• 한국산업융합학회 논문집
• /
• 제23권2_2호
• /
• pp.163-171
• /
• 2020

The condition of tire tread is a key parameter closely related to the driving safety of a vehicle, which affects the contact force of the tire for braking, accelerating and cornering. The major factor influencing the contact force is tread wear, and the more tire tread wears out, the higher risk of losing control of a vehicle exits. The tire tread condition is generally checked by visual inspection that can be easily forgotten. In this paper, we propose the intelligent tire (iTire) system that consists of an acceleration sensor, a wireless signal transmission unit and a tread classifier. In addition, we also presents classification algorithm that transforms the acceleration signal into the frequency domain and extracts the features of several frequency bands as inputs to an artificial neural network. The artificial neural network for classifying tire wear was designed with an Multiple Layer Perceptron (MLP) model. Experiments showed that tread wear classification accuracy was over 80%.

• 무역상무연구
• /
• 제30권
• /
• pp.145-174
• /
• 2006

An anti-dumping has become the trade policy of choice for developing countries as well as advanced countries, hence it is the impending issue to the export-oriented countries including Korea. After colligating the analysis on the trade and industrial policy between Korea and China as well as the analysis on the preceding research, the main reasons of anti-dumping were selected as followings; an unemployment rate, real GDP growth rate and consumer price increase as internal factors, and trade balance, regional coefficient and trade specification index as external factors. Then, the research on how the above seven variable factors can affect the number of anti-dumping measures was accomplished. For the empirical analysis, the above information was used after reorganizing them by on the quarterly basis. Through the use of the correlation analysis, backward elimination of multiple regression analysis model and time-series analysis, it has appeared that the unemployment rate appeared to be the most important factors of anti-dumping measures in addition to the increase rate of trade balance. The variable such as the unemployment rate is uncontrollable for us, so it is appropriate to establish and operate an preemptive monitoring system based on the increasing rate of the amount of export and increasing rate of trade surplus.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 봄 학술논문 발표대회
• /
• pp.51-52
• /
• 2021

The maintenance of educational facilities is divided into inspection and management of facility managers residing in the school and Educational Environment Improvement Projects(EEIP) to carry out maintenance work. Educational support organizations collect maintenance requests through facility inspections by school-specific facility managers, and carry out numerous maintenance projects during the year. The EEIP has the characteristic of Program Management with interrelationships between projects, not multiple projects management. The purpose of the EEIP is to eliminate the inconvenience of school facility users and increase their satisfaction, and achieving the goal is judged to be successful. Despite the importance of management and performance measurement utilizing Critical Success Factor(CSF) for the operation of successful educational facility maintenance management programs, the system for achieving the goals is insufficient. This study derives CSFs for each stage of the EEIP for the success of the EEIP. The CSFs for each stage of the EEIP is expected to serve as a basis for evaluation of educational facility maintenance management programs and can be used as an evaluation index in the future.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.219-220
• /
• 2022

In order to meet the trend, construction public data are already disclosing not only data generated at the construction site but also various data ranging from inspection reports and public construction contracts through multiple portals. However, unlike the excellence of the open performance evaluated by the number of data, it is difficult to evaluate the specific level of disclosure because there is no case of analyzing the quality, ease of use, and possibility of further opening of the public construction data set. On the other hand, performance measurement is already performed using an internationally agreed evaluation method in different fields such as real estate, population, and environment. So it is essential to analyze the current status of public data openings in the construction field and to derive improvement tasks. Therefore, this study conducted a survey of researchers with the highest system utilization targeting representative public data open systems in the construction field, such as E-AIS(세움터) and KISCON. To ensure fairness and increase comparability, the questionnaire was composed using evaluation items on implementing public data conducted annually by the World Wide Web Foundation, an international non-profit organization. With these responses, we investigated the status of public data disclosure and opinions on data quality and derived tasks to improve public data disclosure in construction through the analysis of the results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1301-1316
• /
• 2024

In modern warfare, missiles play a pivotal role but typically spend the majority of their lifecycle in long-term storage or standby mode, making it difficult to detect failures. Preemptive detection of missiles that will fail is crucial to preventing severe consequences, including safety hazards and mission failures. This study proposes a contamination-based stacking ensemble model, employing the local outlier factor (LOF), to detect such missiles. The proposed model creates multiple base LOF models with different contamination values and combines their anomaly scores to achieve a robust anomaly detection. A comparative performance analysis was conducted between the proposed model and the traditional single LOF model, using production-related inspection data from missiles deployed in the military. The experimental results showed that, with the contamination parameter set to 0.1, the proposed model exhibited an increase of approximately 22 percentage points in accuracy and 71 percentage points in F1-score compared to the single LOF model. This approach enables the preemptive identification of potential failures, undetectable through traditional statistical quality control methods. Consequently, it contributes to lower missile failure rates in real battlefield scenarios, leading to significant time and cost savings in the military industry.

