Predictive maintenance of planetary gearboxes using FFT and machine learning technique

Planetary gearboxes are widely used in manufacturing processes, and non-destructive assessment is becoming increasingly important for monitoring their state. We outlined a fine-tuned random decision tree (FT-RDT) this study classifying fault-finding the gearbox via signals generated by vibrations. This approach concentrates on identification of worn gears, consequently distinct classes—healthy ringed gears containing damaged tooth faces, planetary featuring faces—were established. Each categories consists 150 specimens, divided into two separate sets 50 specimens testing data 100 training. The Fast Fourier Transform (FFT) was to convert temporal frequencies. next step gather 24 statistical characteristics from frequency data. retrieved characteristic fed fault classification procedure (FT-RDT). Combining these methods yields rates accuracy across train test 92.75% 91.50%, demonstrating excellent reliability capability problem solution that created.