• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.

• Journal of Animal Science and Technology
• /
• 제65권6호
• /
• pp.1254-1269
• /
• 2023

This study aims to predict the change in corn share according to the grazing of 20 gestational sows in a mature corn field by taking images with a camera-equipped unmanned air vehicle (UAV). Deep learning based on convolutional neural networks (CNNs) has been verified for its performance in various areas. It has also demonstrated high recognition accuracy and detection time in agricultural applications such as pest and disease diagnosis and prediction. A large amount of data is required to train CNNs effectively. Still, since UAVs capture only a limited number of images, we propose a data augmentation method that can effectively increase data. And most occupancy prediction predicts occupancy by designing a CNN-based object detector for an image and counting the number of recognized objects or calculating the number of pixels occupied by an object. These methods require complex occupancy rate calculations; the accuracy depends on whether the object features of interest are visible in the image. However, in this study, CNN is not approached as a corn object detection and classification problem but as a function approximation and regression problem so that the occupancy rate of corn objects in an image can be represented as the CNN output. The proposed method effectively estimates occupancy for a limited number of cornfield photos, shows excellent prediction accuracy, and confirms the potential and scalability of deep learning.

• ETRI Journal
• /
• 제45권5호
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

• 시스템엔지니어링학술지
• /
• 제7권2호
• /
• pp.7-11
• /
• 2011

A high-speed railway system represents a typical example of large-scale multi-disciplinary system, consisting of subsystems such as rolling-stock, electrical hardware, electronics, control, information, communication, civil technology etc. The system design and acquisition data of the large-scale system must be the subject under strict configuration control and management. Systems engineering technology development project for Korea next generation High-speed Electric Multiple Unit (HEMU) system in progress is a national large system development project that is not only a large-size and complex but also multi-disciplinary in nature. Therefore, all stakeholders must understand and share the functional and performance requirements of HEMU throughout its life-cycle phases. Also in the test and evaluation phase, all systems requirements must be verified. In 2011, the prototype train manufacturing will be completed. It will do test run on the commercial line and all systems requirements are verified until 2012. For the system verification, the test and evaluation process have to be established before the test trial run. Using a systems engineering tool, the system design database(SDD) with requirements traceability and development process management in the course of the development have to be established. This paper represents the test and evaluation process development based on the SEMP(Systems Engineering Management Plan) developed in the design stage. The test and evaluation process is refined and updated in comparison to the design stage one. The test and evaluation process consists of procedure, test and evaluation method and schedule. So through this process, it is defined that each systems requirements is verified on which test and about what time.

• 한국철도학회논문집
• /
• 제18권4호
• /
• pp.354-362
• /
• 2015

콘크리트궤도의 경우, 허용침하기준이 30mm 이하로 매우 엄격하게 관리되기 때문에, 궤도 하부의 토공노반(강화노반, 상부노반, 하부노반)의 침하에 대한 관리가 필수적으로 요구되고 있다. 이를 위해서는 먼저 이들 노반 재료의 침하특성에 대해 보다 정확한 이해와 자료의 축적이 우선되어야 할 것이다. 이에 본 연구에서는 노반 재료를 대상으로 대형 오이도미터시험과 삼축압축시험을 통해 여러 입도조건, 함수비 변화조건, 반복하중 조건 등에 의한 장기침하특성을 평가하였다. 강화노반 재료가 설계기준에 적합하게 조성될 경우, 열차하중 하에서 발생되는 침하는 매우 적었다. 한편, 노반재료의 경우 일정 하중 하에서 함수비가 증가할 때, 입도조건에 따라 침하 발생량이 매우 크게 발생할 수 있는 것을 확인할 수 있었다.

• 항공우주기술
• /
• 제12권2호
• /
• pp.209-220
• /
• 2013

본 논문에서는 항공우주연구원에서 주최하는 2012년 인간 동력 항공기 시범 경진대회에 참가하기 위하여 제작한 충남대학교 Light Bros. 팀의 Human Powered Aircraft인 Volante 날개에 대한 설계/제작과정과 프로펠러의 설계/제작과정을 기술하였다. 동력장치는 두 개의 프로펠러로 구성되어 있고 베벨기어와 지상에서 작동하게 만들어졌다. 프로펠러의 상태변화와 시간에 따른 동력변화를 측정하여 가장 효율적인 프로펠러는 찾는 것이다. 복합재의 사용과 글라이더 형태의 큰 Aspect Ratio(AR)을 갖는 날개의 하중 해석 및 구조 해석을 수행하였다. 주익 Spar의 모델링 및 구조 해석을 수행한 후 구조 시험을 통해 변위 및 Strain 비교를 수행하였으며 결과적으로 주익의 성능 및 안전성을 확인하였다.

