Dynamic-Balance Monitoring Scheme for Industrial Fans using Neural-Network based Machine Learning Approach

Abstract

Dynamic balancing is a very essential and commonly used technique for the rotating equipment, specially for induced draft (ID) fans of industries. Dynamic balancing is an offline condition monitoring technique which is done when there is unbalance in the rotating part of the equipment. The unbalance of a single impeller of ID fan will result in high vibration problem to the whole ID fan and also to the motors which are in physical contact with the vibrating ID fan. Due to high vibration, the rotating ID fan impeller may get damaged. Therefore, dynamic balancing is done in the ID fan impellers on maintenance schedule basis or when there is increased vibration observed on the online monitoring system. This process takes a long time to diagnose and locate the point of unbalance and it is very dangerous for the maintenance team to visit the restricted areas of the plants where these huge fans are placed for the plant process. To avoid these issues, this paper proposes a new dynamic-balance monitoring (DBM) scheme for getting useful information regarding dynamic balancing for industrial fans using convolution neural-network (CNN) based machine learning approach and Fast Fourier transform (FFT). The historical data is used to train the proposed algorithm. The technique is valid for DBM of all rotating industrial machinery and previously it was not done in any literature.