In diagnosing mechanical faults of rotating machinery, it is very important to know the vibration feature of the machine with various forms of fault. A rotor system with fault is generally a complicated non-linear vibrating system. Its vibration is in a very complex form. Rotating machinery is very popular in industrial applications. Most of the mechanical failures are due to vibrations. It is more so in case of rotating machinery. Main cause of vibrations is faults in the rotating systems like unbalance, looseness, etc. In this paper Artificial Neural Networks (ANN) are used to identify unbalance and looseness in rotor bearing system. Here it is considered as two class classification problem. Experiments are conducted to collect the vibration data in both horizontal and vertical directions, from the rotating system. Statistical features are extracted from the vibration data and fed to neural networks for classifying the unbalance and looseness. These results are useful for making maintenance decision.