AN OPTIMIZING SEARCH BASED IDENTIFICATION METHOD OF STOCHASTIC TIME-DELAY SYSTEMS

Some significant improvements on the commonly used identification method of time-delay systems,i.e.,method of direct least-squares estimation with step-by-step search,are made in this paper.Firstly it is discussed how to design a proper digital filter in order to obtain a unimodal criterion function with respect to time delay.Then it is proposed that the golden section method can be used to search the time delay optimizingly,while the system parameters are simultaneously estimated by applying the least-squares method.The proposed optimizing search based method has such advantages as less computational load and more extensive practical applications.Simulation results are also included in the paper.