arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.13098stat.MLcs.LGmath.DS
收藏

基于准势与机器学习的随机动力系统平均逃逸时间控制

Controlling mean exit time of stochastic dynamical systems based on quasipotential and machine learning

Nanjing University of Science and Technology(南京理工大学);Universität Augsburg(奥格斯堡大学)

Yang Li, Shenglan Yuan, Shengyuan Xu

AI总结:

本文提出结合准势与神经网络计算全局准势函数,并通过迭代数值算法设计控制器,实现对随机动力系统平均逃逸时间的精确控制。

摘要:

在白噪声存在的情况下,逃逸吸引域的平均逃逸时间在多个科学领域中具有实际重要性。本文提出了一种基于准势概念和机器学习的策略,用于控制一般随机动力系统的平均逃逸时间以达到期望值。具体而言,我们开发了一种神经网络架构来计算全局准势函数。随后,我们设计了一个系统的迭代数值算法,以针对给定的平均逃逸时间计算控制器。此外,我们借助有效的Hamilton-Jacobi方案和训练好的神经网络,识别了亚稳吸引子之间的最概然路径。数值实验表明,我们的控制策略有效且具有足够的准确性。

英文摘要:

The mean exit time escaping basin of attraction in the presence of white noise is of practical importance in various scientific fields. In this work, we propose a strategy to control mean exit time of general stochastic dynamical systems to achieve a desired value based on the quasipotential concept and machine learning. Specifically, we develop a neural network architecture to compute the global quasipotential function. Then we design a systematic iterated numerical algorithm to calculate the controller for a given mean exit time. Moreover, we identify the most probable path between metastable attractors with help of the effective Hamilton-Jacobi scheme and the trained neural network. Numerical experiments demonstrate that our control strategy is effective and sufficiently accurate.

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。

↑