Invited SurveyParametric time-domain methods for non-stationary random vibration modelling and analysis — A critical survey and comparison☆
Section snippets
Acronyms
AIC Akaike information criterion PE prediction error (method) AR autoregressive RELS recursive extended least squares (method) ARMA autoregressive moving average RML recursive maximum likelihood (method) BIC Bayesian information criterion RML-TARMA RML-estimated TARMA (model) FS-TAR functional series TAR (model) RSS residual sum of squares FS-TARMA functional series TARMA (model) SP-TARMA smoothness priors TARMA (model) KF Kalman filter ST-ARMA short-time ARMA NID normally independently distributed STFT short-time Fourier
Important conventions and symbols
A functional argument in parentheses designates function of a real variable; for instance is a function of analog time .
A functional argument in brackets designates function of an integer variable; for instance is a function of normalized discrete time . The conversion from discrete normalized time to analog time is based upon , with standing for the sampling period.
A time instant used as superscript to a function indicates the set of values of the function up to
Non-stationary signal representations
Non-stationary signal representations may be of the parameterized or non-parameterized type. Parameterized representations attempt to model a non-stationary signal via a description that may be specified via a more or less limited number of parameters. As already indicated, they are based upon conceptual extensions of the ARMA representations of the stationary case [17], [18], and, being in the focus of this paper, are presented in detail in the next subsection.
Non-parameterized representations
Non-stationary TARMA model identification
Given a single, N-sample long, non-stationary signal record (realization) and a selected representation class (unstructured, stochastic, or deterministic parameter evolution), the TARMA identification problem may be stated as the problem of selecting the corresponding model “structure”, the model AR and MA parameters and , respectively, and the innovations variance that “best” fit the available measurements. Model “fitness” may be understood in various ways, a
Model-based analysis
Once a TARMA representation has been obtained, model-based analysis may be performed. This includes the computation of non-parameterized representations (such as the model's impulse response function, autocovariance function, appropriate time-frequency distributions) which are now obtained based upon the TARMA representation, as well as “frozen” modal quantities.
Application of the methods to non-stationary vibration modelling and analysis
The parametric modelling methods of Section 3 are presently applied to the problem of modelling and analysis of a non-stationary random vibration signal. Their various performance characteristics, including the attained accuracy, are studied via Monte Carlo experiments. Comparisons with the non-parametric spectrogram and Wigner–Ville distribution methods are also made.
Concluding remarks
A critical overview and comparison of parametric methods for non-stationary random vibration modelling and analysis, based upon a single vibration signal realization, was presented. The methods were all based upon time-dependent ARMA representations, which, according to the form of time-dependence, were classified as unstructured parameter evolution, stochastic parameter evolution and deterministic parameter evolution. As implied by its name, the first class imposes no “structure” on the signal
Acknowledgements
The authors wish to acknowledge the partial financial support of this study by the VolkswagenStiftung (Grant No. I/76938). They also wish to thank Professor S.G. Braun of Technion (Israel) for his encouragement on this undertaking, and one anonymous referee for his constructive comments that led to improvements in the manuscript.
References (86)
- et al.
The analysis of non-stationary signals using time-frequency methods
Journal of Sound and Vibration
(1996) - et al.
Natural frequencies and dampings identification using wavelet transform: application to real data
Mechanical Systems and Signal Processing
(1997) - et al.
Non-stationary functional series TARMA vibration modelling and analysis in a planar manipulator
Journal of Sound and Vibration
(2000) - et al.
Time-frequency analysis in gearbox fault detection using the Wigner–Ville distribution and pattern recognition
Mechanical Systems and Signal Processing
(1997) - et al.
A polynomial-algebraic method for non-stationary TARMA signal analysis, 2, Application to modelling and prediction of power consumption in automobile active suspension systems
Signal Processing
(1998) - et al.
Non-stationary modelling of vibration signals for monitoring the condition of machinery
Mechanical Systems and Signal Processing
(1990) - et al.
Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography
Mechanical Systems and Signal Processing
(2004) - et al.
A time-varying coefficient vector AR modelling of non-stationary covariance time series
Signal Processing
(1993) - et al.
A wavelet-based approach for the identification of linear time-varying dynamical systems
Journal of Sound and Vibration
(2000) - et al.
The application of auto-regressive time series modelling for the time–frequency analysis of civil engineering structures
Engineering Structures
(2001)
Non-stationary signals: phase-energy approach — theory and simulations
Mechanical Systems and Signal Processing
The directional Choi–Williams distribution for the analysis of rotor-vibration signals
Mechanical Systems and Signal Processing
Simulation of earthquake records using time-varying ARMA(2,1) model
Probabilistic Engineering Mechanics
Spectral analysis of the convolution and filtering of non-stationary stochastic processes
Journal of Sound and Vibration
A time-filtered Wigner transformation for use in signal analysis
Mechanical Systems and Signal Processing
Fault detection in gear drives with non-stationary rotational speed, 2, the time–frequency approach
Mechanical Systems and Signal Processing
On-line physical parameter estimation with adaptive forgetting factors
Mechanical Systems and Signal Processing
Changing spectrum estimation
Journal of Sound and Vibration
Time-varying parametric modelling of speech
Signal Processing
Results on AR-modelling of non-stationary signals
Signal Processing
Non-linear systems representation using ARMAX models with time-dependent coefficients
Mechanical Systems and Signal Processing
The poles and zeros of a linear time varying system
Linear Algebra and its Applications
Non-linear and Non-stationary Time Series Analysis
Random Vibration and Statistical Linearization
Random Data: Analysis and Measurement Procedures
Random Vibration and Spectral and Wavelet Analysis
Random Vibration and Spectral Analysis
Smoothness Priors Analysis of Time Series
Non-stationary vibration modelling and analysis via functional series TARMA models
Identification and model updating of a non-stationary vibrating structure
Probabilistic Methods in Structural Engineering
System Identification: Theory for the User
System Identification
Inverse Problem Theory: Methods for Data Fitting and Model Parameter Estimation
Spectral Analysis and Time Series
Time Series Analysis Forecasting and Control
Vibration-based on-line fault detection in non-stationary structural systems via a statistical model based method
Wavelet analysis of vibration, parts 1 and 2
Journal of Vibration and Acoustics
Identification of nonstationary systems using time-frequency methods
Spectral analysis for non-stationary signals from mechanical measurements: a parametric approach
Mechanical Systems and Signal Processing
Functional series TARMA modelling and simulation of earthquake ground motion
Earthquake Engineering and Structural Dynamics
Non-stationary random vibration modelling and analysis via functional series TARMAX models
Cited by (281)
Output-only modal identification with recursive dynamic mode decomposition for time-varying systems
2024, Measurement: Journal of the International Measurement ConfederationShort-term damping estimation for time-varying vibrating structures in nonstationary operating conditions
2023, Mechanical Systems and Signal ProcessingUncertainty quantification in operational modal analysis of time-varying structures based on time-dependent autoregressive moving average model
2023, Journal of Sound and VibrationVibration of a semi-rigid cantilever in a cylinder's unsteady wake at zero incidence angle
2022, Journal of Sound and Vibration
- ☆
Research supported by the VolkswagenStiftung — Grant no I/76938.