The feedback stabilization of finite-state fuzzy cognitive maps. (September 2022)

• Record Type: Journal Article
• Authors: Xiaojie, Wang; Chao, Luo; Chen, Lv
• Is Part Of: Transactions of the Institute of Measurement and Control. Volume 44:Number 13(2022)
• Page Start: 2485
• Page End: 2499
• Publication Date: 2022-09
• Subjects: Control -- cognitive learning -- reasoning -- stabilization; Automatic control -- Periodicals; Measuring instruments -- Periodicals; Commande automatique -- Périodiques; Mesure -- Instruments -- Périodiques; 681.2
• DOI: 10.1177/01423312221085785
• Languages: English
• ISSNs: 0142-3312

Abstract

Fuzzy cognitive maps (FCMs) are a kind of cognitive model for knowledge representation and causal inference. Meanwhile, as fuzzy dynamical systems, FCMs have also been widely applied in the control-related fields, such as mobile robots, unmanned aerial vehicles (UAVs), and industrial controls. However, the existing works mainly focused on the practical applications but lacked the necessary theoretical discussions related to the FCM-based control mechanism. As is known, stabilization is one of the fundamental issues in the control fields. Till date, rigorous research on the stabilization of FCMs is still an issue to be studied. In this article, using state feedback control method, the global stabilizations of finite-state FCMs are investigated. First, utilizing the semi-tensor product (STP) of matrices, the algebraic expression of FCM can be derived. Some theorems ensure the sufficient condition for the existence of the state feedback controller of the global stabilization. Second, the constructive design processes of state feedback controllers are discussed in detail. Third, the global stabilization is further extended into partial stabilization, where only specific concepts of FCMs can be stabilized. The corresponding theoretical analysis is implemented. Finally, the effectiveness of the proposed methods is verified by several examples.