Three-dimensional magnetic flux leakage inspection and defect compound inversion imaging method

Abstract

The invention provides a three-dimensional magnetic flux leakage inspection and defect compound inversion imaging method. The method comprises the following steps: selecting an imaging area from a pipeline to be detected; scanning the pipeline to be detected to obtain a final three-dimensional magnetic flux leakage field detecting value; analyzing the three-dimensional magnetic flux leakage field detecting value according to the principal component analysis to obtain actual eigenvalue vectors corresponding to a plurality of eigenvalues; determining the opening outline of a defect, and building a three-dimensional outline strip model of the defect; building a forward radial basis function nerve network model; inputting an initial depth vector into the forward radial basis function nerve network model to obtain forecasted eigenvalue vectors corresponding to the eigenvalues; if the difference between the actual eigenvalue vectors and the forecasted eigenvalue vectors is smaller than an error threshold, carrying out inversion imaging, otherwise, modifying the initial depth vector, and continuing iterative operation till the difference between the actual eigenvalue vectors and the forecasted eigenvalue vectors is smaller than or equal to the error threshold. The method is more targeted and good in stability, is helpful to reduce the calculated amount and improves the imaging precision.

Description

technical field [0001] The invention relates to the technical field of nondestructive testing, in particular to a neural network iterative inversion imaging method for three-dimensional magnetic flux leakage testing defects. Background technique [0002] Magnetic flux leakage testing is a more commonly used non-destructive testing method, which is widely used in the quality testing and safety monitoring of ferromagnetic materials such as oil and gas pipelines, storage tank floors, and steel wire ropes. In recent years, with the continuous improvement and improvement of defect quantification technology, people hope that the distribution of pipeline corrosion defects can be transformed into graphics and images that can be directly recognized by the naked eye, so as to realize defect imaging. However, due to the complex nonlinear relationship between defect shape and magnetic flux leakage signal, defect imaging has become a difficult and hot spot in the current research of magn...

AI Technical Summary

Problems solved by technology

For example, the MFL defect reconstruction method based on the cuckoo search and particle filter hybrid algorithm can accurately realize the defect contour reconstruction to a certain extent, especially reduce signal noise and improve the robustness of the iterative method to noise, but still It is the two-dimensional reconstruction of the defect contour, and the calculation model is too complicated and the efficiency is not high

Images