• Industrial Engineering and Management Systems
• /
• 제10권3호
• /
• pp.209-220
• /
• 2011

Self-tapping screws have some operational peculiarities. In spite of their economical advantage that requires no prior tapping operation, a weakness of self-tapping screw-tightening operations is that screws can easily be tightened at a non-right angle, thus resulting in an improper tightening strength. Increases in outsourced workers have reduced labor costs, but the accompanying high worker fluidity means that new workers are more frequently introduced into factories. It is necessary to train new workers for self-tapping screw-tightening operations, which occupies a considerable portion of ordinary assembly works. The purpose of this study is to develop and implement a skill transfer system for the operation. This study (1) proposes a set of characteristic values for evaluating the quality of the operation and develops a device that can measure these values; (2) proposes criteria for evaluating the resultant quality of the tightening; and (3) develops a skill training system for better work performance. Firstly, sets of characteristic values for evaluating the quality of the operation, namely, torque, vertical pressure forces and horizontal vibration forces, are proposed. A device that can measure these values is developed. Secondly, criteria for evaluating the resultant quality of the tightening are identified, involving tightening torque, maximum vertical pressure and timing, vibration area during the processing and tightening period, and work angle. By using such parameters, workers with the proper aptitude can be identified. Thirdly, a skill training system for the operation is developed. It consists of screwdriver operation training and screw-tightening training with feedback information about the results of the operation. Finally, the validity of the training system is experimentally verified using new operators and actual workers.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 C
• /
• pp.2038-2040
• /
• 2000

The main objective of this paper is to design and test a new type of polymer ZnO surge arrester for AC power system of railroad vehicles. Metal oxide surge arrester for most electric power system applications, electric train and subway are now being used extensively to protect overvoltage due to lightning. Surge arresters with porcelain housing must not have explosive breakage of the housing to minimize damage to other equipment when subjected to internal high short circuit current. When breakdown of ZnO elements in a surge arrester occurs due to flashover, fault short current flows through the arrestor and internal pressure of the arrester rises. The pressure rise can usually be limited by fitting a pressure relief diaphragm and transferring the arc from the inside to the outside of the housing. However, there is possibility of porcelain fragmentation caused by the thermal shock, pressure rise. etc. Non-fragmenting of the housing is the most desired way to prevent damage to other equipment. The pressure change which is occurred by flashover become discharge energy. This discharge energy raises to damage arrester housing and arrester housing is dispersed as small fragment. Therefore, the pressure relief design is requested to obstruct housing dispersion. The main research works are focused on the structure design by finite element method, pressure relief of module, and studies of performance of surge arrester for electric railway vehicle.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2000년도 춘계학술대회 논문집 유기절연재료 방전 플라즈마
• /
• pp.74-77
• /
• 2000

The main objective of this paper is to design and test a new type of polymer ZnO surge arrester for AC power system of railroad vehicles. Metal oxide surge arrester for most electric power system applications, electric train and must not have explosive breakage of the housing to minimize damage to other equipment when subjected to internal high short circuit current. When breakdown of ZnO elements in a surge arrester occurs due to flashover, fault short current flows through the arrester and internal pressure of the arrester rises. The pressure rise can usually be limited by fitting a pressure relief diaphragm and transferring the arc from the inside to the outside of the housing. However, there is possibility of porcelain fragmentation caused by the thermal shock. pressure rise, etc. Non-fragmenting of the housing is the most desired way to prevent damage to other equipment. The pressure change which is occurred by flashover become discharge energy. This discharge energy raises to damage arrester housing and arrester housing is dispersed as small fragment. Therefore, the pressure relief design is requested to obstruct housing dispersion. The main research works are focused on the structure design by finite element method, pressure relief of module, and studies of performance of surge arrester for electric railway vehicle.

• 전기전자학회논문지
• /
• 제22권4호
• /
• pp.922-932
• /
• 2018

방사형 거리 센서는 측량 및 자율 주행에 널리 사용된다. 이러한 센서의 작동 원리 및 적용 방법의 교육이 필요하다. 상용 방사형 거리 센서의 저성능화를 통한 저가화가 계속되고 있지만, 교육 목적으로 사용하기에는 여전히 고가이다. 본 논문에서는 교육용 로봇에 활용할 수 있는 저가의 포토트랜지스터의 방사형 배열을 이용한 물체추적기능을 갖는 거리 센서 모듈을 제안한다. 제안하는 방법은 포토트랜지스터를 180도 범위의 배열로 배치하여 빠르게 움직이는 물체의 위치를 즉시 감지할 수 있으며 서보 모터를 사용한 센서 회전으로 감지 각도 범위를 향상하고 물체를 추적한다. 제안된 센서의 스캔 속도는 상업용 거리 센서보다 50~200배 빨라서 1ms의 제어 루프를 가지는 고성능의 교육용 모바일 로봇에 적용할 수 있다.