• 제목/요약/키워드: Train Detection

검색결과 383건 처리시간 0.027초

자기검사 Pulse별 잉여수연산회로를 이용한 고신뢰화 Fault Tolerant 디지털필터의 구성에 관한 연구 (Implementation of High Reliable Fault-Tolerant Digital Filter Using Self-Checking Pulse-Train Residue Arithmetic Circuits)

  • 김문수;손동인;전구제
    • 대한전자공학회논문지
    • /
    • 제25권2호
    • /
    • pp.204-210
    • /
    • 1988
  • The residue number system offers the possibility of high-speed operation and error detection/correction because of the separability of arithmetic operations on each digit. A compact residue arithmetic module named the self-checking pulse-train residue arithmetic circuit is effectively employed as the basic module, and an efficient error detection/correction algorithm in which error detection is performed in each basic module and error correction is performed based on the parallelism of residue arithmetic is also employed. In this case, the error correcting circuit is imposed in series to non-redundant system. This design method has an advantage of compact hardware. Following the proposed method, a 2nd-order recursive fault-tolerant digital filter is practically implemented, and its fault-tolerant ability is proved by noise injection testing.

  • PDF

MAGLEV 차량의 실시간 속도 및 위치 검출 (Real-time speed and position detection of MAGLEV vehicle system)

  • 윤여원;박석하;함상용;손영수;김양모
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1997년도 하계학술대회 논문집 A
    • /
    • pp.346-348
    • /
    • 1997
  • This paper presents microprocessor-based real-time speed and position detection by inductive radio loop in new transportation system, such as magnetically levitated train system, rubber tyred train, and linear-motor car. The constant elapsed time method is used in this study for high accurate detection over a wide speed range. And for reliability and safety of the system, it is duplicated and data-bus level comparison is performed by fail-safe comparator.

  • PDF

Numerical study of anomaly detection under rail track using a time-variant moving train load

  • Chong, Song-Hun;Cho, Gye-Chun;Hong, Eun-Soo;Lee, Seong-Won
    • Geomechanics and Engineering
    • /
    • 제13권1호
    • /
    • pp.161-171
    • /
    • 2017
  • The underlying ground state of a railway plays a significant role in maintaining the integrity of the overlying concrete slab and ultimately supporting the train load. While effective nondestructive tests have been used to evaluate the rail track system, they can only be performed during non-operating time due to the stress wave generated by active sources. In this study, finite element numerical simulations are conducted to investigate the feasibility of detecting unfavorable substructure conditions by using a moving train load. First, a train load module is developed by converting the train load into time-variant equivalent forces. The moving forces based on the shape functions are applied at the nodes. A parametric study that takes into account the bonding state and the train class is then performed. All the synthetic signals obtained from numerical simulations are analyzed at the frequency domain using a Fast Fourier transform (FFT) and at the time-frequency domain using a Short-Time Fourier transform (STFT). The presence of a void condition amplifies the acceleration amplitude and the vibration response. This study confirms the feasibility of using a moving train load to systematically evaluate a rail track system.

철도건널목 지능화시스템 시범 구축 (Pilot Implementation of Intelligence System for Accident Prevention at Railway Level Crossing)

  • 조봉관;류상환;황현철;정재일
    • 한국철도학회:학술대회논문집
    • /
    • 한국철도학회 2010년도 춘계학술대회 논문집
    • /
    • pp.1112-1117
    • /
    • 2010
  • The intelligent safety system for level crossing which employs information and communication technology has been developed in USA and Japan, etc. But, in Korea, the relevant research has not been performed. In this paper, we analyze the cause of railway level crossing accidents and the inherent problem of the existing safety equipments. Based on analyzed results, we design the intelligent safety system which prevent collision between a train and a vehicle. This system displays train approaching information in real-time at roadside warning devices, informs approaching train of the detected obstacle in crossing areas, and is interconnected with traffic signal to empty the crossing area before train comes. Especially, we present the video based obstacle detection algorithm and verify its performance with prototype H/W since the abrupt obstacles in crossing areas are the main cause of level crossing accidents. We identify that the presented scheme detects both pedestrian and vehicle with good performance. Currently, we demonstrate developed railway crossing intelligence system at one crossing of Young-dong-seon line of Korail with Sea Train cockpit.

