Accelerating Thermal Simulations in Additive Manufacturing by Training Physics-Informed Neural Networks With Randomly Synthesized Data
Accelerating Thermal Simulations in Additive Manufacturing by Training Physics-Informed Neural Networks With Randomly Synthesized Data
复制标题
通过使用随机合成数据训练物理信息神经网络来加速增材制造中的热模拟
DOI：
10.1115/1.4062852
复制
发表时间：
2024
影响因子：
3.1
通讯作者：
McComb, Christopher
中科院分区：
文献类型：
--
作者：
Chen, Jiangce;Pierce, Justin;Williams, Glen;Simpson, Timothy W.;Meisel, Nicholas;Prabha Narra, Sneha;McComb, Christopher
在基于融合的增材制造（AM）工艺中，增材制造零件的温度历史对确定工艺-结构-性能关系起着至关重要的作用。因此，从零件设计和工艺规划的温度历史预测到制造过程中的现场温度监测和控制，各种增材制造任务都需要快速的热模拟方法。然而，由于所需要的多尺度模拟的空间和时间尺度较大，传统的数值模拟方法无法满足这些应用对时间效率的严格要求。虽然数据驱动的代理模型因其快速计算能力而受到关注，但这些模型的性能依赖于训练数据的大小和质量，而创建这些数据的成本通常非常高。物理信息神经网络（pinn）通过在训练过程中施加物理原理来减轻对大型数据集的需求。本文研究了在激光粉末床熔合（L-PBF）制造过程中，使用PINN来预测零件的时变温度分布。值得注意的是，本研究中使用的PINN使模型能够仅在随机合成的数据上进行训练。这些训练数据的获取成本低廉，并且数据集中随机性的存在提高了训练模型的泛化性。结果表明，PINN模型比在标记数据上训练的同类人工神经网络具有更高的准确率。此外，在这项工作中训练的PINN模型在预测激光路径扫描策略的温度方面保持了很高的准确性，而这些策略在训练数据中是看不到的。
The temperature history of an additively manufactured part plays a critical role in determining process-structure-property relationships in fusion-based additive manufacturing (AM) processes. Therefore, fast thermal simulation methods are needed for a variety of AM tasks, from temperature history prediction for part design and process planning to in situ temperature monitoring and control during manufacturing. However, conventional numerical simulation methods fall short in satisfying the strict requirements of time efficiency in these applications due to the large space and time scales of the required multiscale simulation. While data-driven surrogate models are of interest for their rapid computation capabilities, the performance of these models relies on the size and quality of the training data, which is often prohibitively expensive to create. Physics-informed neural networks (PINNs) mitigate the need for large datasets by imposing physical principles during the training process. This work investigates the use of a PINN to predict the time-varying temperature distribution in a part during manufacturing with laser powder bed fusion (L-PBF). Notably, the use of the PINN in this study enables the model to be trained solely on randomly synthesized data. These training data are both inexpensive to obtain, and the presence of stochasticity in the dataset improves the generalizability of the trained model. Results show that the PINN model achieves higher accuracy than a comparable artificial neural network trained on labeled data. Further, the PINN model trained in this work maintains high accuracy in predicting temperature for laser path scanning strategies unseen in the training data.