Feature Extraction of Fault Engine Audio Signal Based on Wavelet Packet Transform

摘要

Due to the different structure of the machine parts,machine vibrations sent audio signal have different frequency.The early defect,audio signal can be analyzed well by wavelet packet transform.Aiter wavelet packet decomposition and reconstruction,Audio signal noise reduced.And then through high and low frequency decomposition,we can constitute the energy characteristics.The experiment shows:the extracted features have good structure.