Identify and classify vibration fault based on artificial intelligence techniques

Abstract

Steam turbines (ST) need to be protected from damaging faults in the event it ends up in a danger zone. Some examples of faults include vibration, thrust, and eccentricity. Vibration fault represents one of the challenges to designers, as it could cause massive damages and its fault signal is rather complex. Researches in the field intend to prevent or diagnose vibration faults early in order to reduce the cost of maintenance and improve the reliability of machine production. This work aims to diagnose and classify vibration faults by utilized many schemes of Artificial Intelligence (AI) technique and signal processing, such as Fuzzy logic-Sugeno FIS (FLS), Back Propagation Neural Network (BPNN) hybrid with FL-Sugeno (NFS), and BPNN hybrid with FL-Mamdani FIS (NFM). The signal of the fault and the design of the FL and NN were done using MATLB. The results will be compared based on its ability to feed the output signal to the control system without disturbing system behavior. The results showed that the NFS scheme is able to generate linear and stable signals that could be fed to modify the main demand of the ST protection system. This work concluded that the hybrid of more than one AI technique will improve the reliability of protection system and generate smooth signals that are proportional to the fault level, which can then be used to control the speed and generated power in order to prevent the increase of vibration faults.