BearingFaultDetection

This project introduces a CNN-based approach for bearing fault prediction using vibration signals. Our model effectively identifies various bearing fault types with high accuracy and reliability. This work has the potential to revolutionize predictive maintenance in industrial settings by providing early fault detection, thereby preventing costly downtimes, production losses, and safety hazards. Timely fault identification also allows for proactive maintenance scheduling, optimizing resource allocation and minimizing operational disruptions. The project successfully implemented a machine learning approach to detect and classify faults in aircraft bearings. The use of a Random Forest classifier, along with detailed feature extraction and visualization, provided robust and reliable fault detection, crucial for maintaining the safety and reliability of aircraft machinery.