Volume - 7 | Issue - 2 | june 2025
Published
03 June, 2025
Efficient monitoring and control of heavy-duty water motors are essential for optimizing performance, preventing failures, and reducing maintenance costs. This paper presents an IoT-enabled motor health monitoring and remote operation system that integrates real-time sensor data acquisition, predictive maintenance, and automated control. The system employs an Arduino UNO board, ACS720 current sensor, DS18B20 temperature sensor, vibration sensor, and JSN-SR04T ultrasonic sensor to identify motor faults such as phase imbalance, overloads, and dry runs. A YF-S201 flow sensor and water level sensors facilitate effective water supply management. The system includes an LCD display and a web-based dashboard for real-time monitoring. Furthermore, machine learning models, including Linear Regression for efficiency prediction, Random Forest Regression for lifespan estimation, and Logistic Regression for failure detection, enhance predictive maintenance capabilities. The proposed system offers a cost-effective and automated solution for safe and efficient motor operation, thereby improving reliability in pumping stations and household water systems.
KeywordsPredictive Maintenance Remote Motor Operation Machine Learning for Fault Detection Real Time Data Acquisition