Multiple sensor fault diagnosis by evolving data-driven approach Academic Article

abstract

• Sensors are indispensable components of modern plants and processes and their reliability is vital to ensure reliable and safe operation of complex systems. In this paper, the problem of design and development of a data-driven Multiple Sensor Fault Detection and Isolation (MSFDI) algorithm for nonlinear processes is investigated. The proposed scheme is based on an evolving multi-Takagi Sugeno framework in which each sensor output is estimated using a model derived from the available input/output measurement data. Our proposed MSFDI algorithm is applied to Continuous-Flow Stirred-Tank Reactor (CFSTR). Simulation results demonstrate and validate the performance capabilities of our proposed MSFDI algorithm. 2013 Elsevier Inc. All rights reserved.

authors

• Langari, Gholamreza

published proceedings

• INFORMATION SCIENCES

author list (cited authors)

• El-Koujok, M., Benammar, M., Meskin, N., Al-Naemi, M., & Langari, R.

citation count

• 28

complete list of authors

• El-Koujok, M||Benammar, M||Meskin, N||Al-Naemi, M||Langari, R

publication date

• January 2014

publisher

• Elsevier  Publisher

published in

• n0020-0255ISSN  Journal

keywords

• Data-driven Approach
• Nonlinear System
• Sensor Fault Diagnosis

Digital Object Identifier (DOI)

• 10.1016/j.ins.2013.04.012

start page

• 346

end page

• 358

volume

• 259

URL

• http://dx.doi.org/10.1016/j.ins.2013.04.012