• 수산해양기술연구
• /
• 제52권3호
• /
• pp.232-240
• /
• 2016

Marine casualties originated from fishing vessels occupied about 71.2% of the whole marine casualties in Korea from 2008 to 2014, which has not changed much for a long time. Therefore, a pragmatic counterplan to decrease in casualties in fishing vessel is indispensable for reduction of marine casualties in Korea. Since the casualties occurred by fishing vessels may incline to a specific type of casualties according to the difference in the operating type; in this paper, 11 fishing types which occurred casualties frequently in numbers and occupied ratio were selected. Since the most frequent occurring casualties in fishing vessels were from collisions and fire explosion in statistics from KMST (2008~2014), the study focused on them. The collision is given a great deal of weight in all the casualties mostly due to the negligence of duty regardless of the job types. Gill netter, trap fishing boat, jig boat, multiple fishing boat and stow netter have their own specific causes of casualties in collision according to the operating types. The cause of fire explosion was mainly due to poor inspection and maintenance the electric cord. For this reason, it may be necessary for an operator to make strict precaution on the other vessels under way systematically, keep the regulation for preventing collisions, and for an engineer on watch to make a check the electricity periodically to reduce the fire explosion.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권5호
• /
• pp.161-168
• /
• 2021

균열은 건물, 교량, 도로, 수송관 등의 기반시설의 안전성에 영향을 주는 요소이다. 본 연구에서는 검사 비용과 시간을 줄일 수 있는 자동화된 균열 탐지 시스템을 다룬다. 환경과 표면에 강건한 시스템을 구성하기 위해서, 본 연구에서는 여러 사전 연구에서 사용된 다양한 표면의 균열 데이터 셋을 수집하여 통합 데이터 셋을 구축하였다. 이후, 컴퓨터 비전 분야에 높은 성능을 발휘하는 VGG, ResNet, WideResNet, ResNeXt, DenseNet, EfficientNet 딥러닝 모델을 적용하였다. 통합 데이터 셋은 훈련 집합(80%)과 테스트 집합(20%)으로 나누어 모델 성능을 검증하기 위해서 사용했다. 실험 결과, DenseNet121 모델이 높은 마라미터 효율성을 가지면서도 테스트 집합에 대해 96.20%의 정확도를 달성하여 가장 높은 성능을 보여주었다. 딥러닝 모델의 균열 검출 성능 검증을 통해, DenseNet121를 활용하여 컴퓨팅 자원이 적은 소형 디바이스에서도 높은 균열 검출 성능을 보이는 탐지 시스템을 구축이 가능함을 확인했다.

• 항공우주시스템공학회지
• /
• 제12권3호
• /
• pp.38-44
• /
• 2018

군용항공기는 다양한 임무의 수행을 통한 비행시간 누적과 예상 불가능한 외기 환경에 의한 복합적인 요인으로 구조적으로 취약한 부위에서 피로균열이 발생할 수 있다. 피로 균열은 점차 진전되어 극심한 경우 해당 구조가 파괴될 위험이 있으며 이는 비행 안전성에 큰 영향을 미칠 수 있다. 본 논문에서는 항공기 주익과 동체의 연결부위를 보호하기 위해 장착한 페어링 내부의 지지대에서 주기검사 중 균열 현상을 개선하기 위한 일련의 품질개선에 관한 연구를 수행하였다. 균열의 원인파악을 위해 주익 조립 공정에 따른 예하중 발생 여부에 대해 조사하고 파단면 분석을 수행하였다. 또한, 균열의 재발방지를 위해 지지대의 설계를 개선하는 방안을 제시하였고, 응력 및 피로 수명해석을 통해 구조 건전성을 검증하였다.

• 한국구조물진단유지관리공학회 논문집
• /
• 제22권1호
• /
• pp.147-157
• /
• 2018

철근콘크리트 교량에 대한 대부분의 내진설계기준들은 전체 교량 시스템의 붕괴를 방지하기 위한 성능보장설계를 암시적 또는 명시적으로 적용하고 있다. 이러한 개념 및 규정들을 명시하는 이유는 교량 전체 시스템에 설계지진하중이 작용하는 동안 철근콘크리트 교각들이 완전한 소성회전성능을 발휘할 때까지 구조적인 다른 구성요소들의 취성적인 파괴를 방지하기 위함이다. 이를 위해 철근콘크리트 교량에 대한 내진설계기준들에서는 취성적인 전단파괴를 피하도록 규정하고 있다. 성능보장의 중요한 요소 중의 하나가 교각의 연성거동을 보장하기 위한 전단강도가 충분히 확보되어야 하고 신뢰할 수 있어야 한다. 실험체 8개에 대하여 실험을 수행하였으며 모든 실험체에서 변위비 1.5%에서 다수의 휨-전단 균열이 발생되었고 최종단계까지 균열폭이 증가되었고 균열이 진전되었다. 휨-전단 균열의 각도는 부재 축과 $42^{\circ}{\sim}48^{\circ}$의 범위로 계측되었다. 본 연구에서는 실험에서 계측된 횡방향철근이 부담하는 전단강도에 대한 분석을 중심으로 하였다. 횡방향철근이 부담하는 전단강도, 축력 작용에 의한 전단강도, 콘크리트에 의한 전단강도 등 3요소에 대해 분석하였고 비교하였다. 실험체들의 콘크리트 응력은 도로 교설계기준의 응력한계를 초과하였다.

• 한국정보통신학회논문지
• /
• 제21권12호
• /
• pp.2341-2346
• /
• 2017

안와 내에서 안구의 상대적 위치는 여러 병적인 상태를 짐작할 수 있는 하나의 기준이 될 수 있다. 특히 안와골절, 갑상선 안질환, 안와 종양 등의 진단과 이에 약물 및 수술적 치료의 결과를 판단하는데 유용하다. 현재 안구 돌출 값을 측정하기 위해 주로 사용되는 대표적 측정 기기인 Hertel과 Naugle 안구돌출계 등은 검사자가 다를 경우, 같은 검사자가 반복적으로 측정하더라도 검사할 때마다 안와의 고정부위가 달라지는 등 측정자에 의한 오차가 필연적이다. 또한 동일한 안구 돌출 계라고 하더라도 제조 회사가 다르다면 안와의 고정부위 디자인이 달라 검사자에의한 측정 오차가 발생한다. 본 논문에서는 안구돌출값의 측정을 3차원 영상 측정기술인 백색광 간섭계를 이용하여 검사 정밀도 및 반복 정도를 크게 올릴 수 있는 자동 측정 방법에 대한 연구를 제안하고자 한다.