PROJECT TITLE :

Nonparametric Estimation of Time-Varying Systems Using 2-D Regularization

ABSTRACT:

In this paper a nonparametric time-domain estimation methodology of linear time-varying systems from measured noisy knowledge is presented. The challenge with time-varying systems is that the time-varying 2-dimensional (a pair of-D) impulse response functions (IRFs) aren't uniquely determined from a single set of input and output signals as within the case of linear time-invariant systems. Due to this nonuniqueness, the number of possible solutions is growing quadratically with the amount of samples. To decrease the degrees of freedom, user-outlined (adjustable) constraints will be imposed. During this explicit case, it is imposed that the complete a pair of-D IRF is sleek. This can be implemented by a 2-D kernel-primarily based regularization. This regularization is applied over the system time (the direction of the impulse responses) and simultaneously over the global time (representing the system memory). To illustrate the potency of the proposed method, it's demonstrated on a measurement example as a conceptual instrument for measuring and analyzing time-varying systems.