ABSTRACT
During the 1960s, many subroutines were written for the estimation of parameters in different model structures. This chapter discusses features, algorithms, and user interface primarily for the second-generation identification software. It also discusses the features of the third generation software and reports on some experimentation in that area. System identification is the art and science of building mathematical models of dynamical systems using observed data. The theory and methodology is by now well-established and in its mainstream edition it is well-founded in the methods of mathematical statistics. The rapid development in software techniques has opened up many new possibilities for better user support in all programming tasks. A desired feature of such packages is that they should support as wide a class of model structures as possible; at the same time, the syntax for these different structures is uniform and transparent.
