大口徑管道裂紋缺陷漏磁數(shù)據(jù)生成與評估方法

打開文本圖片集
Chen Ximing,Li Kun,F(xiàn)u Mengkai,etal.A method for generating and evaluating magnetic flux leakage data for large-diameterpipelinecrack defectsbasedonnumericalsimulationanddiffusionalgorithm[J].China Petroleum Machinery,2025,53(7):1-11.
AMethod for Generating and Evaluating Magnetic FluxLeakage DataforLarge-diameter Pipeline Crack DefectsBased on Numerical Simulation and Diffusion Algorithm
Chen Ximing Li KunFu Mengkai Zhu Jianjun Liu Xiaoben (CollegeofMechanical andTransportation Engineering,China UniversityofPetroleum(Beijing))
Abstract:Considering that the sample size of magnetic flux leakage(MFL)data forlarge-diameter pipeline crack defects is insufficient tosupport the quantitative identification,a database generation method integrating numerical simulation of MFL fieldanddifusion algorithm was proposed,and it was verified through full-scale pul test and thre-dimensional MFL simulation modeling.The results show that the crack defect size hasa clear impact on the MFL signal.For the axial component,the peak value is positivelycorrelated withthe defectdepth,and the troughspacing is positively corelated with the defectlength.Fortheradial component,which shows anantisymmetric distribution,the absolute peak value is positively correlated with the depth,and the spacing between the positive and negative peaks is positively correlated with the length.Theaccuracy of the three-dimensional MFL simulation model reaches the engineering requirement (average error 45% ),and 24O groups of crack defect simulation databases wereconstructed.The data generated from the diffusion model have the same distribution as the simulation data.Afteroptimizing themodelbasedonthe pulltestdatawith environmentalnoise,75.4%of the generated datapass theKNN test( K=5 ),and have the feature distribution highly similar to the real data.The research conclusions provide a basis of MFL data for the quantitative evaluation of pipeline crack defects.
Keywords: Large-diameter pipeline;crack defect;magnetic flux leakage defct;ful-scale pulltest; finite ele ment simulation;diffusion model
0引言
油氣管道隨著運行時間的延長不可避免地會產(chǎn)生腐蝕或裂紋等缺陷,其中裂紋缺陷在疲勞或應(yīng)力腐蝕的作用下易導(dǎo)致管道破裂失效[。(剩余13420字)