Machine learning for topology optimization: Physics-based learning through an independent training strategy
Machine learning for topology optimization: Physics-based learning through an independent training strategy
复制标题
用于拓扑优化的机器学习：通过独立的训练策略进行基于物理的学习
DOI：
10.1016/j.cma.2022.115116
复制
发表时间：
2022-08
影响因子：
7.2
通讯作者：
Fernando V. Senhora;Heng Chi;Yuyu Zhang;L. Mirabella;T. Tang;Glaucio H. Paulino
中科院分区：
文献类型：
--
作者：
Fernando V. Senhora;Heng Chi;Yuyu Zhang;L. Mirabella;T. Tang;Glaucio H. Paulino
拓扑优化的高计算成本阻碍了其作为创成式设计工具的广泛使用。为了减少这种计算成本，我们提出了一种人工智能方法，在不牺牲其精度的情况下大大加快了拓扑优化。由此产生的人工智能驱动的拓扑优化可以完全捕获问题的根本物理。因此，机器学习模型由一个带有剩余连接的卷积神经网络组成，能够概括它从训练集中学到的知识，以解决具有不同几何、边界条件、网格大小、体积分数和过滤器半径的各种问题。我们将机器学习模型与拓扑优化分开进行训练，这使我们能够实现相当大的加速比(比传统的拓扑优化快30倍)。通过几个设计实例，我们证明了所提出的人工智能驱动的拓扑优化框架是有效的、可扩展的和高效的。该框架的加速使拓扑优化成为工程师寻找更轻、更坚固结构的更具吸引力的工具，有可能彻底改变工程设计过程。虽然这项工作集中在柔度最小化问题上，但所提出的框架可以推广到其他目标函数、约束和物理问题。
The high computational cost of topology optimization has prevented its widespread use as a generative design tool. To reduce this computational cost, we propose an artificial intelligence approach to drastically accelerate topology optimization without sacrificing its accuracy. The resulting AI-driven topology optimization can fully capture the underlying physics of the problem. As a result, the machine learning model, which consists of a convolutional neural network with residual links, is able to generalize what it learned from the training set to solve a wide variety of problems with different geometries, boundary conditions, mesh sizes, volume fractions and filter radius. We train the machine learning model separately from the topology optimization, which allows us to achieve a considerable speedup (up to 30 times faster than traditional topology optimization). Through several design examples, we demonstrate that the proposed AI-driven topology optimization framework is effective, scalable and efficient. The speedup enabled by the framework makes topology optimization a more attractive tool for engineers in search of lighter and stronger structures, with the potential to revolutionize the engineering design process. Although this work focuses on compliance minimization problems, the proposed framework can be generalized to other objective functions, constraints and physics.