TY - GEN
T1 - Predictive Design of a Multilayered Laminate Shell Based on AI and 1st-Order Classical Laminate Theory
AU - Helaili, Sofiene
AU - Rezgui, Taysir
AU - Najar, Fehmi
AU - Chafra, Moez
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - The design of multilayered laminate shells and plates requires a very specific approach. This is a multistage approach that begins with a pre-design work to select the number of layers, the layer thickness, and the layer reinforcement type depending on the application and based on previous works. After that, the predesign is subject to verification, and the structural element made of multilayered laminates is checked. The loads, the load combinations, and the structural calculation make it possible to determine the loads to which the structural element would be subjected: the bending moments, the shear forces, and the concentrated forces. The shells are structural elements mainly subject to bending moments, but their dimensioning also depends on the nature of the supports: fixed, articulated, or a combination of them. In this paper, a pre-design approach using artificial intelligence has been developed. A database of laminated shells was generated based on input parameters. Criteria related to resistance and deformation made it possible to calculate an objective function to determine the optimal design. This same base was used to teach an artificial intelligence algorithm to predict the optimal design. The algorithm has been tested, and the results are predictive to some degree of accuracy.
AB - The design of multilayered laminate shells and plates requires a very specific approach. This is a multistage approach that begins with a pre-design work to select the number of layers, the layer thickness, and the layer reinforcement type depending on the application and based on previous works. After that, the predesign is subject to verification, and the structural element made of multilayered laminates is checked. The loads, the load combinations, and the structural calculation make it possible to determine the loads to which the structural element would be subjected: the bending moments, the shear forces, and the concentrated forces. The shells are structural elements mainly subject to bending moments, but their dimensioning also depends on the nature of the supports: fixed, articulated, or a combination of them. In this paper, a pre-design approach using artificial intelligence has been developed. A database of laminated shells was generated based on input parameters. Criteria related to resistance and deformation made it possible to calculate an objective function to determine the optimal design. This same base was used to teach an artificial intelligence algorithm to predict the optimal design. The algorithm has been tested, and the results are predictive to some degree of accuracy.
KW - AI
KW - CLT theory
KW - Multilayered laminate
UR - http://www.scopus.com/inward/record.url?scp=85205975230&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-70428-4_16
DO - 10.1007/978-3-031-70428-4_16
M3 - Conference contribution
AN - SCOPUS:85205975230
SN - 9783031704277
T3 - Lecture Notes in Mechanical Engineering
SP - 147
EP - 153
BT - Advances in Mechanical Engineering and Mechanics III - Selected Papers from the 6th Tunisian Congress on Mechanics, CoTuMe 2023
A2 - Bouraoui, Tarak
A2 - Mzali, Slah
A2 - Ben Moussa, Naoufel
A2 - Zemzemi, Farhat
A2 - Benameur, Tarek
A2 - Aifaoui, Nizar
A2 - Znaidi, Amna
A2 - Ennetta, Ridha
A2 - Djemal, Fathi
PB - Springer Science and Business Media Deutschland GmbH
T2 - 6th Tunisian Congress on Mechanics, CoTuMe 2023
Y2 - 17 March 2023 through 19 March 2023
ER -