The objective of this paper is to present first results of a running study on optimisation of aircraft components (composite panels of a typical vertical tail plane) by using Genetic Algorithms (GA) and Neural Networks (NN). The panels considered are standardised to same extent bur still there is a wide scope of discrete and continuous design variables that can be adjusted to increase performance or reduce structural weight. A NN is trained for every panel configuration using a back-propagation algorithm with data sets taken tram finite element analyses spread randomly over the design space. The trained network is then used to predict the values of the constraint functions (strain and buckling multipliers). The approach is formulated in this manner to maintain maximum flexibility regarding the implementation of new variables or models and with the prospect of optimising the assembly as a whole. Results show that in design problems with high dimensionality the approach becomes more attractive, especially when the optimisation has to be run repeatedly for panels under different loading/sizing conditions. The optimisation algorithm has proven to be robust though dependent on the smoothness of the network output function. A modified method that feeds back the found optima is proposed to improve accuracy of the NN and decrease preparation time.
Optimization of composite panels using neural networks and genetic algorithms
Optimierung von Verbundwerkstoffplatten mit neuronalen Netzwerken und genetischen Algorithmen
2003
11 Seiten, 4 Bilder, 7 Quellen
Conference paper
English
Minimum Weight Optimization of Composite Stiffened Panels Using Neural Networks
British Library Conference Proceedings | 2003
|Two-Level Optimization Technique of Composite Laminate Panels by Genetic Algorithms
British Library Conference Proceedings | 1996
|