Detection of Damaged Tooth by Support Vector Machines
Gear is one of the most important and commonly used components in machine system. Early detection of gear damage is crucial to prevent the machine system from malfunction. This paper proposes a method for detection of damaged tooth based on support vector machines. Statistical parameters of standard deviation, root mean square value, maximum value and mean value are extracted from the vibration signal as representative features of tooth conditions to be input to the support vector machine classifier. The validity of the presented method is confirmed by the application of detecting early damaged tooth during the cyclic fatigue test. The vibration acceleration on gear box is acquired as original data. Furthermore, the signal of each gear tooth is separately extracted from the signal for a further analysis.The experimental results demonstrate the effectiveness of the proposed method.