Model selection approaches for non-linear system identification: a review

The identification of non-linear systems using only observed finite datasets has become a mature research area over the last two decades. A class of linear-in-the-parameter models with universal approximation capabilities have been intensively studied and widely used due to the availability of many linear-learning algorithms and their inherent convergence conditions. This article presents a systematic overview of basic research on model selection approaches for linear-in-the-parameter models. One of the fundamental problems in non-linear system identification is to find the minimal model with the best model generalisation performance from observational data only. The important concepts in achieving good model generalisation used in various non-linear system-identification algorithms are first reviewed, including Bayesian parameter regularisation and models selective criteria based on the cross validation and experimental design. A significant advance in machine learning has been the development of the support vector machine as a means for identifying kernel models based on the structural risk minimisation principle. The developments on the convex optimisation-based model construction algorithms including the support vector regression algorithms are outlined. Input selection algorithms and on-line system identification algorithms are also included in this review. Finally, some industrial applications of non-linear models are discussed.

An efficient Riemann solver for unsteady flows with non-ideal gases

A Riemann solver is presented for the Euler equations of gas dynamics with real gases. This represents a more efficient version of an algorithm originally presented by the author.

Fractional order and non-linear system identification algorithms for biomedical applications

We discuss the modelling of dielectric responses of amorphous biological samples. Such samples are commonly encountered in impedance spectroscopy studies as well as in UV, IR, optical and THz transient spectroscopy experiments and in pump-probe studies. In many occasions, the samples may display quenched absorption bands. A systems identification framework may be developed to provide parsimonious representations of such responses. To achieve this, it is appropriate to augment the standard models found in the identification literature to incorporate fractional order dynamics. Extensions of models using the forward shift operator, state space models as well as their non-linear Hammerstein-Wiener counterpart models are highlighted. We also discuss the need to extend the theory of electromagnetically excited networks which can account for fractional order behaviour in the non-linear regime by incorporating nonlinear elements to account for the observed non-linearities. The proposed approach leads to the development of a range of new chemometrics tools for biomedical data analysis and classification.

The tragedy of non-ideal theory

This paper has three aims. First, it argues that the present use of ‘ideal theory’ is unhelpful, and that an earlier and apparently more natural use focusing on perfection would be preferable. Second, it has tried to show that revision of the use of the term would better expose two distinctive normative issues, and illustrated that claim by showing how some contributors to debates about ideal theory have gone wrong partly through not distinguishing them. Third, in exposing those two distinct normative issues, it has revealed a particular way in which ideal theory even under the more specific, revisionary definition will often be central to working out what to do in non-ideal circumstances. By clarifying the terms on which debates over ideal and non-ideal theory should take place, and highlighting the particular problems each deals with, it tries to clear the ground for turning to the actual problem, which is what to do in our non-ideal and often tragic circumstances.

Ultrasonic density measurement cell design and simulation of non-ideal effects

This paper presents a theoretical analysis of a density measurement cell using an unidimensional model composed by acoustic and electroacoustic transmission lines in order to simulate non-ideal effects. The model is implemented using matrix operations, and is used to design the cell considering its geometry, materials used in sensor assembly, range of liquid sample properties and signal analysis techniques. The sensor performance in non-ideal conditions is studied, considering the thicknesses of adhesive and metallization layers, and the effect of residue of liquid sample which can impregnate on the sample chamber surfaces. These layers are taken into account in the model, and their effects are compensated to reduce the error on density measurement. The results show the contribution of residue layer thickness to density error and its behavior when two signal analysis methods are used. (c) 2006 Elsevier B.V. All rights reserved.

A review of new vibration issues due to non-ideal energy sources

We analyze the dynamical coupling between energy sources and structural response that must not be ignored in real engineering problems, since real motors have limited output power. We present models of certain problems that render descriptions that are closer to real situations encountered in practice.

Some comments on the numerical simulation of self-synchronization of four non-ideal exciters

In this paper, self-synchronization of four non-ideal exciters is examined via numerical simulation. The mathematical model consists of four unbalanced direct Current motors with limited power supply mounted on a flexible Structural frame support. (c) 2004 Elsevier B.V. All rights reserved.

On an Non-Ideal Global and Local Energy Transfer, Using an Electro-Magneto and Magneto-Rheological Dampers

In this paper, we investigated the nonlinear vibrations of a Non-ideal (NIS) electromechanical absorber (NEVA), taking into account a modified mathematical model of (MR) Damper. We observed the presence of the Sornmerfeld effect (it is the steady state frequencies of the DC motor, which it will usually increasing as more power (Voltage) is given to it, in a step-by-step fashion. When a resonance condition it is reached, the better part of this energy it is consumed to generate large amplitude vibrations of the foundation, without sensible change of the motor frequency). The obtained results, by using numerical and analytical simulations, were discussed, in details.

Comments on nonlinear dynamics of a non-ideal Duffing-Rayleigh oscillator: Numerical and analytical approaches

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Right-to-left shunt determination in dog lungs under inhalation anesthesia with rebreathing and non-rebreathing system

OBJETIVO: Comparar a formação de shunt venoso-arterial em pulmões de cães submetidos a anestesia geral inalatória utilizando-se sistemas de anestesia com e sem reinalação, com fração inspirada de oxigênio de 0,4 e 0,9, respectivamente. MÉTODOS: Empregaram-se 20 cães induzidos com tiopental sódico (30mg/kg) e mantidos com sevoflurano (3%) e alocados em dois grupos (n=10); os animais de GI foram ventilados com modalidade controlada em sistema semifechado, sem reinalação, F I O2 = 0,9, e os de GII, com modalidade controlada, sistema semifechado, com reinalação e F I O2 = 0,4. Os atributos analisados durante o experimento foram: freqüência cardíaca, pressão arterial média, shunt pulmonar venoso-arterial, hematócrito, hemoglobina, pressão parcial de oxigênio arterial, pressão parcial de oxigênio no sangue venoso misto, saturação de oxigênio no sangue venoso misto, pressão parcial de dióxido de carbono arterial e pressão de vapor de água nos alvéolos (P VA). RESULTADOS: A P VA foi significativamente maior em GII. A análise estatística dos valores encontrados de shunt mostrou que GI e GII apresentaram diferenças significativas, sendo que os resultados de GI são maiores que os de GII em todos os momentos avaliados. Já a análise de momentos dentro de um mesmo grupo não demonstrou diferenças. CONCLUSÃO: O sistema de anestesia sem reinalação com F I O2 = 0,9 desenvolveu maior grau de shunt pulmonar venoso-arterial que o sistema de anestesia com reinalação e F I O2 = 0,4. A umidificação dos gases em GII contribuiu para diminuir o shunt.

An overview on non-ideal vibrations

We analyze the dynamical coupling between energy sources and structural response that must not be ignored in real engineering problems, since real motors have limited output power.

Using transient and steady state considerations to investigate the mechanism of loss of stability of a dynamical system

This work presents the complete set of features for solutions of a particular non-ideal mechanical system near the fundamental and near to a secondary resonance region. The system comprises a pendulum with a horizontally moving suspension point. Its motion is the result of a non-ideal rotating power source (limited power supply), acting oil the Suspension point through a crank mechanism. Main emphasis is given to the loss of stability, which occurs by a sequence of events, including intermittence and crisis, when the system reaches a chaotic attractor. The system also undergoes a boundary-crisis, which presents a different aspect in the bifurcation diagram due to the non-ideal supposition. (c) 2004 Published by Elsevier B.V.