Process fault isolation based on transfer entropy algorithm

Payman Hajihosseini; Karim Salahshoor; Behzad Moshiri

doi:10.1016/j.isatra.2013.11.007

Process fault isolation based on transfer entropy algorithm

ISA Trans. 2014 Mar;53(2):230-40. doi: 10.1016/j.isatra.2013.11.007. Epub 2013 Dec 5.

Authors

Payman Hajihosseini¹, Karim Salahshoor², Behzad Moshiri³

Affiliations

¹ Department of Electrical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran. Electronic address: p_hajihosseini@kiau.ac.ir.
² Automation and Instrumentation Department, Petroleum University of Technology, Tehran, Iran. Electronic address: salahshoor@put.ac.ir.
³ Control & Intelligent Processing, Center of Excellence, School of ECE, University of Tehran, Tehran, Iran. Electronic address: moshiri@ut.ac.ir.

PMID: 24315057
DOI: 10.1016/j.isatra.2013.11.007

Abstract

Complexity of industrial plants and their stringent environmental and safety regulations have necessitated early detection and isolation of process faults. All the existing fault isolation methods can be categorized into two general groups: model-based and data-based. Transfer entropy is a data-based method for measuring propagation direction of disturbance and finding its root cause. In this paper, a new transfer entropy-based method is proposed to isolate different process faults. The novelty of this paper lies in using the transfer entropy idea to generate distinct patterns of information flow among process variables, recognize their correlations in the context of the transferred information in any abnormal condition, and finally isolate different process faults. The experimental results clearly demonstrate the superiority of the proposed method to the conventional methods.

Keywords: Classifier; Fault detection and isolation; Probability density function; Transfer entropy; Wavelet.