Quantized H∞ stabilization for delayed memristive neural networks

• Published in: Neural computing & applications Vol. 35; no. 22; pp. 16473 - 16486
• Main Authors: Yan, Zhilian, Zuo, Dandan, Guo, Tong, Zhou, Jianping
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Closed loop systems; Closed loops; Communication; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Control systems design; Controllers; Data Mining and Knowledge Discovery; Dynamic models; Euclidean space; Feedback control; H-infinity control; Image Processing and Computer Vision; Neural networks; Original Article; Probability and Statistics in Computer Science; Stabilization; Time dependence; Time lag; Sampled-data control; Memristive neural networks; control; Dynamic quantizer
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-023-08510-3

The issue of H ∞ stabilization for delayed memristive neural networks with dynamic quantization is considered. The aim is to design a quantized sampled-data controller guaranteeing that the closed-loop system is globally asymptotically stable with a prescribed H ∞ disturbance attenuation level. By means of set-valued maps and the differential inclusion theory, the network under consideration is transformed into a dynamic model subject to time-dependent bounded uncertainty. Then, two different time-dependent two-sided loop functionals are constructed for the non-necessarily and necessarily differential time delay situations, respectively. Two sufficient conditions on the stability and H ∞ performance are derived via using these constructed functionals and a few inequality techniques. On the foundation of these conditions, co-designs of the needed feedback gain and dynamic quantization parameter are presented. Finally, three examples are provided to verify the applicability of the quantized sampled-data controller design methods.