Abstract
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.
Highlights
Rotating machines, such as centrifugal compressors, are widely used due to their high performance and robustness [1]
A canonical variate residuals-based (CVR-based) contribution plot method based on Td and Hotelling’s Q statistics for isolating faulty variables has been developed
The use of the proposed diagnostic method for incipient fault diagnosis using data captured from a continuous stirred tank reactor (CSTR) simulation program and an operational industrial centrifugal compressor
Summary
Rotating machines, such as centrifugal compressors, are widely used due to their high performance and robustness [1]. The experimental results indicate that the proposed health index can detect slowly developing faults earlier than Hotelling’s T 2 and Q statistics while still maintaining an acceptable false alarm rate. Another major task of data-driven MHMS is to find the influential variables that are most likely related to a detected fault. A canonical variate residuals-based (CVR-based) contribution plot method based on Td and Hotelling’s Q statistics for isolating faulty variables ( for incipient fault identification tasks) has been developed. The use of the proposed diagnostic method for incipient fault diagnosis using data captured from a CSTR simulation program and an operational industrial centrifugal compressor
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
