An Estimation Method of Defect Size From MFL Image Using Visual Transformation Convolutional Neural Network

• Published in: IEEE transactions on industrial informatics 2019-01, Vol.15 (1), p.213-224
• Main Authors: Lu, Senxiang, Feng, Jian, Zhang, Huaguang, Liu, Jinhai, Wu, Zhenning
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Big Data; Computer simulation; Convolutional neural network (CNN); Data management; Defects; Estimation; fault detection; Feature extraction; Industrial applications; intelligence fault diagnosis; Learning theory; Machine learning; Magnetic dipoles; Magnetic flux; magnetic flux leakage (MFL); Magnetic flux leakage testing; Magnetic resonance imaging; mesher magnetic dipole; Neural networks; Nondestructive testing; Numerical models; Size measurement; Structural integrity; Training; Transformations; visual transformation; Visualization
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2018.2828811

In most current nondestructive testing systems, a magnetic flux leakage (MFL) method is widely used in various industry fields, where the structural integrity of specimens is of vital importance. The estimation of defect size in specimen from the MFL measurements is a key and difficult problem. The traditional methods have low precision because feature extraction procedure relies on prior knowledge and the ability of designer. Inspired by the idea of convolutional neural network (CNN), a novel visual transformation CNN (VT-CNN) is proposed in this paper to overcome the limitation of traditional method in a feature extraction procedure. By adding a visual transformation layer according to the characteristics of the MFL measurements, the VT-CNN can distinguish the defect feature with different sizes more accurately. Moreover, since the VT-CNN method is designed based on the deep learning theory, more industrial big data with accurate label should be used to train the network. Due to the difficulty of making real industrial big data, a novel mesher magnetic dipole model is designed to simulate this industrial process. A large simulated MFL measurement of irregular defects produced by this model can increase the number of training samples and improve the robustness of the network. Experiments to estimate natural corrosion defects on real industrial pipelines are performed to validate the proposed framework. The experimental results are illustrated in detail, which highlights the superiority of the proposed method in industrial applications.