교통안전시설물의 관리는 도로교통의 안전과 직결되는 문제이다. 운전자는 신호등, 표지판, 노면표시 등을 통해 운전에 필요한 정보 를 얻는다. 노후된 표지판과 노면표시는 운전자에게 잘못된 정보를 제공할 수 있으므로 주기적인 시설물의 관리가 필요하다. 본 연구 는 딥 러닝 기술을 활용해 운전자 시각의 영상 자료에서 교통안전표지를 자동으로 탐지하고자 하며, 교통안전표지의 공통된 색상 특 징을 기반으로 클래스를 그룹으로 묶어 데이터셋을 구축하는 방법을 제안한다. 객체탐지의 성능지표로 널리 활용되는 mAP를 사용해 클래스 묶음 여부에 따른 탐지 성능을 비교한 결과, 색상 기반 클래스 묶음을 적용한 모델의 탐지 성능이 비교군에 비해 약 36% 상승 함을 확인하였다.

Recently, SDAS(Advanced driver-assistance system) are being installed to assist driving of vehicles and improve driver convenience. LDWS(Lane departure warning system) and FCWS(Forward collision warning system) are the core of the technology. Among these, FCWS is evaluated as a key assistive technology to prevent vehicle crashes. Accordingly, many algorithms are being developed and tested to improve detection speed and actual detection algorithms are being commercialized. In this paper, We propose the design of a system that optimizes FCWS speed by considering the AI performance of the terminal device when implemented as an embedded system.

In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder’s status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.

The high-level radioactive waste repository must ensure its performance for a long period of time enough to sufficiently reduce the potential risk of the waste, and for this purpose, multibarrier systems consisting of engineered and natural barrier systems are applied. If waste nuclides leak, the dominating mechanisms facilitating their movement toward human habitats include advection, dispersion and diffusion along groundwater flows. Therefore, it is of great importance to accurately assess the hydrogeological and geochemical characteristics of the host rock because it acts as a flow medium. Normally, borehole investigations were used to evaluate the characteristics and the use of multi-packer system is more efficient and economical compared to standpipes, as it divides a single borehole into multiple sections by installing multiple packers. For effective analyses and groundwater sampling, the entire system is designed by preselecting sections where groundwater flow is clearly remarkable. The selection is based on the analyses of various borehole and rock core logging data. Generally, sections with a high frequency of joints and evident water flow are chosen. Analyzing the logging data, which can be considered continuous, gives several local points where the results exhibit significant local changes. These clear deviations can be considered outliers within the data set, and machine learning algorithms have been frequently applied to classify them. The algorithms applied in this study include DBSCAN (density based spatial clustering of application with noise), OCSVM (one class support vector method), KNN (K nearest neighbor), and isolation forest, of which are widely used in many applications. This paper aims to evaluate the applicability of the aforementioned four algorithms to the design of multi-packer system. The data used for this evaluation were obtained from DB-2 borehole logging data, which is a deep borehole locates near KURT.

This study assessed the measurement technique of odorous substances using a GC/MOS system with MOS sensor at the detector and the method detection limits were determined for odorous substances such as hydrogen sulfide, acetaldehyde, toluene, m,pxylene, and o-xylene. The portable GC/MOS system was able to separate and measure about 16 out of 22 odorous substances including sulfur compounds, aldehydes, and VOCs. The peak values for hydrogen sulfide, acetaldehyde, toluene, m,p-xylene, and o-xylene showed a nonlinear relationship with concentration and a correlation coefficient of 0.95 or higher was confirmed. The method detection limits for hydrogen sulfide, acetaldehyde, toluene, m.pxylene, and o-xylene using the portable GC/MOS system were determined to be 0.005, 0.023, 0.016, 0.004, and 0.051 ppm, respectively. It is expected that the system can measure odor samples with concentrations of least 50 ppb without additional pretreatment or concentration processes.

