Auxiliary model based parameter estimation for dual-rate output error
systems with colored noise
q
Jie Ding
⇑
, Chunxia Fan, Jinxing Lin
College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210046, PR China
article info
Article history:
Received 18 April 2012
Received in revised form 3 August 2012
Accepted 11 September 2012
Available online 21 September 2012
Keywords:
Dual-rate sampled data
Auxiliary model
Output error model
Least square
Recursive prediction error method
abstract
The dual-rate sampled-data systems can offer better quality of control than the systems
with single sampling rate in practice. However, the conventional identification methods
run in the single-rate scheme. This paper focuses on the parameter estimation problems
of the dual-rate output error systems with colored noises. Based on the dual-rate sampled
and noise-contaminated data, two direct estimation algorithms are addressed: the auxil-
iary model based recursive extended least squares algorithm and the recursive prediction
error method. The auxiliary model is employed to estimate the noise-free system output.
An example is given to test and illustrate the proposed algorithms.
Ó 2012 Elsevier Inc. All rights reserved.
1. Introduction
The control variables in process industry are limited by the physical or mechanical factors of the systems and need to be
sampled by different data sampling/holding rates, resulting in the multirate systems [1,2]. Multirate systems may offer bet-
ter quality of control than the systems with single sampling rate in practice, and thus have wide engineering applications in
the networked control systems [3–6], signal processing [7], telecommunication [8] and so on. For research convenience, the
dual-rate sampled-data systems [9–12] are primarily studied as special cases of multirate systems with the system output
sampling period being a multiple of the input holding period.
To develop an appropriate identification model structure that is consistent with the dual-rate sampled data, two model
transformation techniques are frequently employed, one is the lifting technique [13] that can transform the dual-rate system
into a lifted multivariable state-space model, and then identify this new model. The other one is the polynomial transforma-
tion technique [14,15]. The main drawback of the two techniques is that the transformed models contain more parameters to
be estimated than the original single-rate systems do, and the estimation process includes the transformation from the new
model to the original one which will influence the estimation accuracy.
A better way is to identify the parameters of single-rate models from dual-rate sampled data directly. Ding and Chen pro-
posed two algorithms that directly estimate the parameters of single-rate models from dual-rate sampled data by using an
auxiliary model [16–18] and an FIR model [19], respectively. Ding presented two direct approaches of identifying single-rate
models of dual-rate systems [20], one is the generalized Yule–Walker algorithm and the other one is a two-stage algorithm
0307-904X/$ - see front matter Ó 2012 Elsevier Inc. All rights reserved.
http://dx.doi.org/10.1016/j.apm.2012.09.016
q
This work was supported by the National Natural Science Foundation of China (61203028) and the Initial Science Research Foundation of Nanjing
University of Posts and Telecommunications.
⇑
Corresponding author.
E-mail addresses: dingjie@njupt.edu.cn (J. Ding), fancx@njupt.edu.cn (C. Fan), jxlin2004@126.com (J. Lin).
Applied Mathematical Modelling 37 (2013) 4051–4058
Contents lists available at SciVerse ScienceDirect
Applied Mathematical Modelling
journal homepage: www.elsevier.com/locate/apm