基于自适应遗传算法的LS—SVM漏磁缺陷重构

Defect Reconstruction from Magnetic Flux Leakage Signals Based on AGA-LS-SVM

提出基于自适应遗传算法的最小二乘支持向量机算法（AGA-LS-SVM）的新方法，用于二维缺陷重构，建立由缺陷的漏磁信号到缺陷二维轮廓的映射关系。该方法实现人工裂纹缺陷的二维轮廓的重构，试验结果表明，该方法具有速度快、精度高和很好的泛化能力，为漏磁检测定量化提供了一种可行的方法。

A new method for the reconstruction of 2-D profiles is presented based on the adaptive genetic algorithm and the least squares support vector machines technique （AGA-LS-SVM） and the mapping relationship from MFL signals to 2-D profiles of defects is established. The reconstruction of 2-D profiles of artificial crack defects in the magnetic flux leakage testing is implemented by this algorithm. The results show that LS-SVM possesses quick speed, high accuracy and very good generalization ability and it is a good way for the quantification of the MFL testing.