• Journal of Biosystems Engineering
• /
• v.13 no.4
• /
• pp.9-19
• /
• 1988

The threshing of head-feed combine may be accomplished mainly by the action of impact between threshing teeth and rice. In this study, it was attempted to assess threshing performance characteristics of head-feed threshing teeth. And the characteristics of threshing teeth will be applied to the method which could analyze the time and order of impact between teeth and the rice, which was used as a basis for predicting the threshing performance and determining the optimum design parameters. The results of the study are summarized as follows: 1. About 50% of threshed material were threshed by the beginning 7 impacts on the rice bundle. Threshing torque decreased until 25 impacts and did not change thereafter. 2. There was significant difference in the threshability according to the shape of threshing teeth. The triangular-shaped tooth was the most efficient in threshability ratio and the semicircle-shaped tooth was the lowest. There was no significant difference in specific energy requirement for the varied teeth design. Torn-head ratio being generated by the semicircle-shaped and the triangular-shaped teeth in series was less than that by a single tooth with the triangular-shaped and the double setting of the triangular-shaped. Chaff generation ratio by the triangular-shaped and the semicircle-shaped teeth was less than the others tried. 3. The triangular-shaped teeth in series, which was newly designed for this study, showed an intermediate characteristics between the double setting of the triangular-shaped and the semicircle- shaped teeth. Threshability ratio of the triangular-shaped teeth in series was higher than that of the semicircle and lower than the double setting of the triangular-shaped tooth. Torn-head generation ratio for it was about same as that of the semicircle. Chaff being generated by the triangular-shaped teeth in series was about same as the double setting of the triangular-shaped teeth. 4. About 40% of threshed grains which passed through concave were concentrated under the threshing tooth and the rest of grains displayed a skew distribution toward the inlet of threshing chamber.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2017

The Convolutional Neural Network(CNN) can be divided into two stages: feature extraction and classification. The hyperparameters such as kernel size, number of channels, and stride in the feature extraction step affect the overall performance of CNN as well as determining the structure of CNN. In this paper, we propose a method to optimize the hyperparameter in CNN feature extraction stage using Parameter-Setting-Free Harmony Search (PSF-HS) algorithm. After setting the overall structure of CNN, hyperparameter was set as a variable and the hyperparameter was optimized by applying PSF-HS algorithm. The simulation was conducted using MATLAB, and CNN learned and tested using mnist data. We update the parameters for a total of 500 times, and it is confirmed that the structure with the highest accuracy among the CNN structures obtained by the proposed method classifies the mnist data with an accuracy of 99.28%.

• Archives of design research
• /
• v.20 no.3 s.71
• /
• pp.119-128
• /
• 2007

With the development of digital technologies, CAID became an essential part in the industrial design process. Creating photo-realistic images from a virtual scene with 3D models is one of the specialized task for CAID users. This task requires a complex interface of setting the positions and the parameters of camera and lights for optimal rendering results. However, the user interface of existing CAID tools are not simple for designers because the task is mostly accomplished in a parameter setting dialogue window. This research address this interface issues, in particular the issues related to lighting, by developing and evaluating TLS(Tangible Lighting Studio) that uses Augmented Reality and Tangible User Interface. The interface of positioning objects and setting parameters become tangible and distributed in the workspace to support more intuitive rendering task. TLS consists of markers, and physical controller, and a see-through HMD(Head Mounted Display). The user can directly control the lighting parameters in the AR workspace. In the evaluation experiment, TLS provide higher effectiveness, efficiency and user satisfaction compared to existing GUI(Graphic User Interface) method. It is expected that the application of TLS can be expanded to photography education and architecture simulation.

• Journal of the Korea Concrete Institute
• /
• v.29 no.2
• /
• pp.141-148
• /
• 2017

This study is experimentally investigated the effects of various steam curing parameters on the early-age compressive strength development of high strength concrete (over 40 MPa) in the precast plant production. High strength concrete are used only ordinary portland cement (type I) and water-cement ratio selected 3cases (25%, 35% and 45%). Also, steam curing parameters are as followings ; (1) Preset period 2cases (3 hours and 6 hours) (2) Maximum curing temperature 3cases ($45^{\circ}C$, $55^{\circ}C$ and $65^{\circ}C$) (3) Maintenance time of curing temperature 3cases (4 hours, 6 hours and 8 hours) (4) Maximum rate of heating and cooling $15^{\circ}C$/hr. Initial setting time and adiabatic temperature rising ratio of these concrete according to water-cement ratio are tested before main tests and examined the compressive strength development for the steam curing parameters. Also compressive strength are compared with optimum steam curing condition and standard curing at test ages. As test results, the optimum steam curing conditions for high strength concrete(over 40 MPa) are as followings. (1) Preset period ; over initial setting time of concrete (2) Maximum curing temperature ; bellow $55^{\circ}C$ (3) Maintenance time of curing temperature ; bellow 6hours. Also strength development of steam curing concrete show in the reversed strength at 28 days. It is to propose an efficient steam curing condition for high strength concrete in the precast method.

