Convolutional encoder-decoder network using transfer learning for topology optimization

被引:1
作者
Ates, Gorkem Can [1 ]
Gorguluarslan, Recep M. [1 ]
机构
[1] TOBB Univ Econ & Technol, Dept Mech Engn, Sogutozu Cd 43 Cankaya, TR-06560 Ankara, Turkiye
关键词
Deep learning; Transfer learning; Fine-tuning; VGG network; Topology optimization; SEMANTIC SEGMENTATION; DEEP;
D O I
10.1007/s00521-023-09308-z
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
State-of-the-art deep neural networks have achieved great success as an alternative to topology optimization by eliminating the iterative framework of the optimization process. However, models with strong predicting capabilities require massive data, which can be time-consuming, particularly for high-resolution structures. Transfer learning from pre-trained networks has shown promise in enhancing network performance on new tasks with a smaller amount of data. In this study, a U-net-based deep convolutional encoder-decoder network was developed for predicting high-resolution (256 x 256) optimized structures using transfer learning and fine-tuning for topology optimization. Initially, the VGG16 network pre-trained on ImageNet was employed as the encoder for transfer learning. Subsequently, the decoder was constructed from scratch and the network was trained in two steps. Finally, the results of models employing transfer learning and those trained entirely from scratch were compared across various core parameters, including different initial input iterations, fine-tuning epoch numbers, and dataset sizes. Our findings demonstrate that the utilization of transfer learning from the ImageNet pre-trained VGG16 network as the encoder can improve the final predicting performance and alleviate structural discontinuity issues in some cases while reducing training time.
引用
收藏
页码:4435 / 4450
页数:16
相关论文
共 52 条
  • [1] Fine-tuning convolutional neural network with transfer learning for semantic segmentation of ground-level oilseed rape images in a field with high weed pressure
    Abdalla, Alwaseela
    Cen, Haiyan
    Wan, Liang
    Rashid, Reem
    Weng, Haiyong
    Zhou, Weijun
    He, Yong
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2019, 167
  • [2] Topology optimization of 2D structures with nonlinearities using deep learning
    Abueidda, Diab W.
    Koric, Seid
    Sobh, Nahil A.
    [J]. COMPUTERS & STRUCTURES, 2020, 237
  • [3] Efficient topology optimization in MATLAB using 88 lines of code
    Andreassen, Erik
    Clausen, Anders
    Schevenels, Mattias
    Lazarov, Boyan S.
    Sigmund, Ole
    [J]. STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2011, 43 (01) : 1 - 16
  • [4] Two-stage convolutional encoder-decoder network to improve the performance and reliability of deep learning models for topology optimization
    Ates, Gorkem Can
    Gorguluarslan, Recep M.
    [J]. STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2021, 63 (04) : 1927 - 1950
  • [5] Banga S, 2018, Arxiv, DOI arXiv:1808.07440
  • [6] Microstructure Representation and Reconstruction of Heterogeneous Materials Via Deep Belief Network for Computational Material Design
    Cang, Ruijin
    Xu, Yaopengxiao
    Chen, Shaohua
    Liu, Yongming
    Jiao, Yang
    Ren, Max Yi
    [J]. JOURNAL OF MECHANICAL DESIGN, 2017, 139 (07)
  • [7] Semantic Segmentation of Remote Sensing Images Using Transfer Learning and Deep Convolutional Neural Network With Dense Connection
    Cui, Binge
    Chen, Xin
    Lu, Yan
    [J]. IEEE ACCESS, 2020, 8 (08): : 116744 - 116755
  • [8] Multi-Objective Topology Optimization of Rotating Machines Using Deep Learning
    Doi, Shuhei
    Sasaki, Hidenori
    Igarashi, Hajime
    [J]. IEEE TRANSACTIONS ON MAGNETICS, 2019, 55 (06)
  • [9] Frid-Adar M, 2018, Arxiv, DOI arXiv:1810.02113
  • [10] Generative Adversarial Networks
    Goodfellow, Ian
    Pouget-Abadie, Jean
    Mirza, Mehdi
    Xu, Bing
    Warde-Farley, David
    Ozair, Sherjil
    Courville, Aaron
    Bengio, Yoshua
    [J]. COMMUNICATIONS OF THE ACM, 2020, 63 (11) : 139 - 144