With the introduction and implementation of the National Research and Development Innovation Act in 2021, researchers are required to have a greater understanding of research ethics and to comply more strictly. The range of misconduct in research and the standards for sanctions have been expanded with the introduction of the National Research and Development Innovation Act. In addition, researchperforming institutions and specialized agencies have been obligated to establish their own research management systems and standards according to the changed criteria. The Korea Institute of Nuclear Nonproliferation and Control (KINAC), a nuclear regulatory authority that is conducting national R&D in related fields, has sought to strengthen research ethics by revising related regulations, introducing a plagiarism detection system, and expanding related education in accordance with these policies. In this study, we analyzed the effectiveness of the plagiarism detection system as a basic quality control measure for research results and a tool for enhancing research ethics, which was introduced. KINAC did not simply introduce a plagiarism detection program but established institutional improvements and other regulatory measures to support it, with the aim of more effectively managing research results. To analyze the effectiveness of this system, we calculated the plagiarism rate by sampling 30 papers each year for the three years before the introduction of the plagiarism detection system. When comparing the plagiarism rates before and after the introduction of the plagiarism detection system, no exceptional cases of high plagiarism rates were found in papers published after the introduction of the system. Although most of the papers before the introduction of the system showed a satisfactory plagiarism rate, some cases showed high plagiarism rates. We analyzed the cause of such cases in detail. Some exceptional cases were also found to be included in the range of misconduct regulated by the National Research and Development Innovation Act. As no such cases were found after the introduction of the system, we could infer that the system is effectively functioning as a tool for basic quality control and enhancing research ethics. In the future, we plan to expand the sample qualitatively and quantitatively by including other forms of outcomes published by the institution, not just papers, and conduct a more detailed analysis. Based on the results, we will develop various improvement plans for enhancing the quality and research ethics of the institution’s research results.

양식장 부표 등과 같은 해상의 소형 장애물을 탐지하고 거리와 방위를 시각화시켜 주는 해상물체탐지시스템은 선체운동으로 인한 오차를 보정하기 위해 3축 짐벌이 장착되어 있지만, 파도 등에 의한 카메라와 해상물체의 상하운동으로 발생하는 거리오차를 보정 하지 못하는 한계가 있다. 이에 본 연구에서는 외부환경에 따른 수면의 움직임으로 발생하는 해상물체탐지시스템의 거리오차를 분석하 고, 이를 평균필터와 이동평균필터로 보정하고자 한다. 가우시안 표준정규분포를 따르는 난수를 이미지 좌표에 가감하여 불규칙파에 의 한 부표의 상승 또는 하강을 재현하였다. 이미지 좌표의 변화에 따른 계산거리, 평균필터와 이동평균필터를 통한 예측거리 그리고 레이저 거리측정기에 의한 실측거리를 비교하였다. phase 1,2에서 불규칙파에 의한 이미지 좌표의 변화로 오차율이 최대 98.5%로 증가하였지만, 이동평균필터를 사용함으로써 오차율은 16.3%로 감소하였다. 오차보정 능력은 평균필터가 더 좋았지만 거리변화에 반응하지 못하는 한계 가 있었다. 따라서 해상물체탐지시스템 거리오차 보정을 위해 이동평균필터를 사용함으로써 실시간 거리변화에 반응하고 오차율을 크게 개선할 수 있을 것으로 판단된다.

본 연구는 딥러닝을 위한 비선형 변환 접근법을 사용하여 Single-lap joint의 접착 영역을 조사하기 위한 진동 응답 기반 탐지 시스템 을 제시한다. 산업 혹은 공학 분야에서 분해가 쉽지 않은 구조 내에 보이지 않는 부분의 상태와 접착된 구조의 접착 부위 상태를 알기 어려운 문제가 있다. 이러한 문제를 해결하기 위해 본 연구는 비선형 변환을 이용하여 기준 시편의 진동 응답으로 다양한 시편의 접착 면적을 조사하는 탐지 방법을 제안한다. 이 연구에서는 CNN 기반 딥러닝으로 진동 특성을 파악하기 위해 비선형 변환을 적용한 주파 수 응답 함수를 사용했고 분류를 위해 가상의 스펙트로그램을 사용했다. 또한, 제시된 방법을 검증하기 위해 알루미늄, 탄소섬유복합 재 그리고 초고분자량 폴리에틸렌 시편에 대한 진동 실험, 분석적 해, 유한요소해석을 수행했다.

