Genetic optimization of stiffened plates without the FE mesh support

Abstract

SUMMARYThis paper deals with the optimization of beam sti eners on plates by varying their positions in order to minimize the maximum de ection of the plate. Genetic algorithms are used. The research strategy consists in substituting, for ÿnite element calculations in the optimization process, an approximate response of a neural network, or an approximate response from a Ritz method. This paper shows how it is possible to deal with more important problems and to envisage more general baseline design for sti ened plates by adding the orientation angle of each sti ener as a design variable. This paper also shows how one can free oneself from the FE mesh, i.e. how one no longer needs the support of the mesh for the sti eners.

Optimum Structural Design Using Bio-Inspired Search Methods: A Survey and Applications

“…Marcelin [71,72] uses GAs to reduce the number of evaluations of the objective function by approximation, using two methods-an artificial neural network and the Ritz method. It is applied to the optimization of a stiffened plate, considering the position and angle of the stiffeners.…”

A geometry constraint handling technique for stiffener layout optimization problem

“…However, in case a base plate has a concave shape as Fig. 3, it is difficult to describe the geometry constraint mathematically with just the coordinates of two end points of the stiffener, which is the main reason why most of the previous researches [3][4][5][6][7][8][9] inside the base plate, where the stiffener cannot be placed, it becomes more difficult. In addition, if the base plate shape is complex, many inequality constraints are needed to define a feasible region O: For example, Fig.…”

“…However, it was claimed that the overlooked variables (i.e. positions and lengths of stiffeners) also affect the dynamics of base structures significantly [3][4][5][6][7][8][9].…”

A metamodel using neural networks and genetic algorithms for an integrated optimal design of mechanisms

“…We already used the genetic algorithms method on several occasions, within the framework of various problems in optimisation of systems or mechanical structures. These algorithms appeared very effective, such as the difficult case of optimising gears [1], or optimising supports with applications in machining [12,13], or optimising the position of stiffeners on plates [14,15].…”