Stochastic Linearization of Multivariate Nonlinearities

Abstract

Stochastic linearization is a method used in Quasilinear Control (QLC) to replace a nonlinearity by an equivalent gain and a bias, utilizing the statistical properties of random inputs. In this paper, the theory of stochastic linearization is extended to nonlinear functions of multiple variables or inputs forming a multivariate Gaussian vector. The result is applied to find the stochastic linearization of a bivariate saturation nonlinearity in a general feedback control system. The accuracy of stochastic linearization has been investigated by a Monte Carlo simulation and has been found out to be fairly high. Finally, a practical example of optimal control design using QLC is presented.