  • PDF

고속차량(KTX) ATC 신호에 미치는 살사재료별 영향 분석 (The Analysis of Influence on High-speed Train(KTX) ATC Signals according Sand Materials)

  • 윤차중;노명규
    • 전기학회논문지
    • /
    • 제63권6호
    • /
    • pp.834-840
    • /
    • 2014
  • When the high speed train (KTX) departs from station in the high-speed line, intermittent on-board signal disappearance causes a hindrance of the operation punctuality. Therefore, we have a research objective to verify the causes of hindrance and to find an improvement plan. process of research, when train leaves the station, we applied sand on the rail to improve adhesive power, that sand has an effect on the ATC(Automatic Train Control) signal wave. We detected & analyzed signal waves which is came from detecting device by changing operation condition in accordance with sand material overage detection to be achieved.

Cascade Network Based Bolt Inspection In High-Speed Train

  • Gu, Xiaodong;Ding, Ji
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권10호
    • /
    • pp.3608-3626
    • /
    • 2021
  • The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

Detection and Localization of Image Tampering using Deep Residual UNET with Stacked Dilated Convolution

  • Aminu, Ali Ahmad;Agwu, Nwojo Nnanna;Steve, Adeshina
    • International Journal of Computer Science & Network Security
    • /
    • 제21권9호
    • /
    • pp.203-211
    • /
    • 2021
  • Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

위치신호 보상 및 추정을 통한 초고속 자기부상철도 추력 성능 향상 (Thrust Performance Improvement through Position Signal Compensation and Estimation in Super Speed Maglev)

  • 이진호;조정민;한영재;이창영
    • 한국산학기술학회논문지
    • /
    • 제14권10호
    • /
    • pp.4739-4746
    • /
    • 2013
  • 본 논문에서는 초고속 자기부상철도 추진 제어에 필수적인 차량의 위치검지에 있어서 위치신호 송신지연 및 송신주기가 추력에 미치는 영향을 수치적으로 분석하고 test bed를 이용한 실험을 통해 이를 확인하였다. 위치신호 송신문제를 해결하기 위한 방안으로서 위치신호 보상 및 추정 기법을 제시하였으며 제시된 방법을 test bed에 적용하여 효용성을 검증하였다. 적용 결과 추력이 크게 증가하였으며 이에 따라 차량의 가속도 및 속도 성능이 향상됨을 확인하였다. 본 방법은 향후 개발 예정인 한국형 초고속 자기부상철도의 위치검지시스템에 효과적으로 사용될 수 있을 것으로 판단된다.

시공간 네트워크를 이용한 열차 경합해소모형 (The Train Conflict Resolution Model Using Time-space Network)

  • 김영훈;임석철
    • 한국철도학회논문집
    • /
    • 제18권6호
    • /
    • pp.619-629
    • /
    • 2015
  • 열차 경합해소 문제는 열차의 경합이 발생되거나 예측될 때 지연 확산을 최소화하기 위해 열차 운행스케줄을 조정하는 것이다. 기존연구에서는 폭발적으로 증가하는 변수로 인해 풀 수 있는 문제의 크기가 제한적이다. 본 논문에서는 열차 운영단계에서 열차 경합을 해소하기 위해 시공간 네트워크를 이용한 열차 경합해소모형을 제안한다. 제안한 모형은 시공간 네트워크에서 경합발생 이후 운행 열차들에 대해 정차 역에서의 정차 허용치만을 부여함으로써 문제의 크기를 조절하였다. 또한, 경로흐름변수를 사용해 대형문제도 풀 수 있도록 하였다. 제안한 모형을 이용하여 열차경합의 지연파급분석과 경합해소 실험결과를 제시하였다.

영상 생성적 데이터 증강을 이용한 딥러닝 기반 SAR 영상 선박 탐지 (Deep-learning based SAR Ship Detection with Generative Data Augmentation)

  • 권형준;정소미;김성태;이재석;손광훈
    • 한국멀티미디어학회논문지
    • /
    • 제25권1호
    • /
    • pp.1-9
    • /
    • 2022
  • Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.