ISSN:
1662-9752
Source:
Scientific.Net: Materials Science & Technology / Trans Tech Publications Archiv 1984-2008
Topics:
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Notes:
In this paper, algorithms are presented for predicting peen forming parameters of integralaircraft wing panels with complex airfoil shapes. The peen forming deformation is divided intostretching deformation and bending deformation. The stretching deformation is assumed to resultfrom the tensile strain within the plane panel, and the bending deformation corresponds to thedifference of maximum and minimum curvature of the airfoil surface. The distribution of theforming tensile strain within the panel is obtained by optimal mapping of the airfoil surface in thesense that the stretching deformation energy from the plane panel to its spatial shape is minimized.In order to fit the nonlinear relation between the peening parameters and the deforming parameters,a back-propagation (BP) artificial neural network (ANN) is modeled with input parameters ofthickness, curvature, tensile strain, etc, to predict the peening parameters of coverage, air pressureand intensity. Experimental peen forming data are given to train the BP ANN. It’s verified that thepredicting methods are effective
Type of Medium:
Electronic Resource
URL:
http://www.tib-hannover.de/fulltexts/2011/0528/02/14/transtech_doi~10.4028%252Fwww.scientific.net%252FMSF.532-533.937.pdf
Permalink