Reduced order dynamical models for complex dynamics in manufacturing and natural systems using machine learning
Reduced order dynamical models for complex dynamics in manufacturing and natural systems using machine learning
复制标题
使用机器学习的制造和自然系统中复杂动力学的降阶动力学模型
DOI：
10.1007/s11071-022-07695-x
复制
发表时间：
2022
影响因子：
5.6
通讯作者：
Singh, Shweta
中科院分区：
文献类型：
--
作者：
Farlessyost, William;Singh, Shweta
制造系统和自然系统的动态分析分别提供了关于制造资源和自然资源生产的关键信息。目前全工业过程工厂的动态模型作为高度精确的第一原理关系存在。然而，它们的集成是计算密集型的，并且不能提供对驱动整体动态的基本机制的简化理解。类似地，对于自然系统，大多数动态模型是基于第一原理的，具有高数据要求和低状态精度。因此，可能为了简单和易于训练而牺牲准确性的低阶模型可以证明是有用的。然而，很少有人尝试寻找化学制造过程和自然系统的低阶模型，工作重点是对单个机制进行建模。我们试图通过使用机器学习（ML）方法，SINDy，在大豆柴油加工厂和流域系统上验证，以填补这一研究空白。这种ML方法将稀疏的灰箱建模与额外的非线性优化相结合，以将控制动态识别为常微分方程。我们发现一个线性ODE模型的过程工厂，给出了一个准确的输入和输出之间的关系，并选择内部摩尔流量反映潜在的线性化学计量机制和内部质量平衡。对于自然系统，我们修改的SINDy方法，包括过去的动态训练模型，这给出了一个非线性模型的径流动态的效果。这改善了动态转换，但福尔斯达不到准确的状态估计。我们的结论是，建议ML的方法工作良好的非混沌系统具有最小的滞后，但当这个条件不满足是有限的。
Dynamical analysis of manufacturing and natural systems provides critical information about production of manufactured and natural resources, respectively. Current dynamic models for full industrial process plants exist as highly accurate first-principle relationships. However, their integration is computationally intensive and provides no simplified understanding of the underlying mechanisms driving the overall dynamics. Similarly, for natural systems, most dynamical models are first principle based, with high data requirements and low state accuracy. Consequently, lower-order models that may sacrifice accuracy for simplicity and ease of training can prove useful. Yet, there have been few attempts at finding low-order models of chemical manufacturing processes and natural systems, with work focusing on modeling individual mechanisms. We seek to fill this research gap by using a machine learning (ML) approach, SINDy, validated on a soybean-diesel process plant and watershed system. This ML method combines sparse, grey-box modeling with additional nonlinear optimization to identify governing dynamics as ODEs. We find a linear ODE model for the process plant that gives an accurate relation between input and output and selected internal molar flow rates reflective of underlying linear stoichiometric mechanisms and an internal mass balance. For the natural system, we modify the SINDy approach to include the effect of past dynamics on training the model, which gives a nonlinear model for streamflow dynamics. This improves dynamical transitions, but falls short of accurate state estimation. We conclude that the proposed ML approach works well for non-chaotic systems with minimal hysteresis, but is limited when this condition is not met.
登录
查看更多内容
钢支撑框架伪动力混合仿真的数据驱动子结构技术
DOI：
10.1007/978-3-031-03811-2_42
发表时间：
2021
期刊：
ArXiv
影响因子：
--
作者：
F. Mokhtari;A. Imanpour
通讯作者：
A. Imanpour
DOI：
10.1073/pnas.1517384113
发表时间：
2016-04-12
影响因子：
11.1
作者：
Brunton, Steven L.;Proctor, Joshua L.;Kutz, J. Nathan
通讯作者：
Kutz, J. Nathan
影响因子：
5.6
作者：
A. Shabana
通讯作者：
A. Shabana
影响因子：
3.3
作者：
London, Alex John
通讯作者：
London, Alex John
用于识别制造系统整体动力学控制方程的白盒机器学习方法：蒸馏塔案例研究
影响因子：
--
作者：
Subramanian, Renganathan;Moar, Raghav Rajesh;Singh, Shweta
通讯作者：
Singh, Shweta