<![CDATA[Induction motors are essential components in industrial systems, where bearing failures can cause increased vibration, overheating, reduced performance, and unexpected production downtime. Conventional monitoring methods are generally manual and periodic, limiting the ability to detect early signs of failure in real time. This study aims to develop an Internet of Things (IoT)-based monitoring and early fault detection system for induction motor bearings using a DS18B20 temperature sensor, ADXL345 vibration sensor, ESP32 microcontroller, Blynk cloud platform, and a risk score decision method. The research employed a research and development (R&D) approach with a prototyping model to design and evaluate the proposed system. Experimental results showed that the DS18B20 sensor was able to detect temperature changes properly, while the ADXL345 sensor successfully measured vibration changes with readings relatively close to reference instruments. The Blynk platform successfully displayed temperature and vibration monitoring data in real time, although minor delays were observed due to network conditions. System testing under four simulated operating conditions confirmed that the risk score method successfully classified motor conditions into normal, warning, danger, and shutdown categories according to predefined thresholds. The developed system demonstrates the potential to support continuous monitoring and early fault detection of induction motor bearings, contributing to more effective preventive maintenance in industrial applications.]]>
