arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07018physics.comp-phcs.LG
收藏

使用超网络和隐式表示的复杂几何上的离散无关代理建模

Discretization-independent surrogate modeling over complex geometries using hypernetworks and implicit representations

University of Michigan(密歇根大学)

James Duvall, Karthik Duraisamy, Shaowu Pan

摘要:

偏微分方程(PDE)的数值解需要昂贵的模拟,限制了它们在设计优化,基于模型的控制和大规模逆问题中的应用。代理建模技术寻求在保持主要解的特征和行为的同时减少计算开销。传统的基于卷积神经网络的代理建模框架需要有损像素化和数据预处理,并且在实际工程应用中通常是无效的。我们提出了替代的基于深度学习的代理模型,用于PDE解决方案的离散化独立的连续表示,可用于复杂,可变几何和网格拓扑结构的域的学习和预测。提出并比较了三种方法:设计变量编码多层感知器(DV-MLP),设计变量超网络(DV-Hnet)和非线性独立对偶系统(NIDS)。每种方法都利用一个主网络,它消耗逐点空间信息来提供连续的表示,允许在域中的任何位置进行预测。输入特征包括最小距离函数评估,以隐式地对问题几何进行编码。定义和区分问题实例的几何设计变量在每种方法中的使用方式不同,表现为额外的主网络输入特征(DV-MLP)或超网络输入(DV-Hnet和NIDS)。该方法适用于预测解决方案周围的复杂的,参数定义的几何形状的非参数定义的网格模型预测获得了许多数量级的速度比全阶模型。测试用例包括具有复杂几何形状和有限训练数据的车辆空气动力学问题,其中设计变量超网络表现最好,尽管参数数量更大,但具有竞争力的最佳模型时间。

英文摘要:

Numerical solutions of partial differential equations (PDEs) require expensive simulations, limiting their application in design optimization, model-based control, and large-scale inverse problems. Surrogate modeling techniques seek to decrease the computational expense while retaining dominant solution features and behavior. Traditional Convolutional Neural Network-based frameworks for surrogate modeling require lossy pixelization and data-preprocessing, and generally are not effective in realistic engineering applications. We propose alternative deep-learning based surrogate models for discretization-independent, continuous representations of PDE solutions, which can be used for learning and prediction over domains with complex, variable geometry and mesh topology. Three methods are proposed and compared; design-variable-coded multi-layer perceptron (DV-MLP), design-variable hypernetworks (DV-Hnet), and non-linear independent dual system (NIDS). Each method utilizes a main network which consumes pointwise spatial information to provide a continuous representation, allowing predictions at any location in the domain. Input features include a minimum-distance function evaluation to implicitly encode the problem geometry. The geometric design variables, which define and distinguish problem instances, are used differently by each method, appearing as additional main-network input features (DV-MLP), or as hypernetwork inputs (DV-Hnet and NIDS). The methods are applied to predict solutions around complex, parametrically-defined geometries on non-parametrically-defined meshes with model predictions obtained many orders of magnitude faster than the full order models. Test cases include a vehicle-aerodynamics problem with complex geometry and limited training data, with a design-variable hypernetwork performing best, with a competitive time-to-best-model despite a much greater parameter count.

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。

↑