Research of Pipeline Leak Eigenvector Extracting Based on Wavelet Packet

As an important part of pipeline safety, pipeline leak detection is usually done by extracting feature vectors of leakage signal. Many researchers used wavelet packet algorithm to extract feature vector, but because of mixing effects of wavelet packet, the acquired feature vector may be not accurate. To solve this problem, the authors propose an improved wavelet packet algorithm to extract the feature vector. The improved algorithm is different from the traditional algorithm in decomposition and reconstruction and the feature vector is constituted by three time-frequency domain parameters. A lot of experiments have been performed to extract feature vector based on the proposed algorithm, with the results showing that the proposed algorithm can overcome the mixing effects and accurately extract the feature vector.