Author
Aggelos G. Poulimenos
Bio: Aggelos G. Poulimenos is an academic researcher from University of Patras. The author has contributed to research in topics: Autoregressive–moving-average model & Parametric statistics. The author has an hindex of 7, co-authored 13 publications receiving 411 citations.
Papers
More filters
TL;DR: A critical survey and comparison ofparametric time-domain methods for non-stationary random vibration modelling and analysis based upon a single vibration signal realization confirms the advantages and high performance characteristics of parametric methods.
246 citations
TL;DR: The results of the study demonstrate the applicability, effectiveness, and high accuracy of the non-stationary FS-TARMA approach in capturing and analyzing the TV structural dynamics.
70 citations
TL;DR: In this paper, the problem of parametric time-domain identification and dynamic analysis for time-varying (TV) mechanical structures under unobservable random excitation is addressed.
51 citations
01 Jan 2004
TL;DR: In this paper, a statistical model-based method for fault detection in non-stationary structural systems is proposed, based upon baseline structural modelling using nonstationary Functional Series Time-dependent AutoRegressive with eXogenous excitation (FS-TARX) models and on-line inspection schemes utilizing statistical decision making.
Abstract: The problem of vibrationnbased onnline fault detection in non-stationary structural systems is considered, and a statistical model based method is introduced. The method is based upon baseline structural modelling using non-stationary Functional Series Time-dependent AutoRegressive with eXogenous excitation (FS-TARX) models and on-line inspection schemes utilizing statistical decision making. The effectiveness of the method is demonstrated via its application to a laboratory system consisting of a ibridge-likei structure with a sliding mass.
14 citations
08 Sep 2005
TL;DR: Maximum Likelihood (ML) and Multi-Stage Weighted Linear / Non-Linear Least Squares (MS-WLLS / MS-WNLS) estimation methods are formulated for non-stationary Functional Series Time-dependent ARMA (FS-TARMA) models and are demonstrated via Monte Carlo experiments.
Abstract: Maximum Likelihood (ML) and Multi-Stage Weighted Linear / Non-Linear Least Squares (MS-WLLS / MS-WNLS) estimation methods are formulated for non-stationary Functional Series Time-dependent ARMA (FS-TARMA) models. The methods' effectiveness, as well as their superiority over Ordinary Linear / Non-Linear Least Squares (OLLS / ONLS) type methods not accounting for innovations serial heteroscedasticity, are demonstrated via Monte Carlo experiments.
11 citations
Cited by
More filters
TL;DR: A systematic review of over 20 major time-frequency analysis methods reported in more than 100 representative articles published since 1990 can be found in this article, where their fundamental principles, advantages and disadvantages, and applications to fault diagnosis of machinery have been examined.
719 citations
TL;DR: A general control design approach is proposed when global stabilization is feasible via state feedback, and instead of designing the logical form of a stabilizing feedback law directly, it is suggested that its algebraic representation should be constructed and then converted to logical form.
Abstract: State feedback stabilization for Boolean control networks is investigated in this technical note. Based on the algebraic representation of logical dynamics in terms of the semi-tensor product of matrices, a necessary and sufficient condition is derived for the existence of a globally stabilizing state feedback controller, and a general control design approach is proposed when global stabilization is feasible via state feedback. Instead of designing the logical form of a stabilizing feedback law directly, we first construct its algebraic representation and then convert the algebraic representation back to the logical form. An example is worked out to illustrate the proposed design procedure.
264 citations
TL;DR: A critical survey and comparison ofparametric time-domain methods for non-stationary random vibration modelling and analysis based upon a single vibration signal realization confirms the advantages and high performance characteristics of parametric methods.
246 citations
TL;DR: An overview of the principles and techniques of time-series methods for fault detection, identification and estimation in vibrating structures is presented, and certain new methods are introduced.
Abstract: An overview of the principles and techniques of time-series methods for fault detection, identification and estimation in vibrating structures is presented, and certain new methods are introduced. The methods are classified, and their features and operation are discussed. Their practicality and effectiveness are demonstrated through brief presentations of three case studies pertaining to fault detection, identification and estimation in an aircraft panel, a scale aircraft skeleton structure and a simple nonlinear simulated structure.
213 citations