Relay‐based identification of Wiener model

Abstract

Wiener model belongs to a broad class of non-linear model structures called the block-oriented models. Various chemical, biological and electrical processes can be represented as a Wiener structure. There are vast numbers of approaches to identify the Wiener model; however, most of them are only theoretically sound. Therefore, there is a need for developing an industrial grade, simple identification scheme. The present research work attempts to explore the possibility of identifying Wiener models using relay feedback identification technique, which has been applied efficiently but limited mostly to linear structures. Here, the authors consider not all but wider probable cases of the linear subsystem, which include real roots, complex conjugate roots, first-order, integrating second-order and repeated roots. The proposed method is simple and requires less prior knowledge about the system. The technique being somehow general can be applied effectively to linear and unstable systems as well. Various simulation examples are used to demonstrate the efficacy of the proposed identification scheme.

Application of Fractional Calculus for Parameter Estimation of Nonlinear Wiener Systems With Time Delay

“…For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ and dynamic disturbances was developed and presented in [18]. Recently, Meher and Manjhi [19] illustrated another relay-based identification technique for Wiener systems, which is applicable to stable as well as unstable systems.…”

“…The MATLAB function fsolve was utilized to estimate the unknown parameters using (38). Wienertype nonlinear systems with significant nonlinearity have been selected from the literatures [17], [19], and [39] and simulated to evaluate the performance of the proposed method compared to existing relay feedback methods RF1 method [19], RF2 method [39], and RF3 method [17]. The performance was analyzed and compared in the following examples with and without noise.…”

“…Example 1: Consider a simple case of the Wiener-type system whereby the linear subsystem G 1 (s) = 1 (5s+1) e −s is followed by the output nonlinearity f 1 (v) = 2(1 − e −0.693v ), as studied in [19].…”

Gradient‐based recursive parameter estimation for a periodically nonuniformly sampled‐data Hammerstein–Wiener system based on the key‐term separation

“…Nonlinear systems have attracted numerous attention of researchers owing to their simple structures and effectual reflections to nonlinear plants, [1][2][3][4] for example, the Hammerstein systems, [5][6][7] the Wiener systems, [8][9][10] the Hammerstein-Wiener (H-W) systems, 11,12 and the Wiener-Hammerstein (W-H) systems. 13,14 A Hammerstein system consists of a static input nonlinear element in series with a dynamic linear subsystem.…”

Robust identification for input non‐uniformly sampled Wiener model by the expectation‐maximisation algorithm

“…Trusna Meher et al developed an industrial-grade, simple new identification scheme that used relay feedback identification techniques in Ref. [3]. These researches mainly considered the single rate system that the update period of the controller's output signal (the input signal of the object) is the same as the sampling period of the sensor (the output signal of the object).…”