This study presents a neural network (NN)-based approach for optimising material composition in multi-layered functionally graded (FG) plates to minimise steady-state thermal stress. The focus is on the metal-ceramic composition across the thickness of heat-resistant FG plates, with the volume fractions of the ceramic constituent in each layer treated as design variables. A fully-connected NN, configured with an open-source Bayesian optimisation framework, is employed to predict the maximum in-plane thermal stress for various combinations of design variables. ; The optimal distribution of material composition is determined by applying a backpropagation algorithm to the NN. Numerical computations on ten- and twelve-layered FG plates demonstrate the usefulness of this approach in designing FG materials. NNs trained with 8000 samples enable the successful acquisition of valid optimal solutions within a practical timeframe.
Zielona Góra: Uniwersytet Zielonogórski
IJAME, volume 29, number 4 (2024)
Biblioteka Uniwersytetu Zielonogórskiego
2024-12-16
2024-12-16
7
https://zbc.uz.zgora.pl/repozytorium/publication/91610
Nazwa wydania | Data |
---|---|
Optimisation of material composition in functionally graded plates using a structure-tuned deep neural network | 2024-12-16 |
Rani, Pooja Singh, Kuldip Jurczak, Paweł - red.
Rani, P. Singh, K. Muwal, R. Jurczak, Paweł - red.
Patra, Rajesh Barik, Sakti Pada Chaudhuri, P.K. Jurczak, Paweł - red.
Praczyk, Tomasz Korbicz, Józef (1951- ) - red.
Patan, Krzysztof Witczak, Marcin Korbicz, Józef (1951- ) Korbicz, Józef (1951- ) - ed. Sauter, Dominique - ed.
Duch, Włodzislaw Adamczak, Rafał Diercksen, Geerd H.F. Rutkowska, Danuta - ed. Zadeh, Lotfi A. - ed.
Witczak, Marcin Korbicz, Józef (1951- ) - red.
Szabó, Tamás Horváth, Gábor Korbicz, Józef (1951- ) - red. Patton, Ronald J. - red.