Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults

Energies

David Mba¹  Xiaochuan Li¹  Demba Diallo²  Claude Delpha³ 

[1] Faculty of Computing, Engineering and Media, De Montfort University, Leicester LE1 9BH, UK;Laboratoire Génie Electrique et Électronique de Paris (GeePs), CNRS, CentraleSupélec, Université Paris-Sud, 91190 Gif Sur Yvette, France;Laboratoire des Signaux et Systèmes (L2S), CNRS, CentraleSupélec, Université Paris-Sud, 91192 Gif Sur Yvette, France;

关键词: slowly evolving faults;    fault detection;    fault identification;   

DOI  :  10.3390/en12040726

来源: DOAJ

【 摘 要 】

This study puts forward a novel diagnostic approach based on canonical variate residuals (CVR) to implement incipient fault diagnosis for dynamic process monitoring. The conventional canonical variate analysis (CVA) fault detection approach is extended to form a new monitoring index based on Hotelling’s $T^2$ , $Q$ and a CVR-based monitoring index, $T_d$ . A CVR-based contribution plot approach is also proposed based on $Q$ and $T_d$ statistics. Two performance metrics: (1) false alarm rate and (2) missed detection rate are used to assess the effectiveness of the proposed approach. The CVR diagnostic approach was validated on incipient faults in a continuous stirred tank reactor (CSTR) system and an operational centrifugal compressor.

【 授权许可】

Unknown