<![CDATA[AC motors are critical assets in water treatment plants because they operate continuously to drive key processes. Reactive or schedule-based maintenance can miss early degradation and increase the risk of unplanned downtime. This study presents a field implementation of an Internet of Things (IoT)-based predictive maintenance system in a WTP. The system integrates vibration, temperature, and rotational speed (RPM) sensors with a cloud-based IoT pipeline for real-time data acquisition. Operational data were collected for 30 days from a single motor unit and analyzed using Random Forest and Long Short-Term Memory models. To address limited abnormal-event data, Generative Adversarial Network (GAN)-based augmentation was applied during training. The results show that LSTM performed more consistently than Random Forest; after augmentation, the F1-score improved from 0.92 to 0.95. The monitoring data also captured warning-level changes during operation, including vibration up to 3.9 mm/s, temperature up to 95 °C, and rotational speed dropping to around 1420 RPM, which may indicate abnormal operating conditions requiring inspection. Given the single-unit scope and short duration, the findings are reported as an initial implementation case study. Nevertheless, the work demonstrates the feasibility of a low-cost IoT-based monitoring and prediction framework to support maintenance decisions in WTP operations.]]>
Copyrights © 2025
