Showing papers on "Eddy-current testing published in 2007"

Thickness measurement of non-magnetic plates using multi-frequency eddy current sensors

Abstract: A robust feature in multi-frequency eddy current (MEC) testing has been found that can be directly linked to the thickness of the plate under test. It is shown mathematically that the peak frequency of the imaginary part of the inductance change when an air-cored coil is placed next to a non-magnetic metallic plate is inversely proportional to the thickness of the plate for a given material. Experimental results indicate that this relationship also holds for a ferrite-cored U-shaped coil. In addition, this peak frequency has been shown to be relatively independent of lift-off variations. Use of this new feature provides a fast and accurate method to gauge the thickness of plates. Measurements made for a sample air-cored and ferrite U-cored coil next to copper and aluminium plates of various thicknesses verified the proposed method.

Thermographic crack detection by eddy current excitation

Abstract: Eddy current thermography is a new NDT-technique for the detection of cracks in electroconductive materials It combines the well established inspection techniques eddy current testing and thermography The advantage of this method is to use the high performance of eddy current testing without the known problem of the edge effect Especially for components of complex geometry this is an important factor which may overcome the increased expense for inspection set-up The principle of this technique and an algorithm to increase the sensitivity for small defects are described Some inspection examples on aero engines parts are presented which show the potential of eddy current thermography

Advantage of a combined ultrasonic and eddy current examination for railway inspection trains

Abstract: Some years ago, two railway inspection trains (RIT) already equipped with ultrasound, had additional advanced eddy current techniques installed. Recently, a new RIT was equipped with a system that was designed, from the beginning, to employ a combination of these two techniques for non-destructive rail inspection. The eddy current technique has been developed to enable identification and evaluation of rolling contact fatigue (RCF) defects. The ultrasound technique is aimed at measurements in the rail bulk volume, which are not feasible using the eddy current technique. Experience gained from application has shown that clear improvement on rail inspection can be achieved. For example, following Deutsche Bahn DB (German Rail) AG guideline, defects which are classified as group 2 using ultrasound testing can be further labelled as 'distinguished positions' if, for example, head checking can be identified in the same position using the eddy current technique. In other words, the new technique is capable of identifying two fundamentally different types of defects occurring at the same location. Such defects can then be classified as Group 1, equivalent according to the DB AG guideline. Furthermore, problem cases in the past, such as the decision whether a weld or rail joint is present for a fishing table, can be reliably determined using additional information from the eddy current technique. In this paper, examples will be provided to demonstrate application.

Application of eddy currents induced by permanent magnets for pipeline inspection

Abstract: This paper presents an alternative to the common concentric coil method to induce low-frequency eddy currents in ferromagnetic pipe and tubes. Pairs of permanent magnets rotating around the central axis of these cylinders in proximity of the surface can be used to induce high current densities in the material that is the object of the inspection. Anomalies and wall thickness variations are detected with an array of sensors that measure local changes in the magnetic field produced by the current flowing in the material. This electromagnetic technology is being developed for pipeline inspection platforms that either crawl slowly inside a pipe to maneuver past physical barriers or are pushed by flexible rods. These devices move down the pipeline independent of the product flow, and potentially stop for detailed defect assessment. Fundamental finite element modeling analysis and experimental investigations performed during this development have led to the derivation of a first-order analytical equation for designing rotating exciters and positioning sensors. The rotating permanent magnet system has the potential for broader application because the sensor configurations can be small in physical size, allowing them to pass obstructions that currently prevent inspection using available NDE implementations.

Analysis of the Liftoff Effect of Phase Spectra for Eddy Current Sensors

Abstract: This paper presents an analytical model that describes the inductance change when a double air-cored coil sensor is placed next to a conducting plate. Analysis of the analytical model reveals that the phase signature of such a sensor is virtually liftoff independent. This finding is verified by numerical evaluations. This paper also finds that the phase signature of a ferrite U-cored sensor can be approximated by that of a double air-cored sensor of similar size and, therefore, possesses a similar liftoff-independent property. Measurements made with a sample U-cored sensor next to plates of nonmagnetic and magnetic materials verified the theoretical results.

