Please use this identifier to cite or link to this item:
|Title:||A self-organizing map approach for process fault diagnosis during process transitions|
|Authors:||Ng, Y.S. |
|Source:||Ng, Y.S.,Srinivasan, R. (2004). A self-organizing map approach for process fault diagnosis during process transitions. AIChE Annual Meeting, Conference Proceedings : -. ScholarBank@NUS Repository.|
|Abstract:||A self-organizing map (SOM) based approach to monitor process transitions is presented. The framework integrates SOM with clustering and sequence comparison methods for plant wide monitoring and fault diagnosis. Process abnormality is detected through cluster analysis while syntactic pattern recognition technique and profile sequence comparison techniques render data based fault diagnosis and machine learning possible. A statistical monitoring scheme based on sequence alignment technique has also been introduced to monitor the severity of process fault, and to generate variables residuals during abnormal events to facilitate plant wide fault diagnosis. The application of the methods to a distillation column startup shows the method effectiveness in detecting and classifying process faults. The proposed method offers several advantages over other monitoring techniques, e.g., it accounts the multivariate nature of chemical processes, and is able to visualize high dimensional data. The proposed technique is much faster than conventional signals comparison methods. This is an abstract of a paper presented at the AIChE Annual Meeting (Austin, TX 11/7-12/2004).|
|Source Title:||AIChE Annual Meeting, Conference Proceedings|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 9, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.