mlsanityData to 7 Oct 2026

Deep learning for determining a near-optimal topological design without any iteration

arXiv 1801.05463 ↗First posted 13 Jan 2018cs.LG physics.comp-phcited by 40

Not on the map. Why?

Abstract (arXiv)

In this study, we propose a novel deep learning-based method to predict an optimized structure for a given boundary condition and optimization setting without using any iterative scheme. For this purpose, first, using open-source topology optimization code, datasets of the optimized structures paired with the corresponding information on boundary conditions and optimization settings are generated at low (32 x 32) and high (128 x 128) resolutions. To construct the artificial neural network for the proposed method, a convolutional neural network (CNN)-based encoder and decoder network is trained using the training dataset generated at low resolution. Then, as a two-stage refinement, the conditional generative adversarial network (cGAN) is trained with the optimized structures paired at both low and high resolutions, and is connected to the trained CNN-based encoder and decoder network. The performance evaluation results of the integrated network demonstrate that the proposed method can determine a near-optimal structure in terms of pixel values and compliance with negligible computational time.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 9; 2024: 5; 2025: 4; 2026: 6.

40 papers.

Sort:

By area:

  1. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  2. 2022Diffusion Models Beat GANs on Topology Optimizationcited by 79
  3. 2023Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generationcited by 51
  4. 2021NTopo: Mesh-free Topology Optimization using Implicit Neural Representationscited by 41
  5. 2022Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computingcited by 24
  6. 2022Topology Optimization via Machine Learning and Deep Learning: A Reviewcited by 22
  7. 2023Deep Learning in Deterministic Computational Mechanicscited by 21
  8. 2021Real-Time Topology Optimization in 3D via Deep Transfer Learningcited by 14
  9. 2023Constraining Generative Models for Engineering Design with Negative Datacited by 11
  10. 2023Diffusing the Optimal Topology: A Generative Optimization Approachcited by 9
  11. 2021De-homogenization using Convolutional Neural Networkscited by 6
  12. 2023DMF-TONN: Direct Mesh-free Topology Optimization using Neural Networkscited by 6
28 more
  1. 2023Latent Diffusion Models for Structural Component Designcited by 4
  2. 2023Topology Optimization using Neural Networks with Conditioning Field Initialization for Improved Efficiencycited by 3
  3. 2023Dynamically configured physics-informed neural network in topology optimization applicationscited by 3
  4. 2024NITO: Neural Implicit Fields for Resolution-free Topology Optimizationcited by 3
  5. 2024Neural Networks for Generating Better Local Optima in Topology Optimizationcited by 3
  6. 2025A surrogate model for topology optimisation of elastic structures via parametric autoencoderscited by 3
  7. 2021Speeding up Computational Morphogenesis with Online Neural Synthetic Gradientscited by 2
  8. 2022Conditional Generative Models for Simulation of EMG During Naturalistic Movementscited by 2
  9. 2024Deep Generative Design for Mass Productioncited by 2
  10. 2024Inverse design with conditional cascaded diffusion modelscited by 2
  11. 2025Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimizationcited by 2
  12. 2021GANTL: Towards Practical and Real-Time Topology Optimization with Conditional GANs and Transfer Learningcited by 1
  13. 2021Robust Topology Optimization Using Multi-Fidelity Variational Autoencoderscited by 1
  14. 2022An Adaptive and Scalable ANN-based Model-Order-Reduction Method for Large-Scale TO Designscited by 1
  15. 2024Deep Generative Model-based Synthesis of Four-bar Linkage Mechanisms with Target Conditionscited by 1
  16. 2025A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitoring benchmark validationcited by 1
  17. 2026Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimizationcited by 1
  18. 2026Trajectory-Aware Flow Matching for Topology Optimisationcited by 1
  19. 2021A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)cited by 0
  20. 2022FRC-TOuNN: Topology Optimization of Continuous Fiber Reinforced Composites using Neural Networkcited by 0
  21. 2022SELTO: Sample-Efficient Learned Topology Optimizationcited by 0
  22. 2022Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Componentscited by 0
  23. 2023Machine Learning-Based Multi-Objective Design Exploration Of Flexible Disc Elementscited by 0
  24. 2025Censored Sampling for Topology Design: Guiding Diffusion with Human Preferencescited by 0
  25. 2026TopoEdit: Fast Post-Optimization Editing of Topology Optimized Structurescited by 0
  26. 2026AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Controlcited by 0
  27. 2026Adversarial Agents on Topology Optimization: Understanding the Fragility and Robustness of Deep Learning-based and Physics-Based Design Models under Adversarial Perturbationcited by 0
  28. 2026HGTO: A Unified Graph-Based Physics-Informed Formulation for Structural Topology Optimizationcited by 0