This paper presents a log-transformed model-based performance analysis system for analyzing and improving manufacturing performance of the smart factory in the display business. Two years of data related to traditional manufacturing performance such as Cycle-time, WIP(Work-In-Process), and Throughput were investigated from the smart factory that producing the display for this research. We assessed manufacturing competitiveness based on how the operational level of automation affects improvements in manufacturing performances. We analyzed functional relationships between the indicators were derived using logtransformed regression analysis how the manufacturing performance indicators change according to the operational level of smart factory automation. As a result, we knew that the 170K production, which was planned capacity in the line design phase, achieved by running an automation level of only 59%. Based on this research, we suggest building an autopoietic optimize performance model to improving manufacturing competitiveness of smart manufacturing.

The study examined the relationship between workers’safety awareness, safety performance and the components of the intelligent image analysis system in accordance with preventing the workers from safety hazard in dangerous working area. Based on the safety performance model, we include safety knowledge, safety motivation, safety compliance and safety participation, and we also define three additional factors of the intelligent image analysis system such as functional feature, penalty and incentive by using factor analysis. SEM(Structural Equation Modeling) analyses on the data from the total of 73 workers showed that functional feature of intelligent analysis system and incentive were positively related to safety knowledge and safety motivation. And mediation effects of the relationship were verified to safety compliance and safety participation through safety knowledge as well.

To prevent safety hazards in dangerous working area, we have proposed an intelligent image analysis system. Six common patterns of safety violations of workers’ are defined and its motion detection algorithms are developed for alarm to CCTV　monitoring system. Developed algorithms are implemented at 195 dangerous areas such as chemical and gas treated room. The results of violated motion detection ratio by developed system shows 94.95% of true positive cases, and 0.21% of false positive cases from all 587,645 event cases in one month implementation period. In the period, it is observed that the number of safety rule violations and the following accidents are decreased.

본 연구는 동아시아 영역에 속해있는 5개 SKYNET 관측소(서울, 지바, 엣추 지마, 후쿠에 지마, 헤도 미사키)에서 6년 간 관측한 AOT 자료를 활용하여 MODIS에서 산출된 AOT를 검증하였고, 아울러 에어로솔 기후장 분석도 함께 수행하였다. 검증연구를 위해 관측소 25 km 이내의 MODIS AOT를 평균하였고, MODIS 관측시각 30분 전후 SKYNET AOT를 평균하여 시공간 일치 자료를 생산하였다. 시공간 일치 자료의 비교 결과 MODIS AOT의 정확도는 에어로솔 종류에 크게 영향을 받지 않았으나, MODIS AOT 산출과정 중 거대 입자 모형의 사용비율이 높아질수록 SKYNET AOT에 비해서 비교적 큰 값을 산출하는 경향을 보였다. 또한 AOT가 낮은 대기에서 MODIS AOT는 과대 추정하는 경향을 보였고 그 경향성은 AOT가 높아질수록 줄어들었다. MODIS-SKYNET AOT간의 회귀분석 결과 기울기는 0.86, Y절편은 0.16으로 나타났고 결정계수(R2)는 0.61로 나타났다. 이러한 통계적 결과로 미루어 볼 때 동아시아 영역에서 산출된 MODIS AOT는 지상 관측에 견줄 만큼 정확하다고 볼 수 있다.