Modelling and Prediction of Gas Turbine Blade Failure Induced by Centrifugal Force using Expert Analytical System

NIL

Abstract

To provide accurate forecasts of a gas turbine blade failure and operational condition, the intricate relationship between centrifugal force and gas turbine blade failure has to be understood and established using advanced expert modeling approaches. The present research has explored the use of Artificial Neural Networks (ANN) to simulate and forecast a gas turbine blade failure induced by centrifugal forces. A multilayer feedforward neural network was trained using operational data such as speed of rotation, blade material properties and induced blade stress values. The results gotten from the blade modelling using the ANN showed that the ANN comparatively outperforms traditional approaches in terms of the blade failure and operational condition prediction accuracy, making it a valuable tool for enhancing turbine performance and operational sustainability. The ANN was a
choice expert analytical modelling tool for the blade due to its ability to handle nonlinear interactions and big datasets. It was therefore concluded that it is a significant machine learning tool for predicting failures in mechanical systems such as the gas turbine blade.