Open AccessDynamic Thresholds for a Reliable Diagnosis of Switched Systems
Author(s) -
Ayman Abboudi,
Fouad Belmajdoub
Publication year - 2021
Publication title -
journal européen des systèmes automatisés/journal européen des systèmes automaitsés
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.16
H-Index - 20
eISSN - 2116-7087
pISSN - 1269-6935
DOI - 10.18280/jesa.540604
Subject(s) - bond graph , fault detection and isolation , computer science , observer (physics) , reliability (semiconductor) , graph , convergence (economics) , detector , real time computing , reliability engineering , algorithm , artificial intelligence , engineering , theoretical computer science , mathematics , actuator , telecommunications , power (physics) , physics , combinatorics , quantum mechanics , economics , economic growth
Safety, availability and reliability are the main concern of many industries. Thus, fault detection and isolation of industrial machines, which are in most cases switched systems, is a primary task in many companies. The presented paper proposes a new diagnostic approach for switched systems using two powerful tools: bond graph and observer. A diagnostic layer detects model errors using bond graph, and a smart algorithm identifies and locates faults using observer. Although observers serve as fault detectors, they also have their own errors caused by convergence delay of calculations; even in the case of no sensor defect, the residue does not converge to zero. In this paper, we propose a new method to solve this problem by integrating dynamic thresholds in the detection procedure, which helped to avoid false alarms and ensure a highly reliable diagnosis.