arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.13805math.NAcs.LGcs.NA
收藏

基于龙格-库塔神经网络的模型降阶

Model Order Reduction based on Runge-Kutta Neural Network

Siemens AG(西门子股份公司);Technical University of Munich(慕尼黑工业大学)

Qinyu Zhuang, Juan Manuel Lorenzi, Hans-Joachim Bungartz, Dirk Hartmann

摘要:

模型降阶(MOR)方法可以生成具有实时能力的数字孪生,这可以在工业中实现各种新的价值流。虽然传统的基于投影的方法对于线性问题具有鲁棒性和准确性,但将机器学习用于处理非线性问题成为减少复杂问题的新选择。这种方法通常包括两个步骤。第一步是基于投影的降维方法,第二步是模型重建的神经网络。在这项工作中,我们分别对这两个步骤进行了一些修改,并研究了它们如何受到三个仿真模型测试的影响。在所有情况下,适当的正交分解(POD)用于降维。对于该步骤,将生成具有恒定输入参数的输入快照数据库的效果与时间相关输入参数进行比较。对于模型重建步骤,比较了两种类型的神经网络架构:多层感知器(MLP)和龙格库塔神经网络(RKNN)。MLP直接学习系统状态,而RKNN学习系统状态的导数并作为Runge-Kutta积分器预测新的状态。

英文摘要:

Model Order Reduction (MOR) methods enable the generation of real-time-capable digital twins, which can enable various novel value streams in industry. While traditional projection-based methods are robust and accurate for linear problems, incorporating Machine Learning to deal with nonlinearity becomes a new choice for reducing complex problems. Such methods usually consist of two steps. The first step is dimension reduction by projection-based method, and the second is the model reconstruction by Neural Network. In this work, we apply some modifications for both steps respectively and investigate how they are impacted by testing with three simulation models. In all cases Proper Orthogonal Decomposition (POD) is used for dimension reduction. For this step, the effects of generating the input snapshot database with constant input parameters is compared with time-dependent input parameters. For the model reconstruction step, two types of neural network architectures are compared: Multilayer Perceptron (MLP) and Runge-Kutta Neural Network (RKNN). The MLP learns the system state directly while RKNN learns the derivative of system state and predicts the new state as a Runge-Kutta integrator.

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。

↑