Enhancing Fault Diagnosis in IoT Sensor Data through Advanced Preprocessing Techniques

Through innovation in the data collection environment, data-driven fault diagnosis has become increasingly important. This study aims to develop an algorithm to improve the accuracy of fault diagnosis based on Internet of Things (IoT) sensor data. In this research, current data collected through IoT sensors is utilized, focusing on diagnosing four states: bearing defects, shaft misalignment, rotor imbalance, and belt looseness. Additionally, to enhance the efficiency of the fault diagnosis algorithm, we introduce a preprocessing technique that utilizes descriptive statistics to reduce the data dimensionality. The experiments are conducted based on current data and vibration data, ensuring reliability from both types of data. The experimental results indicate a significant improvement in the accuracy and computational time of the fault diagnosis algorithm. After experimenting with various candidate algorithms, XGBoost version 1.7.6 exhibited the highest performance of classification. This research contributes to enhancing safety and reliability based on IoT sensors and suggests potential applications in the field of fault diagnosis.