Novel leakage detection by ensemble 1DCNN-VAPSO-SVM in oil and gas pipeline systems

In this paper, a novel ensemble model of one-dimensional convolution neural network (1DCNN) and support vector machine (SVM) is proposed to improve the detection accuracy in the process of pipeline leakage detection. Firstly, 1DCNN is constructed by experiments on different network structures and parameters, and it is used to extract data features adaptively. Then, an improved particle swarm optimization (PSO) algorithm is put forward, called variable amplitude PSO (VAPSO), with the adjustment strategy of parameter variable amplitude vibration to optimize the parameter combination in SVM and decrease the risk of trapping into local optimum in the training process. Finally, the data features extracted adaptively from the network are input into the improved VAPSO-SVM to classify. It is demonstrated by the experimental results that, compared with the existing models, the developed ensemble model has the capacity to extract the features of pipeline data more quickly and accurately with effective improvement in the classification accuracy, and has better robustness in the process of pipeline leakage detection. • The deep learning method is used to extract features adaptively. • Improve PSO algorithm with adjusting parameter variable amplitude vibration (VAPSO). • The proposed VAPSO algorithm is used to optimize the parameters of SVM. • The ensemble 1DCNN-VAPSO-SVM model is proposed. • Input features extracted from 1DCNN into improved SVM for pipeline leakage detection.