arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.10060cs.LGmath.DS
收藏

连续线性系统的保稳定数据推断

Inference of Continuous Linear Systems from Data with Guaranteed Stability

Max Planck Institute of Dynamics of Complex Technical Systems(马克斯·普朗克复杂技术系统动力学研究所);Otto-von-Guericke University Magdeburg(马格德堡奥托·冯·格里克大学)

Pawan Goyal, Igor Pontes Duff, Peter Benner

摘要:

从数据中学习动力系统的机器学习技术在工程设计中起着重要的作用。本研究的重点是从数据中学习连续线性模型。稳定性是动态系统的一个关键特征,在预测和控制等设计任务中尤为重要。因此,需要开发提供稳定性保证的方法。为此,我们利用[Gillis/Sharma,Automatica,2017]中提出的稳定矩阵的参数化来实现所需的模型。此外,为了避免估计导数信息学习连续系统,我们制定了一个积分形式的推理问题。我们还讨论了一些扩展,包括与控制系统相关的扩展。数值实验表明,一个稳定的矩阵参数化和微分方程的积分形式的组合,使我们能够学习稳定的系统,而不需要导数信息,这可能是具有挑战性的情况下,获得噪声或有限的数据。

英文摘要:

Machine-learning technologies for learning dynamical systems from data play an important role in engineering design. This research focuses on learning continuous linear models from data. Stability, a key feature of dynamic systems, is especially important in design tasks such as prediction and control. Thus, there is a need to develop methodologies that provide stability guarantees. To that end, we leverage the parameterization of stable matrices proposed in [Gillis/Sharma, Automatica, 2017] to realize the desired models. Furthermore, to avoid the estimation of derivative information to learn continuous systems, we formulate the inference problem in an integral form. We also discuss a few extensions, including those related to control systems. Numerical experiments show that the combination of a stable matrix parameterization and an integral form of differential equations allows us to learn stable systems without requiring derivative information, which can be challenging to obtain in situations with noisy or limited data.

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。

↑