Intelligent leak level recognition of gas pipeline valve using wavelet packet energy and support vector machine model

This paper presents an acoustical signal analysis scheme model for intelligent recognition of the leak level of a gas pipeline valve. The scheme is based on wavelet packet energy theory and a support vector machine (SVM) model. In this approach, the acoustical signal of the leak is obtained using an acoustic emission (AE) sensor. The energy of each node at the fourth level of the wavelet packet decomposed signal is extracted as a leak feature for the SVM classification process. SVM is applied to perform recognition of the leak level and the performance of the classification process due to the kernel function for the SVM and classifier is evaluated in terms of its accuracy, Cohen's kappa and training time. The experimental results demonstrate that the intelligent recognition model based on the wavelet packet energy feature parameter and SVM classifier (with linear kernel function) is optimal for recognising the leak level of a gas pipeline valve.