当前位置: X-MOL 学术J. Mech. Behav. Biomed. Mater. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Exploring the potential of transfer learning for metamodels of heterogeneous material deformation
Journal of the Mechanical Behavior of Biomedical Materials ( IF 3.9 ) Pub Date : 2020-12-31 , DOI: 10.1016/j.jmbbm.2020.104276
E. Lejeune , B. Zhao

From the nano-scale to the macro-scale, biological tissue is spatially heterogeneous. Even when tissue behavior is well understood, the exact subject specific spatial distribution of material properties is often unknown. And, when developing computational models of biological tissue, it is usually prohibitively computationally expensive to simulate every plausible spatial distribution of material properties for each problem of interest. Therefore, one of the major challenges in developing accurate computational models of biological tissue is capturing the potential effects of this spatial heterogeneity. Recently, machine learning based metamodels have gained popularity as a computationally tractable way to overcome this problem because they can make predictions based on a limited number of direct simulation runs. These metamodels are promising, but they often still require a high number of direct simulations to achieve an acceptable performance. Here we show that transfer learning, a strategy where knowledge gained while solving one problem is transferred to solving a different but related problem, can help overcome this limitation. Critically, transfer learning can be used to leverage both low-fidelity simulation data and simulation data that is the outcome of solving a different but related mechanical problem. In this paper, we extend Mechanical MNIST, our open source benchmark dataset of heterogeneous material undergoing large deformation, to include a selection of low-fidelity simulation results that require ≈ 2 − 4 orders of magnitude less CPU time to run. Then, we show that transferring the knowledge stored in metamodels trained on these low-fidelity simulation results can vastly improve the performance of metamodels used to predict the results of high-fidelity simulations. In the most dramatic examples, metamodels trained on 100 high fidelity simulations but pre-trained on 60,000 low-fidelity simulations achieves nearly the same test error as metamodels trained on 60,000 high-fidelity simulations (1 − 1.5% mean absolute percent error). In addition, we show that transfer learning is an effective method for leveraging data from different load cases, and for leveraging low-fidelity two-dimensional simulations to predict the outcomes of high-fidelity three-dimensional simulations. Looking forward, we anticipate that transfer learning will enable us to better capture the influence of tissue spatial heterogeneity on the mechanical behavior of biological materials across multiple different domains.



中文翻译:

探索异质材料变形元模型的转移学习潜力

从纳米尺度到宏观尺度,生物组织在空间上是异质的。即使组织行为被很好地理解,材料属性的确切对象特定空间分布也常常是未知的。并且,当开发生物组织的计算模型时,对于每个感兴趣的问题,模拟材料特性的每个合理的空间分布通常在计算上过于昂贵。因此,开发生物组织的精确计算模型的主要挑战之一是捕获这种空间异质性的潜在影响。最近,基于机器学习的元模型已成为解决该问题的一种易于处理的计算方式,因为它们可以基于有限数量的直接模拟运行进行预测。这些元模型很有希望,但是它们通常仍需要大量直接仿真才能达到可接受的性能。在这里,我们表明,转移学习是一种将解决一个问题时获得的知识转移到解决另一个不同但相关的问题上的策略,可以帮助克服这一局限性。至关重要的是,转移学习可用于利用低保真度模拟数据和模拟数据,这是解决不同但相关的机械问题的结果。在本文中,我们扩展了机械MNIST,这是我们经历大变形的异质材料的开源基准测试数据集,以包括一些低保真模拟结果,这些结果需要大约2-4个数量级的CPU运行时间。然后,我们表明,转移存储在这些低保真度模拟结果训练的元模型中的知识可以极大地提高用于预测高保真度模拟结果的元模型的性能。在最引人注目的示例中,在100个高保真模拟中训练但在60,000个低保真模拟中进行预训练的元模型与在60,000个高保真模拟中训练的元模型实现几乎相同的测试误差(1 − 1.5表示绝对百分比误差)。此外,我们证明了转移学习是一种有效的方法,可以利用来自不同工况的数据,并利用低保真度的二维模拟来预测高保真度的三维模拟的结果。展望未来,我们预计转移学习将使我们能够更好地捕获组织空间异质性对跨多个不同域的生物材料的机械行为的影响。

更新日期:2021-02-25
down
wechat
bug