• Proceedings of the Korea Society for Energy Engineering kosee Conference
• /
• 1995.11a
• /
• pp.115-115
• /
• 1995

다중 효용관식 증발기는 보통의 증발기에서 응축하여 제거하는 증기를 다음 효용관의 가열원으로 재사용하는 것으로 그 자체로도 에너지 절감효과가 있는 것으로 알려져 있다[1,2,4]. 기계식증기 재압축 증발기는 보통 증발기에서 응축시켜 제거하는 발생 증기를 압축하여 고온의 증기로 만든 다음 가열원으로 재이용하는 장치로 이에 대한 효용은 문헌에 잘 나타나있다[3,4]. 여기서는 다중효용관과 증기 재압축기를 조합한 증발기 중에서 Forward feed 방식의 다중효응관에 증기 재압축기를 부착한 경우에 대하여 타당한 물질수지, 열수지, 전열 식, 상평형식을 소개하였다. 또한 압축기의 용량을 결정하기 위한 단열압축공정의 지배방정 식을 소개하였다. 원료의 조건, 효용관의 수 및 총전열온도차가 주어지면 상기의 지배방정식의 해를 구할 수 있는데. 본연구에서는 Gauss-Seidel의 연속치환법을 이용하였다. 이와 같이 지배방적식의 해를 구하면 효용관의 면적, 압축펌프의 용량, 각효용관 입출구의 조건 등이 계산된다. 다중효용관 기계식 증기 재압축 증발장치의 최적화를 위하여는 효용관의 전열면적당 가격과 압축펌프의 용량당 가격 그리고 펌프를 운전하는데 필요한 전력의 요금 등의 자료가 요구된다. 총전열온도차에 따른 운전비와 시설비의 합이 최소가 되는 점이 최적 총전열온도차가 되는데 이 점을 구할 때에는 수치적으로 안정한 이분법을 이용하였다. Borland C++를 이용하여 프로그램하였으며 윈도우즈 환경에서 수행되게 하였다. 사용자 쉽게 이용할 수 있게 하기 위하여 각종 필요한 데이터를 입력할 수 있는 Edit box가 화면에 나타나게 하였다. 또한 입력된 데이터를 저장하거나 불려올 수 있는 메뉴, 입력된 데이타를 이용하여 효용관의 면적과 압축기의 용량을 계산하거나 효용관의 수가 주어졌을 때 총전열온도차를 최적화하는 것을 선택할 수 있는 메뉴 그리고 계산 결과를 파일로 혹은 프린트로 출력할 것을 선택할 수 있는 메뉴가 있다. 사용자는 해당되는 데이타를 입력한후 마우스로 원하는 작업의 메뉴를 선택하면 된다.

• Journal of Biosystems Engineering
• /
• v.13 no.2
• /
• pp.38-45
• /
• 1988

This study was intended to develop the system automatically controlling travel direction of combine by means of sensing paddy rows. The control system was composed of three detecting levers having different length, micro-switch, microcomputer and electro-hydraulic control system. Sensor and control system developed was tested to estimate optimum design values and its actual performance as installed in combine. The computer simulation and performance test at simulated and actual field were conducted to test for possibility of practical use. The results of the study arc summarized. as follows: 1. The travel traces of combine hiving the conventional sensor with 2 levers and the new sensor detecting the slope of paddy rows were compared through computer simulation. Turning frequency of combine having new sensor was fewer than that of conventional sensor, but the rate of turning for the combine with new sensor was much greater than that of conventional sensor. 2. As sensor was established behind the tip of divider, the sensor itself well followed paddy rows but the tip of divider did not, resulting in divider being deviated from paddy rows. It was analyzed that the sensor should be attached closer to the tip of divider to have a better performance of the control system. 3. The greater the length of sensor lever for given location of sensor attachment and combine forward speed, the higher sensitivity of turning in control system. Moreover, increasing combine speed resulted in a worse performance of control system following paddy rows. Consequently, it was necessary that an optimum length of sensor attachment and for the range of combine operational speed. 4. Field test of combine installed with the sensor and electro-hydraulic system developed in this study showed that it may be operated smoothly and well behaved to paddy rows to 4th gear of combine speed which was 59cm/s. Consequently. it was concluded that the combine with the guidance control system developed in this study may be successfully used for paddy combining.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.309-316
• /
• 2020

We predict the mortality of the elderly patients visiting the emergency department who are over 65 years old using Feed Forward Neural Network (FFNN) and Convolutional Neural Network (CNN) respectively. Medical data consist of 99 features including basic information such as sex, age, temperature, and heart rate as well as past history, various blood tests and culture tests, and etc. Among these, we used random forest to select features by measuring the importance of features in the prediction of mortality. As a result, using the top 80 features with high importance is best in the mortality prediction. The performance of the FFNN and CNN is compared by using the selected features for training each neural network. To train CNN with images, we convert medical data to fixed size images. We acquire better results with CNN than with FFNN. With CNN for mortality prediction, F1 score and the AUC for test data are 56.9 and 92.1 respectively.

