A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Neural network approach for determination of fatigue crack depth profile in a metal, using alternating current field measurement data
A neural-network-based technique is described to determine the depth profile of a fatigue crack in a metal from the output signal of an alternating current field measurement (ACFM) probe. The main feature of this technique is that it requires only the measurements along the crack opening. The network uses the multilayer perceptron structure for which the training database is established by systematically producing semi-elliptical multi-hump cracks with narrow openings and random lengths and depth profiles. A fast pseudo-analytic ACFM probe output simulator is also used to produce network input data around each crack for a specified inducer. To demonstrate the accuracy of the proposed inversion technique, the simulated results of cracks with both common and complex geometries are studied. The comparison of the actual and reconstructed depth profiles substantiates the technique introduced here. To further validate the technique, the experimental results associated with several fatigue cracks of complex geometries are presented.
Neural network approach for determination of fatigue crack depth profile in a metal, using alternating current field measurement data
A neural-network-based technique is described to determine the depth profile of a fatigue crack in a metal from the output signal of an alternating current field measurement (ACFM) probe. The main feature of this technique is that it requires only the measurements along the crack opening. The network uses the multilayer perceptron structure for which the training database is established by systematically producing semi-elliptical multi-hump cracks with narrow openings and random lengths and depth profiles. A fast pseudo-analytic ACFM probe output simulator is also used to produce network input data around each crack for a specified inducer. To demonstrate the accuracy of the proposed inversion technique, the simulated results of cracks with both common and complex geometries are studied. The comparison of the actual and reconstructed depth profiles substantiates the technique introduced here. To further validate the technique, the experimental results associated with several fatigue cracks of complex geometries are presented.
Neural network approach for determination of fatigue crack depth profile in a metal, using alternating current field measurement data
Ravan, M. (author) / Sadeghi, S.H.H. (author) / Moini, R. (author)
IET Science, Measurement and Technology ; 2 ; 32-38
2008
7 Seiten, 16 Quellen
Article (Journal)
English
| Springer Verlag | 2024
Measurement of fatigue crack growth using low-profile eddy-current sensors
| British Library Online Contents | 2011
Measurement of fatigue crack growth using low-profile eddy-current sensors
| British Library Online Contents | 2011
CRACK DEPTH MEASUREMENT USING EDDY-CURRENT NDE
| British Library Online Contents | 2002