Gaussian process models for mitigation of operational variability in the structural health monitoring of wind turbines

被引:65
作者
Avendano-Valencia, Luis David [1 ]
Chatzi, Eleni N. [2 ]
Tcherniak, Dmitri [3 ]
机构
[1] Univ Southern Denmark, Fac Engn, Maersk McKinney Moller Inst, Grp Appl & Data Sci, Campusvej 55, Odense 5230, Denmark
[2] Swiss Fed Inst Technol, Dept Civil Environm & Geomat Engn, Inst Struct Engn, Stefano Franscini Pl 5, Zurich 8093, Switzerland
[3] Bruel & Kjaer Sound & Vibrat Measurement AS, Innovat Team, Skodsborgvej 307, Naerum 2850, Denmark
关键词
Environmental and operational variability; Structural Health Monitoring; Non-stationary vibration; Wind turbine; Gaussian process regression; Time-series models; ENVIRONMENTAL-CONDITIONS; DAMAGE DIAGNOSIS; UNCERTAINTY; SYSTEMS; FAULT;
D O I
10.1016/j.ymssp.2020.106686
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
The analysis presented in this work relates to the quantification of the effect of a selected set of measured Environmental and Operational Parameters (EOPs) on the dynamic properties of low and high frequency vibration, in the context of a vibration monitoring campaign implemented on the blade of an operating wind turbine. To this end, a Gaussian Process (GP) time-series modelling approach is adopted, in which the coefficients of a time-series model are driven by a Gaussian Process Regression on the selected EOPs. The properties of the data acquisition system allow to evaluate low and high frequency dynamics, the former associated with the structural dynamics of the blade, and the latter with the wave transmission properties of the material, assessed with the help of an electromechanical actuator installed on the blade. In this form, a multi-temporal-scale approach is adopted here, where a GP Linear Parameter Varying Auto-Regressive model is selected to represent low frequency (structural) dynamics, while in parallel a GP Continuous Wavelet Transform model is used to represent high frequency dynamics (associated with wave transmission properties in the material). In both cases the blade is considered in its healthy state as well as in various operational regimes, including idle, and rotating at two different set points. As a result, it is demonstrated that GP time-series modelling succeeds in evaluating and isolating the influence of different EOPs in the features of the vibration response of the wind turbine blade, and at the same time, normalize their effects to enhance the detectability of damage. (C) 2020 Elsevier Ltd. All rights reserved.
引用
收藏
页数:23
相关论文
共 36 条
[21]   Improvement of damage detection methods based on experimental modal parameters [J].
Radzienski, Maciej ;
Krawczuk, Marek ;
Palacz, Magdalena .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2011, 25 (06) :2169-2190
[22]   Application of mother wavelet functions for automatic gear and bearing fault diagnosis [J].
Rafiee, J. ;
Rafiee, M. A. ;
Tse, P. W. .
EXPERT SYSTEMS WITH APPLICATIONS, 2010, 37 (06) :4568-4579
[23]   Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification [J].
Reynders, Edwin ;
Wursten, Gersom ;
De Roeck, Guido .
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2014, 13 (01) :82-93
[24]   Functionally Pooled models for the global identification of stochastic systems under different pseudo-static operating conditions [J].
Sakellariou, J. S. ;
Fassois, S. D. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 72-73 :785-807
[25]   A nonlinear cointegration approach with applications to structural health monitoring [J].
Shi, H. ;
Worden, K. ;
Cross, E. J. .
13TH INTERNATIONAL CONFERENCE ON MOTION AND VIBRATION CONTROL (MOVIC 2016) AND THE 12TH INTERNATIONAL CONFERENCE ON RECENT ADVANCES IN STRUCTURAL DYNAMICS (RASD 2016), 2016, 744
[26]   Effects of environmental and operational variability on structural health monitoring [J].
Sohn, Hoon .
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2007, 365 (1851) :539-560
[27]   Metamodeling of dynamic nonlinear structural systems through polynomial chaos NARX models [J].
Spiridonakos, M. D. ;
Chatzi, E. N. .
COMPUTERS & STRUCTURES, 2015, 157 :99-113
[28]   Polynomial Chaos Expansion Models for the Monitoring of Structures under Operational Variability [J].
Spiridonakos, Minas D. ;
Chatzi, Eleni N. ;
Sudret, Bruno .
ASCE-ASME JOURNAL OF RISK AND UNCERTAINTY IN ENGINEERING SYSTEMS PART A-CIVIL ENGINEERING, 2016, 2 (03)
[29]  
Tcherniak D., 2016, P 8 EUR WORKSH STRUC, P1
[30]   Active vibration-based structural health monitoring system for wind turbine blade: Demonstration on an operating Vestas V27 wind turbine [J].
Tcherniak, Dmitri ;
Molgaard, Lasse L. .
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2017, 16 (05) :536-550