warranty cost at market.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1804-1814
• /
• 2015

In order to explore the characteristics of electrons in DC negative corona discharge, an improved plasma chemical model is presented for the simulation of bar-plate DC corona discharge in dry air. The model is based on plasma hydrodynamics and chemical models in which 12 species are considered. In addition, the photoionization and secondary electron emission effect are also incorporated within the model as well. Based on this model, electron mean energy distribution (EMED), electron density distribution (EDD), generation and dissipation rates of electron at 6 typical time points during a pulse are discussed emphatically. The obtained results show that, the maximum of electron mean energy (EME) appears in field ionization layer which moves towards the anode as time progresses, and its value decreases gradually. Within a pulse process, the electron density (ED) in cathode sheath almost keeps 0, and the maximum of ED appears in the outer layer of the cathode sheath. Among all reactions, R1 and R2 are regarded as the main process of electron proliferation, and R₂₂ plays a dominant role in the dissipation process of electron. The obtained results will provide valuable insights to the physical mechanism of negative corona discharge in air.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.09a
• /
• pp.82-88
• /
• 2001

Manufactured easy elevator can drives from the first floor to fifth floor as sequence control circuit in cause opening than existing equipment of experiment and practice, the structure of in the first implementation process are hand-worked control component with push-button, L/S and relay, it is structured a lamp to express that the door open and moving of cage by mechanical action of For/Rev motor-braker of which load. The second structure of implement process to control from the first floor to the fifth floor with the PLC elevator program can control by the sensor of hand-operated function of L/Sl~L/S5 in time that the S/Wl~S/W5 of PLC control panel operates to the For/Rev. The function of two kind process that an elevator is driven by PLC program and the sequence control relay circuit is a mechanical relay sequence control field and it is equipment apparatus of it to get appropriately the technology of For/Rev in that mechanical operating cause of a load using the PLC program. Also the wring circuit using a plug, dissembly. the circuit and the principle of component, and PLC program with the function test can be used the implementation field to the total technology theory about FA.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.4
• /
• pp.460-468
• /
• 2009

The purpose of this study is propose an alternative for flight attendants to acquire equipment that could enhance the ability to adapt in flying conditions. Introducing and acquiring weapon system, such equipments should be deeply considered in multilateral aspects; reinforcements in the overall strategic status in the army, the ramifications that can contribute to military resources, and economic situations in the country. To do this, we first induced several criteria that can be used for evaluating alternatives. After that, we applied the analytic hierarchy process(AHP) approach to putting all factors into considerations in decision making for equipment acquirement. The results of this study are expected to have usefulness in formulating strategies and policies in selecting equipment acquisition alternatives for flight attendants.

• Resources Recycling
• /
• v.9 no.6
• /
• pp.53-57
• /
• 2000

In the present paper, a current technical progress for recycling of used steel can is described. The developed technology was a kind of pre-treatment through an automatic equipment system to increase recycling and melting efficiency of used steel co. The process consisted of several unit processes such as breaking of steel can bale, removing dust, separation of aluminum can, delacquering, and compressing to bale. Also, aluminum powders were recovered as a by-product at the delacquering step. The process was carried out automatically through by use of the developed equipment system. The automatic system could be very available in mass treatment of used steel can.

• Nuclear Engineering and Technology
• /
• v.53 no.3
• /
• pp.1004-1012
• /
• 2021

High density polyethylene (HDPE) pipe has many advantages over metallic pipe, and has been used in non-safety related application for years in some nuclear power plants (NPPs). Recently, HDPE pipe was introduced into safety related applications. The main difference between safety-related and non-safety-related pipes in NPPs is the design method of extra loadings such as gravity, temperature, and earthquake. In this paper, the mechanical behavior of HDPE pipe under various loads in pipe gallery was studied by finite element analysis (FEA). Stress concentrations were found at the fusion regions on inner surface of mitered elbows of HDPE pipe system. The effects of various factors were analyzed, and the influence of various loads on the damage of HDPE pipe system were evaluated. The results of this paper provide a reference for the design of nuclear safety-related Class 3 HDPE pipe. In addition, as the HDPE pipes analyzed in this paper were suspended in pipe gallery, it can also serve as a supplementary reference for current ASME standard on Class 3 HDPE pipe, which only covers the application for buried pipe application.