Scholarlink

Alternating current field measurement (ACFM) technology is an emerging nondestructive testing method, which has been used widely in oil industry for detecting and evaluating of surface cracks on structures. It is hard to achieve real-time and high-precision cracks inversion for ACFM based on traditional characteristic signals. In this paper, based on the finite element method (FEM) model of electromagnetic coupling ACFM probe, the energy spectrum and phase threshold determination method is present to obtain the crack characteristic signals in real time. The real-time and high- precision cracks inversion system for ACFM is set up and verified by artificial cracks. The length and depth of cracks are calculated using the characteristic signals obtained from experiments based the Genetic Algorithm (GA) and Back Propagation (BP) neural network real-time and high- precision cracks inversion algorithm. The results show that the FEM model of electromagnetic coupling ACFM probe can simulate the characteristic signals perfectively. The energy spectrum and phase threshold determination method can obtain the crack characteristic signals in real time. The GA-BP neural network can invert the length and depth of crack perfectly and the relative error of inversion accuracy is less than 10%.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on Real-time and High-Precision Cracks Inversion Algorithm for ACFM Based on GA-BP Neural Network

  • 章节

  • 出版模式：

    开放获取

  • 发表日期：

    2025年

查看全文
  • Wei Li,
  • Xin’an Yuan,
  • Jianming Zhao,
  • Xiaokang Yin,
  • Xiao Li

摘要

Alternating current field measurement (ACFM) technology is an emerging nondestructive testing method, which has been used widely in oil industry for detecting and evaluating of surface cracks on structures. It is hard to achieve real-time and high-precision cracks inversion for ACFM based on traditional characteristic signals. In this paper, based on the finite element method (FEM) model of electromagnetic coupling ACFM probe, the energy spectrum and phase threshold determination method is present to obtain the crack characteristic signals in real time. The real-time and high- precision cracks inversion system for ACFM is set up and verified by artificial cracks. The length and depth of cracks are calculated using the characteristic signals obtained from experiments based the Genetic Algorithm (GA) and Back Propagation (BP) neural network real-time and high- precision cracks inversion algorithm. The results show that the FEM model of electromagnetic coupling ACFM probe can simulate the characteristic signals perfectively. The energy spectrum and phase threshold determination method can obtain the crack characteristic signals in real time. The GA-BP neural network can invert the length and depth of crack perfectly and the relative error of inversion accuracy is less than 10%.