Turbinacsapágy rezgéskiváltó okának feltárása mesterséges intelligenciával

Abstract

This study presents the practical application of artificial intelligence (AI) to identify the cause of excessive vibration in the turbine bearing of a conventional power plant. The vibration had occurred sporadically for years, and conventional diagnostic methods were unable to determine the cause of the excessive vibration in the fifth bearing of the turbine shaft.

To solve the problem, we used a neural network program, which utilized all available measurement data from the power plant to train the AI system. After training, the AI revealed that the natural frequency determined by the condenser’s water level, combined with the shaft’s rotational frequency, was the actual cause of the event.