Fault detection and diagnosis, FDD via improved univariate statistical process control charts, USPC
A new approach for detecting and diagnosing fault via correlation technique is introduced in this study. The correlation coefficient is determined using multivariate analysis technique, Partial Correlation Analysis (PCorrA). Individual charting technique such as Shewhart, Exponential Weight Moving A...
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/5943/1/NoorlisaHarun2004_FaultDetectionAndDiagnosisFDD.pdf |
| Summary: | A new approach for detecting and diagnosing fault via correlation technique is introduced in this study. The correlation coefficient is determined using multivariate analysis technique, Partial Correlation Analysis (PCorrA). Individual charting technique such as Shewhart, Exponential Weight Moving Average (EWMA), and Moving Average and Moving Range (MAMR) charts are a used to facilitate the Fault Detection and Diagnosis (FDD). A precut multi component distillation is used as the case study in this work. Based on the result from this study Shewhart control chart gives the best performance with the highest FDD efficiency. |
|---|