Title :
System identification based on quantized I/O data corrupted with noises and its performance improvement
Author :
Suzuki, Hiromi ; Sugie, Toshiharu
Author_Institution :
Dept. of Syst. Sci., Kyoto Univ.
Abstract :
This paper proposes an identification method for linear systems based on the quantized input-output (I/O) data in the presence of measurement noises. First, the parameter estimation error due to quantization of I/O data is analyzed from the statistical viewpoint when an instrumental variable (IV) method or the least squares (LS) one is adopted. Then, based on the analysis, an IV method suitably adjusted for quantized data is obtained. In addition, a multi-step algorithm is proposed to enhance the estimation performance. The validity of the proposed method is evaluated through a numerical example
Keywords :
iterative methods; linear systems; parameter estimation; quantisation (signal); statistical analysis; I/O data quantization; instrumental variable method; least squares; linear system; measurement noise; multistep algorithm; parameter estimation error analysis; quantized input-output data; statistical analysis; system identification; Control systems; Digital control; Instruments; Least squares approximation; Linear systems; Noise measurement; Parameter estimation; Quantization; System identification; USA Councils; Linear system identification; discrete-time systems; uniform quantization;
Conference_Titel :
Decision and Control, 2006 45th IEEE Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
1-4244-0171-2
DOI :
10.1109/CDC.2006.377541
