Monitoring Three Phase Induction Motor Performance for Predictive maintenance Using IoT and ML

Abstract

Fault detection and performance monitoring are vital on 3-phase induction motors for early detection and preventing serious infrastructure damage in manufacturing environments. They improve safety, credibility, and availability as well as lower the cost of maintenance for modern industrial systems. Despite the fact that it is affordable, dependable, and sturdy, 3-phase induction motors have been widely used in many industrial operations. However, monitoring and fault detection alone for 3 phase induction motor, may not be helpful on how to efficiently correct the fault and can result on long downtime for a technician to easily find solution. This system is a method for doing predictive maintenance by utilizing IoT sensors and ML to monitor the performance of a three-phase induction motor and provide possible quick solution when a certain fault is detected. The system is made up of sensors attached on the motor to detect temperature, vibration, speed, current, and voltage parameters. After sensing, they send the data to an Arduino Uno for real time analysis. The data is run through the ML algorithms to forecast the motor's performance and identify any irregularities or defects and provides a quick guide to correct it. This system makes it possible to identify potential motor problems before they escalate and require costly downtime and repairs. For potential areas for development, the data gathered by the sensors could be used to improve the performance of the motor. A three-phase induction motor was used to test the proposed system, and the findings was to demonstrate the effectiveness in tracking the motor's operation, spotting irregularities and suggest a solution. In conclusion, the method for tracking a three-phase induction motor's performance using IoT and ML was a used as a tool for predictive maintenance that saves maintenance expenses, increase motor longevity, increase accuracy, and decrease downtime.