Mechanical failure classification for spherical roller bearing ofhydraulic injection molding machine using DWT–SVM

This paper presents a combined discrete wavelet transform (DWT) and support vector machine (SVM) technique for mechanical failure classification of spherical roller bearing application in high performance hydraulic injection molding machine. The proposed technique consists of preprocessing the mechanical failure vibration signal samples using Db2 discrete wavelet transform at the fourth level of decomposition of vibration signal for mechanical failure classification. After feature extraction from vibration signal, support vector machine is used for decision of mechanical failure types of the spherical roller bearing. The classification results indicate the effectiveness of the combined DWT and SVM based technique for mechanical failure classification of hydraulic injection molding machine.