Cloud Enabled Predictive Maintenance Tool for Induction Motor

Predictive maintenance is to foresee the failures and to take the preemptive actions. The recent advancements in cloud storage have provided an incredible opening to store the data coming from different sources such as factories, buildings, machines and sensors. The stored data are not only used to monitor the devices connected with the cloud but used to predict the failure of the devices in advance. The proposed system is to predict the failure of an induction motor and to schedule the preventive maintenance. Usually, induction motors are widely used in conveyer belts, elevators, compressors and pumps etc. The productivity of an induction motor can be increased by decreasing the fault occurrence. The various parameters which affect the performance are voltage, current, vibration, speed, power factor and frequency. Accelerometer is used for finding the vibration of the motor. Current sensor, voltage sensor and speed sensor are used to measure current, voltage and speed of the induction motor. The values from the sensors are digitized and stored in the cloud for further processing. Machine Learning (ML) based predictive model is developed based on the historical data from the sensors during normal and abnormal conditions of the induction motor. The induction motor's behavior is continuously monitored with respect to current operating characteristics. This can be monitored remotely in a dashboard using PC, Tablets or Mobile. The ML prediction algorithm generates the maintenance call automatically and thus eliminates the breakdown.