Balancing of an Unbalanced Jeffcott Rotor Using Artificial Neural Network to Predict the Correction Mass and Phase Angle

In the modern era, technology s undeniable impact on various industries is particularly prominent in rotating machinery applications, including engine rotors and industrial turbomachinery. A common challenge in this domain is rotor imbalance, leading to detrimental consequences such as excessive vibrations, bearing wear, and machinery breakdowns. This study aims to investigate Jeffcott rotor dynamics through precise MATLAB modeling, intentionally introducing mass imbalance to simulate real-world scenarios accurately. A Vector-Balancing technique is employed to address this imbalance, and an Artificial Neural Network (ANN) is trained to proactively mitigate rotor imbalances, drawing upon the results obtained from the modeling process. This enables the ANN to effectively address rotor imbalances, enhancing the reliability and performance of rotating machinery applications. To validate the effectiveness of this ANN-based approach in addressing rotor imbalance issues across various rotating machinery applications, physical validation is carried out using a physically con-structed rotor model. The VIBXPERT device balances the physical model, confirming the re-liability and efficacy of this approach. This research underscores the practical applicability of ANN-based strategies in effectively addressing rotor imbalance issues, ensuring the longevity and reliability of diverse rotating machinery applications.