TY - GEN
T1 - Extracting Fault Subspaces for Fault Identification of a Polyester Film Process
AU - VALLE, Sergio
AU - QIN, Joe J.
AU - PIOVOSO, Michael J.
AU - BACHMANN, Mike
AU - MANDAKORO, Nori
PY - 2001/6
Y1 - 2001/6
N2 - Although fault detection has been well studied in process monitoring under stationary conditions, the identification of faults in chemical processes is a difficult task. In this paper, we present a new approach in the use of a fault identification index to identify faults based on fault directions extracted from abnormal data using singular value decomposition. The proposed method is demonstrated on an industrial polyester film process which is characterized by frequent set-point changes and multiple grade changes. Further, a comparison between the fault identification index and the contribution plot method is given.
AB - Although fault detection has been well studied in process monitoring under stationary conditions, the identification of faults in chemical processes is a difficult task. In this paper, we present a new approach in the use of a fault identification index to identify faults based on fault directions extracted from abnormal data using singular value decomposition. The proposed method is demonstrated on an industrial polyester film process which is characterized by frequent set-point changes and multiple grade changes. Further, a comparison between the fault identification index and the contribution plot method is given.
UR - http://www.scopus.com/inward/record.url?scp=0034842247&partnerID=8YFLogxK
U2 - 10.1109/ACC.2001.945682
DO - 10.1109/ACC.2001.945682
M3 - Conference paper (refereed)
SN - 0780364953
T3 - Proceedings of the American Control Conference
SP - 4466
EP - 4471
BT - Proceedings of the 2001 American Control Conference
PB - Institute of Electrical and Electronics Engineers
T2 - 2001 American Control Conference, ACC 2001
Y2 - 25 June 2001 through 27 June 2001
ER -