Skip to Main content Skip to Navigation
Journal articles

Statistical detection and isolation of additive faults in linear time-varying systems

Qinghua Zhang 1 Michèle Basseville 2 
1 I4S - Statistical Inference for Structural Health Monitoring
IFSTTAR/COSYS - Département Composants et Systèmes, Inria Rennes – Bretagne Atlantique
Abstract : This paper describes a statistical approach to fault detection and isolation for linear time-varying (LTV) systems subject to additive faults with time-varying profiles. The proposed approach combines a generalized likelihood ratio (GLR) test with a recursive filter that cancels out the dynamics of the monitored fault effects. To our knowledge, the proposed recursive filter is new for the considered faults. The resulting algorithm handles fault isolation with weaker assumptions than usual, in particular regarding the requirements on the number of sensors and on the stability of the monitored system. Numerical results for leakage detection in a gas transportation network illustrate the effectiveness of the proposed method.
Document type :
Journal articles
Complete list of metadata
Contributor : Qinghua Zhang Connect in order to contact the contributor
Submitted on : Friday, April 2, 2021 - 3:30:24 PM
Last modification on : Friday, June 17, 2022 - 1:27:31 PM
Long-term archiving on: : Saturday, July 3, 2021 - 6:41:03 PM


Files produced by the author(s)



Qinghua Zhang, Michèle Basseville. Statistical detection and isolation of additive faults in linear time-varying systems. Automatica, Elsevier, 2014, 50 (10), pp.2527-2538. ⟨10.1016/j.automatica.2014.09.004⟩. ⟨hal-01081899⟩



Record views


Files downloads