管道漏磁内检测缺陷智能识别

10月 9, 2026 · 2 分钟阅读时长

研究方向 / 方向 5

漏磁（MFL）内检测是油气长输管道腐蚀、裂纹等缺陷检测的主要手段：检测器磁化管壁，缺陷处磁力线外泄，传感器阵列记录三轴漏磁信号。一次内检测产生海量信号，人工判读费时且依赖经验，而带真实开挖标签的缺陷样本又很少。

缺陷识别与量化。 与东南大学王建立教授合作，课题组提出级联深度学习方法：先用预训练 YOLO 网络在漏磁信号图上定位缺陷，再用 Vision Transformer 或多输入并行卷积网络回归缺陷长、宽、深，实现检测与量化一体化。

YOLOv5 与 ViT 级联的漏磁缺陷检测框架
级联深度学习框架：漏磁信号采集与扩增、YOLOv5 快速定位缺陷、ViT 精细分类

样本生成与信号重建。 针对标签样本稀缺，用扩散模型和生成模型合成带标签的漏磁缺陷信号，并建立合成信号质量评价方法，用合成数据提升缺陷检测精度；针对检测器高速运行或通道失效造成的欠采样，提出多先验张量补全方法重建漏磁信号。

漏磁内检测牵拉试验管段与人工缺陷
漏磁内检测牵拉试验：试验管段布置、人工缺陷与检测器

代表性论文（5 篇）

  1. J Xie, J Yang, K Fu, L Tai, X Wang, J Zhu, J Wang. Quantitative Assessment of Pipeline Defects Utilizing a Dual-Stage Deep Learning Framework: Integration of Pretrained YOLO Network and Multi-input Parallel Convolution …. Journal of Pipeline Science and Engineering, 100282, 2025.
  2. J Yang, Y Zhang, C Su, K Fu, J Zhu, J Wang. Multi-Priors Tensor Completion for Highly Under-sampled Magnetic Flux Leakage Signal Reconstruction. Journal of Pipeline Science and Engineering, 100382, 2025.
  3. J Yang, J Xie, X Gao, K Fu, J Zhu, J Wang. Synthetic Magnetic Flux Leakage Signal Generation Using Diffusion Models: A Novel Approach to Improve Pipeline Defect Detection Accuracy. Journal of Pipeline Science and Engineering, 100363, 2025.
  4. X Chen, M Fu, X Liu, J Zhu. Synthesizing Labeled Magnetic Flux Leakage Signals for Pipeline Integrity Assessment: A Generation and Evaluation Methodology. IEEE Transactions on Instrumentation and Measurement, 2025.
  5. P Chen, R Li, K Fu, Z Zhong, J Xie, J Wang, J Zhu. A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data. Mechanical Systems and Signal Processing 206, 110919, 2024.