Zhang Yong
1.Northeast Petroleum University Physics and Electronic Engineering，Daqing 163318，China； 2.Northeast Petroleum University Artificial Intelligence Energy Research Institute，Daqing 163318，ChinaYang Wenwu
1.Northeast Petroleum University Physics and Electronic Engineering，Daqing 163318，China； 2.Northeast Petroleum University Artificial Intelligence Energy Research Institute，Daqing 163318，ChinaWang Mingji
Northeast Petroleum University Physics and Electronic Engineering，Daqing 163318，ChinaSun Tong
2.Northeast Petroleum University Artificial Intelligence Energy Research Institute，Daqing 163318，China； 3.Key Laboratory of Networking and Intelligent Control of Heilongjiang Province，Daqing 163318，ChinaLiu Jie
1.Northeast Petroleum University Physics and Electronic Engineering，Daqing 163318，China； 2.Northeast Petroleum University Artificial Intelligence Energy Research Institute，Daqing 163318，ChinaZhou Xingda
1.Northeast Petroleum University Physics and Electronic Engineering，Daqing 163318，China； 2.Northeast Petroleum University Artificial Intelligence Energy Research Institute，Daqing 163318，China1.Northeast Petroleum University Physics and Electronic Engineering，Daqing 163318，China; 2.Northeast Petroleum University Artificial Intelligence Energy Research Institute，Daqing 163318，China; 3.Key Laboratory of Networking and Intelligent Control of Heilongjiang Province，Daqing 163318，China
TE832
Aiming at the difficulty in extracting the feature information of the leakage signal in the process of long-distance oil and gas pipeline leakage detection, a new pipeline negative pressure wave signal feature extraction method is proposed. A complete set of empirical mode decomposition algorithm with adaptive noise is used to denoise the collected negative pressure wave signal, and the Hausdorff distance between the probability density of the component after CEEMDAN decomposition and the original signal is evaluated. Select the effective mode and reconstruct. The cloud model feature entropy and kurtosis of the reconstructed signal are calculated as feature parameters, and the support vector machine is used for classification and recognition. Through laboratory data verification, the method of combining CEEMDAN, Hausdorff distance and cloud model feature entropy can effectively improve the accuracy of oil and gas pipeline leak detection, and realize the identification of small leak signals with a flow rate of less than 4^3m/h. Certain field application value.
