• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.224-224
• /
• 2000

Biaffine Matrix Inequalities(BIs) are known to give more general and flexible frameworks in control designs than Linear Matrix Inequalities(LMIs). However, BMIs are nonconvex constraints and very difficult to solve. In this paper, BMI problems are solved using Evolution Strategy(ES). Numerous BMI problems are solved to verify performances of ES solver for BMI problems and compared with those of Genetic Algorithms and Branch-and-Cut algorithm.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.184-193
• /
• 2003

Biaffine Matrix Inequality (BMI) is known to provide the most general framework in control synthesis, but problems involving BMI's are very difficult to solve because nonconvex optimization should be solved. In the previous paper, we proposed a new solver for problems involving BMI's using Evolutionary Algorithms (EA). In this paper, we solve several control synthesis examples such as Reduced-order control, Simultaneous stabilization, Multi-objective control, $H_{\infty}$ optimal control, Maxed $H_2$ / $H_{\infty}$control design, and Robust $H_{\infty}$ control. Each of these problems is formulated as the standard BMI form, and solved by the proposed algorithm. The performance in each case is compared with those of conventional methods.