Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan 250022, China.
Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan 250022, China.
Neural Netw. 2022 Sep;153:152-163. doi: 10.1016/j.neunet.2022.05.031. Epub 2022 Jun 10.
In this paper, two novel and general predefined-time stability lemmas are given and applied to the predefined-time synchronization problem of memristive complex-valued bidirectional associative memory neural networks (MCVBAMNNs). Firstly, different from the generally fixed-time stability lemma, the setting of an adjustable time parameter in the derived predefined-time stability lemma causes it to be more flexible and more general. Secondly, the model studied in the complex-valued BAM neural networks model, which is different from the previous discussion of the real part and imaginary part respectively. It is more practical to study the complex-valued nonseparation. Thirdly, two effective controllers are designed to realize the synchronization performance of BAM neural networks based on the predefined-time stability, and the analysis is given based on general predefined-time synchronization. Finally, the correctness of the theoretical derivation is verified by numerical simulation. A secure communication scheme based on predefined-time synchronization of MCVBAMNNs is proposed, and the effectiveness and superiority of the results are proved.
本文提出了两个新颖且通用的预定时间稳定性引理，并将其应用于忆阻复值双向联想记忆神经网络（MCVBAMNNs）的预定时间同步问题。首先，与通常的固定时间稳定性引理不同，所得到的预定时间稳定性引理中可调时间参数的设置使其更加灵活和通用。其次，所研究的模型在复值 BAM 神经网络模型中，与之前分别讨论实部和虚部的情况不同，研究复值非分离情况更具实际意义。第三，设计了两个有效的控制器，基于预定时间稳定性实现 BAM 神经网络的同步性能，并基于一般预定时间同步进行了分析。最后，通过数值模拟验证了理论推导的正确性。提出了一种基于 MCVBAMNNs 预定时间同步的安全通信方案，并验证了结果的有效性和优越性。
