Research On Preprocessing Method Of Pipeline Fault Data Based On Magnetic Flux Leakage Internal Detection

With the continuous development of the national economy,the demand for energy is also increasing,in which oil and natural gas are important energy and chemical raw materials.The safe storage and transportation of oil and natural gas are of great significance to the people’s life,industrial generation and national defense construction.In order to ensure the safety of the oil pipeline,the leakage detection technology is used to detect the oil pipeline,and the detection data in the leakage magnetic field is analyzed to determine whether the pipeline is missing.However,before data processing and analysis,magnetic flux leakage data need to be pre-processed to ensure the authenticity and availability of data.The background and significance of the research are first introduced in the thesis.The process of data preprocessing is then introduced.Detailed algorithm design and simulation test for each step of preprocessing are respectively shown.The specific research contents are as follows:Firstly,we design a data validation decision algorithm and data correction algorithm.A three level data sampling algorithm is designed for effectiveness evaluation.Data correction is divided into mileage point correction and baseline correction.Different correction methods are designed.In the baseline correction,a two stage correction method is proposed.Lastly,the algorithms proposed are simulated to evaluate the advantages and disadvantages.Secondly,a data anomaly detection algorithm is designed.In the light of the different features of abnormal data,three different anomaly detection algorithms are designed:anomaly detection algorithm based on threshold segmentation,anomaly detection algorithm based on differential segmentation,and anomaly detection algorithm based on floating form based local STD.The algorithm is simulated to test the accuracy of anomaly detection.Thirdly,a magnetic flux leakage data interpolation algorithm based on LS-KNN is proposed.Firstly,two classical data interpolation algorithms are introduced:three spline interpolation algorithm and classic Kriging interpolation algorithm.Then the LS-KNN interpolation algorithm is designed according to the missing data features.The algorithm is firstly classified by KNN,and LS training samples are modeled according to different kinds of missing data.Two LS linear fitting is used to predict missing values.The three algorithms are simulated,and the interpolation accuracy is compared finally.Fourthly,a magnetic flux leakage data interpolation algorithm based on LSKNNcompressed sensing is proposed.The algorithm is based on the compressed sensing algorithm and the LS-KNN algorithm.The data are firstly processed sparsely according to the data after LSKNN interpolation,and the matrix is then reconstructed to realize the interpolation of missing data.Finally,the three algorithms are simulated and analyzed,and the interpolation accuracy is analyzed.Finally,on the basis of summarizing the whole paper,the future research direction is prospected.