Development of differential probes in pulsed eddy current testing for noise suppression

Abstract: Differential probes are developed to suppress noises and improve the sensitivity and robustness of pulsed eddy current (PEC) testing. As the close magnetic circuit is used to concentrate the magnetic field, three-core probe and U-shape probe gain high signal to noise ratio (SNR) with limited excitation current, the latter also reduces the influence caused by probe tilting. Lift-off effect is a great obstacle for practical application of pulsed eddy current testing, so probes developed with two-stage differential design can carry out the effective suppression of the lift-off effect. Verifying experiments are also presented, by which the performance of these differential probes are tested and compared in this paper.

Eddy current nondestructive testing with giant magneto-impedance sensor

Abstract: Technologies based on magnetic sensors with high sensitivity such as magneto-resistance (AMR, GMR), fluxgate or squid sensors have demonstrated their capability to improve the performances of the classical eddy current (EC) probes. In this paper, a new kind of magnetic sensor based on giant magneto-impedance (GMI) effect has been evaluated. This sensor combines good sensitivity performances at low frequencies and small size. The design of a probe using this new technology has been optimized with fast semi-analytical models. The performances of this GMI based probe have then been successfully evaluated on a 304 L stainless steel mock up for the detection of embedded flaws.

High-frequency eddy current conductivity spectroscopy for residual stress profiling in surface-treated nickel-base superalloys

Abstract: Recent research results indicated that eddy current conductivity measurements can be exploited for nondestructive evaluation of subsurface residual stresses in surface-treated nickel-base superalloy components. Most of the previous experimental studies were conducted on highly peened (Almen 10-16A) specimens that exhibited harmful cold work in excess of 30% plastic strain. Such high level of cold work causes thermo-mechanical relaxation at relatively modest operational temperatures; therefore the obtained results were not directly relevant to engine manufacturers and end users. The main reason for choosing peening intensities in excess of recommended normal levels was that in low-conductivity engine alloys the eddy current penetration depth could not be forced below 0.2 mm without expanding the measurements above 10 MHz which is beyond the operational range of most commercial eddy current instruments. In this paper we report the development of a new high-frequency eddy current conductivity measuring system that offers an extended inspection frequency range up to 50 MHz with a single spiral coil. In addition to its extended frequency range, the new system offers better reproducibility, accuracy, and measurement speed than the previously used conventional system.

Eddy Current Inspection of Closed Fatigue and Stress Corrosion Cracks

Abstract: This study evaluates the effect of loading on closed crack openings on eddy current signals caused by the crack. Three plate specimens having a fatigue crack and another three specimens having stress corrosion cracking are prepared. Four-point bending of the specimens is carried out to introduce compressive stress to close the opening of the cracks. Then eddy current signals due to the crack are gathered using a plus point type probe. The bending was conducted with a variable load; the eddy current signals remain almost unchanged regardless of the loading.

Numerical evaluation of the ill-posedness of eddy current problems to size real cracks

Abstract: This study evaluates whether or not eddy current testing is applicable to the sizing of cracks that appear in a general structure. Two 10 mm thick specimens with artificial stress corrosion cracking are prepared, eddy current testing is performed to gather eddy current signals that result from cracking, and numerical inversions are performed to evaluate the maximum depths of the cracking. The inversions estimate the depths of the cracks are 0.8 and 1.6 mm. Although the simulated signals agree well with the measured ones, destructive tests reveal that the true depths are 1.27 and 2.58 mm. Another numerical simulation is conducted to discuss the ill-posedness of the inverse problem of sizing crack depths from eddy current signals. The simulation simply models a crack as a rectangular region with a constant length and uniform conductivity inside and calculates the eddy current signals of 1024 cracks having variety of depths, widths, and conductivities. Analyzing the results of the simulation reveal that information contained in conventional single-frequency eddy current tests is not sufficient to size conductive cracks in a general sense.

Lift-off effect in high-frequency eddy current conductivity spectroscopy

Abstract: Precision eddy current measurements have been shown to be capable of characterizing the near-surface residual stress and cold work profiles in surface-treated components. To capture the peak compressive residual stress in moderately shot-peened (Almen 4–8 A) nickel-base superalloys, the eddy current inspection frequency has to be as high as 50–80 MHz. Unfortunately, spurious self- and stray-capacitance effects render the complex eddy current coil impedance variation with lift-off, the so-called lift-off curve, highly nonlinear, which makes it difficult to achieve accurate eddy current conductivity measurements beyond 25 MHz in the presence of even the slightest lift-off uncertainties. As opposed to the well-known inductive lift-off effect that decreases with increasing probe size, the capacitive lift-off effect increases with probe size. Both effects increase with frequency with the inductive effect being initially stronger, but then taken over at high frequencies by the faster growing capacitive effect. Since the two effects produce opposite curvature in the lift-off curve, in the frequency range where they are approximately equal to the lift-off curve becomes essentially linear and fairly accurate, conductivity measurements can be conducted even in the presence of lift-off variations.

