| 학회 |
한국화학공학회 |
| 학술대회 |
2017년 봄 (04/26 ~ 04/28, ICC 제주) |
| 권호 |
23권 1호, p.270 |
| 발표분야 |
공정시스템 |
| 제목 |
Dual Monitoring Method for the Hyper Compressor in LDPE Production Plant Using Fault Detection Model Based on Weighted PCA and Compressor Efficiency Index |
| 초록 |
Due to the increasing interest in safety and productivity, fault detection is becoming important. A data-based monitoring method is proposed to detect faults in low density polyethylene (LDPE) production plant in this research. Previous fault detection studies for the LDPE production plant focused on detecting reactor faults. However, since the compressor is operated in considerably high pressure, it could incur critical damage compared to the fault that happened in the reactor. So in this research, fault detection model focused on compressor section is developed. This study proposes dual monitoring method. Firstly, the fault detection model based on a weighted principal component analysis (WPCA) algorithm is introduced. Based on WPCA model, monitoring statistics Hotelling’s T2 and principal component control limit (PCCL) are used. Second monitoring method uses compressor efficiency index. It put focus on detecting emergency shut down which occurred during the operation of LDPE process for 4 years. The result shows that all fault cases are detected using dual monitoring method. |
| 저자 |
김지선1, 이창송2, 박병언1, 이정근1, 이규황2, 이호경2, 이인범1
|
| 소속 |
1포항공과대, 2LG화학 |
| 키워드 |
이상진단 |
| E-Mail |
|
| 원문파일 |
초록 보기 |
