• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.31-36
• /
• 2003

This paper proposes an acceleration method of PCA(Principal Component Analysis) based feature detection. The feature detection method makes decision whether the target feature is included in a given image, and if included, calculates the position and extent of the target feature. The position and scale of the target feature or face is not known previously, all the possible locations should be tested for various scales to detect the target. This is a search Problem in huge search space. This Paper proposes a fast face and feature detection method by reducing the search space using the multi-stage prediction map and contour Prediction map. A Proposed method compared to the existing whole search way, and it was able to reduce a computational complexity below 10％ by experiment.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.2
• /
• pp.128-134
• /
• 2008

This paper presents a machining error compensation methodology due to deflection of micro cutting tools in side cutting processes. Generally in order to compensate for tool deflection errors it is necessary to carry out a series of simulations, cutting force prediction, tool deflection estimation and compensation method. These can induce numerous calculations and expensive costs. This study proposes an improved approach which can compensate for machining errors without simulation processes concerning prediction of cutting force and tool deflection. Based on SEM images of test cutting specimens, polynomial relationships between machining errors and corrected tool positions were induced. Taking into account changes of cutting conditions caused by tool position variation, an iterative algorithm was applied in order to determine corrected tool position. Experimental works were carried out to validate the proposed approach. Comparing machining errors of nominal cutting with those of compensated cutting, overall machining errors could be remarkably reduced.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.568-574
• /
• 2006

User adaptive services have been important features in many applications. To provide such services, various techniques with various kinds of data are being used. In this paper, we propose a method to analyze user's past moving paths and predict the goal position and the path to the goal by observing the user's current moving path. We develop a spatiotemporal similarity measure between paths. We choose a past path which is the most similar to the current path using the similarity. Based on the chosen path, user's spatiotemporal position is estimated. Through experiments we confirm this method is useful and effective.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.3
• /
• pp.43-53
• /
• 2022

In this study, analysis of the flow characteristics of pintle-controlled nozzle with split-line TVC system and the thrust performance prediction was performed. The numerical computation was verified by comparing the thrust coefficient derived from the analysis results with the experimental data. By applying the same numerical analysis technique, the flow characteristics of nozzle were confirmed according to operating altitude, pintle stroke position and TVC angle with the 1/10 scale. As the TVC angle increased, thrust loss occurred and the tendency of AF was different depending on the position of the pintle stroke. Based on the analysis results, the relation of thrust coefficient was derived by applying the response surface methods. The thrust performance model with a slight difference of 1.2% on average from the analysis result was generated.

• Design & Manufacturing
• /
• v.17 no.4
• /
• pp.1-7
• /
• 2023

In the fabrication of curved multi-display glass for automotive use, the surface roughness of the mold is a critical quality factor. However, the difficulty in detecting micro-cutting signals in a micro-machining environment and the absence of a standardized model for predicting micro-cutting forces make it challenging to intuitively infer the correlation between cutting variables and actual surface roughness under machining conditions. Consequently, current practices heavily rely on machining condition optimization through the utilization of cutting models and experimental research for force prediction. To overcome these limitations, this study employs a surface roughness prediction formula instead of a cutting force prediction model and converts the surface roughness prediction formula into experimental data. Additionally, to account for changes in surface roughness during machining runtime, the theory of position variables has been introduced. By leveraging artificial neural network technology, the accuracy of the surface roughness prediction formula model has improved by 98%. Through the application of artificial neural network technology, the surface roughness prediction formula model, with enhanced accuracy, is anticipated to reliably perform the derivation of optimal machining conditions and the prediction of surface roughness in various machining environments at the analytical stage.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1327-1335
• /
• 2011

Recently, also in railway vehicles, related products are being designed and manufactured through RAMS activities in order to secure their reliability, availability, maintainability & safety. Subway operators are conducting R&D on various preventive maintenance methods and applying them to the field so as to establish a reliability centered maintenance(RCM) system. In this connection, manufacturers shall carry out R&D based on reliability from the first design stage of development to provide high quality products to subway operators. And operators shall have the products operated properly to their particular operating environment and managed based on the standard maintenance manual. Not only that, but the related field data shall be fed back into the manufacturers to upgrade upcoming products by organic cooperation between manufacturer and operators. However, the mutually beneficial cooperative relationship is not still developed in the domestic railway industry. In terms of methodology for life prediction, this study was intended to analyze field data on relays used for rolling stocks considering operational characteristics in the position of subway operators and predict parts reliability using reliability prediction program from the standpoint of manufacturers as well.

• International Journal of Fluid Machinery and Systems
• /
• v.2 no.1
• /
• pp.80-91
• /
• 2009

In this study, a prediction theory for specific noise that is the overall characteristic of the fan has been proposed. This theory is based on total pressure prediction and broadband noise prediction. The specific noises of two forward curved fans with different number of blades were predicted. The flow around the impeller having 120 blades (MF120) was more biased at a certain positions than the impeller with 40 blades (MF40). An effective domain of the energy conversion of MF40 has extended overall than MF120. The total pressure was affected by the slip factor and pressure loss caused by the vortex flow. The suppression of a major pressure drop by the vortex flow and expansion of the effective domain for energy conversion contributed to an increase in the total pressure of MF40 at the design point. The position of maximum relative velocity was different for each fan. The relative velocity of MF120 was less than that of MF40 due to the deviation angle. The specific noise of MF120 was 2.7 dB less than that of MF40 due to the difference in internal flow. It has been quantitatively estimated that the deceleration in the relative velocity contributed to the improvement in the overall performance.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2002.11a
• /
• pp.1-6
• /
• 2002

To provide an easy operation of drift prediction model in SAR(search and rescue) mission a GUI program running on Window environment has developed. Users can make choice of input data on the screen by just clicking the mouse and the prediction results of datum points and trajectories of vessels are drawn on the map. The program contains both Leeway Equation model and mathematical model. The FORTRAN language was used in programming and Lehay Winteracter 4.0 software was utilized for graphic presentation. The result of May, 2001 Busan field experiment was plotted with that of model prediction for demonstration purpose.

• Fire Science and Engineering
• /
• v.17 no.3
• /
• pp.55-60
• /
• 2003

This study established analysis theory for flow characteristics prediction of the spray nozzle and predicted discharge and discharge type of the spray nozzle from numerical analysis. It could know that discharge type of the spray nozzle from prediction data determine to position of nozzle and needle, and flow characteristics prediction of the spray nozzle could know that the characteristics according to shape of nozzle and needle is decided. New model of the spray nozzle that can maximize efficiency of fire suppression from flow characteristics and prediction data of the spray nozzle is presented. The result of this study utilize to data necessary to develop new model of the spray nozzle. Also the result of this study wish to contribute to resource technology security of the spray nozzle, technique ripple effect enlargement of same kind industry and technical development activation of fire protection field etc.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.355-362
• /
• 2012

The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.