FRC-TOuNN: Topology Optimization of Continuous Fiber Reinforced Composites using Neural Network

被引:30
作者
Chandrasekhar, Aaditya [1 ]
Mirzendehdel, Amir [2 ]
Behandish, Morad [2 ]
Suresh, Krishnan [1 ]
机构
[1] Univ Wisconsin, Dept Mech Engn, Madison, WI 53706 USA
[2] Palo Alto Res Ctr, Palo Alto, CA USA
关键词
Topology optimization; Fiber composites; Neural network; Automatic differentiation; OPTIMAL ORIENTATION; DESIGN; THICKNESS; ENERGY; LENGTH;
D O I
10.1016/j.cad.2022.103449
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper, we present a topology optimization (TO) framework to simultaneously optimize the matrix topology and fiber distribution of functionally graded continuous fiber-reinforced composites (FRC). Current approaches in density-based TO for FRC use the underlying finite element mesh both for analysis and design representation. This poses several limitations while enforcing sub-element fiber spacing and generating high-resolution continuous fibers. In contrast, we propose a mesh-independent representation based on a neural network (NN) both to capture the matrix topology and fiber distribution. The implicit NN-based representation enables geometric and material queries at a higher resolution than a mesh discretization. This leads to the accurate extraction of functionally-graded continuous fibers. Further, by integrating the finite element simulations into the NN computational framework, we can leverage automatic differentiation for end-to-end automated sensitivity analysis, i.e., we no longer need to manually derive cumbersome sensitivity expressions. We demonstrate the effectiveness and computational efficiency of the proposed method through several numerical examples involving various objective functions. We also show that the optimized continuous fiber reinforced composites can be directly fabricated at high resolution using additive manufacturing.(c) 2022 Elsevier Ltd. All rights reserved.
引用
收藏
页数:12
相关论文
共 77 条
[31]   Full-scale topology optimization for fiber-reinforced structures with continuous fiber paths [J].
Li, Hang ;
Gao, Liang ;
Li, Hao ;
Li, Xiaopeng ;
Tong, Haifeng .
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2021, 377
[32]   Investigation into the topology optimization for conductive heat transfer based on deep learning approach [J].
Lin, Qiyin ;
Hong, Jun ;
Liu, Zheng ;
Li, Baotong ;
Wang, Jihong .
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER, 2018, 97 :103-109
[33]   Optimization formulations for the maximum nonlinear buckling load of composite structures [J].
Lindgaard, Esben ;
Lund, Erik .
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2011, 43 (05) :631-646
[34]   Current and future trends in topology optimization for additive manufacturing [J].
Liu, Jikai ;
Gaynor, Andrew T. ;
Chen, Shikui ;
Kang, Zhan ;
Suresh, Krishnan ;
Takezawa, Akihiro ;
Li, Lei ;
Kato, Junji ;
Tang, Jinyuan ;
Wang, Charlie C. L. ;
Cheng, Lin ;
Liang, Xuan ;
To, Albert. C. .
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2018, 57 (06) :2457-2483
[35]   Optimal orientation of orthotropic materials using an energy based method [J].
Luo, JH ;
Gea, HC .
STRUCTURAL OPTIMIZATION, 1998, 15 (3-4) :230-236
[36]  
Mildenhall B, 2020, Arxiv, DOI [arXiv:2003.08934, DOI 10.48550/ARXIV.2003.08934]
[37]   Topology Optimization for Manufacturing with Accessible Support Structures [J].
Mirzendehdel, Amir M. ;
Behandish, Morad ;
Nelaturi, Saigopal .
COMPUTER-AIDED DESIGN, 2022, 142
[38]   Topology optimization with accessibility constraint for multi-axis machining [J].
Mirzendehdel, Amir M. ;
Behandish, Morad ;
Nelaturi, Saigopal .
COMPUTER-AIDED DESIGN, 2020, 122
[39]   Exploring feasible design spaces for heterogeneous constraints [J].
Mirzendehdel, Amir M. ;
Behandish, Morad ;
Nelaturi, Saigopal .
COMPUTER-AIDED DESIGN, 2019, 115 :323-347
[40]   Strength-based topology optimization for anisotropic parts [J].
Mirzendehdel, Amir M. ;
Rankouhi, Behzad ;
Suresh, Krishnan .
ADDITIVE MANUFACTURING, 2018, 19 :104-113