Search

In this paper, a new switching sequence convex optimization (SSCO) algorithm is proposed for solving non-convex optimization problem with complex time-varying relaxation matrix structures that arises during output feedback design. Firstly, the introduced time-varying relaxation matrix combines the membership functions and the designed switching mechanism to adjust the positive and negative terms of the inequality constraints. As a result, relaxed controller design conditions with complex matrix structures are established. The proposed SSCO algorithm employs switching optimization variables and inner approximation strategy, which is able to compute non-convex optimization problems with complex matrix structures more flexibly and converge quickly. It is worth noting that the implementation of the SSCO algorithm requires a set of strictly feasible initial solutions. Therefore, an initialization iterative algorithm is proposed, which overcomes the difficulties of transforming the solving problem into a typical non-convex optimization problem and linearizing multiple different concave parts, by which a set of optimized feasible solutions are obtained. Finally, simulation examples are used to demonstrate the superiority of the design scheme proposed in this paper. [ABSTRACT FROM AUTHOR]

In this paper, a new two-dimensional gaussian hierarchical priority fuzzy system (TGHPFS) is proposed to handle interval-valued data. TGHPFS first performs hierarchical clustering of the average value of interval-valued data in each dimension to generate two-dimensional gaussian membership functions of two-level rules. The two levels of rules are associated by calculating the activation strength of the second-level rules to the first-level rules and setting the connection threshold. The regularized least squares method is used to optimize the consequents of the second-level rules. The two-dimensional gaussian membership function designed in this paper is used to model the antecedents of interval-valued data, solving the correlation problem between the left and right values of interval-valued data. The effectiveness of TGHPFS is validated using real-world datasets, and the proposed method is compared with other latest methods to show the superiority of TGHPFS. [ABSTRACT FROM AUTHOR]

In this paper, the ability of disturbance rejection is considered for nonlinear systems presented by Takagi-Sugeno (T-S) fuzzy model with time-varying delay. First, a membership function dependent Lyapunov-Krasovskii functional is designed to handle the time-varying delay and an observer-based switching controller is designed to cope with the time derivative of membership function. For each switching signal, an invariant set is estimated corresponding to the switching controller, and the subset of the intersection is also an invariant set if the number of switching is finite with energy bounded disturbance. Then, for the trajectory starting from the origin, the ability of disturbance rejection is measured by H ∞ performance and for other cases, two sets are designed such that any trajectories beginning with the smaller one will remain in the larger one. Finally, the merits of the proposed method are demonstrated by two examples. [ABSTRACT FROM AUTHOR]