The existence of rotating components such as bearings, gears, and shafts contributes to the health degradation of industrial equipment such as motors and fans, which can lead to complete failure or breakdown of the equipment if not addressed promptly. With the aid of different machine learning techniques and algorithms, early defect identification, diagnosis, and prognosis of equipment are now feasible, leading to comprehensive condition monitoring and predictive maintenance of the equipment. This chapter describes a regression-based prediction model that can forecast equipment health and is effective in estimating the remaining usable life. A case study using gearbox sensor data from an industrial fan-motor system has been used to validate the concept. It is observed that the proposed model can predict the fault accurately and is capable of suggesting the appropriate operating conditions for the equipment to increase its useful life and get more time for the maintenance plan.

Online condition monitoring and predictive maintenance are crucial for the safe operation of equipments. This paper highlights an unsupervised statistical algorithm based on principal component analysis (PCA) for the predictive maintenance of industrial induced draft (ID) fan. The high vibration issues in ID fans cause the failure of the impellers and, sometimes, the complete breakdown of the fan-motor system. The condition monitoring system of the equipment should be reliable and avoid such a sudden breakdown or faults in the equipment. The proposed technique predicts the fault of the ID fan-motor system, being applicable for other rotating industrial equipment, and also for which the failure data, or historical data, is not available. The major problem in the industry is the monitoring of each and every machinery individually. To avoid this problem, three identical ID fans are monitored together using the proposed technique. This helps in the prediction of the faulty part and also the time left for the complete breakdown of the fan-motor system. This helps in forecasting the maintenance schedule for the equipment before breakdown. From the results, it is observed that the PCA-based technique is a good fit for early fault detection and getting alarmed under fault condition as compared with the conventional methods, including signal trend and fast Fourier transform (FFT) analysis.

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.

1. Farley T, Rogers S, Nardini D. Understanding Mill Vibration Phenomena. Innoval Technology Limited, 2008. Google Scholar