Impact detection in an aircraft composite panel—A neural-network approach

LeClerc, J.R.; Worden, Keith; Staszewski, Wiesław J.; Haywood, Jonathan

doi:10.1016/j.jsv.2006.07.019

Cited by 99 publications

(70 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the total average radial error is around 60mm. Results obtained in this work are similar to the ones presented in previous works that used different techniques such as Artificial Neural Networks (LeClerc et al [2007]), Genetic Algorithms (Mahzan et al [2007]) and Case Based Reasoning (Mujica et al [2008]) (Mujica et al [2008]). However, the methodology presented in this work uses the information gathered from the sensors, without computing new or additional features.…”

Section: Analysis Results and Discussionsupporting

confidence: 88%

“…This section describes the same experimental setup previously used to demosntrate that the problem of identifying impact locations can be solved successfully using several approaches, for instance: Artificial Neural Networks can be used as a regressor, a classifier and as a combination of both (LeClerc et al [2007]). Another option is the utilisation of Genetic Algorithms (Mahzan et al [2007]) or Case Based Reasoning combined with different dimensionality reduction (or features extraction) techniques sucha as: Self Organizing Maps -SOM- (Mujica et al [2008]), Principal Component Analysis (PCA), Partial Least Square (PLS), Curvilinear Distance Analysis (CDA) and some extensions of them (Mujica et al [2008]).…”

Section: Methodsmentioning

confidence: 99%

“…Typical multilayer perceptrons were trained with experimental data using the backpropagation learning rule. This approach was tested by Haywood et al [2005] in Smart Layer and by LeClerc et al [2007] in a large aircraft structure.…”

Section: Impact Identification As Prediction Problemmentioning

confidence: 99%

See 2 more Smart Citations

Multiway Partial Least Square (MPLS) to estimate impact localization in structures

Mujica

Ruiz

Berjaga

et al. 2009

IFAC Proceedings Volumes

View full text Add to dashboard Cite

This paper presents results from the application of Multiway Partial Least Square (MPLS) as a regressor tool in order to estimate the localization of impacts in an aircraft structure. MPLS is a technique that maximizes the covariance between the predictor matrix X and the predicted matrix Y for each component of the space. The structure can be considered as a small scale version of part of a wing aircraft. 574 experiments were performed impacting the wing over its surface and receiving vibration signals from nine sensors. Experiments are divided in four groups depending on their localization and probability of occurrence. A PLS model is build using three of these groups and tested using the remaining group. Results are presented, discussed and compared with results of other methods.

show abstract

Section: Analysis Results and Discussionsupporting

confidence: 88%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multiway Partial Least Square (MPLS) to estimate impact localization in structures

Mujica

Ruiz

Berjaga

et al. 2009

IFAC Proceedings Volumes

View full text Add to dashboard Cite

show abstract

“…Altogether, these methods can be classified as passive and active [2]. The former includes methods based on acoustic emission [3,4], operational load monitoring [1,5] and impact detection techniques [1,[6][7][8][9][10]. The latter covers various methods based on vibration analysis [11][12][13][14] and non-destructive techniques, such X-ray [15,16], shearography [1,17], vibro-thermography [18,19], ultrasonic and acousto-ultrasonic testing [20,21], and guided ultrasonic waves [22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Triple correlation for detection of damage-related nonlinearities in composite structures

et al. 2015

View full text Add to dashboard Cite

Nonlinear effects in vibration responses are investigated for the undamaged composite plate and the composite plate with a delamination. The analysis is focused on higher harmonic generation in vibration responses for various excitation amplitude levels. This effect is investigated using the triple correlation technique. The dynamics of composite plate was modelled using two-dimensional finite elements and the classical lamination theory. The doubled-node approach was used to model delamination area. Mode shapes and natural frequencies were estimated based on numerical models. Next, the delamination divergence analysis was used to obtain relative displacements for delaminated plies. Experimental modal analysis test was carried out to verify the numerical models. The two strongest vibration modes as well as two vibration modes with the smallest and largest motion level of delaminated plies were selected for nonlinear vibration test. The Fisher criterion was employed to verify The results show that the method can be used not only to reveal nonlinearities, but also to reliably detect impact damage in composites. These results are confirmed using the statistical analysis.

show abstract

“…Several modern techniques e.g., statistical process control, neural networks, advanced signal processing, genetic algorithm, wavelet analysis etc., have been researched for detecting damage in composite materials, many of them showing the effectiveness of dynamic response measurements in monitoring the health of engineering structures [14][15][16][17][18][19][20][21][22][23]. These methods are generally classified as modern-type methods for damage detection.…”

Section: Introductionmentioning

confidence: 99%

Damage monitoring in sandwich beams by modal parameter shifts: A comparative study of burst random and sine dwell vibration testing

Shahdin¹,

Morlier²,

Gourinat³

2010

Journal of Sound and Vibration

View full text Add to dashboard Cite

This paper presents an experimental study on the effects of multi-site damage on the vibration response of honeycomb sandwich beams, damaged by two different ways i.e., impact damage and core-only damage simulating damage due to bird or stone impact or due to mishandling during assembly and maintenance. The variation of the modal parameters with different levels of impact energy and density of damage is studied. Vibration tests have been carried out with both burst random and sine dwell testing in order to evaluate the damping estimation efficiency of these methods in the presence of damage. Sine dwell testing is done in both up and down frequency directions in order to detect structural non-linearities. Results show that damping ratio is a more sensitive parameter for damage detection than the natural frequency. Design of experiments (DOE) highlighted density of damage as the factor having a more significant effect on the modal parameters and also proved that sine dwell testing is more suitable for damping estimation in the presence of damage as compared to burst random testing.

show abstract

Impact detection in an aircraft composite panel—A neural-network approach

Cited by 99 publications

References 1 publication

Multiway Partial Least Square (MPLS) to estimate impact localization in structures

Multiway Partial Least Square (MPLS) to estimate impact localization in structures

Triple correlation for detection of damage-related nonlinearities in composite structures

Damage monitoring in sandwich beams by modal parameter shifts: A comparative study of burst random and sine dwell vibration testing

Contact Info

Product

Resources

About