Speaker
Description
In Industry 4.0, smart systems like Artificial Neural Networks could significantly enhance the condition monitoring methodologies to ensure the reliable and safe operation of the system. Transverse breathing cracks are considered a serious fault in rotor-bearing systems that could affect operation efficiency. This paper presents an ANN-based approach to estimate crack depth, crack location, and unbalance mass using vibration data derived from numerical models. The rotor-bearing system is modeled using the finite element method and the Strain Energy Release Rate (SERR) approach for crack modelling, incorporating both open and breathing crack scenarios under varying unbalanced conditions and rotation speeds. The combined effect of a crack with unbalance situation in rotating systems is numerically investigated and an ANN is developed for fault estimation based on vibration response. The results demonstrate the potential of this smart system as an effective tool for real-time condition monitoring in rotating machinery.
