Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

PURPOSES : Safety Evaluation of Wind Loads of Renewable Energy and Photovoltaic Power Structures. METHODS : Structural safety evaluation was conducted on the wind load of 3kW Photovoltaic Power Structures using ABAQUS. Wind speed was reviewed for 36m/s and 60m/s. Effective Mass and Mass Contribution of Photovoltaic Power Structures was utilized up to 90%. 7 steps were set and applied to structural analysis. RESULTS : As a result of the structural analysis, it was confirmed that the long-term blowing load was affected rather than the size of the wind load. Weak areas were identified at the point of the horizontal beam rather than the modules of the Photovoltaic Power Structures. In particular, it was confirmed that stress exceeding the allowable stress was generated at the junction. In order to secure the safety of Photovoltaic Power Structures, it is judged that reinforcement of the branch is necessary. CONCLUSIONS : The safety of Photovoltaic Power Structures structures for wind load is influenced by persistence rather than the size of the wind load. Therefore, in order to prevent this, it is judged that reinforcement of the branch is necessary.

외부하중을 받는 구조물로부터 계측된 신호의 파워 스펙트럴 밀도함수는 모달 파라미터(고유진동수, 감쇠비)에 대한 상당량 의 정보를 함축하고 있다. 시스템 식별기술은 이러한 신호나 해당 스펙트럼으로부터 모달 파라미터를 추출하는 기법이라고 볼 수 있 다. 파라미터를 추출하는 또 다른 기법으로는 샘플링(신호)을 이용하여한 확률분포의 모수(평균, 분산)를 추정하는 기법이다. 본 연구 에서는 파워 스펙트럼 밀도함수를 확률분포로 치환함으로써 기존 확률통계분야에서 모수를 추출하는 기법(최대우도법)에 의해 모달 파라미터를 추정하는 기법을 제안한다. 모드형상을 추정하는 기법을 개발하고 모드형상에 의해 분해된 모드응답으로부터 고유진동수, 고유감쇠비를 순차적으로 산정하는 기법을 제시한다. 더 나아가, 외부하중이 스펙트럼 해석모델로 치환 가능한 경우에는 이 하중모델 은 통합하여 모델 파라미터까지 산정하는 기법으로 확대한다. 본 연구에서 제시된 기법을 검증하기 위한 수치해석과 실구조물의 응답 에 대한 적용이 이루어졌으며, 검증결과 제안된 모드식별체계가 안정적이며, 신뢰도가 높은 모달파라미터 추정이 가능함을 알 수 있었다.

타워형 집광태양열발전의 핵심요소인 헬리오스타트는 경량화를 통한 설비비 저감이 매우 중요한다. 반사판 면적 16m2의 기 존 헬리오스타트 대비 샌드위치 패널을 사용하여 무게를 50% 경량화한 헬리오스타트의 풍하중 평가를 수행하였다. 반사판이 수직, 45 도 경사인 경우에 대해 전산유체역학 해석을 하여 반사판에 작용하는 풍압을 산정하고 구조해석을 수행하여 최대응력의 발생부위 및 반사판의 변위에 의한 반사각도의 이격을 계산하였다. 45도 경사진 반사판이 바람이 불어오는 반대편으로 향한 경우가 바람을 마주보 는 배치보다 최대 풍하중이 더 크게 나타났으며, 반사판 풍하측으로의 유동박리에 의한 후류의 발달도 반사판의 배치에 따라 매우 상 이한 형태를 보였다. 경량화 모델의 경우 반사판 구동을 위한 기어의 배치를 변경하여 핵심 지지체인 기둥의 강성을 확보할 필요가 있 음을 확인하였다.

