Lalita Udpa

Electromagnetic NDE signal inversion by function-approximation neural networks

In the magnetic flux leakage (MFL) method of nondestructive testing commonly used to inspect ferromagnetic materials, a crucial problem is signal inversion, wherein the defect profiles must be recovered from measured signals. This paper proposes a neural-network-based inversion algorithm to solve the problem. Neural networks (radial-basis function and wavelet-basis function) are first trained to approximate the mapping from the signal to the defect space. The trained networks are then used iteratively in the algorithm to estimate the profile, given the measurement signal. The paper presents the results of applying the algorithm to simulated MFL data.

Frequency invariant classification of ultrasonic weld inspection signals

Automated signal classification systems are finding increasing use in many applications for the analysis and interpretation of large volumes of signals. Such systems show consistency of response and help reduce the effect of variabilities associated with human interpretation. This paper deals with the analysis of ultrasonic NDE signals obtained during weld inspection of piping in boiling water reactors. The overall approach consists of three major steps, namely, frequency invariance, multiresolution analysis, and neural network classification. The data are first preprocessed whereby signals obtained using different transducer center frequencies are transformed to an equivalent reference frequency signal. Discriminatory features are then extracted using a multiresolution analysis technique, namely, the discrete wavelet transform (DWT). The compact feature vector obtained using wavelet analysis is classified using a multilayer perceptron neural network. Two different databases containing weld inspection signals have been used to test the performance of the neural network. Initial results obtained using this approach demonstrate the effectiveness of the frequency invariance processing technique and the DWT analysis method employed for feature extraction.

Three-dimensional defect reconstruction from eddy-current NDE signals using a genetic local search algorithm

This paper introduces a model-based approach to reconstruct three-dimensional defect profiles from eddy-current nondestructive evaluation signals. The method casts the defect characterization problem as an exercise in maximization of an appropriate cost function. The method uses an edge-based finite-element forward model to simulate the underlying physical process and a genetic search algorithm to solve the optimization (maximization) problem. The paper presents techniques to reduce the computation cost for evaluating the cost function as well as local search methods to speed the genetic search process. Test results confirm the validity of the approach.

Element-free Galerkin method for static and quasi-static electromagnetic field computation

Conventional finite-element methods (FEMs) rely on an underlying tessellation to describe the geometry and the basis functions that are used to represent the unknown quantity. Alternatively, however, it is possible to represent both the geometry and basis as a set of points. This alternative scheme has been used extensively in solid mechanics to compute stress and strain distributions. This paper presents an adaptation of the scheme to the analysis of electromagnetic problems in both the static and quasi-static regimes. It validates the proposed model against both analytical solutions and benchmarked FEMs. The paper demonstrates the efficacy of the proposed method by applying it to a range of problems.

Neural network-based inversion algorithms in magnetic flux leakage nondestructive evaluation

Magnetic flux leakage (MFL) methods are commonly used in the nondestructive evaluation (NDE) of ferromagnetic materials. An important problem in MFL NDE is the determination of flaw parameters such as the flaw length, depth, and shape (profile) from the measured values of the flux density B. Commonly used methods use a forward model in a loop to determine B for a given set of flaw parameters. This approach iteratively adjusts the flaw parameters to minimize the error between the measured and predicted values of B. This article proposes the use of neural networks as forward models. The proposed approach uses two neural networks in feedback configuration—a forward network and an inverse network. The second network is used to predict the profile given the measured value of B, and acts to constrain the solution space. Results of applying these methods to MFL data obtained from a two-dimensional finite-element model, with rectangular flaws of various dimensions, are presented.

Adaptive Wavelets for Characterizing Magnetic Flux Leakage Signals From Pipeline Inspection

This paper presents an iterative inversion scheme using radial basis function neural network (RBFNN) for predicting the depth profile of a defect in the pipe-wall from the information in the magnetic flux leakage (MFL) signal. Due to the high dimensionality of the data the method uses a multi-resolution approach with adaptive wavelets. The algorithm is fast and provides full three dimensional profile of the defect in the pipewall which is important for predicting the remaining life of the pipe.

An incremental learning algorithm with confidence estimation for automated identification of NDE signals

An incremental learning algorithm is introduced for learning new information from additional data that may later become available, after a classifier has already been trained using a previously available database. The proposed algorithm is capable of incrementally learning new information without forgetting previously acquired knowledge and without requiring access to the original database, even when new data include examples of previously unseen classes. Scenarios requiring such a learning algorithm are encountered often in nondestructive evaluation (NDE) in which large volumes of data are collected in batches over a period of time, and new defect types may become available in subsequent databases. The algorithm, named Learn++, takes advantage of synergistic generalization performance of an ensemble of classifiers in which each classifier is trained with a strategically chosen subset of the training databases that subsequently become available. The ensemble of classifiers then is combined through a weighted majority voting procedure. Learn++ is independent of the specific classifier(s) comprising the ensemble, and hence may be used with any supervised learning algorithm. The voting procedure also allows Learn++ to estimate the confidence in its own decision. We present the algorithm and its promising results on two separate ultrasonic weld inspection applications.

Finite-element neural networks for solving differential equations

The solution of partial differential equations (PDE) arises in a wide variety of engineering problems. Solutions to most practical problems use numerical analysis techniques such as finite-element or finite-difference methods. The drawbacks of these approaches include computational costs associated with the modeling of complex geometries. This paper proposes a finite-element neural network (FENN) obtained by embedding a finite-element model in a neural network architecture that enables fast and accurate solution of the forward problem. Results of applying the FENN to several simple electromagnetic forward and inverse problems are presented. Initial results indicate that the FENN performance as a forward model is comparable to that of the conventional finite-element method (FEM). The FENN can also be used in an iterative approach to solve inverse problems associated with the PDE. Results showing the ability of the FENN to solve the inverse problem given the measured signal are also presented. The parallel nature of the FENN also makes it an attractive solution for parallel implementation in hardware and software.

Finite-Element Model for Simulation of Ferrite-Core Eddy-Current Probe

The finite-element method is widely used in modeling eddy-current phenomena. However, its application in eddy-current nondestructive testing involving probe motion requires remeshing for each coil position. Remeshing is not only cumbersome but also a major source of computational noise. We have used the reduced magnetic vector potential formulation to model an air-core probe scan without remeshing the coil in different positions. In this paper, we present a method to model the scanning of ferrite-core probe. With this method, finite-element meshes for the test sample and the ferrite core are generated separately. The coil is not meshed. The magnetic field and magnetic vector potential due to the coil are evaluated analytically. An iterative but fast procedure is used to update the total field. The method is simple, flexible, accurate, and efficient.

Motion-based filtering of magneto-optic imagers

Abstract The magneto-optic imager (MOI) is a powerful device for the nondestructive inspection (NDI) of aging aircraft. MOI produces analog images of magnetic flux leakage associated with eddy current distribution around surface and subsurface structures. The main advantages of using MOI are its fast inspection speed and easy interpretation compared with conventional Eddy Current NDI instruments. However, due to the magnetic domain wall structures of the sensor, the MOI images are corrupted by noise, which lowers the MOI inspection capabilities. The domain walls produce serpentine pattern noise, which can be reduced by improving the sensor or by use of image processing methods. This paper introduces a motion-based image processing method to reduce the background noise. Initial results of implementing the algorithm on real field data are presented.