TY - GEN
T1 - Gas turbine diagnostics under variable operating conditions
AU - Loboda, Igor
AU - Feldshteyn, Yakov
AU - Yepifanov, Sergiy
PY - 2007
Y1 - 2007
N2 - Operating conditions (control variables and ambient conditions) of gas turbine plants and engines vary considerably. The fact that health monitoring has to be uninterrupted creates the need for a run time diagnostic system to operate under any conditions. The diagnostic technique described in this paper utilizes the thermodynamic models in order to simulate gaspath faults and uses neural networks for the faults localization. This technique is repeatedly executed and the diagnoses are registered. On the basis of these diagnoses and beforehand known faults, the correct diagnosis probabilities are then calculated. The present paper analyses the influence of the operating conditions on a diagnostic process. In the technique, different options are simulated of a diagnostic treatment of the measured values obtained under variable operating conditions. The mentioned above probabilities help to compare these options. The main focus of the paper is on the so called multipoint (multimode) diagnosis that groups the data from different operating points (modes) to set only a single diagnosis.
AB - Operating conditions (control variables and ambient conditions) of gas turbine plants and engines vary considerably. The fact that health monitoring has to be uninterrupted creates the need for a run time diagnostic system to operate under any conditions. The diagnostic technique described in this paper utilizes the thermodynamic models in order to simulate gaspath faults and uses neural networks for the faults localization. This technique is repeatedly executed and the diagnoses are registered. On the basis of these diagnoses and beforehand known faults, the correct diagnosis probabilities are then calculated. The present paper analyses the influence of the operating conditions on a diagnostic process. In the technique, different options are simulated of a diagnostic treatment of the measured values obtained under variable operating conditions. The mentioned above probabilities help to compare these options. The main focus of the paper is on the so called multipoint (multimode) diagnosis that groups the data from different operating points (modes) to set only a single diagnosis.
KW - Fault classification
KW - Gas turbine diagnostics
KW - Multipoint diagnosis
KW - Neural networks
KW - Thermodynamic model
UR - http://www.scopus.com/inward/record.url?scp=34548758557&partnerID=8YFLogxK
U2 - 10.1115/GT2007-28085
DO - 10.1115/GT2007-28085
M3 - Contribución a la conferencia
AN - SCOPUS:34548758557
SN - 079184790X
SN - 9780791847909
T3 - Proceedings of the ASME Turbo Expo
SP - 829
EP - 838
BT - Proceedings of the ASME Turbo Expo 2007 - Power for Land, Sea, and Air
T2 - 2007 ASME Turbo Expo
Y2 - 14 May 2007 through 17 May 2007
ER -