Premium
Data‐driven fault detection and isolation for multimode processes
Author(s) -
Liu Jialin
Publication year - 2011
Publication title -
asia‐pacific journal of chemical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.348
H-Index - 35
eISSN - 1932-2143
pISSN - 1932-2135
DOI - 10.1002/apj.549
Subject(s) - fault detection and isolation , subspace topology , fault (geology) , principal component analysis , control chart , isolation (microbiology) , computer science , root cause , process (computing) , data mining , pattern recognition (psychology) , statistics , reliability engineering , artificial intelligence , engineering , mathematics , seismology , microbiology and biotechnology , actuator , biology , geology , operating system
Contribution plots of the monitored statistics, Q and T 2 , are investigated to locate faulty variables when the statistics are out of their control limits. It is a popular method for fault isolation; however, it is well known that the smearing out of contributions leads to misdiagnose the faulty variables. Alternatively, the reconstruction‐based contribution approach is claimed to guarantee correct diagnosis. It has been examined in this paper that the approach fails to locate faulty variables when encountering multiple sensor faults. A fault isolation chart on principal component subspace is provided to locate faulty variables for a process with multiple operating regions. The results of an industrial application show that the proposed approach locates faulty variables precisely, whereas the root causes of the abnormalities have been successfully identified. Copyright © 2011 Curtin University of Technology and John Wiley & Sons, Ltd.