Comparison of two B-polynomial methods: application to the identification of time delayed processes

An extensive literature exists on the estimation of the model parameters of time delayed processes. The objective of this paper is to review the main B-polynomial approaches to the delay estimation problem. More specifically, two algorithms are discussed and compared theoretically and in simulation. The algorithms involve various procedures to assess how the model relates to the observed data, to a priori knowledge, and to the algorithms’ intended use. Simulation results indicate that both the algorithms can suitably identify the model parameters, including the time delay. This paper also discusses advantages and disadvantages of the methods and gives some guidelines for choosing the appropriate algorithm.