통계적 패턴 인식 분류 기법을 이용한 FCC공정 설비의 시계열 데이터 분석 및 상태 진단

초록

In this study, the condition of equipment was diagnosed by using time series data of MAB (Main Air Blower) among FCC (Fluid Catalytic Cracking) process equipment. Diagnosis is a technique for predictive maintenance of equipment using current sensor data. In this study, data-based approach that uses historical data was used for diagnosis. The sensor data was used for analysis after eliminating unwanted noise which may cause errors in pattern recognition through preprocessing. In addition, a sensor that can be an indicator of failure is selected based on the maintenance history, and descriptive statistical values that can be a characteristic of each sensor is extracted at certain time intervals. And extracted feature values are projected on 2-dimensional space through PCA (Principal Component Analysis) that is one of dimensionality reduction algorithms. The failure history data was classified using the Naive Bayesian classification method. And this diagnosis module was tested by using some of the actual data and verified the availability.