Defect Profile Reconstruction Research Articles

Induced Current Thermo-Electrical Impedance Tomography for Nonferromagnetic Metal Material Surface Defect Profile Reconstruction

Nonferromagnetic metal materials are widely used in industry. Defects generated during manufacture and use may lead to serious accidents. The defect reconstruction is important for nondestructive evaluation. Eddy current pulsed thermography (ECPT) is a well-known nondestructive testing and evaluation method, but hardly reconstruct fully defect profile. Electrical impedance tomography (EIT) shows promising potential in defect profile reconstruction, but suffers from electrode number limitation. In this paper, EIT is introduced to ECPT image sequences processing, and a new method, induced current thermo-electrical impedance tomography (ICTEIT), is developed. The proposed method takes each infrared camera pixel as a virtual electrode, captures the electric current distribution with spatial resolution as high as camera, and reconstructs conductivity distribution at pixel level from which the defect profile can be identified. Experiments with different defects are carried out to verify the performance of the proposed method.

Automatic reconstruction of irregular shape defects in pulsed thermography using deep learning neural network

Quantitative defect and damage reconstruction play a critical role in industrial quality management. Accurate defect characterisation in Infrared Thermography (IRT), as one of the widely used Non-Destructive Testing (NDT) techniques, always demands adequate pre-knowledge which poses a challenge to automatic decision-making in maintenance. This paper presents an automatic and accurate defect profile reconstruction method, taking advantage of deep learning Neural Networks (NN). Initially, a fast Finite Element Modelling (FEM) simulation of IRT is introduced for defective specimen simulation. Mask Region-based Convolution NN (Mask-RCNN) is proposed to detect and segment the defect using a single thermal frame. A dataset with a single-type-shape defect is tested to validate the feasibility. Then, a dataset with three mixed shapes of defect is inspected to evaluate the method’s capability on the defect profile reconstruction, where an accuracy over 90% on Intersection over Union (IoU) is achieved. The results are compared with several state-of-the-art of post-processing methods in IRT to demonstrate the superiority at detailed defect corners and edges. This research lays solid evidence that AI deep learning algorithms can be utilised to provide accurate defect profile reconstruction in thermography NDT, which will contribute to the research community in material degradation analysis and structural health monitoring.

Defect reconstruction of magnetic flux leakage measurements based on single dimension PSO algorithm

Magnetic flux leakage (MFL) detection is widely used in the technology of oil and gas pipeline intelligent detection at present. For the defect reconstruction problem in MFL detection, a new improved particle swarm optimization (PSO) algorithm, called SDPSO, is introduced to enhance the accuracy of defect profile reconstruction in this paper. In order to reduce the interaction between multidimensional information, dimensional coupling will deteriorate the search speed and convergence accuracy of the algorithm, a single dimension evolution strategy is complemented to optimize the tradition PSO algorithm. Each generation of evolution only updates a single dimension of the objective function. The dimension with the maximum error between the candidate signal and reference signal is selected as the one which need to be updated in next generation. In order to testify the performance of the proposed method, the simulated signals are utilized to compare with PSO algorithm. The experiment results verify that the proposed method has a higher adequacy of the performance in terms the quality of the solution and robustness for noise.

Defect reconstruction from magnetic flux leakage measurements employing modified cuckoo search algorithm.

Accurate and efficient estimation for defect profile of magnetic flux leakage (MFL) signals is important for nondestructive evaluation in industry. To improve the accuracy of defect profile reconstruction, an improved reconstruction method based on modified cuckoo search (CS), called MCS, is proposed in this paper. Firstly, a novel single-dimension updating evolution strategy is proposed to avoid the interference between multiple dimensions, which can make full use of the appropriate nest position in the historical search. Secondly, an adaptive multi-strategy difference evolution is introduced into the evolution process to improve the diversity and efficiency of CS algorithm. The proportion factor of each strategy in multi-strategy difference evolution is adjusted dynamically according to the value of the objective fitness. Finally, various MFL signals are selected to verify the effectiveness of the proposed MCS algorithm. The experiment results illustrate that the proposed method has high performance on the quality of the solution and robustness for noise.

Fast reconstruction of defect profiles from magnetic flux leakage measurements using a RBFNN based error adjustment methodology

Magnetic flux leakage (MFL) inspection is one of the most commonly used electromagnetic in-line inspection methods for detecting anomalies due to corrosion in the underground pipelines. An effective defect reconstruction method is very important for MFL detection. This study proposes a fast radial basis function neural network (RBFNN) based error adjustment (EA) methodology to reconstruct the defect profiles from MFL measurements. In the proposed model, the defect profile is updated according to the difference between the estimated and actual signals. The specific updating scheme is determined by the well trained RBFNN according to the difference. This profile updating strategy ensures that this method can approximate the actual profile faster than other methods. The effectiveness of the proposed algorithm is demonstrated by simulation and experimental data under various conditions. The results demonstrate that the proposed model exhibits faster convergence performance in a robust and stable manner while maintaining good reconstruction accuracy.

Precise Inversion for the Reconstruction of Arbitrary Defect Profiles Considering Velocity Effect in Magnetic Flux Leakage Testing

In magnetic flux leakage type nondestructive testing (NDT), there exists velocity effect, which may cause the distortion of the defect signals and reduce the estimated accuracy of defect profile. In this paper, the distortions are analyzed by using finite-element method (FEM), and the influence of velocity effect on reconstruction of defect profiles is discussed under the condition of the simulation and experiment. This paper proposes an effective method for reconstructing arbitrary defect profiles in different velocity conditions. In the proposed method, the FEM considering velocity effect is employed as the forward model. A weighting conjugate gradient algorithm is applied to update the defect profile iteratively in two gradient directions. The algorithms effectiveness is tested on a series of artificial defects under various velocity conditions. The results demonstrate that the proposed model can achieve the better reconstruction accuracy than the ignoring velocity effect models. The properties of the presented method are so stable and robust that they make our approach a promising technique for the practical application of profile reconstruction for NDT.

