Vibration monitoring has shown reliable efficiencies in fault detection and isolation (FDI) since they reflect operational conditions. Reliable signal processing techniques provide reliable FDI parameters for artificial intelligence-based data-driven ...
Vibration monitoring has shown reliable efficiencies in fault detection and isolation (FDI) since they reflect operational conditions. Reliable signal processing techniques provide reliable FDI parameters for artificial intelligence-based data-driven diagnostics. This study employs a deep neural network (DNN) for diagnosis after correlation-based discriminative feature selection. Results show a reliable test accuracy of 95.6% with a minimal false alarm rate.