The bend-twist coupling effect of anisotropic materials such as composite laminates can be used to create smart structures capable of adapting their shapes to changing operating conditions. This effect can be useful in wind energy systems with composite blades for improving the rotor operational range as a passive control strategy. However, it is difficult to design such structures in order to attain a desired angle when bent. This paper proposes a metamodel-based methodology to design laminates with bend-twist coupling effect by means of genetic algorithms (GA) and artificial neural networks (ANN) integrated with a finite element model (FEM) capable of defining the stacking sequence that a laminate needs to reach a certain twist angle when submitted to bending load. The genetic algorithm uses a deterministic tournament for selection, a two-point method for crossover and an ANN trained with FEM simulations is used as the fitness function for reducing computational time. This strategy could ease the design of this type of structures in practical scenarios.
|Título de la publicación alojada||2019 IEEE 2nd International Conference on Renewable Energy and Power Engineering, REPE 2019|
|Editorial||Institute of Electrical and Electronics Engineers Inc.|
|Número de páginas||5|
|ISBN (versión digital)||9781728145624|
|Estado||Publicada - nov. 2019|
|Publicado de forma externa||Sí|
|Evento||2nd IEEE International Conference on Renewable Energy and Power Engineering, REPE 2019 - Toronto, Canadá|
Duración: 2 nov. 2019 → 4 nov. 2019
Serie de la publicación
|Nombre||2019 IEEE 2nd International Conference on Renewable Energy and Power Engineering, REPE 2019|
|Conferencia||2nd IEEE International Conference on Renewable Energy and Power Engineering, REPE 2019|
|Período||2/11/19 → 4/11/19|
Nota bibliográficaPublisher Copyright:
© 2019 IEEE.