Efficient Fault Classification in Rotating Machinery Using the K-Nearest Neighbor Algorithm

Rotating machines are widely used in industries. Rolling bearings, which are essential components of these ma-chines, are prone to damage. Therefore, diagnosing faults in rolling bearings quickly and accurately is crucial for maintenance purposes. Machine learning has become a very effective tool for diagnosing faults in rolling bearings. The KNN Algorithm is one such technique that effectively categorizes faults. This study proposes an intelligent fault classification system for bearing faults based on the KNN Algorithm. The proposed model accurately identifies different types of fault conditions in rolling bearings. Our proposed model achieves superior results and has been compared with existing methods.