Signal Classification for Pipeline Security Threat Event Based on Optimized Support Vector Machine

Abstract

The way of efficiently classifying the manual digging, machine excavation, vehicle passing and other pipeline security threats, is an imperative problem for optical fiber pipeline security warning system. To solve this problem, a security threats classification method based on optimized support vector machine is proposed. In this method, after feature extraction based on wavelet to the original vibration signal, the artificial bee colony algorithm is introduced to optimize the penalty factor and kernel parameter of support vector machine under specified fitness function, and the optimized support vector machine is used to classify the pipeline security threats. To testify the performance of the proposed method, the experiment based on UCI feature datasets and actual vibration signal are made. Comparing with the support vector machine optimized by other algorithms, higher classification accuracy and less time consumption is achieved by the proposed method. Therefore, the effectiveness and the engineering application value of this proposed method is testified.