TARX Model for Pneumatic Cylinder and Identification

Abstract

Pneumatic cylinder is nonlinear system with some uncertain parameters. Owing that fact we introduce next assumptions a) the nonlinear model of the pneumatic cylinder can be approximated with time-varying ARX model (TARX model) b) owing the influence of the combination of heat coefficient, unknown discharge coefficient and change of temperature, we suppose that parameters of the pneumatic cylinder are random (stochastic parameters) c) observations have a Gaussian distribution Due to the abovementioned reasons, it is assumed that the pneumatic cylinder model is a linear stochastic model with variable parameters. We will use a recursive algorithm with forgetting factor. Such algorithms overcome shortcoming which is inherent to Kalman filter approach. That is a priori knowledge of stochastic disturbance variance and covariance matrix of the parameters noise.