This paper considers the problem of effective feature extraction of acoustic signals from oil and gas pipelines under different working conditions. A feature extraction of pipeline leakage detection method is proposed based on multi-feature entropy fusion and local linear embedding (LLE). First, seven kinds of commonly used entropy which can reflect the characteristics of the signal better are extracted from the pipeline signal through experiments, including permutation entropy, envelope entropy, approximate entropy, fuzzy entropy, energy entropy, sample entropy and dispersion entropy. The seven-dimensional feature vectors are obtained by feature fusion. Second, the LLE algorithm is used to reduce the dimension of the feature vector to complete the secondary feature extraction. Finally, the support vector machine (SVM) is used to identify the working conditions of the pipeline. The experimental results show that, compared with other dimensionality reduction methods, single-feature entropy method and multi-feature entropy fusion method, the proposed method can identify the types of pipeline working conditions effectively and reduce the problems of false negatives and false positives in pipeline leakage detection.

This paper is concerned with the development of improved multi-strategy MPA-VMD method and its application in pipeline leakage detection. Aiming at the shortcomings of the marine predator algorithm (MPA) itself, which has a slow convergence speed and is easy to fall into local optimum, an improved MPA is proposed and used to find two important parameters in variational mode decomposition (VMD), and then dynamic entropy is used to select effective modes. In the initial stage of the population, a good point set strategy is adopted to enhance the search accuracy by increasing the diversity of the initial population; in the search process, a nonlinear convergence factor and the Cauchy distribution are introduced to optimize the predator step size to enhance the global search ability of the algorithm. The ability of the algorithm is enhanced to jump out of the local optimum, and the convergence speed of the algorithm is further improved; the effective mode after VMD is selected by the method of symbolic dynamic entropy. The experimental results show that compared with MPA-VMD, grey wolf optimization-VMD and particle swarm optimization-VMD methods, the devised method has improved signal-to-noise ratio, reduced mean square error and mean absolute error, and has better denoising effect.

This paper is concerned with the pipeline leakage detection problem. A pipeline signal feature extraction method based on improved variational mode decomposition (VMD) and multi-feature fusion are proposed. First of all, the mode number K-value of VMD decomposition is determined by combining the empirical mode decomposition (EMD) method and the centre frequency method. Next, according to the variance contribution rates, the effective mode components are selected from the mode components obtained by VMD, subsequently, the effective mode components are reconstructed to get the de-noised signal. Then, the characteristic parameters that might distinguish the different pipeline signals are selected from different aspects. Moreover, the selected characteristic parameters are formed feature vector to put into support vector machine (SVM) to recognize the different pipeline events. Finally, the laboratory pipeline samples are employed to verify the effectiveness and superiority of the proposed method.

In order to solve the problem of recognition error caused by noise interference in oil and gas pipeline signal and traditional pipeline leakage detection relies on expert experience to extract features manually, an oil and gas pipeline leakage detection model based on deep learning is proposed in this paper. The model consists of data preprocessing part and pattern recognition part. Firstly, a signal denoising algorithm based on variational mode decomposition (VMD) and Manhattan distance (MD) is proposed to reduce the error caused by data quality in the subsequent pattern recognition process. Secondly, combined with the one-dimensional and temporal characteristics of pipeline signal, the signal denoised by VMD-MD algorithm is used as the input of one-dimensional convolution neural network (1DCNN) in deep learning, then the data features are learned independently through the characteristics of network structure. Finally, the network structure and parameters are optimized and analyzed to build the optimal pipeline leakage detection model according to the experiment. The experimental results show that, compared with other existing models, the ensemble VMD-MD-1DCNN model has a better improvement in each evaluation index, which verifies the effectiveness of its application in pipeline leakage detection.