Research On MR-EMD Noise Reduction And Feature Extraction Method Of Oil And Gas Pipeline Defect Signal

With the development of oil and gas industry in China,pipeline transportation is widely used in oil and gas industry.However,due to the impact of multiple factors,the pipeline has defects,and even leakage,then there are serious consequences such as fire,casualties and so on.Therefore,it is of great practical significance to study defect detection methods for oil and gas pipelines,in order to identify defects quickly,master the integrity status of pipelines and ensure safe operation.In this paper,the method of pulsed magnetic eddy current detection is used to detect defects in oil and gas pipelines,and the methods of signal noise reduction,feature extraction and classification are studied,which realize the classification and recognition of defects,and the methods have the highest accurancy.(1)Based on the analysis of traditional noise reduction methods,a noise reduction method based on the combination of mean removal and EMD has been proposed.The noise energy in the signal was firstly reduced by means of mean removal,and then the noise was reduced by EMD.The results show that this method can remove the noise in the signal very well and preserve the mutation characteristics of the signal completely.(2)The processed signals have been decomposed by EMD,and the IMF containing useful information has been selected for feature extraction.After standardization,PCA was used to reduce the dimension of feature matrix,remove redundant information and construct a new sample matrix.Finally,the support vector machine based on RBF is used to realize defect recognition and classification.(3)The signal processing and analysis method proposed in this paper is applied to the signal analysis of pipeline defects measured on the spot.The results show that the accuracy of normal and defect sample identification is up to 97.09%,and the accuracy of crack and hole defect identification is up to 88.56%,which is higher than the traditional analysis method.In conclusion,the research content of this paper provides theoretical support and reference for defect detection of oil and gas pipelines.