A digital model for the performance prediction of gas turbine performance is presented. The gas turbine unit is installed in an industrial site and is equipped with remote monitoring for the main operating parameters. These include temperatures and pressures in key points, power, fuel consumption, and environmental parameters. Different load conditions are investigated, and monitoring includes signals for damage prevention (bearings vibration, lubricant temperatures). An inverse data processing allows to calculate the main performance indexes (system and cycle efficiency; compressor and turbine isentropic efficiency). Different models were evaluated, focusing on ARMA and a Support Vector Machine model for prediction of performance and unexpected events. Possibly leading to alarm/damage conditions.
Digital model of a gas turbine performance prediction and preventive maintenance
Roberta Rossi
2019-01-01
Abstract
A digital model for the performance prediction of gas turbine performance is presented. The gas turbine unit is installed in an industrial site and is equipped with remote monitoring for the main operating parameters. These include temperatures and pressures in key points, power, fuel consumption, and environmental parameters. Different load conditions are investigated, and monitoring includes signals for damage prevention (bearings vibration, lubricant temperatures). An inverse data processing allows to calculate the main performance indexes (system and cycle efficiency; compressor and turbine isentropic efficiency). Different models were evaluated, focusing on ARMA and a Support Vector Machine model for prediction of performance and unexpected events. Possibly leading to alarm/damage conditions.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
