• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.13-14
• /
• 2020

본 논문에서는 엣지 컴퓨팅 환경에서 머신러닝을 활용해 에스컬레이터 이상 감지 및 결함 분류를 하는 연구를 진행하였다. 엣지 컴퓨팅 기반 머신러닝을 사용해 에스컬레이터의 이상 감지 및 결함 분류를 위한 OneM2M환경을 구축하였으며 에스컬레이터에서 발생하는 소음에서 고장 유형에 따라 나타나는 주파수를 이용한다. Edge TPU를 활용해 엣지 컴퓨팅 시스템의 처리량을 최대화하고, 각 작업의 수행시간을 최소화함으로써 엣지 컴퓨팅 환경에서 이상 감지와 결함 분류를 수행할 수 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.175-189
• /
• 2023

Fault detection and diagnosis (FDI) algorithms are actively being researched for ensuring the integrity and reliability of environment perception sensors in autonomous vehicles. In this paper, a fault detection algorithm based on a multi-sensor perception system composed of radar, camera, and lidar is proposed to guarantee the safety of an autonomous vehicle's perception system. The algorithm utilizes reference generation filters and residual generation filters based on finite impulse response (FIR) filter estimates. By analyzing the residuals generated from the filtered sensor observations and the estimated state errors of individual objects, the algorithm detects faults in the environment perception sensors. The proposed algorithm was evaluated by comparing its performance with a Kalman filter-based algorithm through numerical simulations in a virtual environment. This research could help to ensure the safety and reliability of autonomous vehicles and to enhance the integrity of their environment perception sensors.

• Journal of KIISE:Information Networking
• /
• v.36 no.4
• /
• pp.339-350
• /
• 2009

In wireless sensor networks, the limited battery resources of sensor nodes have a direct impact on network lifetime. To reduce unnecessary power consumption, it is often the case that only a minimum number of sensor nodes operate in active mode while the others are kept in sleep mode. In such a case, however, the network service can be easily unreliable if any active node is unable to perform its sensing or communication function because of an unexpected failure. Thus, for achieving reliable sensing, it is important to maintain the sensing level even when some sensor nodes fail. In this paper, we propose a new fault-tolerance scheme, called FCP(Fault-tolerant Coverage Preserving), that gives an efficient way to handle the degradation of the sensing level caused by sensor node failures. In the proposed FCP scheme, a set of backup nodes are pre-designated for each active node to be used to replace the active node in case of its failure. Experimental results show that the FCP scheme provides enhanced performance with reduced overhead in terms of sensing coverage preserving, the number of backup nodes and the amount of control messages. On the average, the percentage of coverage preserving is improved by 87.2% while the additional number of backup nodes and the additional amount of control messages are reduced by 57.6% and 99.5%, respectively, compared with previous fault-tolerance schemes.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2007.09a
• /
• pp.115-123
• /
• 2007

설계 하중이 큰 대형 구조물의 기초로 많이 사용되는 현장타설말뚝은 현장에서 지반을 굴착하여 조립된 철근망을 삽입한 후, 콘크리트를 타설하여 제작되므로 복잡한 시공 과정과 현장의 특수한 지하수 및 지반 조건으로 인하여 현장타설말뚝의 내부에는 결함이 포함될 수 있다. 발생 가능한 대표적인 결함으로 연약한 말뚝 선단, 말뚝체 콘크리트의 품질 저하, 말뚝과 지반의 접촉 불량, 주 철근의 부식 등이 있으며, 이들 결함을 감지하기 위한 건전도 시험법으로 공대공초음파 검층, 충격반향시험, 충격응답시험, 감마-감마 검층법 등이 있다. 결함은 말뚝의 수평지지력을 감소시키며, 일반적으로 발생하는 비대칭단면 결함에 의한 응력 집중현상과 수평 하중에 의한 휨모멘트는 연직지지거동에 영향을 준다. 따라서 결함을 감지하고 평가하는 것이 현장타설말뚝의 품질관리에 있어 매우 중요하다.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.689-696
• /
• 2021

