In the architecture and construction industries, structural design for large buildings has always been laborious, time-consuming, and difficult to optimize. It is an iterative process that involves two steps: analyzing the current structural design by a slow and computationally expensive simulation, and then manually revising the design based on professional experience and rules. In this work, we propose an end-to-end learning pipeline to solve the size design optimization problem, which is to design the optimal cross-sections for columns and beams, given the design objectives and building code as constraints. We pre-train a graph neural network as a surrogate model to not only replace the structural simulation for speed but also use its differentiable nature to provide gradient signals to the other graph neural network for size optimization. Our results show that the pre-trained surrogate model can predict simulation results accurately, and the trained optimization model demonstrates the capability of designing convincing cross-section designs for buildings under various scenarios.

建筑物的结构设计过程耗时而且繁琐。本文提出了一种使用基于图的管道结构，通过深度学习训练和预训练的不同iable结构模拟器，学习建议优化的方案，减少建筑重量和碳足迹。实验结果表明，该方法的建筑结构性能与遗传算法（GA）优化的结构性能相当，同时满足所有约束条件。

学习模拟和设计结构工程