Defect profile reconstruction from MFL signals based on a specially-designed genetic taboo search algorithm

Defect profile reconstruction from MFL signals based on a specially-designed genetic taboo search algorithm

2-D Defect Profile Reconstruction from Ultrasonic Guided Wave Signals Based on Radial Wavelet Basis Function Neural Network with ELM

The reconstruction of defect profiles based on ultrasonic guided waves means the acquisition of defect profiles and parameters from ultrasonic guided wave signals. To achieve multi-resolution approximation, this paper proposed a reconstruction approach based on Radial Wavelet Basis Function Neural Network (RWBFNN), which combines wavelet analysis and neural network. Gaussian radial basis functions and Mexican hat wavelet frames are used as scaling functions and wavelet functions respectively. The training and testing samples contain simulation data and experimental data. The input data sets are defect echo signals, and the output data sets are 2-D profile parameters. To reduce the training time and simplify the profile reconstruction procedure without losing accuracy, Extreme Learning Machine (ELM) is adopted simultaneously. The results indicate that significant advantages can be obtained over other defect profile reconstruction schemes, and the accuracy of the predicted defect profile can be controlled by the resolution of the network with the lower computational complexity.

2-D defect profile reconstruction from ultrasonic guided wave signals based on QGA-kernelized ELM

The reconstruction of defect profiles based on ultrasonic guided waves means the acquisition of defect profiles and parameters from ultrasonic guided wave inspection signals, and it is the key for the inversion of ultrasonic guided waves. A method for the reconstruction of 2-D profiles based on kernelized extreme learning machine (ELM) is presented, and quantum genetic algorithm (QGA) is adopted to optimize the cost parameter C and kernel parameter γ of kernelized ELM. The input data sets of kernelized ELM are defect echo signals, and the output data sets are 2-D profile parameters. The mapping from defect echo signals to 2-D profiles is established. The sample database is achieved by practical experiments and numerical simulations. Then, 2-D profile reconstruction of artificial defects in ultrasonic guided wave testing is implemented with QGA-kernelized ELM. To compare the generalization performance and reconstruction results, another reconstruction model based on LS-SVM is designed simultaneously with the same kernel. Finally, experimental results indicate that proposed method possesses faster speed, lower computational complexity and better generalization performance, and it is a feasible and effective approach to reconstruct 2-D defect profiles.

KPLS-RWBFNN model for MFL 2D defect profile reconstruction

Kernel partial least squares (KPLS) is normally very efficient for tackling nonlinear systems by mapping an original input space into a high-dimensional feature space and creating a linear PLS model in the feature space. Unlike other nonlinear PLS techniques, KPLS does not entail any nonlinear optimisation procedures. However, due to the linear inner model of PLS, KPLS is still inappropriate for describing the significant nonlinear characteristic data structure while dealing with complex physical systems in practical situations. Under this circumstance, radial wavelet basic function neural network (RWBFNN) can replace the linear inner model of PLS in the nonlinear kernel-based algorithm. Thus, KPLS-RWBFNN model is proposed in this paper and applied to multi-resolution approximation reconstruction of 2D defect profiles in magnetic flux leakage testing. The reconstructions of 2D defect profiles by this method are implemented, and the comparisons among reconstructions by KPLS, RWBFNN and the proposed approach are also undertaken. Meanwhile, the reconstructions of 2D defects by RWBFNN and the proposed approach at different SNR are also executed. The results indicate that KPLS-RWBFNN model could simplify the structure of the network while holding well-behaved generalisation and multi-resolution approximation and predict the 2D defect profiles accurately and rapidly with good robustness.

159 パルス渦電流探傷試験信号を用いた配管減肉形状の逆解析(材料力学IV,一般講演)

159 パルス渦電流探傷試験信号を用いた配管減肉形状の逆解析(材料力学IV,一般講演)

A method of 2D defect profile reconstruction from magnetic flux leakage signals based on improved particle filter

Defect profile reconstruction in magnetic flux leakage (MFL) testing means the reconstruction of defect profiles and parameters according to inspected MFL signals, and it is the key point in realising MFL inversion. In this paper, the inversion problem is described as a classical discrete-time tracking problem based on state and measurement equations. A state-space approach is adopted to solve the inversion problem by establishing the state-space model of defect profile and MFL signals, and apply the improved particle filter algorithm to the defect profile reconstruction. The results indicate that the improved particle filter-based inversion algorithm is an effective and feasible new method of MFL inversion due to its accuracy and robustness against noise. Meanwhile, the improved resampling algorithm further improves the efficiency.

Model-Based Inversion Technique Using Element-Free Galerkin Method and State Space Search

This paper presents a signal inversion technique in nondestructive evaluation (NDE) application for defect profile reconstruction using the element-free Galerkin (EFG) method and state space search. The advantage of EFG method is that it relies only on a set of nodes, instead of a complex mesh to discretize the solution domain. In the inversion procedure, remeshing is avoided to increase the efficiency and accuracy of the solution, which is a major advantage over the traditional finite-element method (FEM). The iterative state space search method using the tree structure is developed for implementing the defect updating scheme. Preliminary results are presented for validation. The robustness of the technique has been shown on noisy signals.

Recent Investigations on the Reconstruction of Defect Profiles from Data Obtained by Pulsed Positron Beams

Recent Investigations on the Reconstruction of Defect Profiles from Data Obtained by Pulsed Positron Beams