Electric doors have been applied in urban trains since 2007 and operated for a long time. Recently, the failure of mechanical devices in electric doors have been increasing. The door is a device that is directly related to the safety of passengers. The rivet breakage of a ball/nut assembly may occur to an accident during train operation. In this study, the operating voltage and acceleration data of the door were collected for rivet condition monitoring, and 4 features were extracted in the frequency domain using the acceleration data. The classification performance of the rivet condition according to the axial direction of the acceleration data and 4 kernel functions was evaluated using SVM algorithm. When the X-axis data and Gaussian kernel function were used, the highest classification performance was shown for the electric door’s rivet with 90% accuracy.

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

기후변화에 따른 자연재해의 증가하고 있다. 이에 자연재해에 의한 토목구조물의 피해 및 붕괴를 예방하기 위하여 처짐 및 균열을 지속적인 관리가 필요하다. 이에 효과적인 구조물 관리를 위해 광학 이미지 기술이 유지관리 기술에 적용되고 있 다. 하지만 광학이미지 기술은 촬영에 따른 주변 조건의 영향이 크며, 그 때문에 촬영조건에 대한 검증이 필요하다. 이를 위해 본 논문에서 촬영조건으로 자연광, 촬영매수, 촬영거리를 따른 수직변위 추정값의 정확도에 대해 검증하였다. 실험을 통 해 확인한 결과 자연광이 수직변위를 추정하는데 자연광이 가장 큰 영향을 미치는 것을 확인할 수 있었고, 촬영거리 또한 수직변위를 검토하는데 주요한 영향을 미치는 것을 확인할 수 있었다. 본 결과를 통해서 외부환경에서 촬영하는데 활용하여 변위 추정 시 발생하는 오차를 최소화할 수 있으며, 이러한 과정을 통해 구조물 유지관리에 적용할 수 있다.

Trouble prevention of facilities in operation process plays an Important role for Improving facilities productivity as pro-duct-on systemization is installed with development of facilities automatization Condition monitoring predicts machine's in-ternal c