Fourier-transformed eddy current technique to visualize cross-sections of conductive materials

Abstract: A pulsed eddy current NDE system is useful for detecting deep flaws in conductive materials. We have developed a pulsed eddy current NDE system using a magneto-resistive sensor. The induction coil generates a pulsed magnetic field which has a frequency component between 0 and 3 kHz, and a maximum amplitude of about 4 μ T . Aluminum plates with flaws at depths of 1 and 2 mm were measured, and the intrinsic frequency responses of the plates were obtained using a proposed Fourier transformation method. Cross-sectional images of the samples could then be directly constructed from the intrinsic responses. We also demonstrated estimation of quantitative values for the depths of flaws. The estimated depth was well defined for a sample with a flaw at a depth of 2 mm. The estimated value was slightly different for a sample with a flaw at a depth of 1 mm due to lack of frequency components above 3 kHz. These results indicate that the proposed system is a very promising tool for NDE tomography.

Advanced use of soft computing and eddy current test to evaluate mechanical integrity of metallic plates

Abstract: The up-to-date structural designing makes by now widely use of high performance numerical codes, mainly in terms of computational powerful, cost and sizing, only available till some time before to limited groups of users. This allowed the experts to focus their attention on a qualifying aspect of the designing, i.e. an use of the materials very close to their limit behavior. Late innovative approaches in material mechanics gave in addition the opportunity to build models very close to the actual behavior but without introducing heavy computational aspects. In this paper, phenomena which relate mechanical stresses with electromagnetic properties of a defined material have been exploited in order to reconstruct electromagnetic maps starting from mechanical quantities by means of support vector regression machines (SVRMs). Purpose of the proposed study is to reconstruct a stress map in strained metallic plates by using electromagnetic measures. Moreover, an heuristic approach is proposed in order to estimate electromagnetic behavior of a stressed plate starting from easily measurable mechanical quantities. It would be very interesting when electrical or mechanical measurements are very hard to realize. The proposed approach could be very useful in such situations as quality controls of civil buildings, without the necessity of applying expensive and time-consuming destructive or non-destructive testing. In this way, it is possible to have a substantially precise idea of mechanical stresses in metallic materials by estimating the local variation of electromagnetic field into the same material using a SVRM-based interpolator.

A nondestructive strategy for the distinction of natural fatigue and stress corrosion cracks based on signals from eddy current testing

Abstract: In this paper, a novel nondestructive strategy is proposed for distinguishing differences between a stress corrosion crack (SCC) and a fatigue crack (FC) based on signals from eddy current testing (ECT). The strategy consists of measurement procedures with a special ECT probe and crack type judgment scheme based on an index parameter that is defined as the amplitude ratio of the measured signals. An ECT probe, which can induce eddy current flowing mainly in a selected direction, is proposed and applied to detect crack signals by scanning along the crack with different probe orientations. It is clear that the ratio of the amplitudes of signals detected for parallel and perpendicular probe orientations is sensitive to the microstructure of the crack, i.e., the parameter is much bigger for a fatigue crack than that of a SCC. Therefore, whether a crack is a SCC or a FC can be recognized nondestructively by comparing the index parameter with a threshold value that can be previously determined. In order to verify the validity of the proposed strategy, many artificial SCC and FC test pieces were fabricated and ECT inspections were performed to measure the corresponding crack signals. Numerical simulations were also conducted to investigate the physical principles of the new methodology. From both the numerical and experimental results, it is demonstrated that the strategy is very promising for the distinction of artificial SCC and FC; there is also good possibility that this method can be applied to natural cracks if the threshold value can be properly determined.