This study is designed to predict the overall electric power load, to apply the method of time sharing and to reduce simultaneous load factor of electric power when authorized by user entering demand plans and using schedules into the user’s interface for

This study is designed to predict the overall electric power load, to apply the method of time sharing and to reduce simultaneous load factor of electric power when authorized by user entering demand plans and using schedules into the user’s interface for a certain period of time. This is about smart grid, which reduces electric power load through simultaneous load factor of electric power reduction system supervision agent. Also, this study has the following characteristics. First, it is the user interface which enables authorized users to enter and send/receive such data as demand plan and using schedule for a certain period of time. Second, it is the database server, which collects, classifies, analysis, save and manage demand forecast data for a certain period of time. Third, is the simultaneous load factor of electric power control agent, which controls usage of electric power by getting control signal, which is intended to reduce the simultaneous load factor of electric power by the use of the time sharing control system, form the user interface, which also integrate and compare the data which were gained from the interface and the demand forecast data of the certain period of time.

본 논문은 고층건축물의 비틀림방향 응답을 평가하기 위하여 필요한 변동비틀림모멘트계수와 변동비틀림모멘트의 파워스펙트럼밀도계수의 경험식을 제안한 연구이다. 이러한 경험식을 제안하기 위하여, 다양한 형상비와 변장비를 가진 27개의 각주형 모형을 제작한 후 노풍도을 다양하게 변화시켜 풍력실험 을 실시하였다. 본 논문에서 비틀림방향 변동풍력의 경험식은 주로 건물의 노풍도와 형상비 그리고 변장비에 의하여 분석되어졌다.

가섭선 및 애자가 연결되어 있는 복잡한 구조물인 송전철탑의 3차원 모델링을 통하여 동특성을 파악하고, 풍하중에 대한 응답 특성을 정적, 동적 및 좌굴 해석을 가섭선의 절단 유무에 따라 분석하였다. 우선, 고유치해석을 통해, 송전철탑이라는 구조시스템이 일반 건축물과는 달리 극소수의 저차 모드가 구조물의 동적 거동을 좌우하지 않고, 상대적으로 많은 모드들이 동적 거동에 기여한다는 것을 확인하였다. 두 번째로, 정적 해석과 좌굴 해석을 통해, 대상 구조물이 정적인 개념의 풍하중에 대해서 구조적으로 안전하고 좌굴에 대해서도 충분한 안전율을 확보하고 있음을 확인하였다 그러나, 모든 가섭선이 단절되는 극단적인 경우에는 안전율이 상당히 낮아졌으며 이러한 경우에 구조물의 붕괴 및 전도를 방지할 대책에 대한 검토가 필요하다고 사료된다 마지막으로, 풍하중의 시간에 따른 변화를 고려한 동적해석을 통해, 풍하중의 동적 변동성분이 구조물의 응답을 증가시키고 있음을 확인하였다.

This paper describes dynamic characteristics of a power transmission tower consisting of lots of power lines and insulators. A numerical 3D modeling for the static, dynamic and buckling analyses of the power transmission tower is presented considering the case when the power lines are cut. Eigenvalue analysis indicates that the transmission tower shows different behavior comparing to usual structures governed by several low modes. The transmission tower is governed by lots of modes. It is verified that the transmission tower is structurally safe against the static wind and buckling loads. But the structural and buckling safety is not guaranteed when all power lines are cut, which comes to collapse the transmission tower. Further study is in need to overcome such case. Wind dynantic analysis shows that fluctuating wind loads increase the response of the tower.

Biomass-fired power plants produce electricity and heat by burning biomass in a boiler. However, one of the most serious problems faced by these plants is severe corrosion. In biomass boilers, corrosion comes from burnt fuels containing alkali, chlorine, and other corrosive substances, causing boiler tube failures, leakages, and shorter lifetimes. To mitigate the problem, various approaches implying the use of additives have been proposed; for example, ammonium sulfate is added to convert the alkali chlorides (mainly KCl) into the less corrosive alkali sulfates. Among these approaches, the high temperature corrosion prevention technology based on ammonium sulfate has few power plants being applied to domestic power plants. This study presents the results obtained during the co-combustion of wood chips and waste in a circulating fluidized bed boiler. The aim was to investigate the characteristics of pollution load in domestic biomass power plants with ammonium sulfate injection. By injecting the ammonium sulfate, the KCl content decreased from 68.9 to 5 ppm and the NOx were reduced by 18.5 ppm, but SO2 and HCl were increased by 93.3 and 68 ppm, respectively.