안전한 해양플랜트 운용을 위해 장비 성능평가를 실시하고 그 결과를 모니터링 할 수 있는 시스템이 필요하다. 현재는 육상으로부터 멀리 떨어진 해양플랜트의 특성상 장비 성능평가를 위해 정기적으로 계측 데이터를 저장매체에 저장한 후 육상으로 운반해야한다. 이로인해 성능평가 주기가 길어지고, 다음 성능평가가 시행되기 전까지의 장비의 성능 저하 정도를 알 수 없어 장비의 고장을 방지하기 어렵다. 따라서 육상이 아닌 해양플랜트 내에 온보드(on-board) 형태의 장비 성능 모니터링 시스템을 구축할 필요가 있다. 본 논문에서는 해양플랜트 내에서 장비 성능을 평가하고 그 결과를 가시화하는 장비 성능 모니터링 시스템을 개발하기 위한 초기 단계로, 장비 성능 모니터링 시스템의 데이터베이스를 설계 및 구축하고자 한다. 이를 위해 주요 장비의 태그 데이터를 선정하여 분석을 진행하였다. 최종적으로 장비 상태를 실시간으로 계측한 데이터를 해양플랜트 내에서 저장 및 관리하기 위해 온보드 형태의 장비 성능 모니터링 시스템을 위한 데이터베이스를 설계 및 구축 하였다.

PURPOSES : The purpose of this study is to evaluate the performance characteristics of stone mastic asphalt (SMA) pavement by comparison with polymer modified asphalt (PMA) pavement and conventional asphalt pavement, to check the performance characteristics according to the pavement type, pavement materials, traffic volume, and environmental factors and to analyze the quality variation characteristics according to the pavement materials using data extracted from the database of the expressway long-term pavement performance. METHODS : Approximately 10% outlier data of pavement performance data were excluded in order to increase the reliability of the analysis results before evaluating the asphalt pavement performance. The performance model was developed through linear regression analysis by setting the performance period as the independent variable and the highway pavement condition index (HPCI) as the dependent variable. Descriptive statistic analysis of HPCI using the static package for social science (SPSS) tool and the analysis of variance was performed to identify the quality variation characteristics according to the pavement materials. The amount of de-icing agent and traffic level of service were classified as two levels in order to check the influence of traffic volume and environmental factors on the performance characteristics of the asphalt pavement. RESULTS : The tentative pavement performance lives were calculated at 19.3 years for new the SMA pavement (GPS-2), 14.3 years for the SMA overlay on the asphalt pavement (GPS-6), and 10.3 years for the SMA overlay on the concrete pavement (GPS-7). In case of the asphalt overlay, the tentative performance lives were calculated at 8.2 years for the PMA overlay on the asphalt pavement (GPS-6), 7.2 years for the PMA overlay on the concrete pavement (GPS-7), 7.2 years for the conventional asphalt overlay on the asphalt pavement (GPS-6), and 5.5 years for the conventional asphalt overlay on the concrete pavement (GPS-7). CONCLUSIONS : It was confirmed that the SMA pavement showed better performance and quality variation characteristics than the PMA and conventional asphalt pavement. The performance characteristics of the asphalt pavement (GPS-2) was better than the asphalt overlay pavement, and the asphalt overlay on the asphalt pavement (GPS-6) had better performance characteristics than the asphalt overlay on the concrete pavement (GPS-7). It was observed that the asphalt overlay on the asphalt pavement (GPS-6) was strongly influenced by the traffic volume and the asphalt overlay on concrete pavement (GPS-7) was strongly influenced by the traffic volume and de-icing agent.

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

Google Trends is a useful tool not only for setting search periods, but also for providing search volume to specific countries, regions, and cities. Extant research showed that the big data from Google Trends could be used for an on-line market analysis of opinion sensitive products instead of an on-site survey. This study investigated the market share of tumor necrosis factor-alpha (TNF-α) inhibitor, which is in a great demand pharmaceutical product, based on big data analysis provided by Google Trends. In this case study, the consumer interest data from Google Trends were compared to the actual product sales of Top 3 TNF-α inhibitors (Enbrel, Remicade, and Humira). A correlation analysis and relative gap were analyzed by statistical analysis between sales-based market share and interest-based market share. Besides, in the country-specific analysis, three major countries (USA, Germany, and France) were selected for market share analysis for Top 3 TNF-α inhibitors. As a result, significant correlation and similarity were identified by data analysis. In the case of Remicade’s biosimilars, the consumer interest in two biosimilar products (Inflectra and Renflexis) increased after the FDA approval. The analytical data showed that Google Trends is a powerful tool for market share estimation for biosimilars. This study is the first investigation in market share analysis for pharmaceutical products using Google Trends big data, and it shows that global and regional market share analysis and estimation are applicable for the interest-sensitive products.