Modeling of Eddy Current Sensor using Geometric and Electromagnetic Data

Abstract: In this paper a new modeling method for an eddy current sensor is presented using geometric and electromagnetic data of a sensor and a measuring target It can predict not only sensor output but also medium behavior related to sensor output The geometric data of a sensor coil and the eddy current generated on a measuring target are simplified to an array of circular loops. And to perform computations of the network circuit between sensor coil loops and eddy current loops using the geometric and electromagnetic data in order to consider all possible interactions, the equivalent network circuit of eddy current sensor’s behavior has been drawn. Because the sensor’s initial value, medium behavior, and final value can be shown quantitatively by the proposed modeling method as the geometric and electromagnetic data varies, it can precisely predict the sensor output depending on the measuring goal and application field. Thus the model can be utilized to improve accuracy, eliminate the need for calibration before use, and produce the best design for any given purpose.

Bare PCB Inspection System With SV-GMR Sensor Eddy-Current Testing Probe

Abstract: This paper describes bare printed circuit board (PCB) inspection based on eddy-current testing (ECT) technique with high scanning speed. A high-frequency ECT probe composed of a meander coil as an exciting coil and the spin-valve giant magnetoresistance (SV-GMR) sensor was fabricated and is proposed. The ECT probe was designed based on crack inspection over flat surface, especially suitable for microdefect detection on high-density bare PCB. The ECT signal detected by the SV-GMR sensor was acquired by high-speed A/D converter for applying the signal processing based on digital technique. Harmonic analysis based on Fourier transform was used to analyze the ECT signal at fundamental frequency in order to increase inspection speed and this technique allowed the ECT probe to scan bare PCB, with high sampling frequency and with high-spatial resolution inspection. Experimental results verified the possibility and the performance of the proposed PCB inspection system based on ECT technique

3-D movement simulation techniques using FE methods: Application to eddy current non-destructive testing

Abstract: In this paper, sample calculations were performed with a three-dimensional (3-D) numerical method to describe the response of an eddy current (EC) probe to defects in a conducting plate. The governing field equations are given in terms of coupled magnetic vector and electrical scalar potentials and solved using a 3-D finite element method implemented in Matlab environment. The displacement of the sensor operating in absolute or differential mode is simulated using three methods: The first and second methods known, respectively, as the nodal interpolation technique (NIT) and the Lagrange multiplier technique (LMT) consist in ensuring the connection between fixed and moved 3-D independent meshes. The third method known as the properties assignment technique (PAT) is based on the geometrical band. In this work, these methods are used to compute the real and imaginary parts of the impedance correlation at every position of the coil(s). This allows the characterisation of the presence of a defect through the EC distribution.

Introduction to the Principles of Materials Evaluation

Abstract: Introduction Fundamentals of Materials Evaluation and the Concept of Lifetime of Materials Testing Various Methods in Materials Evaluation Mechanical Properties of Materials Effects of Stress on a Material Stress-Strain Relationships and Elastic Properties Hardness References Sound Waves: Acoustic and Ultrasonic Properties of Materials Vibrations and Waves Relationship between Mechanical Properties and Wave Propagation Launching Waves in Materials References Thermal Properties of Materials Thermal Effects in Materials Temperature Dependence of Materials Properties Effects of Heat on Structure of Materials References Electrical and Magnetic Properties of Materials Electrical Insulators Electrical Conductors Electrical Measurements for Materials Testing Magnetic Fields References Effects of Radiation on Materials Basics of X-Rays Interaction of X-Rays with Materials Exposure, Dose, and Dose Rate References Mechanical Testing Methods Tensile Testing Hardness Tests Cracks and Failure of Materials Impact and Fracture Tests References Ultrasonic Testing Methods Generation of Ultrasound in Materials Inhomogeneous and Layered Materials Angle Beams and Guided Waves References Electrical Testing Methods Basics of Eddy Current Testing Eddy Current Sensors Factors Affecting Eddy Current Response References Magnetic Testing Methods Magnetization Magnetic Methods for Evaluation of Defects Magnetic Particle Inspection References Radiographic Testing Methods X-Ray Imaging Radiographic Film Radiographs References Thermal Testing Methods Heat Transfer Thermal Inspection Procedures References Destructive vs Nondestructive Testing Testing Options Materials Characterization References Defect Detection Terminology for Nondestructive Evaluation Probability of Detection Statistical Variation of Signal Levels References Reliability and Lifetime Extension Reliability and Criteria for Decisions Lifetime Extension References Appendix: Solutions to Exercises Index *Each Chapter Provides References to Original Papers and Suggested Material for Further Reading

