신경망 모델 기반 조선소 조립공장 작업상태 판별 알고리즘

Korean Journal of Construction Engineering and Management, 2013

Owners' efforts to acquire Green building certification, which started in 2002, have been rapidly increasing since 2006. The causes of the increased owners' interests are due to various incentives, legal obligation, and purpose of advertising. As project owners generally are deficient in capabilities and knowledge on how to deal with administrative works on certification, they tend to fulfill the minimum requirements for certification. However, effective administration process need capabilities of identifying individual making decision point and review information. The implementation of green building certification system is expected to provide comfort to both occupants and potential users. Furthermore it contributes to reducing energy costs throughout the phase of O&M. In addition, technology innovation in green industry can be obtained. Therefore, this study is intended to support owners in order that they can clarify certification tasks and make a rational decision-making in time. For this purpose, first of all, the major decision points were selected as the gateways of green building certification process. And then management system based on IDEF3 modeling was developed for supporting owners'decision-making performance. This management system will improve owners'overall capacity in handling all the tasks regarding the certification of Green building.

2020

The purpose of this paper is to develop a fire HRA (Human Reliability Analysis) procedure for full power operation of domestic NPPs (Nuclear Power Plants). For the development of fire HRA procedure, the recent research results of NUREG-1921 in an effort to meet the requirements of the ASME/ANS PRA Standard were reviewed. The K-HRA method, a standard method for HRA of a domestic level 1 PSA (Probabilistic Safety Assessment) and fire related procedures in domestic NPPs were reviewed. Based on the review, a procedure for the fire HRA required for a domestic fire PSA based on the K-HRA method was developed. To this end, HRA issues such as new operator actions required in the event of a fire and complexity of fire situations were considered. Based on the four kinds of HFE (Human Failure Event) developed for a fire HRA in this research, a qualitative analysis such as feasibility evaluation was suggested. And also a quantitative analysis process which consists of screening analysis and detailed analysis was proposed. For the qualitative analysis, a screening analysis by NUREG-1921 was used. In this research, the screening criteria for the screening analysis was modified to reduce vague description and to reflect recent experimental results. For a detailed analysis, the K-HRA method and scoping analysis by NUREG-1921 were adopted. To apply K-HRA to fire HRA for quantification, efforts to modify PSFs (Performance Shaping Factors) of K-HRA to reflect fire situation and effects were made. For example, an absence of STA (Shift Technical Advisor) to command a fire brigade at a fire area is considered and the absence time should be reflected for a HEP (Human Error Probability) quantification. Based on the fire HRA procedure developed in this paper, a case study for HEP quantification such as a screening analysis and detailed analysis with the modified K-HRA was performed. It is expected that the HRA procedure suggested in this paper will be utilized for fire PSA for domestic NPPs as it is the first attempt to establish an HRA process considering fire effects.

2004

The Purpose of this paper is to propose performance evaluation schemes of flexible manufacturing cell using a generalized stochastic Petri net. In the competitive and global manufacturing environment, to evaluate the feasibility and manufacturability of a product in the product design stage is highly required. Through this process, all the possible problems which may occur in the manufacturing stage can be fixed in early stage. The scheme of generalized stochastic Petri net utilizing both immediate and exponential distributed transitions are applied to model a manufacturing cell with flexible machines, material handler, transporter and buffers. Performance analyses are performed based on behavioral, structural and quantitative properties. A flexible manufacturing cell is evaluated using a Petri net simulator.

Journal of Korea Multimedia Society, 2012

Journal of the Korea Academia Industrial Cooperation Society, 2017

The purpose of this study is to develop and validate the Korean Job Crafting Scale. First, previous studies on the concept and measurement of job crafting were reviewed, and items were developed based on this review. The content validity of the scale was examined using a focus group interview consisting of 10 HRM professionals. Following modification of the items, the measurements were administered to 305 employees from 8 Korean firms, and exploratory factor analysis was conducted in order to examine the factorial validity of the scale. Subsequently, confirmatory factor analysis was implemented concerning data collected from 295 employees who work in 7 Korean firms. Results indicated that the measurement model sufficiently explained the data at an appropriate level, and the subscales featured convergent and discriminant validity. If the scale developed in this study is validated in further studies, it can be employed to conduct research regarding job crafting in Korean organizations.

2010

As for the present wind power industry, most of the computerization for monitoring and control is based on the traditional development methodology, but it is necessary to improve SCADA system since it has a phenomenon of backlog accumulation in the applicable aspect of back-data as well as in the operational aspect in the future. Especially for a system like offshore wind power where a superintendent cannot reside, it is desirable to operate a remote control system. Therefore, it is essential to establish a monitoring system with appropriate control and monitoring inevitably premised on the integrity and independence of data. As a result, a study was carried out on the modeling of offshore wind power data-centered database. In this paper, a logical data modeling method was proposed and designed to establish the database of offshore wind power. In order for designing the logical data modeling of an offshore wind power system, this study carried out an analysis of design elements for the database of offshore wind power and described considerations and problems as well. Through a comparative analysis of the final database of the newly-designed offshore wind power system against the existing SCADA System, this study proposed a new direction to bring about progress toward a smart wind power system, showing a possibility of a service-oriented smart wind power system, such as future prediction, hindrance-cause examination and fault analyses, through the database integrating various control signals, geographical information and data about surrounding environments.

