近日,上海大学的孙升及其研究小组取得一项新进展。经过不懈努力,他们利用集成有限元建模和深度学习实现介电弹性体复合材料中驱动性能的计算机优化
本研究提出了一种创新的集成框架,结合有限元建模(FEM)和深度学习技术,用于优化介电弹性(DE)复合材料的微观结构。首先,FEM被用来计算不同填料组合的驱动性能和有效模量。这些数据随后被用来训练一个卷积神经网络(CNN)。CNN的目的是学习从填料组合到性能映射的复杂关系。然后,将训练好的CNN集成到一个多目标遗传算法(NSGA-II)中。
与传统的FEM-NSGA-II方法相比,这种结合深度学习的方法在相同的时间内能够生成具有更高驱动性能和材料模量的设计方案。这个框架的独特之处在于,它利用人工智能来探索和引导大量的设计可能性,从而有效地优化高性能DE复合材料的微观结构。
据悉,介电弹性体(DEs)要求在施加电压下平衡的电动驱动性能和机械完整性。为了优化其驱动性能和材料模量,人们采用了高介电颗粒作为填料,这为设计提供了广泛的空间,可以调整颗粒的浓度、形态和分布。
附:英文原文
Title: In silico optimization of actuation performance in dielectric elastomer composites via integrated finite element modeling and deep learning
Author: Jiaxuan Ma, Sheng Sun
Issue&Volume: 2024-01-08
Abstract: Dielectric elastomers (DEs) require balanced electric actuation performance and mechanical integrity under applied voltages. Incorporating high dielectric particles as fillers provides extensive design space to optimize concentration, morphology, and distribution for improved actuation performance and material modulus. This study presents an integrated framework combining finite element modeling (FEM) and deep learning to optimize the microstructure of DE composites. FEM first calculates actuation performance and the effective modulus across varied filler combinations, with these data used to train a convolutional neural network (CNN). Integrating the CNN into a multi-objective genetic algorithm (NSGA-II) generates designs with enhanced actuation performance and material modulus compared to the conventional FEM-NSGA-II approach within the same time. This framework harnesses artificial intelligence to navigate vast design possibilities, enabling optimized microstructures for high-performance DE composites.
DOI: 10.1016/j.taml.2024.100490
Source: http://taml.cstam.org.cn/article/doi/10.1016/j.taml.2024.100490
Theoretical & Applied Mechanics Letters:《理论与应用力学快报》,创刊于2011年。隶属于中国理论与应用机械学会,最新IF:3.4
官方网址:http://taml.cstam.org.cn/
投稿链接:https://www2.cloud.editorialmanager.com/taml/default2.aspx