The integration of IoT (Internet of Things) technology in industrial maintenance is transforming machine condition monitoring by enabling real time data acquisition and predictive maintenance. This work presents an IoT-based remote monitoring system for blowers in wastewater treatment plants, utilising a Total Degradation Number (TDN) sensor for oil condition assessment, existing vibration sensors, and oil temperature monitoring.
The system continuously tracks critical blower parameters, including the TDN to evaluate oil degradation, oil temperature, vibration levels, and operational runtime. By applying high-frequency AC waveforms, the TDN sensor accurately measures oil capacitance and conductance, deriving the TDN as a simplified index of oil health. Sensor data is seamlessly collected, transmitted to a cloud platform, and displayed on an intuitive dashboard that provides real-time visualization and automated alerts for abnormal conditions.

Field testing in an operational wastewater treatment facility demonstrates the system’s effectiveness in early fault detection, reducing unexpected failures, and optimizing maintenance schedules. The proposed solution enhances equipment reliability, minimizes breakdowns, and extends machine lifespan. Future developments will explore the integration of machine learning algorithms to further refine predictive capabilities and improve overall system performance.