Delay-probability-dependent state estimation for neural networks with hybrid delays
作者：
Highlights：
• By considering discrete delay, distributed delay and probability distribution of time delays, more general system model and state estimator for NNs with hybrid time delays are developed, which takes some well studied models as special cases.
• A innovative augmented LKF containing augmented non-integral and single-integral quadratic terms is built, which can make full use of deterministic and probabilistic information of time delays and set up extensive relationship among different vectors.
• In order to handle the infinitesimal operators of LKF effectively, generalized free-weighting-matrix integral inequality (GFWMII) is chosen to cooperate with wirtinger-based inequality, which is helpful to reduce the conservatism of the main criteria.
摘要
•By considering discrete delay, distributed delay and probability distribution of time delays, more general system model and state estimator for NNs with hybrid time delays are developed, which takes some well studied models as special cases.•A innovative augmented LKF containing augmented non-integral and single-integral quadratic terms is built, which can make full use of deterministic and probabilistic information of time delays and set up extensive relationship among different vectors.•In order to handle the infinitesimal operators of LKF effectively, generalized free-weighting-matrix integral inequality (GFWMII) is chosen to cooperate with wirtinger-based inequality, which is helpful to reduce the conservatism of the main criteria.
论文关键词：Neural networks,Hybrid delays,Probability distribution,H∞ State estimation,Desired performance
论文评审过程：Received 21 October 2021, Revised 16 January 2022, Accepted 9 February 2022, Available online 26 February 2022, Version of Record 26 February 2022.
论文官网地址：https://doi.org/10.1016/j.amc.2022.127016