Research on edge identification of a defect using pulsed eddy current based on principal component analysis

Abstract: It is difficult to identify the edge of a defect in nondestructive testing (NDT), which affects the result of a C-scan image acquired by arrays of pulsed eddy current sensors (APECS). To overcome the problem of low accuracy in identification of the edge of a defect using the conventional eddy current techniques, which only extract features in time domain, features from pulsed eddy current that has a broadband frequency are extracted both in time and frequency domains. A method based on principal component analysis (PCA) is proposed to enhance the accuracy in identification of the edge of a defect, the agreement between theory and experiment shows that the proposed method is applicable and preferable to APECS.

The influence of crack shapes and geometries on the results of the thermo-inductive crack detection

Abstract: For thermo-inductive crack detection, a metallic work-piece is placed in a high frequency magnetic field which induces eddy currents in a very thin layer of the surface. This eddy current heats up the sample and the emitted infrared radiation is viewed by an infrared sensitive camera. An inhomogeneous temperature distribution on the surface corresponds to inhomogeneities and cracks in the material. The main goal of the thermo-inductive crack detection is on the one side to find cracks and on the other side to determine their depths. For this purpose an examination of all parameters affecting the result of the measurements has to be made. In previous publications it has been shown how the thermal quotient Tcrack/Tsurf depends on several parameters (i.e.: time, pulse length, penetration depth of the eddy current and crack depth). All these investigations were made for rectangular shaped cracks. But metallographic cross-sections show that real cracks have different shapes and different angles depending on the circumstances of the origin of the crack. In this paper results of finite element simulations are presented demonstrating what kind of influence the different shapes have to the thermal contrast. It is also shown in which way the crack geometry affects the temperature distribution on the crack near surface. The calculations take into consideration the distribution of the eddy currents around the crack for both magnetic and non-magnetic materials. The simulations are based on coupled modeling of magnetic and thermal phenomena. The calculated results are in very good agreement with the measurements.

Enhanced Corrosion Detection in Airframe Structures Using Pulsed Eddy Current and Advanced Processing

Abstract: The capabilities of the pulsed eddy current technique to extract depth related information have been successfully demonstrated for hidden corrosion detection. In the present work, the drive pulse and the transient response are analyzed in terms of the Fourier transform to understand the depth of material penetration with pulsed eddy current. A multifrequency analysis of the transient response that allows information to be selectively chosen from different layers is described. An observation time interval and a sampling rate are the components that define high- and low-frequency resolution of a pulsed eddy current system. An example of "in-depth slicing" of a multilayer structure is provided. The use of solid state sensors to acquire transient response is discussed. Examples of pulsed eddy current imaging with arrays of giant magnetoresistors are given. Recently developed two-dimensional arrays enable instant imaging of the structure under the probe without mechanical scanning. They also provide the fastest surface coverage for large area testing when used with 2D scanners. Experiments have been performed on aircraft aluminum skin with a portable prototype system. The advantages and limitations of the technique are discussed.

Concrete rebars inspection by eddy current testing

Abstract: This paper is focused on the nondestructive inspection of concrete rebars by using eddy current testing. Many practical low frequency systems are capable of locating and estimating the size of the cross-section of the rebars via calibration charts. Here we develop a quantitative non-iterative imaging method based on a numerical model of the probe-specimen interaction.

Quantitative Nondestructive Evaluation of the Crack on the Austenite Stainless Steel Using the Induced Eddy Current and the Hall Sensor Array

Abstract: Nondestructive evaluation (NDE) has been effective in the prediction and evaluation of cracks on the surface of structures. Austenite stainless steel such as SUS304 and SUS316 is a paramagnetic metal with delta -ferrite structure. Small amount of partial magnetization is generated in the austenite stainless steel due to the final heat treatment and the mechanical working. The MOI (magneto-optical/eddy current imaging) was developed to inspect fatigue cracks and corrosions. But the surface cracks on the partially magnetized paramagnetic metals, such as austenite stainless steel, are difficult to inspect because the magnetic domains were saturated by external magnetization of the delta -ferrite. In this paper, the magnetic camera with the 64 arrayed Hall sensors by matrix (sensor matrix) was developed to confirm the real time inspection and quantitative nondestructive evaluation (QNDE). As the result, QNDE algorithm was proposed by using single sensor scanning, and the algorithm was introduced in QNDE by sensor matrix. Also, the cracks were inspected in the real time by sensor matrix, which were arrayed with 3.5 mm spatial resolution in square.

