Gas path fault diagnosis framework for a three-shaft gas turbine

Abstract

A diagnostic framework has been developed for the detection of faults in the gas path of a three-shaft aeroderivative gas turbine thermodynamically similar to the Rolls Royce RB211-24GT. The framework involves a large-scale integration of artificial neural networks (ANNs) designed and trained to detect, isolate and assess faults in the gas path components of the engine. The approach has the capacity to assess both multiple-component and multiple-sensor faults. The results obtained demonstrate the promise of ANNs applied to engine diagnostic activities.