arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.14795cs.CE
收藏

用于预测材料加工和增材制造中多物理场解场的高级深度算子网络

Advanced Deep Operator Networks to Predict Multiphysics Solution Fields in Materials Processing and Additive Manufacturing

Shashank Kushwaha, Jaewan Park, Seid Koric, Junyan He, Iwona Jasiuk, Diab Abueidda

AI总结:

本文提出结合序列学习和 ResUNet 架构的 DeepONet 模型,首次用于同时预测材料加工和增材制造中可变条件下的热-机械解场,在精度相当下速度比 FEA 快数个数量级,支持即时预测与设计优化。

摘要:

与经典人工神经网络不同,后者需要为每组新的参数输入重新训练,而最新引入的深度学习框架 Deep Operator Network (DeepONet) 通过将参数函数(无限维对象)作为输入并将其映射到完整解场来逼近线性和非线性解算子。本文首次训练了两种新设计的 DeepONet 公式,结合序列学习和 Residual U-Net (ResUNet) 架构,以同时预测在可变载荷、加载历史、工艺参数甚至可变几何形状下的完整热场和机械解场。展示了两个实际应用:1- 具有多种粘塑性本构定律的钢连铸耦合热-机械分析;2- 增材制造的顺序耦合直接能量沉积。尽管目标应力分布具有高度挑战性的空间变异性,DeepONet 能推断出合理准确的全场温度和应力解,速度比传统且高度优化的有限元分析 (FEA) 快几个数量级,即使 FEA 模拟在最新高性能计算平台上运行。所提出的 DeepONet 模型几乎能即时为未见输入参数提供场预测,为这些关键工业过程的未来初步评估和设计优化打开了大门。

英文摘要:

Unlike classical artificial neural networks, which require retraining for each new set of parametric inputs, the Deep Operator Network (DeepONet), a lately introduced deep learning framework, approximates linear and nonlinear solution operators by taking parametric functions (infinite-dimensional objects) as inputs and mapping them to complete solution fields. In this paper, two newly devised DeepONet formulations with sequential learning and Residual U-Net (ResUNet) architectures are trained for the first time to simultaneously predict complete thermal and mechanical solution fields under variable loading, loading histories, process parameters, and even variable geometries. Two real-world applications are demonstrated: 1- coupled thermo-mechanical analysis of steel continuous casting with multiple visco-plastic constitutive laws and 2- sequentially coupled direct energy deposition for additive manufacturing. Despite highly challenging spatially variable target stress distributions, DeepONets can infer reasonably accurate full-field temperature and stress solutions several orders of magnitude faster than traditional and highly optimized finite-element analysis (FEA), even when FEA simulations are run on the latest high-performance computing platforms. The proposed DeepONet model's ability to provide field predictions almost instantly for unseen input parameters opens the door for future preliminary evaluation and design optimization of these vital industrial processes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