Modeling Dynamical Systems with Neural Hybrid System Framework via Maximum Entropy Approach
Modeling Dynamical Systems with Neural Hybrid System Framework via Maximum Entropy Approach
复制标题
DOI：
10.23919/acc55779.2023.10155820
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Yejiang Yang;Weiming Xiang
中科院分区：
文献类型：
--
作者：
Yejiang Yang;Weiming Xiang
在本文中，通过最大的熵分区方法，提出了一个数据驱动的神经混合系统建模框架，用于复杂的动态系统建模，例如人类运动动力学。使用最大熵方法将从系统收集的采样数据分为分段数据集，然后定义模式过渡逻辑。然后，作为对相应分区的局部动力描述，训练了小型神经网络的集合。遵循系统的神经混合系统模型，基于间隔分析和分裂和组合过程，提供了具有低计算成本的设置可达性分析，以证明我们在计算昂贵的任务中的方法。最后，提供了极限周期和人类行为建模示例的数值示例，以证明开发方法的有效性和效率。
In this paper, a data-driven neural hybrid system modeling framework via the Maximum Entropy partitioning approach is proposed for complex dynamical system modeling such as human motion dynamics. The sampled data collected from the system is partitioned into segmented data sets using the Maximum Entropy approach, and the mode transition logic is then defined. Then, as the local dynamical description for their corresponding partitions, a collection of small-scale neural networks is trained. Following a neural hybrid system model of the system, a set-valued reachability analysis with low computation cost is provided based on interval analysis and a split and combined process to demonstrate the benefits of our approach in computationally expensive tasks. Finally, a numerical examples of the limit cycle and a human behavior modeling example are provided to demonstrate the effectiveness and efficiency of the developed methods.