• Journal of the Korean Chemical Society
• /
• v.53 no.6
• /
• pp.653-662
• /
• 2009

Developing effective tools for predicting absorption, distribution, metabolism, excretion properties and toxicity (ADME/T) of new chemical entities in the early stage of drug design is one of the most important tasks in drug discovery and development today. As one of these attempts, support vector machines (SVM) has recently been exploited for the prediction of ADME/T related properties. However, two problems in SVM modeling, i.e. feature selection and parameters setting, are still far from solved. The two problems have been shown to be crucial to the efficiency and accuracy of SVM classification. In particular, the feature selection and optimal SVM parameters setting influence each other, which indicates that they should be dealt with simultaneously. In this account, we present an integrated practical solution, in which genetic-based algorithm (GA) is used for feature selection and grid search (GS) method for parameters optimization. hERG ion-channel inhibitor classification models of ADME/T related properties has been built for assessing and testing the proposed GA-GS-SVM. We generated 6 different models that are 3 different single models and 3 different ensemble models using training set - 1891 compounds and validated with external test set - 175 compounds. We compared single model with ensemble model to solve data imbalance problems. It was able to improve accuracy of prediction to use ensemble model.

• Transactions on Control, Automation and Systems Engineering
• /
• v.4 no.1
• /
• pp.62-74
• /
• 2002

The tracking of a reference temperature trajectory in a polymerization batch reactor is a common problem and has critical importance because the quality control of a batch reactor is usually achieved by implementing the trajectory precisely. In this study, only energy balances around a reactor are considered as a design model for control synthesis, and material balances describing concentration variations of involved components are treated as unknown disturbances, of which the effects appear as time-varying parameters in the design model. For the synthesis of a tracking controller, a method combining the input-output linearization of a time-variant system with the parameter estimation is proposed. The parameter estimation method provides parameter estimates such that the estimated outputs asymptotically follow the measured outputs in a specified way. Since other unknown external disturbances or uncertainties can be lumped into existing parameters or considered as another separate parameters, the method is useful in practices exposed to diverse uncertainties and disturbances, and the designed controller becomes robust. And the design procedure and setting of tuning parameters are simple and clear due to the resulted linear design equations. The performances and the effectiveness of the proposed method are demonstrated via simulation studies.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.4
• /
• pp.436-443
• /
• 2007

In this paper, an intelligent method called BELBIC (Brain Emotional Learning Based Intelligent Controller) is used to control of Locally Linear Neuro-Fuzzy Model (LOLIMOT) of Washing Machine. The Locally Linear Neuro-Fuzzy Model of Washing Machine is obtained based on previously extracted data. One of the important issues in using BELBIC is its parameters setting. On the other hand, the controller design for Washing Machine is a multi objective problem. Indeed, the two objectives, energy consumption and effectiveness of washing process, are main issues in this problem, and these two objectives are in contrast. Due to these challenges, a Multi Objective Genetic Algorithm is used for tuning the BELBIC parameters. The algorithm provides a set of non-dominated set points rather than a single point, so the designer has the advantage of selecting the desired set point. With considering the proper parameters after using additional assumptions, the simulation results show that this controller with optimal parameters has very good performance and considerable saving in energy consumption.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.2
• /
• pp.3-12
• /
• 1995

A controller utilizing fuzzy logic is developed to control the speed of a motor in a washing machine by choosing an appropriate phase. Due to the hardship imposed on obtaining a result from a relation established for inputs, present speed and present rate of speed, and ouput, a phase, of the system that can be tested against an experimental result, it is impossible to apply a genetic algorithm to fine-tune the fuzzy logic controller. To avoid this difficulty, a proper assumption that the parameters of an if-part of a primary fuzzy logic controller have a functional relationship with an error between computed values and experimental ones in made. Setting up of a fuzzy relationship between the parameters and the errors is then achieved through experimentally obtained data. Genetic Algorithm is then applied to this secondary fuzzy logic controller to verify the fuzzy logic. In the verification process, the primary fuzzy logic controller is used in obtaining experimental results. In this way the kind of difficulty in obtaining enough experimental values used to verify the fuzzy logic with genetic algorithm is gotten around. Selection of the parameters that would produce the least error when using the secondary fuzzy logic controller is done with applying genetic algorithm to the then-part of the controller. In doing so the optimal values for the parameters of the if-part of the primary fuzzy logic controller are assumed to be contained. The experimental result presented in the paper validates the assumption.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.3
• /
• pp.7-11
• /
• 2014

The experimental analysis presented aims at the selection of the most optimal machining parameter combination for wire electrical discharge machining (WEDM) of STD11. Based on the Taguchi experimental design ($L_{27}$ orthogonal array) method, a series of experiments were performed by considering time-on, voltage, time-off, wire speed, and flow rate as input parameters. The surface roughness was considered responses. Based on the signal-to-noise (S/N) ratio, the influence of the input parameters on the responses was determined. The optimal machining parameters setting for the minimum surface roughness was found using Taguchi methodology. In order to investigate the effects of process parameters on the surface machined by WEDM, Several experiments are conducted to consider effects of time-on, voltage, time-off, wire speed and flow rate on the surface roughness. Analysis of variance (ANOVA) as well as regression analysis are performed on experimental data. The best results of surface roughness were obtained at higher voltage, lower wire speed, and lower time-on.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.6 s.144
• /
• pp.654-665
• /
• 2005

In this paper, we present a non-linear integer programming by genetic algorithm (GA) for available sizes of stiffener or thickness of plate in a job site. GA can rapidly search for the approximate global optimum under complicated design environment such as ship. Meanwhile it can handle the optimization problem involving discrete design variable. However, there are many parameters have to be set for GA, which greatly affect the accuracy and calculation time of optimum solution. The setting process is hard for users, and there are no rules to decide these parameters. In order to overcome these demerits, the optimization for these parameters has been also conducted using GA itself. Also it is proved that the parameters are optimal values by the trial function. Finally, we applied this method to compass deck of ship where the vibration problem is frequently occurred to verify the validity and usefulness of nonlinear integer programming.