Solving Time-Varying Complex-Valued Sylvester Equation via Adaptive Coefficient and Non-Convex Projection Zeroing Neural Network

IEEE Access

Baitao Chen¹  Chengze Jiang²  Xiuchun Xiao²  Jiahao Wu²  Qixiang Mei³ 

[1] Education Quality Monitoring and Evaluation Center, Guangdong Ocean University, Zhanjiang, China;School of Electronics and Information Engineering, Guangdong Ocean University, Zhanjiang, China;School of Mathematics and Computer, Guangdong Ocean University, Zhanjiang, China;

关键词: Time-varying complex-valued Sylvester equation (TVCVSE);    zeroing neural network (ZNN);    adaptive coefficient;    non-convex projection;   

DOI  :  10.1109/ACCESS.2021.3116152

来源: DOAJ

【 摘 要 】

The time-varying complex-valued Sylvester equation (TVCVSE) often appears in many fields such as control and communication engineering. Classical recurrent neural network (RNN) models (e.g., gradient neural network (GNN) and zeroing neural network (ZNN)) are often used to solve such problems. This paper proposes an adaptive coefficient and non-convex projection zeroing neural network (ACNPZNN) model for solving TVCVSE. To enhance its adaptability as residual error decreasing as time, an adaptive coefficient is designed based on residual error. Meanwhile, this paper breaks the convex constraint by constructing two complex-valued non-convex projection activation functions from two different aspects. Moreover, the global convergence of the proposed model is proved, the anti-noise performance of the ACNPZNN model under different noises is theoretically analyzed. Finally, simulation experiments are provided to compare the convergence performance of different models, which simultaneously verifies the effectiveness and superiority of the proposed model.

【 授权许可】

Unknown