Title :
Real-time for monitoring aluminium reduction cells using multi-way PCA (MPCA) and dynamic Euclidean distances
Author :
Majid, Nazatul Aini Abd ; Young, Brent ; Taylor, Mark ; Chen, John
Author_Institution :
Univ. of Auckland, Auckland, New Zealand
Abstract :
A real-time process monitoring system for detecting faults within aluminium reduction cells is presented in this paper. This system is developed using an integration of MPCA and Euclidean distances. MPCA is used to detect the specific faults during process monitoring whereas dynamic Euclidean distances are used to diagnose the faults. Results from real-data analysis show that this approach is effective to detect and diagnose anode spikes.
Keywords :
data analysis; fault diagnosis; principal component analysis; production engineering computing; statistical process control; aluminium reduction cells; anode spikes; data analysis; dynamic Euclidean distances; fault detection; fault diagnosis; multiway PCA; real-time process monitoring system; Aluminum; Anodes; Circuit faults; Electrochemical processes; Fault detection; Fault diagnosis; Monitoring; Principal component analysis; Process control; Real time systems;
Conference_Titel :
Control and Automation, 2009. ICCA 2009. IEEE International Conference on
Conference_Location :
Christchurch
Print_ISBN :
978-1-4244-4706-0
Electronic_ISBN :
978-1-4244-4707-7
DOI :
10.1109/ICCA.2009.5410608
