Pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF synergy

Abstract

The invention provides a pipeline defect magnetic flux leakage inversion method based on Adaboost-RBF synergy, relating to the technical field of magnetic flux leakage detection of pipelines. The method comprises the following steps: carrying out magnetic flux leakage detection on standard defects, and carrying out feature extraction; measuring defect shape parameters of front several meters of a pipeline on which to-be-tested defects are located; carrying out the magnetic flux leakage detection on the pipeline on which to-be-tested defects are located, and carrying out feature extraction; determining sample data and to-be-tested data; establishing an Adaboost-RBF neural network initial model; correcting the Adaboost-RBF neural network initial model; and inputting the to-be-tested data into the final model, so as to obtain the shape parameters of the to-be-tested defects, thereby finishing the inversion. By inverting the pipeline defects by virtue of an Adaboost-RBF neural network model, the rapid defect shape reconstitution can be realized, the learning speed is high, the precision is high, the generalization performance is good, and the severity of the defects can be judged, so that the pipeline leakage is prevented, and the loss is avoided.

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