OpenPyStruct: Open-source toolkit for machine learning-driven structural optimization

Danny Smyl, Bozhou Zhuang, Sam Rigby, Edvard Bruun, Brandon Jones, Patrick Kastner, Iris Tien, Adrien Gallet,
OpenPyStruct: Open-source toolkit for machine learning-driven structural optimization,
Engineering Structures,
Volume 343, Part A,
2025,
120869,
ISSN 0141-0296,
https://doi.org/10.1016/j.engstruct.2025.120869.
(https://www.sciencedirect.com/science/article/pii/S014102962501260X)
Abstract: OpenPyStruct (Toolkit URL: OpenPyStruct, Repository URL: Data) is an open-source toolkit that provides finite element model based optimization frameworks for generating training data and machine learning models for global structural optimization of indeterminate continuous structures. The key machine learning feature of OpenPyStruct is its ability to optimize single or multiple arbitrary loading and support conditions. The framework utilizes multi-core central processing unit (CPU) and graphics processing unit (GPU)-enhanced implementations integrating OpenSeesPy for structural optimization. PyTorch is used for accelerated computations. Accompanying machine learning scripts enable users to train high-fidelity predictive models such as transformer with diffusion modules, physics-informed neural networks (PINNs), convolutional operations, and contemporary machine learning techniques to analyze and optimize structural designs. By incorporating state-of-the-art optimization tools, robust datasets, and flexible machine learning resources, OpenPyStruct aims to establish a scalable and fully-transparent engine for structural optimization by engaging the structural engineering community in this open-source toolkit.
Keywords: Structural design; Finite element method; Machine learning; Optimization; Python; Structural engineering