Reconstruction of 3D defect profiles from the MFLT signals by using a radial wavelet basis function neural network iterative model

Xu, Chao; Wang, Changlong; Zuo, Xianzhang; Yuan, Xichao; Ji, Fengzhu
March 2012
Insight: Non-Destructive Testing & Condition Monitoring;Mar2012, Vol. 54 Issue 3, p138
To achieve multi-resolution approximation of 3D defect profile reconstruction from magnetic flux leakage (MFL) signals, a radial wavelet basis function neural network iterative model, which contains a forward model and an inverse model based on a parallel radial wavelet basis function neural network (PRWBFNN), is proposed. The forward model in the loop is to determine the MFL signals for a given set of flaw parameters, and the inverse model is used to predict the profile given the measured value of the MFL signals and acts to constrain the solution space. This approach iteratively adjusts the weights of the inverse network to minimise the error between the measured and predicted values of the MFL signals. The reconstruction results of different defects indicate that significant advantages over other neural network-based defect characterisation schemes could be obtained.


Related Articles

  • Loop-based Flux Formulation for Three-dimensional Magnetostatic Problems. Yan-Lin Li; Sheng Sun; Zu-Hui Ma // Applied Computational Electromagnetics Society Journal;Nov2016, Vol. 31 Issue 11, p1350 

    In this paper, loop basis functions are introduced to expand the magnetic flux density and the magnetostatic subset of Maxwell’s equations are solved in a compact and straightforward manner using finite element method. As linear combinations of div-conforming Schaubert-Wilton-Glisson...

  • Developing a 3D-FEM Model for Electromagnetic Analysis of an Axial Flux Permanent Magnet Machine. Mirimani, Seyyed Mehdi; Vahedi, Abolfazl // Engineering;Apr2010, Vol. 2 Issue 4, p258 

    Recently, many optimal designs for axial flux permanent magnet (AFPM) motors were performed based on finite- element (FE) analysis. Most of the models are based on reduction of 3D problem to 2D problem which is not accurate for design aspects. This paper describes an accurate electromagnetic...

  • 3D Reconstruction Methods Based on Radial Basis Functions for Laser Scanned Data Point Sets. Xiaojun Wu; Yu Wang, Michael; Qi Xia // Computer-Aided Design & Applications;2006, Vol. 3 Issue 1-4, p145 

    Two new approaches of 3D implicit surfaces reconstruction with radial basis functions (RBFs) are proposed in this paper. With the first method, a point set is organized by a balanced binary tree. The cells are controlled to be mildly overlapped and to contain adequate number of points for...

  • Improved 3D full-wave multilevel Green's function interpolation method. Shi, Y.; Chan, C.H. // Electronics Letters;2/3/2011, Vol. 47 Issue 3, p174 

    A subset of infinitely smooth radial basis functions (RBFs), Bessel (BSL) RBF is proposed to improve the computational efficiency of the multilevel Green's function interpolation method for the solution of 3D complex full-wave electromagnetic problems. Numerical results reveal that the...

  • Modeling light propagation in liquid crystal devices with a 3-D full-vector finite-element beam propagation method. Ziogos, Giannis; Kriezis, Emmanouil // Optical & Quantum Electronics;Aug2008, Vol. 40 Issue 10, p733 

    A full-vector finite-element beam propagation method in 3-D is introduced for the simulation of light propagation in liquid crystal (LC) devices. The three electric field components are expressed in terms of mixed finite elements, providing the correct enforcement of boundary conditions....

  • Sensitivity of basal conditions in an inverse model: Vestfonna ice cap, Nordaustlandet/Svalbard. Schäfer, M.; Zwinger, T.; Christoffersen, P.; Gillet-Chaulet, F.; Laakso, K.; Pettersson, R.; Pohjola, V. A.; Strozzi, T.; Moore, J. C. // Cryosphere;2012, Vol. 6 Issue 4, p771 

    The article focuses on the modeling of three-dimensional (3D) flow throughout the whole ice cap with the use of full-Stokes finite element code Elmer/Ice. It involves the use of a Robin inverse method in inferring the basal friction from the observed surface velocities in 1995. It illustrates...

  • Adaptive Meshing of 2D Heterogeneous Objects Using Material Quadtree. Chiu, W. K.; Kou, X. Y.; Tan, S. T. // Computer-Aided Design & Applications;2011, Vol. 8 Issue 2, p289 

    In finite element analysis (FEA), adaptive meshing of an object is usually preferred. With adaptive meshing, geometric accuracies of the mesh and more accurate FEA solution can be achieved while maintaining the computational efficiency. Numerous researches about adaptive meshing have been done...

  • Lagrangian structure of flows in the Chesapeake Bay: challenges and perspectives on the analysis of estuarine flows. Branicki, M.; Malek-Madani, R. // Nonlinear Processes in Geophysics;2010, Vol. 17 Issue 2, p149 

    In this work we discuss applications of Lagrangian techniques to study transport properties of flows generated by shallow water models of estuarine flows. We focus on the flow in the Chesapeake Bay generated by Quoddy (see Lynch and Werner, 1991), a finite-element (shallow water) model adopted...

  • Nonlinear Progressive Damage Analysis of Notched or Bolted Fibre-Reinforced Polymer (FRP) Laminates Based on a Three-Dimensional Strain Failure Criterion. Yue Liu; Zwingmann, Bernd; Schlaich, Mike // Polymers (20734360);Apr2014, Vol. 6 Issue 4, p949 

    Notching and bolting are commonly utilised in connecting fibre-reinforced polymer (FRP) laminates. These mechanical methods are usually superior to other connections, particularly when joining thick composite laminates. Stress distributions, damage modes and ultimate strengths in notched or...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics