论文信息 - Three-dimensional defect inversion from magnetic flux leakage signals using iterative neural network

Three-dimensional defect inversion from magnetic flux leakage signals using iterative neural network

Defect inversion is of special interest to magnetic flux leakage (MFL) inspection in industry. This study proposes an iterative neural network to reconstruct three-dimensional defect profiles from three-axial MFL signals in pipeline inspection. A radial basis function neural network is utilised as the forward model to predict the MFL signals given a defect profile, and the defect profile gets updated based on a combination of gradient descent and simulated annealing in the iterative inversion procedure. Accuracy of the proposed inversion procedure is demonstrated in estimating the profile of different defects in steel pipes. Experimental result based on three-axial simulated MFL data also shows that the proposed inversion approach is robust even in presence of reasonable noise.

[1] Noritaka Yusa,et al. Some advances in numerical analysis techniques for quantitative electromagnetic nondestructive evaluation , 2009 .

[2] Lalita Udpa,et al. Neural network-based inversion algorithms in magnetic flux leakage nondestructive evaluation , 2003 .

[3] Liu Gang,et al. Oil-Gas Pipeline Magnetic Flux Leakage Testing Defect Reconstruction Based on Support Vector Machine , 2009, 2009 Second International Conference on Intelligent Computation Technology and Automation.

[4] Lalita Udpa,et al. Electromagnetic NDE signal inversion by function-approximation neural networks , 2002 .

[5] Peiwen Que,et al. 2D defect reconstruction from MFL signals by a genetic optimization algorithm , 2005, 2005 IEEE International Conference on Industrial Technology.