In this paper, in order to apply Prognostics and Health Management(PHM) to an electronic system or circuit, a circuit capable of detecting and predicting defect characteristics inside the system or circuit is implemented, and the results are described. In the previous study, we demonstrated that the frequency of the amplitude of S-parameter changed as the circuit defect progressed. These characteristics were measured by network analyser. but in this study, even if the same defect detection method is used, a circuit is proposed to check the progress of the defect, the remaining time, and the occurrence of the defect without large measurement devices. The circuit is designed to detect the change in impedance that generates changes of S-parameter, and it is verified through simulation using the measurement results of Bond-wires.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.5
• /
• pp.532-537
• /
• 2004

FEF(Focused Electromagnetic Field) technique was newly developed that is based on the induction principle exciting electromagnetic field. The technique consists of an induction wire and a sensor for detecting electromagnetic field, and is applied in a non-contact mode. In this study, the technique was applied to the evaluation of EDM slits in some conductive materials - aluminum alloy, stainless steel and Inconel alloy. The voltage in the non-defect region is depended upon the measurement lift-off. The voltage signals on defects are measured with peak values, and the peak values changed with the depth of defects. The voltage distributions for all conductive materials are the same trend.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.369-377
• /
• 2023

In the industrial manufacturing sector, quality control is pivotal for minimizing defect rates; inadequate management can result in additional costs and production delays. This study underscores the significance of detecting texture defects in manufactured goods and proposes a more precise defect detection technique. While the DFR(Deep Feature Reconstruction) model adopted an approach based on feature map amalgamation and reconstruction, it had inherent limitations. Consequently, we incorporated a new loss function using statistical methodologies, integrated a skip connection structure, and conducted parameter tuning to overcome constraints. When this enhanced model was applied to the texture category of the MVTec-AD dataset, it recorded a 2.3% higher Defect Segmentation AUC compared to previous methods, and the overall defect detection performance was improved. These findings attest to the significant contribution of the proposed method in defect detection through the reconstruction of feature map combinations.

• Proceedings of the Korean Magnestics Society Conference
• /
• 2001.10a
• /
• pp.122-123
• /
• 2001

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.940-942
• /
• 2005

내장 실시간 시스템은 고 신뢰성 및 고 가용성이 요구된다. 이를 위해서 반드시 필요한 요소들은 결함을 감지 할 수 있는 온라인 모니터링과 감지된 결함에 대한 결함허용(Fault Tolerance) 기법으로 온라인 모니터링에 관련된 연구로는 dRTO 모델[1]의 RMO(Region Monitoring Object)[2]가 있다. 본 논문에서는 효율적인 온라인 모니터링 프레임워크를 내장 시스템에서 널리 사용되는 운영교제인 리눅스에 제공하기 위하여 리눅스상에서 동작하는 RMO 프레임워크를 적용한 LinuxRMO를 설계하고 구현한다. LinuxRMO 가 감시하는 대상은 dRTO모델에서 정의된 RMO의 감시대상인 RTO(Realtime Object)[3] [4]가 아닌 리눅스 프로세스들이다. LinuxRMO는 리눅스 프로세스의 변수 데이터들에 대한 실시간 추적, 프로세스들에 대한 주기적인 감시 및 사용자가 정의한 허용시간을 초과한 프로세스들을 감지하는 역할을 한다.

• ETRI Journal
• /
• v.10 no.1
• /
• pp.64-75
• /
• 1988

GaAs 등 화합물 반도체는 그 표면구조가 아직 확립되어 있지 않고, 표면조건이 소자특성에 큰 영향을 미친다. 소자공정중 이온주입 공정은 self-aligned MESFET(Metal Semiconductor Field Effect Transistor) 제작에 필수적인 기술이나, 이온 주입시 수 $\AA$ 크기의 vacancy 등 격자결함이 발생하며 이들 결함을 제어할 수 있는 기술이 필요하다. 에너지 가변 양전자 소멸기술은 표면에서 $1\mum$정도내에 존재하는 vacancy 형태의 격자결함을 감지해 낼 수 있으며 이들 격자결함의 depth profiling을 할 수 있는 기술이다. 본 고에서는 에너지 가변 양전자 소멸기술의 원리 및 최근 연구결과에 대해서 살펴보기로 한다.