• International Journal of Fluid Machinery and Systems
• /
• v.8 no.4
• /
• pp.264-273
• /
• 2015

This presentation describes an experimental approach for the detection of cavitation in hydraulic machines by use of ultrasonic signal analysis. Instead of using the high frequency pulses (typically 1MHz) only for transit time measurement different other signal characteristics are extracted from the individual signals and its correlation function with reference signals in order to gain knowledge of the water conditions. As the pulse repetition rate is high (typically 100Hz), statistical parameters can be extracted of the signals. The idea is to find patterns in the parameters by a classifier that can distinguish between the different water states. This classification scheme has been applied to different cavitation sections: a sphere in a water flow in circular tube at the HSLU in Lucerne, a NACA profile in a cavitation tunnel and two Francis model test turbines all at LMH in Lausanne. From the signal raw data several statistical parameters in the time and frequency domain as well as from the correlation function with reference signals have been determined. As classifiers two methods were used: neural feed forward networks and decision trees. For both classification methods realizations with lowest complexity as possible are of special interest. It is shown that two to three signal characteristics, two from the signal itself and one from the correlation function are in many cases sufficient for the detection capability. The final goal is to combine these results with operating point, vibration, acoustic emission and dynamic pressure information such that a distinction between dangerous and not dangerous cavitation is possible.

• Journal of Korean Society on Water Environment
• /
• v.24 no.1
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.55-65
• /
• 2004

When a neural network is used to solve a given problem it is necessary to match the complexity of the network to that of the problem because the complexity of the network significantly affects its learning capability and generalization performance. Thus, it is desirable to have an algorithm that can find appropriate network structures in a self-organizing way. This paper proposes algorithms which automatically organize feed forward multi-layer neural networks with sigmoid hidden neurons for given problems. Using both constructive procedures and pruning procedures, the proposed algorithms try to find the near optimal network, which is compact and shows good generalization performance. The performances of the proposed algorithms are tested on four function regression problems. The results demonstrate that our algorithms successfully generate near-optimal networks in comparison with the previous method and the neural networks of fixed topology.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.1
• /
• pp.28-36
• /
• 2008

This paper discusses theimplementation of the low-voltage, low-power, third-order, 1-bit switched capacitor delta-sigma modulator of the implantable cardiac pacemaker. The distributed, feed-forward structure and bulk-driven OTA were used in order to achieve an efficient operation under a supply voltage of 1V or lower. The designed modulator has a dynamic range of 49dB at 0.9V supply voltage and consumes 816nW of power. Such a significant reduction in power consumption allows diverse applications, not only in pacemakers, but also in implantable biomedical devices that operate with limited battery power. The core chip size of the modulator is $1000{\mu}m*500{\mu}m$ manufactured, with the $0.18{\mu}m$ CMOS standard process.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.4
• /
• pp.43-52
• /
• 2008

Radiation characteristics of microstrip patch antennas integrated with mushroom-like EBG structures in length direction, width direction and all directions are analyzed. Patch antennas integrated with EBG structures in length direction shows the best radiation characteristics among the cases integrated in three directions. The case for the feed point of a patch antenna located in the center of both EBG structures integrated with a patch antenna shows better symmetric E-plane radiation pattern, higher forward radiation intensity, and lower backward radiation intensity compared to the case for the center of a patch antenna located in the center of both EBG structures. The variation of the radiation characteristics of patch antennas integrated with EBG structures more than 4 periods versus number of periods of EBG structures integrated is very small.

• Journal of Power Electronics
• /
• v.16 no.3
• /
• pp.1110-1121
• /
• 2016

The mathematical model of a three phase PWM converter under the stationary αβ reference frame is deduced and constructed based on a Proportional-Resonant (PR) regulator, which can replace trigonometric function calculation, Park transformation, real-time detection of a Phase Locked Loop and feed-forward decoupling with the proposed accurate calculation of the inductance voltage vector. To avoid the parallel resonance of the LCL topology, the active damping method of the proportional capacitor-current feedback is employed. As to current vector error elimination, an optimized PR controller of the inner current loop is proposed with the zero-pole matching (ZPM) and cancellation method to configure the regulator. The impacts on system's characteristics and stability margin caused by the PR controller and control parameter variations in the inner-current loop are analyzed, and the correlations among active damping feedback coefficient, sampling and transport delay, and system robustness have been established. An equivalent model of the inner current loop is studied via the pole-zero locus along with the pole placement method and frequency response characteristics. Then, the parameter values of the control system are chosen according to their decisive roles and performance indicators. Finally, simulation and experimental results obtained while adopting the proposed method illustrated its feasibility and effectiveness, and the inner current loop achieved zero static error tracking with a good dynamic response and steady-state performance.

• The KIPS Transactions:PartD
• /
• v.8D no.3
• /
• pp.241-246
• /
• 2001

Area of software measurement in software engineering is active more than thirty years. There is a huge collection of researches but still no a concrete software cost estimation model. If we want to measure the cost-effort of a software project, we need to estimate the size of the software. A number of software metrics are identified in the literature ; the most frequently cited measures are LOC(line of code) and FPA(function point analysis). The FPA approach has features that overcome the major problems with using LOC as a measure of system size. This paper presents an neural networks(NN) models that related software development effort to software size measured in FPs and function element types. The research describes appropriate NN modeling in the context of a case study for 24 software development projects. Also, this paper compared the NN model with a regression analysis model and found the NN model has better estimative accuracy.