CDS&E: Extracting Models from Data - A Novel Data-Driven Simulation Strategy for Reacting Flows

CDS

• 批准号: 1953350
• 负责人: James Sutherland
• 金额: $ 45.32万
• 依托单位: University of Utah
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1953350&HistoricalAwards=false
• 关键词: CDS& Extracting; Models; Data; Novel

Numerical simulation of reacting flows of real systems is computationally challenging because of the large number variables involved. This research will develop a new data-driven modelling approach that directly incorporates information from canonical or reference test cases to extract simplified models with user-defined error limits. In particular, novel machine learning concepts will be used to generate simplified models that are suitable for use in practical, engineering-scale simulations. Such computationally efficient models can have a direct impact in addressing a range of relevant energy and environmental problems, for example oxy-fuel combustion (for easier CO2 capture and sequestration), pollutant and particulate formation in stationary and mobile combustion systems, etc. The techniques developed here are also applicable to other fields where many reaction manifolds or pathways exist such as in plasma physics or atmospheric chemistry.Many systems in nature evolve along manifolds, which are smooth and reduced complexity subspaces of a parameter space which satisfy, often unknown, physical constraints. However, developing models to describe this evolution is challenging. A key challenge to this modeling approach is dealing with the source terms that arise in the reduced order model. These are a reflection of the source terms in the full (high-fidelity) model, but must be well-parameterized by the reduced-order model parameters without causing unphysical behavior like divergence near manifold boundaries and spurious source/sink points. This will harness the power of data science to characterize the geometry of the low-dimensional manifold and use that information to improve the behavior of the derived models. Extracting the low-dimensional model is challenging because it requires identifying a moderate dimensional shape where gridding and meshing techniques which scale exponentially in dimension will fail. This work will instead be limited by properties such as boundary curvature and vector field acceleration which are well-controlled for most physics-defined systems. Moreover, these models will be learned in a robust manner consistent with a simple physical model, in spite of noise in training data which may otherwise result in spurious critical saddle points in the resulting vector field.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

真实的系统的反应流的数值模拟是计算上的挑战，因为涉及大量的变量。这项研究将开发一种新的数据驱动的建模方法，该方法直接结合来自规范或参考测试用例的信息，以提取具有用户定义的误差限制的简化模型。特别是，新的机器学习概念将用于生成适用于实际工程规模模拟的简化模型。这种计算效率高的模型可以直接影响解决一系列相关的能源和环境问题，例如氧燃料燃烧（为了更容易的CO2捕获和隔离）、固定和移动的燃烧系统中的污染物和颗粒形成，这里开发的技术也适用于存在许多反应歧管或路径的其他领域，例如等离子体物理或大气物理。自然界中的许多系统沿沿着流形演化，所述流形是满足通常未知的物理约束的参数空间的光滑且复杂性降低的子空间。 然而，开发模型来描述这种演变是具有挑战性的。这种建模方法的一个关键挑战是处理降阶模型中出现的源项。这些是完整（高保真）模型中源项的反映，但必须通过降阶模型参数进行良好的参数化，而不会导致非物理行为，如歧管边界附近的发散和虚假源/汇点。这将利用数据科学的力量来描述低维流形的几何特征，并使用这些信息来改善衍生模型的行为。提取低维模型是具有挑战性的，因为它需要识别一个中等尺寸的形状，其中网格和网格化技术，在维度上呈指数级缩放将失败。这项工作反而会受到边界曲率和向量场加速度等属性的限制，这些属性对于大多数物理定义的系统来说都是可控的。此外，这些模型将以一种与简单物理模型一致的稳健方式学习，尽管训练数据中存在噪声，否则可能会在所得矢量场中产生虚假的临界鞍点。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。

项目成果

Manifold-informed state vector subset for reduced-order modeling

用于降阶建模的流形通知状态向量子集

• DOI: 10.1016/j.proci.2022.06.019
• 发表时间: 2022
• 期刊: Proceedings of the Combustion Institute
• 影响因子: 3.4
• 作者: Zdybał, Kamila;Sutherland, James C.;Parente, Alessandro
• 通讯作者: Parente, Alessandro

Batch Multi-Fidelity Active Learning with Budget Constraints

具有预算约束的批量多保真主动学习

• 发表时间: 2022
• 期刊: Advances in neural information processing systems
• 作者: Shibo Li, Jeff Phillips

Local manifold learning and its link to domain-based physics knowledge

局部流形学习及其与基于领域的物理知识的联系

• DOI: 10.1016/j.jaecs.2023.100131
• 发表时间: 2023
• 期刊: Applications in Energy and Combustion Science
• 作者: Zdybał, Kamila;D’Alessio, Giuseppe;Attili, Antonio;Coussement, Axel;Sutherland, James C.;Parente, Alessandro
• 通讯作者: Parente, Alessandro

A technique for characterising feature size and quality of manifolds

• DOI: 10.1080/13647830.2021.1931715
• 发表时间: 2021-06-03
• 期刊: COMBUSTION THEORY AND MODELLING
• 影响因子: 1.3
• 作者: Armstrong, Elizabeth;Sutherland, James C.
• 通讯作者: Sutherland, James C.

Local Kernel Ridge Regression for Scalable, Interpolating, Continuous Regression

• 发表时间: 2022
• 期刊: Trans. Mach. Learn. Res.
• 作者: Mingxuan Han;Chenglong Ye;J. M. Phillips