A dual physics-informed neural network for topology optimization
Preprint
Abstract
We propose a novel dual physics-informed neural network for topology optimization (DPNN-TO), which merges physics-informed neural networks (PINNs) with the traditional SIMP-based topology optimization (TO) algorithm. This approach leverages two interlinked neural networks-a displacement network and an implicit density network-connected through an energy-minimization-based loss function derived from the variational principles of the governing equations. By embedding deep learning within the physical constraints of the problem, DPNN-TO eliminates the need for large-scale data and analytical sensitivity analysis, addressing key limitations of traditional methods. The framework efficiently minimizes compliance through energy-based objectives while enforcing volume fraction constraints, producing high-resolution designs for both 2D and 3D optimization problems. Extensive numerical validation demonstrates that DPNN-TO outperforms conventional methods, solving complex structural optimization scenarios with greater flexibility and computational efficiency, while addressing challenges such as multiple load cases and three-dimensional problems without compromising accuracy.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- DCEM: A deep complementary energy method for linear elasticityInternational Journal for Numerical Methods in Engineering, 2024
- DMF-TONN: Direct Mesh-free Topology Optimization using Neural NetworksEngineering with Computers, 2023
- Deep energy method in topology optimization applicationsActa Mechanica, 2022
- Universal machine learning for topology optimizationComputer Methods in Applied Mechanics and Engineering, 2021
- TOuNN: Topology Optimization using Neural NetworksStructural and Multidisciplinary Optimization, 2020
- Accelerated topology optimization by means of deep learningStructural and Multidisciplinary Optimization, 2020
- Non-iterative structural topology optimization using deep learningComputer-Aided Design, 2019
- Deep learning for determining a near-optimal topological design without any iterationStructural and Multidisciplinary Optimization, 2018
- A novel Multi-Grid assisted reanalysis for re-meshed finite element modelsComputer Methods in Applied Mechanics and Engineering, 2017
- Efficient topology optimization in MATLAB using 88 lines of codeStructural and Multidisciplinary Optimization, 2010