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 1311.5250nlin.CDphysics.flu-dyn
收藏

使用机器学习的吸引子控制

Attractor Control Using Machine Learning

Thomas Duriez, Vladimir Parezanovic, Bernd R. Noack, Laurent Cordier, Marc Segond, Markus Abel

摘要:

我们提出了一个通用的策略,利用非线性机制,在系统的无监督方式的复杂动态系统的反馈控制设计。这些动态系统可以具有任意维度的状态空间,具有有限数量的致动器(多个输入)和传感器(多个输出)。控制律将输出映射到输入,并相对于成本函数进行优化,该成本函数包含通过待控制的吸引子的动态或统计特性的物理学。因此,我们能够利用非线性机制,如混沌或频率串扰,服务于控制目标。这种优化基于遗传编程,这是机器学习的一个分支。该机器学习控制器被成功地应用于非线性耦合振子的镇定和强迫Lorenz系统的李雅普诺夫指数的最大化。我们预见到潜在的应用,大多数非线性多输入/多输出控制问题,特别是在实验中。

英文摘要:

We propose a general strategy for feedback control design of complex dynamical systems exploiting the nonlinear mechanisms in a systematic unsupervised manner. These dynamical systems can have a state space of arbitrary dimension with finite number of actuators (multiple inputs) and sensors (multiple outputs). The control law maps outputs into inputs and is optimized with respect to a cost function, containing physics via the dynamical or statistical properties of the attractor to be controlled. Thus, we are capable of exploiting nonlinear mechanisms, e.g. chaos or frequency cross-talk, serving the control objective. This optimization is based on genetic programming, a branch of machine learning. This machine learning control is successfully applied to the stabilization of nonlinearly coupled oscillators and maximization of Lyapunov exponent of a forced Lorenz system. We foresee potential applications to most nonlinear multiple inputs/multiple outputs control problems, particulary in experiments.

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。

↑