In this article, the H∞\mathcal {H}_{\infty } bipartite synchronization issue is studied for a class of discrete-time coupled switched neural networks with antagonistic interactions via a distributed dynamic event-triggered control scheme. Essentially different from most current literature, the topology switching of the investigated signed graph is governed by a double-layer switching signal, which integrates a flexible deterministic switching regularity, the persistent dwell-time switching, into a Markov chain to represent the variation of transition probability. Considering the coexistence of cooperative and antagonistic interactions among nodes, the bipartite synchronization of which the dynamics of nodes converge to values with the same modulus but the opposite signs is explored. A distributed control strategy based on the dynamic event-triggered mechanism is utilized to achieve this goal. Under this circumstance, the information update of the controller presents an aperiodic manner, and the frequency of data transmission can be reduced extensively. Thereafter, by constructing a novel Lyapunov function depending on both the switching signal and the internal dynamic nonnegative variable of the triggering mechanism, the exponential stability of bipartite synchronization error systems in the mean-square sense is analyzed. Finally, two simulation examples are provided to illustrate the effectiveness of the derived results.

中文翻译：

---

H—双层马尔可夫切换合作竞争神经网络的二部同步：一种分布式动态事件触发机制


在本文中，通过分布式动态事件触发控制方案，研究了一类具有对抗性相互作用的离散时间耦合开关神经网络的 H∞\mathcal {H}_{\infty } 二部同步问题。与大多数当前文献本质上不同的是，所研究的符号图的拓扑切换由双层切换信号控制，该信号将灵活的确定性切换规律（持久停留时间切换）集成到马尔可夫链中以表示转换的变化可能性。考虑到节点之间合作和对抗相互作用并存的情况，探索了节点动态收敛到模数相同、符号相反的二分同步。利用基于动态事件触发机制的分布式控制策略来实现这一目标。在这种情况下，控制器的信息更新呈现非周期性的方式，数据传输的频率可以大大降低。此后，通过构造一个依赖于开关信号和触发机制内部动态非负变量的新李亚​​普诺夫函数，分析了二部同步误差系统在均方意义上的指数稳定性。最后，提供了两个仿真例子来说明推导结果的有效性。