Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
406329 | Neurocomputing | 2015 | 7 Pages |
Abstract
This work studies the fault classification issue focused on complicated industrial processes. The basic multivariate statistical approaches, i.e. support vector machine (SVM) as well as principal component analysis (PCA), are studied for multi-fault classification purpose. The Tennessee Eastman (TE) challenging benchmark, which contains 21 abnormalities from real world, is finally utilized to show the effectiveness of the approaches. Such a conclusion can be drawn from the simulation results: although SVM is a powerful tool for multi-classification purposes, the standard PCA approach still shows satisfactory results with less computational efforts.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Chen Jing, Jian Hou,