Rapid flaw depth estimation from SQUID-based eddy current nondestructive evaluation

Abstract: A scheme to rapidly estimate the depth of an unknown flaw from finite element two dimensional calculations using sheet inducer geometry is described. The linear relationship between the phase of the defect magnetic field (difference between the magnetic field arising from eddy currents in flawed and unflawed regions of a plate) and the depth of a flaw is utilized along with two experimental SQUID-based eddy current nondestructive evaluation line scans—one with a flaw at a known depth for reference and the other with the unknown flaw. The results are in good agreement with experimental data obtained with a double-D coil.

Eddy current inspection apparatus and method

Abstract: PROBLEM TO BE SOLVED: To provide an eddy current inspection apparatus and its method, which evaluate characteristics of an object to be inspected with a reduced influence of lift-off etc. even while using a detection sensor with a narrow dynamic range. SOLUTION: The eddy current inspection apparatus is provided with: an exciting coil 1 that is excited by a pulse signal to induce eddy current in the object 4; and a detection sensor 2 for detecting the change of eddy current induced in the object 4. The eddy current inspection apparatus comprises: a logarithmic transformation part 8, an approximate straight line computing part 9, etc., for example, for computing the slope of change over time of values detected by the detection sensor 2; a storage part 10 for storing correlation data between the slope of change over time of values detected by the detection sensor 2 and the characteristics of the object 4 which have been acquired beforehand; and a characteristic computing part 11 for computing characteristics of the object 4, based on the correlation data stored in the memory part 10, from the slope of change over time of values detected by the detection sensor 2 which has been computed by the approximate straight line computing part 9. COPYRIGHT: (C)2009,JPO&INPIT

Electromagnetic Enhancement of Pulsed Eddy Current Signals

Abstract: The sensitivity of pulsed eddy current (PEC) testing is increased when a layer of magnetic material is placed on the far side of the conductive test piece. This procedure ensures preservation of the lift‐off point of intersection (LOI) feature, otherwise non‐existent for the PEC inspections of magnetic materials. The presented method could find applications in non‐destructive inspections for corrosion thinning, thickness measurement of conductive coatings over ferrous substrates, and integrity of thermally insulated pipes. Laboratory‐obtained examples are given to support the method applicability.

Characterization of small cracks in eddy current testing

Abstract: A study on the characterization of small cracks by using eddy current testing (ECT) signal is presented The significant parameters of the ECT data are selected using principal component analysis according to two approaches The ECT signal inversion is then achieved using a parametric model trained with synthetic data obtained with a fast numerical simulation tool The characterization procedure is then tested using experimental data Results show that information can be obtained concerning the area of the cracks

Eddy current inspection device based on resistance transducer of gigantic magnetism

Abstract: A vortex detection device based on huge magnetic resistance transducer is prepared as generating vortex by detected element when excitation coil is near to detected conduction structure based on electromagnetic induction principle and conversely influencing magnetic field generated by excitation coil by vortex, using probe of huge magnetic resistance transducer to detect out variation of magnetic field, sending said variation signal to two phase sensitive rectifiers and making output signal of said rectifier be close relation with parameter of detected element then driving out value of parameter to be detected.

Defect identification in GRID-LOCK® joints

Abstract: Damage detection in aircraft structures is conducted using a variety of nondestructive evaluation (NDE) techniques, including visual inspection, ultrasonic inspection, eddy current inspection, radiography and optical methods. These techniques are well established and have distinct advantages and limitations. Optical NDE methods show significant promise for variety of aerospace structural components, including inspection of bonded metallic GRID-LOCK® structures. In this paper, a full-field surface slope measurement technique (shearography) is utilized to confirm the effectiveness of optical NDE. Two bond defects (one disbond and one weak bond) are incorporated into a GRID-LOCK® test structure and internal pressurization results in qualitative indications of damage on the shearograms. Because accurate characterization of structural defects is critical for flight safety, a quantitative nondestructive evaluation (QNDE) method using a scanning optical probe is also explored. This QNDE method involves use of radial basis function networks (RBFNs) trained and validated using finite element analysis nodal displacements.