“…The first example consists of the optimisation of a multiobjective LinearQuadratic-Gaussian controller design problem proposed by Barratt and Boyd [10] under controller complexity constraints, as formulated in [11], with multiobjective genetic algorithms (MOGA). Two MOGAs were applied to the problem, one without sharing or mating restriction (MOGA-A) and another one with sharing and mating restriction in the decision variable domain (MOGA-B), as described in [12].…”
Abstract. The attainment function has been proposed as a measure of the statistical performance of stochastic multiobjective optimisers which encompasses both the quality of individual non-dominated solutions in objective space and their spread along the trade-off surface. It has also been related to results from random closed-set theory, and cast as a mean-like, first-order moment measure of the outcomes of multiobjective optimisers. In this work, the use of more informative, second-order moment measures for the evaluation and comparison of multiobjective optimiser performance is explored experimentally, with emphasis on the interpretability of the results.
“…The first example consists of the optimisation of a multiobjective LinearQuadratic-Gaussian controller design problem proposed by Barratt and Boyd [10] under controller complexity constraints, as formulated in [11], with multiobjective genetic algorithms (MOGA). Two MOGAs were applied to the problem, one without sharing or mating restriction (MOGA-A) and another one with sharing and mating restriction in the decision variable domain (MOGA-B), as described in [12].…”
Abstract. The attainment function has been proposed as a measure of the statistical performance of stochastic multiobjective optimisers which encompasses both the quality of individual non-dominated solutions in objective space and their spread along the trade-off surface. It has also been related to results from random closed-set theory, and cast as a mean-like, first-order moment measure of the outcomes of multiobjective optimisers. In this work, the use of more informative, second-order moment measures for the evaluation and comparison of multiobjective optimiser performance is explored experimentally, with emphasis on the interpretability of the results.
“…As a consequence, many works were carried out on the synthesis of controllers for such systems. In particular, the linear quadratic regulator (LQR) makes it possible to obtain the optimal corrector within the meaning of a quadratic criterion [1], [4]. The difficulty with this method lies in the choice of the weighting matrices of the quadratic criterion which are generally chosen by trial-and-error in order to satisfy robustness constraints.…”
This paper proposes a new semi-analytic robust mixed H2/H-infinity design method for fixed structure controllers (i.e. PID, the most widely used structure in industry). Precisely, the method consists in determining the parameters of a given structure controller that minimizes the influence of a step load disturbance to the process output with the respect of robustness constraints, i.e. constraints on maximum amplification of measurement noise, minimum module margin and minimum phase margin. The design objective and the robustness constraints are expressed as H2 and H-infinity norms in function of unknown controller parameters. The controller design problem is then reformulated into a nonlinear optimization problem with a set of inequality constraints that can be efficiently solved numerically. Finally, we obtain a controller design tool which provides, when it exists, the unique optimal controller that fulfills the design specifications. The method is based on generic models that can represent common industrial plants. Further, the proposed method enables a graphical representation of the different design tradeoffs. To demonstrate the results, we apply this method for first order processes controlled by PI controller.
SUMMARYIn this paper two modern control techniques, the H2 and H , control design methods, are presented. After a brief theoretical explanation they are applied to a practical example: the control of the air flow rate through an axial ventilator. Modern control techniques are model-based. In the first part of the paper it is explained how a model can be obtained both of the process and of the disturbances acting on it. On the basis of the model, several controllers can be designed. The example clearly illustrates some of the trade-offs of modern control design. The H2 and H , controllers are also compared with a classical PI controller.KEY WORDS Model-based controllers H, LQG Computer-aided control system design (CACSD)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.