국내에는 독자적으로 연구가 수행되어 개인적으로 보관 중인 지질 연구 자료가 다량 존재하는데, 이 자료에 대한 접근성이 떨어지기 때문에 다른 연구자들과의 공유가 용이하지 않다. 이런 자료에 대한 메타데이터를 체계적으로 구축하고 총괄적으로 관리하여 이 자료를 필요로 하는 연구자들이 효과적으로 연구를 수행할 수 있는 기회를 제공하는 것이 이 연구의 목적이다. 국내에서 연구된 약 1000여개의 지질 시료(900여개의 암석과 화석 시료, 100여개의 박편 시 료)를 수집하였고, 각 시료의 고화질 사진, 분류, 시료명, 보유기관, 산지, 좌표, 특징 등에 대한 메타데이터를 구축하였다. 암석과 화석 시료 100개에 대해 추가적으로 3D 모델링을 수행하였다. 이 연구를 통해 유실되거나 방치되는 중요한 지질 자료에 대한 연구자들의 접근성이 높아지고 자료의 공유가 가능해진다. 따라서 연구자들은 반복적인 연구 자료 수 집 작업으로 인한 시간과 비용의 낭비를 줄일 수 있고, 효율적인 연구를 수행하여 경쟁력을 갖춘 연구 결과를 획득할 수 있다. 또한 이미 확보된 시료에 대한 무분별한 반복 채집으로 인해 중요한, 그리고 피해에 취약한 자료가 훼손되는 것을 방지할 수 있다. 향후 전국의 대학과 연구기관에서 보관중인 다양한 암석과 박편 시료에 대한 메타데이터를 추가로 구축하면 자료의 식별 및 진전된 연구가 가능하고, 더불어 전문적인 광물학 및 암석학의 기초 지식에 대한 비교와 분석을 기대할 수 있다.

중국 관광객의 서울과 제주도 관광인식을 알아보기 위해, 인식 특성에 따른 항목 추출, 두 지역을 분석하여 도출 키워드의 관계를 탐구함으로 관광 전략 시사점 도출을 목적으로 하였다. 빅 데이터 분석 프로그램 텍스톰의 중국어 버전을 활용하여 '서울여행', '제주도여행' 키워드를 중국 대표 포털사이트 바이두, 웨이보의 데이터를 수집하여, 빈도분석, TF-IDF분석, N-gram, 인식 항목별 분석 방법을 실시하였다. TF–IDF·N-gram 분석결과 '서울여행'은 역사문화 키워드가 연계되었으며, '제주도여행'은 유흥 및 여행 키워드가 연계되어 지역별 관심도 및 중요행태 차이가 있음을 알 수 있다. 주요 방문지는 서울은 역사문화 관광지 키워드가 도출되었으나, 제주도는 자연경관 키워드가 도출되었다. 주요활동은 서울 전통체험 키워드 도출, 제주도는 소비행태 키워드가 도출되었다. 본 연구는 빅데이터를 활용하여 인식 변화를 빠르게 파악 할 수 있으 며, 중국 관광객의 인식 및 행태의 관계성과 인식 항목별 키워드를 분석함으로써 효과적인 중국 관광객 유치에 대한 기초 데이터로서 의미가 있다.

The research model of panel data analysis in this study was used as the dependent variables and the business characteristics of the welding industry were reflected in the research model for systematic analysis of the effect of welding technology on the welding industry. As a result of the existing research, the domestic welding technology is seriously encroaching on the domestic welding industry between the United States, Japan and China. There is no quantitative statistical analysis on this aspect. In this study, the panel data analysis is used to indicate differences in explanatory power by numerical values of POLS model, fixed effect and random effect. And the prior studies on the current status of welding industry related to arc welding, special welding, multiple welding, welding and bonding technology are applied by the panel data analysis. Therefore, the problems of existing research are diagnosed while presenting the future research directions.

In this study, quality keywords of frequent mention of failures were extracted by analyzing the field operational data of main battle tanks recorded for about 5 years. As a result of the data analysis, the leaf spring assembly of the crew hatches corrosion and failure was frequently occurred. FEA(Finite Element Analysis) and tests were performed to analyze the cause of the failure, and it was confirmed that durability of the leaf spring was insufficient. Therefore a design modification study was conducted to improve durability of the leaf spring, and FEA and durability tests demonstrated the improvement. As a result, the durability of leaf spring was improved at least 3.3 times compared to before improvement. This study will contribute to suggesting the use of data analysis in the defense area and improving the operability of the main battle tanks.

Big data analysis in healthcare research seems to be a necessary strategy for the convergence of sports science and technology in the era of the Fourth Industrial Revolution. The purpose of this study is to provide the basic review to secure the diversity of big data and healthcare convergence by discussing the concept, analysis method, and application examples of big data and by exploring the application. Text mining, data mining, opinion mining, process mining, cluster analysis, and social network analysis is currently used. Identifying high-risk factor for a certain condition, determining specific health determinants for diseases, monitoring bio signals, predicting diseases, providing training and treatments, and analyzing healthcare measurements would be possible via big data analysis. As a further work, the big data characteristics provide very appropriate basis to use promising software platforms for development of applications that can handle big data in healthcare and even more in sports science.

The technology competitions of automobile manufacturers are getting hot. The characteristics of the environment friendly automobile are not only lowering the emission of harmful exhaust gas through the change of the power source, but also paying great attention to improvement of the power efficiency. As the market for pure electric vehicles continues to grow, we have analyzed the global technology competitiveness by DCT (Dual Clutch Transmission) patents. Clustering can be classified into five types ; 1) a cluster associated with a dual clutch transmission system, 2) a cluster of a torque transmission device and a reverse speed ratio, 3) a cluster of co-planar sets and dual clutch assemblies related to transmitting devices, 4) Device clusters, and 5) a cluster of synchronizers and clusters to prevent simultaneous operation of dual clutch transmissions. In recent years, demand for pure electric vehicles has been rapidly increasing, and patent applications related to DCT have been steadily increasing for energy efficiency of motor power sources.

In this study, heat exchangers used in data center and building air-conditioners were tested according to the type of heat exchangers to select them for commercial use. The experiment was performed three samples, one micro channel heat exchanger, the same volume oval coil and the same performance oval coil. The experiment conducted under actual operation conditions in the data center and building. Micro-channel heat exchanger has lower air side pressure drop and higher capacity per volume than oval coil. It may be advantageous when the installation small space or the little design static pressure in the fan, such as in-row systems or CRAC installed in data center.