Detection of cracks in weep holes using neural networks

Aldrin, J. C.; Cheng, A.; Achenbach, J. D.; Andrew, G. A.; Mullis, R. T.
May 2000
AIP Conference Proceedings;2000, Vol. 509 Issue 1, p1979
Academic Journal
Weep holes are incorporated in the risers of wing structures in C-141 aircraft to allow fuel to be properly distributed during flight. Two types of fatigue cracks have been observed emanating from weep holes, top cracks that emanate upward and bottom cracks that propagate toward the wing surface. A new approach using creeping Rayleigh waves has been shown to be successful in detecting top cracks in weep holes. The focus of this paper is the development of a robust automated protocol for the detection of both top and bottom cracks in weep holes. A numerical technique was developed using the boundary element method (BEM) to calculate simulated waveforms for reflection and backscattering of ultrasound from weep holes with top or bottom cracks. The simulations were validated by comparison with experimental results. From parametric studies of this model, a robust protocol incorporating both the pulse echo and pitch catch creeping Rayleigh wave signals from top-cracks was defined. Protocols incorporating neural networks were developed for both top and bottom crack classification. A complete automated procedure for crack detection was successfully trained with both simulated and experimental data and was verified with experimental data for the expected variation in weep hole size and crack length. © 2000 American Institute of Physics.


Related Articles

  • Bending Moment Prediction for Continuous Composite Beams by Neural Networks. Chaudhary, Sandeep; Pendharkar, Umesh; Nagpal, Ashok Kumar // Advances in Structural Engineering;Aug2007, Vol. 10 Issue 4, p439 

    A methodology has been developed for the continuous composite beams to predict the inelastic bending moments (considering the cracking of concrete) from the elastic moments (neglecting the cracking) by using the neural networks. The proposed neural network models predict the inelastic moment...

  • Health Assessment of Concrete Dams by Overall Inverse Analyses and Neural Networks. Fedele, R.; Maier, G.; Miller, B. // International Journal of Fracture;Jan2006, Vol. 137 Issue 1-4, p151 

    In several existing dams alcali–silica reaction (ASR) during several decades of service life, or diffused micro-cracking (due to concrete ageing and/or past extreme loads, such as earthquakes) give rise to deterioration of concrete stiffness and to correlated reduction of its strength. An...

  • Short Term Energy Forecasting with Neural Networks. McMenamin, J. Stuart; Monforte, Frank A. // Energy Journal;1998, Vol. 19 Issue 4, p43 

    Provides information on artificial neural networks. Neural network specification and terminology; Estimation approaches for neural networks; Summary statistics and test statistics for neural networks.

  • Artificial Neural Networks make their mark as a powerful tool for investors. Cheng, Wei; McClain, Bruce W. // Review of Business;Summer97, Vol. 18 Issue 4, p4 

    Presents information on Artificial Neural Networks (ANNs) investment systems, fast becoming a powerful tool for investment forecasting and achieving impressive results. Information on ANNs; Example of the success of ANN; Information on forecasting in investment decisions and its success;...

  • Think neural networks. Woelfel, Joseph // Marketing Tools;Apr/May94, Vol. 1 Issue 6, p62 

    Focuses on artificial neural network as a computer software that models some of the basic elements of the brain. Ability of artificial neural networks to recognize patterns and perform qualitative analysis; Description of artificial neural network system; Operation process; Application of...

  • Determination of cloud liquid water path over the oceans from special sensor microwave/imager... Jung, Thomas; Ruprecht, Eberhard; Wagner, Friedrich // Journal of Applied Meteorology;Aug98, Vol. 37 Issue 8, p832 

    Focuses on the observations made of a neural network (NN), developed to retrieve the cloud liquid water path (LWP). What the retrieval with NN depends on; Information on a data and radiative transfer model; Details on different neural network architectures.

  • Feedforward backpropagation neural networks in prediction of farmer risk preferences. Kastens, Terry L.; Featherstone, Allen M. // American Journal of Agricultural Economics;May96, Vol. 78 Issue 2, p400 

    Compares ordered multinomial logistic regression models with feedforward backpropagation neural network models. Prediction of logistic models; Accommodation of the models for loss functions; Empirical applications of ordered logits.

  • Predict difficult-to-measure properties with neural analyzers. Deshpande, Pradeep B.; Yerrapragada, Srinivas S. // Control Engineering;Jul97, Vol. 44 Issue 10, p55 

    Discusses the capability of artificial neural networks (ANNs) for predicting on-line process variables. Drawbacks of inferential analyzers; Basis of traditional approaches to inferential analyzers; Three layers of multilayer perception ANNs. INSET: Artificial neural networks, a review..

  • Building a better brain. Kirkwood, Craig // Australian Personal Computer;May98, Vol. 19 Issue 5, p99 

    Focuses on the technology associated with neural networks. Definition of neural networks; Information on how a neural network works; Indepth look at neural Internets. INSET: How to get your own neural network.


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics