A magnetic flux leakage inversion method for pipeline defects based on adaboost-rbf collaboration

Abstract

The invention provides a pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF collaboration, and relates to the technical field of pipeline magnetic flux leakage detection. The method includes: performing magnetic flux leakage detection on standard defects and performing feature extraction; measuring the defect shape parameters several meters in front of the pipeline where the defect to be measured is located; conducting magnetic flux leakage detection on the pipeline where the defect to be measured is located and performing feature extraction; determining the sample data and Data to be tested; establish an initial model of the Adaboost‑RBF neural network; correct the initial model of the Adaboost‑RBF neural network; input the data to be tested into the final model to obtain the shape parameters of the defect to be tested and complete the inversion. This invention uses the Adaboost-RBF neural network model to invert pipeline defects, which can perform rapid defect shape reconstruction, fast learning speed, high accuracy, good generalization performance, and can judge the severity of the defect, thereby preventing pipeline leakage ,avoid lost.

Description

Technical field: [0001] The invention relates to the technical field of pipeline magnetic flux leakage detection, in particular to a pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF collaboration (a combination of Adaboost algorithm and RBF neural network and synergistic effect). Background technique: [0002] Magnetic flux leakage testing is a method of non-destructive testing. Compared with other non-destructive testing methods, it has the advantages of high efficiency, reliability, pollution-free and automation. It is also one of the few methods that can be used for in-pipeline testing. The inversion problem in magnetic flux leakage testing refers to finding out whether there is a defect in the tested material according to the given magnetic field signal data, and to calibrate the position and shape of the defect, so as to realize the visualization of defect detection. However, because the relationship between the signal data and the parameters...

AI Technical Summary

Problems solved by technology

However, due to the complex relationship between the signal data and the parameters of the detected defects, despite the efforts made by researchers over the years, the problem of defect inversion is still a technical difficulty in this field

[0003] In the traditional inversion method, the defect inversion method based on finite element method calculates the artificially given defect magnetic flux leakage signal through the finite element method, compares it with the unknown defect magnetic flux leakage signal, and continuously adjusts the given defect size to obtain the unknown defect. Although this method has high accuracy, it is very dependent on the operator's detection experience, and it takes a long time and consumes high resources; the defect inversion method based on the RBF radial basis neural network is based on the relationship between the known defect signal and the defect size , by establishing the RBF neural network model, and then obtaining the size of the unknown defect through the measured signal data of the unknown defect and the RBF model. The defect inversion method of the element calculates the signal data of defects of various specifications through the finite element method, builds a defect database, and then uses the RBF neural network to learn the characteristics of the database data, and then calculates the signal data of artificially given defect sizes through this model, Compared with the measured signal data of unknown defects and corrected, the size of unknown defects can be obtained. This method not only improves the calculation speed, but also has better accuracy, but its accuracy is more dependent on the initial parameters of artificially given defects.

Images