Title :
A comparative study of system identification techniques in the presence of parameter variation, noise, and data anomalies
Abstract :
Recursive algorithms for parameter estimation usually require modifications to handle time-varying parameters. A survey of various strategies to accomplish this is presented, along with a discussion on adapting them to different recursive forms. An experimental test method that indicates relative performance in the presence of varying amounts of noise is proposed and demonstrated
Keywords :
identification; recursive estimation; time-varying systems; data anomalies; parameter variation; recursive algorithms; relative performance; system identification techniques; time-varying parameters; Adaptive control; Adaptive signal processing; Estimation error; Fault detection; Least squares methods; Parameter estimation; Resonance light scattering; Signal processing algorithms; System identification; Testing;
Conference_Titel :
Circuits and Systems, 1996., IEEE 39th Midwest symposium on
Conference_Location :
Ames, IA
Print_ISBN :
0-7803-3636-4
DOI :
10.1109/MWSCAS.1996.587796