The detector response was simulated to design a fork detection system for verifying the characteristics of spent fuel. The fork detection system currently used consists of two fission chamber and an ion chamber, and it is nuclear safeguard equipment that measures the gross neutrons and gross gamma rays emitted from the spent fuel assembly to identify the characteristics of the spent fuel and verify the authenticity of the operation history. In order to improve the current fork detection system, we are developing a system that applies CZT, a room temperature semiconductor detector, and a stilbene detector, which is an organic scintillator. Depletion calculations were performed using the ORIGEN code to determine the radiological characteristics emitted from spent nuclear fuel assembly. The flux of radiation emitted from the spent nuclear fuel assembly was calculated by changing the conditions such as initial enrichment, burnup, and cooling time, which are major variables of spent fuel assembly. The calculated result is used as the source term of the particle transport code. Considering the general operating conditions of the pressurized light water reactor, the conditions were changed in the range of 3-5% for initial enrichment and 30-72 GWD/MTU for burnup, and the cooling time was given within 10 years. MCNP 6.2, a Monte Carlo simulation code, was used to simulate the detector response to radiation emitted from spent nuclear fuel assembly. According to the shape, size, and position of the CZT detector, the gamma counts incident on the detector were calculated and derived the initial design of our fork detection system.

자율운항선박이 상용화되어 연안을 항해하기 위해서는 해상의 장애물을 탐지할 수 있어야 한다. 연안에서 가장 많이 볼 수 있 는 장애물 중의 하나는 양식장의 부표이다. 이에 본 연구에서는 YOLO 알고리즘을 이용하여 해상의 부표를 탐지하고, 카메라 영상의 기하 학적 해석을 통해 선박으로부터 떨어진 부표의 거리와 방위를 계산하여 장애물을 시각화하는 해상물체탐지시스템을 개발하였다. 1,224장 의 양식장 부표 사진으로 해양물체탐지모델을 훈련시킨 결과, 모델의 Precision은 89.0 %, Recall은 95.0 % 그리고 F1-score는 92.0 %이었다. 얻 어진 영상좌표를 이용하여 카메라로부터 떨어진 물체의 거리와 방위를 계산하기 위해 카메라 캘리브레이션을 실시하고 해상물체탐지시 스템의 성능을 검증하기 위해 Experiment A, B를 설계하였다. 해상물체탐지시스템의 성능을 검증한 결과 해상물체탐지시스템이 레이더보 다 근거리 탐지 능력이 뛰어나서 레이더와 더불어 항행보조장비로 사용이 가능할 것으로 판단된다.

Through the process of chemical vapor deposition, Tungsten Hexafluoride (WF6) is widely used by the semiconductor industry to form tungsten films. Tungsten Hexafluoride (WF6) is produced through manufacturing processes such as pulverization, wet smelting, calcination and reduction of tungsten ores. The manufacturing process of Tungsten Hexafluoride (WF6) is required thorough quality control to improve productivity. In this paper, a real-time detection system for oxidation defects that occur in the manufacturing process of Tungsten Hexafluoride (WF6) is proposed. The proposed system is implemented by applying YOLOv5 based on Convolutional Neural Network (CNN); it is expected to enable more stable management than existing management, which relies on skilled workers. The implementation method of the proposed system and the results of performance comparison are presented to prove the feasibility of the method for improving the efficiency of the WF6 manufacturing process in this paper. The proposed system applying YOLOv5s, which is the most suitable material in the actual production environment, demonstrates high accuracy (mAP@0.5 99.4 %) and real-time detection speed (FPS 46).