Computing the $L_\infty$-norm of a time-invariant linear ordinary differential control system is a routine task in robust control, usually delegated to floating-point routines that perform well on most practical systems. Behind the numerical value, however, lies a discrete decision: whether a pole lies on the imaginary axis, and whether a mode of a realization is actually a pole of the transfer matrix. Floating-point arithmetic can only replace this decision with a tolerance. This paper explains, for a control audience, what reliable symbolic-numeric computation offers for this problem: exact arithmetic where a decision has to be made, and certified enclosures where a value has to be computed. We show how the problem is turned into a small polynomial system directly from state-space data, how this system is solved in practice, and what it costs. A benchmark on the {\tt COMPleib} library and on families of systems with known norms shows that two standard numerical routines err in opposite directions on the imaginary-axis decision, and never on the same system, while the certified method decides it correctly on every instance tested and computes the norm at a cost comparable to that of the numerical routines on most systems. We conclude with practical guidelines for users of numerical tools.
Florent Corniquel, Alban Quadrat, Fabrice Rouillier, Grace Younes
原文摘要
The $L_{\infty}$-norm of a linear time-invariant system is a central quantity in robust control, used in robust stability tests, stability margins, and $H_{\infty}$ controller design. Physical models depend on parameters, such as masses, stiffnesses, or gains, so the $L_{\infty}$-norm becomes a function of these parameters. This computation reduces to studying the real critical points of a plane algebraic curve whose coefficients depend on the parameters. Previous approaches based on cylindrical algebraic decomposition describe the $L_{\infty}$-norm on the whole parameter space, but their cost grows very quickly with the number of parameters. In this paper, we propose instead to compute a generic parametrisation of the solutions, valid outside an explicitly characterised set of non-generic parameter values. In the case of one parameter, this parametrisation is obtained by interpolation from a certified solver for the non-parametric case. The resulting algorithm is fully certified, relying on a priori bounds and multimodular computations rather than on Gröbner bases. It is illustrated on examples from the robust control literature.