Diagnosis Model of Pipeline Cracks According to Metal Magnetic MemorySignals Based on Adaptive Genetic Algorithm and Support VectorMachine

摘要

Metal magnetic memory (MMM) signals can reflect stress concentration and cracks on the surface offerromagnetic components, but the traditional criteria used to distinguish the locations of these stress concentrations andcracks are not sufficiently accurate. In this study, 22 indices were extracted from the original MMM signals, and thediagnosis results of 4 kernel functions of support vector machine (SVM) were compared. Of these 4, the radial basisfunction (RBF) kernel performed the best in the simulations, with a diagnostic accuracy of 94.03%. Using the principlesof adaptive genetic algorithms (AGA), a combined AGA-SVM diagnosis model was created, resulting in an improvementin accuracy to 95.52%, using the same training and test sets as those used in the simulation of SVM with an RBF kernel.The results show that AGA-SVM can accurately distinguish stress concentrations and cracks from normal points, enablingthem to be located more accurately.