Blind identification of non-stationary MA systems (original) (raw)
Related papers
Compensation of biased excitation effects for MLS-based nonlinear systems' identification
Signal Processing, 2015
MLS-based identification of nonlinear systems is largely affected by deviations in the excitation signal amenable to the combined effect of DC-offset and an arbitrary gain. These induce orthogonality loss in the MLS filter bank output, thus invalidating the underlying identification construction. In this paper we present a correction algorithm to derive the corrected Volterra kernels from the biased estimations provided by the standard MLSbased procedure.
Initialization Techniques for Improved Convergence of LMS DFEs in Strong Interference Environments
2007
The least-mean square (LMS) decision-feedback equalizer (DFE) was previously shown [1], [2] to possess an extended convergence time in an interference limited environment. In [1] it was shown that the convergence time can be significantly reduced by using the received samples and the training data to initialize (data-aided initialization) the LMS weights with an estimate for the Wiener weights. In this paper, two dataaided initialization techniques for equalization in the presence of severe narrowband interference are discussed and compared. The estimate of the Wiener filter is obtained from data-based averages of the autocorrelation matrix and the cross-correlation vector.
A Blind Approach to Closed-Loop Identification of Hammerstein Systems
2006
This paper is a continuing study of the blind approach for the Hammerstein identification in Sun, and . In the framework of a closed-loop sampled-data system, the output is sampled faster than the updating period of the input. The parameters of the linear dynamics are consistently estimated from the information of the output only, after which the unmeasurable inner signal is uniquely reconstructed. The noise effect is explicitly considered in both the parameter and inner signal estimation. The estimation of the system orders and time delay are studied on the basis of two groups of basic equations obtained by polyphase decomposition. The proposed blind approach is validated and illustrated by a simulated numerical example.
NON-PARAMETRIC IDENTIFICATION OF A CLASS OF NON-LINEAR CLOSE-COUPLED DYNAMIC SYSTEM
A non-parametric identification technique for the identification ofarbitrary memoryless non-linearities has been presented for a class ofclose-coupled dynamic systems which are commonly met with in mechanical and structural engineering. The method is essentially a regression technique and expresses the non-linearities as series expansions in terms of orthogonal functions. Whereas no limitation on the type of test signals is imposed, the method requires the monitoring of the response of each of the masses in the system. The computational efficiency of the method, its easy implementation on analogue and digital machines and its relative insensitivity to measurement noise make it an attractive approach to the non-parametric identification problem. met with in mechanical and structural systems.?-For instance, a 'cubic spring' type non-linearity would require the determination of third-order kernels whose computation in practice becomes prohibitively expensive.20, In addition, the Wiener approach uses white noise inputs. It is often extremely difficult. if not impossible, to generate large enough inputs of this nature so as to drive large (and often massive) dynamic systems in their non-linear range of response. Applications of such techniques to large non-linear rnultidegree-of-freedom systems are few, if any. This paper presents a relatively simple non-parametric approach to the identification of a class of multidegree-of-freedom (MDF) close-coupled non-linear systems ). The method, following Graupe." is basically a rcgression technique. Masri and Caughey'" were the first to apply this technique to the identification of a single-degree-of-freedom oscillator, by expanding the restoring force in a series of Chebyshev polynomials.22 Herein, we extend the method to include a class of MDF systems, and further generalize it through the use of arbitrary orthogonal sets of functions. The technique has the advantage of being computationally efficient and simple to implement on analogue and digital machines. Unlike the Wiener Kernel approach, it is not restricted to 'white noise' type of inputs, and can be used with almost any type of test input. The choice of the class of models, M, has been governed by its wide usage in problems involving the dynamic response of: (i) full scale building structures, (ii) layered soil ma~ses,'~ (iii) mechanical eq~iprnent.'~. and (iv) machine components and subsystems in, for instance, the nuclear industry.26% " shown that even under extremely noisy measurement conditions, the method yields good results.
Efficient Realization Of An Adfe With A New Adaptive Algorithm
2007
Decision feedback equalizers are commonly employed to reduce the error caused by intersymbol interference. Here, an adaptive decision feedback equalizer is presented with a new adaptation algorithm. The algorithm follows a block-based approach of normalized least mean square (NLMS) algorithm with set-membership filtering and achieves a significantly less computational complexity over its conventional NLMS counterpart with set-membership filtering. It is shown in the results that the proposed algorithm yields similar type of bit error rate performance over a reasonable signal to noise ratio in comparison with the latter one.
Earthquake Engineering & Structural Dynamics, 2007
Non-linear structural identification problems have raised considerable research efforts since decades, in which the Bouc-Wen model is generally utilized to simulate non-linear structural constitutive characteristic. Support vector regression (SVR), a promising data processing method, is studied for versatile-typed structural identification. First, a model selection strategy is utilized to determine the unknown power parameter of the Bouc-Wen model. Meanwhile, optimum SVR parameters are selected automatically, instead of tuning manually. Consequently, the non-linear structural equation is rewritten in linear form, and is solved by the SVR technique. A five-floor versatile-type structure is studied to show the effectiveness of the proposed method, in which both power parameter known and unknown cases are investigated. . 910 J. ZHANG, T. SATO AND S. IAI data. Tan and Weng suggested an iterative identification scheme to investigate constitutive non-linear properties of isolated structures. The differential evolution algorithm utilized by Kyprianou et al. [12] performed direct search of the Bouc-Wen model optimum parameters. A method using the Bayesian state estimation and bootstrap filter was presented by Li et al. to estimate parameters of a non-linear system with slip. Ni et al. addressed a one-stage parameter estimate scheme to identify parameters of a friction-type isolator from periodic vibration test data. Hammond [15], Roberts and Sadeghi , and Loh and Chung [17] proposed multi-stage schemes to identify non-linear structural parameters, consisting of the power parameter of the versatile model. Some adaptive tracking approaches have also been proposed to identify time-varying non-linear structural parameters on-line .
Blind Identification of Arma Systems Using the Discrete Random Decrement
The Random Decrement method is a computationally simple technique which was initially proposed in the control engineering field for the recovery of impulse responses of systems under operation. This paper demonstrates the advantage of formalising this exotic technique in the context of digital signal processing, thus bringing it to the fore of modern blind identification methods. The discrete Random Decrement is shown to verify a type of Yule-Walker system of equations from which the poles of the system can be deduced. In addition, it is proven that the identification of the zeros (minimum and maximum phase) can be achieved in a linear sense by increasing the number of observations to a least three. The conditions of application of the Random Decrement are relatively broad, and its effectiveness is demonstrated by simulations.
For Multiple-Input Multiple-Output Open-Loop System Identification
2013
A procedure is presented for input design in MIMO system identification that explicitly takes system gain directionality into account. For ill-conditioned systems, the dynamics tend to be different in the various gain directions. The advantage of this procedure is that the dynamics in all gain directions can be identified. The procedure can be used for any type of excitation signal, e.g., step, PRBS or multi-sinusoidal signals. The superiority of the proposed input designs over more standard designs is demonstrated on a pilot-scale distillation column. The main conclusion of the study is that it is crucial that the various gain directions in a MIMO system are properly excited. The type of input signal (e.g., step or PRBS), or the way of exciting the gain directions, appears to be less important.