A Data-Driven Hybrid Automaton Framework to Modeling Complex Dynamical Systems
A Data-Driven Hybrid Automaton Framework to Modeling Complex Dynamical Systems
复制标题
DOI：
10.1109/icit58465.2023.10143031
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Yejiang Yang;Zihao Mo;Weiming Xiang
中科院分区：
文献类型：
--
作者：
Yejiang Yang;Zihao Mo;Weiming Xiang
在本文中，提出了一种计算有效的数据驱动的混合自动机模型，用于使用多个神经网络捕获未知的复杂动力学系统行为。系统的采样数据由有效的分区分为与其拓扑相对应的组，并根据其定义过渡罩。然后，将计算高效的小型神经网络集合作为其相应拓扑的局部动力描述。在用基于神经网络的混合动力机对系统进行建模后，基于间隔分析以及分裂和组合过程，提供了低计算成本的设置可及可及性分析。最后，提出了一个限制周期的数值示例，以说明开发的模型可以显着降低可及设置计算中的计算成本，而无需牺牲任何建模精度。
In this paper, a computationally efficient data-driven hybrid automaton model is proposed to capture unknown complex dynamical system behaviors using multiple neural networks. The sampled data of the system is divided by valid partitions into groups corresponding to their topologies and based on which, transition guards are defined. Then, a collection of small-scale neural networks that are computationally efficient are trained as the local dynamical description for their corresponding topologies. After modeling the system with a neural-network-based hybrid automaton, the set-valued reachability analysis with low computation cost is provided based on interval analysis and a split and combined process. At last, a numerical example of the limit cycle is presented to illustrate that the developed models can significantly reduce the computational cost in reachable set computation without sacrificing any modeling precision.