Journal of KIISE, 2019

Recently, there has been an increase in P2P lending users, a product that supports investments through lending among individuals using online platforms. However, since P2P lending's investors have to take financial risks, the investors may fail to investment due to the close of investment while they considering whether to invest or not. This paper predicts how long an investment product will take from a certain point to the close in order to provide deadline information for P2P loan investment products. To predicts the investment deadline, we have transforms into Timeseries data and Step data based on investment information on actual P2P products. The regression, classification, and time series prediction model were generated using machine learning algorithm. The results of the performance evaluation showed that in the Timeseries data-based model, the Multi-layer Perceptron regression model and the classification model showed the highest performance at 0.725 and 0.703 respectively. The Step data-based model was also the highest with the Multi-layer Perceptron regression model and the classification model at 0.782 and 0.651 respectively.

Journal of Digital Convergence, 2013

In this paper, we present a procedural modeling algorithms to create Korean traditional stone fence using the fractal subdivision. The main process of the algorithm is to get the next step mesh by subdividing each triangle in the previous step triangular mesh. This process is repeated recursively. Dividing each triangle into four sub-triangles after choosing a random point on each side of the triangle and moving each vertices in the normal direction with random perturbations make the bumpy appearance of stone fences. In each step we remove flat vertices which does not influence the shape of the stone. The discrete curvature determines the flatness of a vertex. New triangles whose vertices are the vertices around the removed vertex are added to make a triangular mesh.

Journal of the Institute of Electronics Engineers of Korea, 2013

We propose adaptive detection algorithm to reduce a false alarm by considering the characteristics of the random noise on the detection system based on a seismic sensor. The proposed algorithm consists of the first step detection using kernel function and the second step detection using detection classes. Kernel function of the first step detection is obtained from the threshold of the Neyman-Pearon decision criterion using the probability density functions varied along the noise from the measured signal. The second step detector consists of 4 step detection class by calculating the occupancy time of the footstep using the frist detected samples. In order to verify performance of the proposed algorithm, the detection of the footsteps using measured signal of targets (walking and running) are performed experimentally. The detection results are compared with a fixed threshold detector. The frist step detection result has the high detection performance of 95% up to 10m area. Also, the false alarm probability is decreased from 40% to 20% when it is compared with the fixed threshold detector. By applying the detection class(second step detector), it is greatly reduced to less than 4%.

Transactions of the Korean Society of Mechanical Engineers A, 2010

Journal of the Korean Society of Marine Engineering, 2008

Journal of manufacturing engineering & technology, 2013

In this paper, in order to overcome shortcomings of manual inspection for the automotive PWM Shaft, we developed an automated inline inspection system. The automated inline inspection system consists of the work feeder unit, conveying unit, outer diameter check unit, run-out and roundness check unit, machine vision, defective separation unit and status alarm unit. We used the machine vision system for automatic inspection process and designed the inline systems for automatic feeding and selecting process. Also the repeated operation test was performed in order to verify the precision and reliability of the proposed automated inline inspection system.

Journal of the Korea Society for Simulation, 2012

Automobile manufacturing consists of body-line, painting-line, and assembly-line. These production lines are disposed in series and go through a flow process, so according to the status of pre & post processing, a suspension happens in a line by a starvation(impossibility of production by insufficient supply) or blocking(impossibility of production by exceed capacity). Therefore, to prevent a loss of production coming from a starvation or blocking, a storage such as WBS or PBS is independently owned and operated. The paper suggests the simulation model of integrated storage which can operate it by integrating each storage performing a role as a buffer of line. Specifically, the paper found the answers about reasonable number of Stacker Crane and AGV(Automatic Guided Vehicle) and suggested a methodology of operation which is available to operate them. Also, it compared an efficiency between a model of current storage and integrated storage through simulation. As a result, it turned out that the model suggested in the paper was more efficient on suspension of painting-line stop than a current storage.

Journal of the Ergonomics Society of Korea, 2007

The analog typed interface of main control room in nuclear power plant(NPP) is gradually being replaced to the one suitable for the digital environment. SKN 3,4 is currently developed in such a way to employ digitalized displays and controls such as computerized procedure system(CPS), large display panel(LDP), and Soft control. The main control room (MCR) of the SKN3, 4 was designed based on the human factors guidelines, which somehow lack of the confidence for the rapidly changing digital environment. Although the suitable review guidelines for the digitalized information displays was developed, the developed guidelines needs to extend to the one to apply for the total digital environment including task environment, hardware and workstation. In order to achieve the research objectives, tremendous guidelines and technical papers related to evaluation issues of digital environment has been collected, analyzed and transformed to electric database forms and then built on database management system to retrieve the appropriate issues for the practical usage of evaluators-in-field.

Journal of the Ergonomics Society of Korea, 2009

While the operator's working environment employs the digital devices and technology which are not be fully digitalized due to its technical constraints, it has been changed to the hybrid environment in which digital and analog elements are combined. The hybrid environments need to study its characteristics and the guidelines for the proper design and evaluation purpose. This paper describes the characteristics and evaluation guidelines for hybrid environment through studying the characteristics of digital and analog environment based on the related human factor guidelines and literatures. The result of this paper would be applied for the human machine system such as main control room in nuclear power plant working under hybrid environment. And also, it may be applied for the evaluation of the generic human working environment which digital and analog elements are jointly used.