Dynamic independent component analysis approach for fault detection and diagnosis

Authors:
George Stefatos;A. Ben Hamza
Affiliations:
Pratt & Whitney, Longueuil, QC, Canada;Concordia Institute for Information Systems Engineering, Concordia University, Montréal, QC, Canada
Venue:
Expert Systems with Applications: An International Journal
Year:
2010

Citing 4
Cited 2

Independent component analysis: algorithms and applications

Neural Networks
Artificial intelligence for monitoring and supervisory control of process systems

Engineering Applications of Artificial Intelligence
Fault diagnosis using dynamic trend analysis: A review and recent developments

Engineering Applications of Artificial Intelligence
Detecting faults in heterogeneous and dynamic systems using DSP and an agent-based architecture

Engineering Applications of Artificial Intelligence

Nonlinear process fault pattern recognition using statistics kernel PCA similarity factor

Neurocomputing
Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis

Information Sciences: an International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

In this paper, we introduce a novel fault detection and diagnosis method using a dynamic independent component analysis-based approach. We also present an innovative mechanism for detecting and diagnosing the faults. The proposed approach is able to accurately detect and isolate the root causes for each individual fault. The Tennessee Eastman challenge process is used to demonstrate the much improved performance of our proposed technique in comparison with other currently existing statistical monitoring and fault detection methods.