Fault isolation in nonlinear systems with structured partial principal component analysis and clustering analysis

✍ Scribed by Yunbing Huang; Thomas J. Mcavoy; Janos Gertler

• Publisher: John Wiley and Sons
• Year: 2000
• Tongue: English
• Weight: 869 KB
• Volume: 78
• Category: Article
• ISSN: 0008-4034
• DOI: 10.1002/cjce.5450780316

✦ Synopsis

Abstract

Partial principal component analysis (PCA) and parity relations are proven to be useful methods in fault isolation. To overcome the limitation of applying partial PCA to nonlinear problems, a new approach utilizing clustering analysis is proposed. By dividing a partial data set into smaller subsets, one can build more accurate PCA models with fewer principal components, and isolate faults with higher precision. Simulations on a 2 × 2 nonlinear system and the Tennessee Eastman (TE) process show the advantages of using the clustered partial PCA method over other nonlinear approaches.