Predictive Maintenance of Industrial Rotating Equipment Using Supervised Machine Learning

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.