减少订单建模（ROM）和模型订单降低（MOR）是降低计算机模型的计算复杂性或存储需求的技术，同时保留在受控误差中的预期保真度。使用替代模型可以简化分析和控制设计。
科学家和工程师使用ROM技术来创建系统级模拟，设计控制系统，优化产品设计和构建digital twinapplications. MATLAB®，S金宝appimulink®，，，，and add-on products let you build accurate ROMs using variousreduced order modeling methods。
为什么使用减少订单建模？
大规模，高保真的非线性模型可能需要数小时甚至几天才能模拟。系统分析和设计可能需要成千上万的模拟，从而提出重大的计算挑战。同样，线性化复杂模型可能会导致高保真模型，这些模型包含不影响应用程序感兴趣的状态的状态。
在这些情况下，您可以使用降低的订单建模方法来显着加快模拟和分析高阶大型系统。您可以通过将模型准确性降低计算复杂性来实现这一速度。降低的准确性基于频率范围，准确性公差和对您应用重要的其他特征。减少的订单建模也可用于将多个复杂组件级模拟模型组合到用于控制分析和设计的系统级仿真中。
You can also use reduced order modeling to create digital twins to represent the current state of the operational asset, or to run real-time simulations of complex physical models for testing on hardware.
减少订单建模方法
There are two main classes of techniques for building reduced order models: model-based and data-driven.
基于模型的方法依赖于对基础模型的数学或物理理解。其中一些技术，例如结构力学中的Craig-Bampton方法，是为特定基于PDE的模型而设计的。在线性系统分析中，线性化，，，，线性参数变化模型，，，，and techniques such as平衡截断and极点简化通常用于简化系统模型。
Data-driven methods use input-output data from the original high-fidelity first-principles model to construct a ROM that accurately represents the underlying system. Data-driven ROMs can be either static or dynamic models. Techniques such as曲线拟合and查找表are useful for creating static ROMs. Dynamic ROMs can be developed using deep learning techniques such asLSTM，，，，前馈神经网，，，，and神经氧，可用于Deep Learning Toolbox™。Other techniques for building dynamics ROMs include非线性ARXandHammerstein-Wiener models使用System Identification Toolbox。非线性ARX模型可以根据机器学习算法使用回归函数统计和机器学习工具箱。
When creating model-based and data-driven reduced order models, engineers need to decide what trade-offs they are willing to make to speed up a model. For example, when creating a model-based ROM, an engineer might need to eliminate system dynamics beyond a certain frequency in the reduced model. An extreme case is when the reduced order model captures only steady-state system behavior. When creating data-driven ROMs, engineers sacrifice physical insights of the model. The most suitable type of ROM technique depends on the application.
