Research on magnetic flux leakage testing of pipelines by finite element simulation combined with artificial neural network

Abstract

Magnetic flux leakage (MFL) testing technology is widely employed in non-destructive testing of pipelines, and the analysis of leakage signals plays a crucial role in assessing pipelinea safety. This paper introduces a novel approach for MFL testing, which combines finite element simulation with artificial neural networks. First, a finite element model for MFL testing of defects is established, the influence of magnetization states on MFL signals is discussed, and the variation of signal extremum with magnetization intensity is analyzed. Next, suitable MFL signal features are selected to focus on the relationship between defect types, defect sizes, and these features. Finally, a kernel extreme learning machine (KELM) predictive model is developed to classify defect types and predict defect sizes. The results indicate that as magnetization intensity increases, the magnetization process of the pipeline can be divided into a nonlinear growth phase and a linear phase, with MFL signal extremum rapidly increasing and then gradually growing linearly. Different geometric features of defects correspond to distinct distributions of MFL signals, effectively reflecting variations in defect types and sizes. Compared to traditional ELM models, the KELM model achieves higher prediction accuracy and stable performance, with the radial basis kernel function significantly enhancing the generalization and predictive capabilities of the neural network.