Volume 2 - Issue 2, March - April 2026

Vibration is one of the major parameters to consider in condition monitoring of rotating system. If an undetected fault is noticed in the rotating system, then it may result in down-time, expensive damage, injury, or even life loss, therefore early fault identification is a critical factor in ensuring and extending the working life of the rotating systems. This paper investigates the vibrations generated in rotor bearing systems due to the combined effect of unbalance and bearing faults. A mathematical model using dimensional analysis (Buckingham's π theorem) is developed to predict vibration responses. Experiments are conducted on a rotor-bearing test rig with artificially created bearing faults (0.35 mm to 1 mm) using electric discharge machining, under various speeds (720-2880 RPM) and unbalance loads (0-165 g). Vibration signals are analyzed using Fast Fourier Transform (FFT), and statistical features (RMS, kurtosis, crest factor, skewness, mean, standard deviation, variance, median) are extracted. An Artificial Neural Network (ANN) algorithm is developed for fault diagnosis. Results show that combined faults produce distinct vibration signatures with amplitude peaks occurring at Ball Pass Frequency of Outer Race (BPFO) and its harmonics. The ANN model demonstrates effective classification of fault severity and unbalance conditions. The proposed methodology provides a reliable approach for early fault detection in industrial rotating machinery.

Mr.Pravin G. Patil, Prof.P.S.Ladgaonkar,"Dynamic Analysis of Rotor Bearing System with Combined Unbalance and Bearing Fault" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(2): Page(1551-1558) Mar-Apr 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.