Multivariate GP-VAR models for robust structural identification under operational variability (2022)

While the concept of structural monitoring has been around for a number of decades, it remains under-exploited in practice. A main driver for this shortcoming lies in the difficulty to robustly and autonomously interpret the information that is extracted from dynamic data. This hindrance in properly deciphering the collected information may be attributed to the uncertainty that is inherent in i) the finite set of measured data, ii) the models employed for capturing the manifested dynamics, and more importantly, iii) the susceptibility of these systems to variations in Environmental and Operational Parameters (EOPs). In previous work of the authors, a Gaussian Process (GP) time-series approach has been introduced, which serves as a hierarchical input–output method to account for the influence of EOPs on structural response. This in turn enables a robust structural identification. In this scheme, the short-term dynamics are modeled by means of linear-in-the-parameters time-series models, while EOV dependence – acting on a long-term time scale – is achieved via GP regression of the model coefficients on measured EOPs. This work corresponds to a further advancement on this modeling approach, corresponding to its generalization to the vector response case. Particularly, the problem of global identification here is solved via an Expectation–Maximization algorithm tailored to the GP time-series model structure. Moreover, an EOP-dependent innovations covariance matrix is integrated in the model, which helps to capture variation in the vibration power. The resulting model does not only have the capability to represent the long-term response of a structure under variable EOPs, but also facilitates the enhanced tracking of modal quantities in contrast to traditional operational modal analysis techniques. The proposed approach is exemplified on the identification of the vibration response of a simulated wind turbine blade at different points along the blade axis in the flap-wise direction, under variability of both the acting wind speeds and ambient temperatures.

Original languageEnglish
Article number103035
JournalProbabilistic Engineering Mechanics
Volume60
Number of pages13
ISSN0266-8920
DOIs
Publication statusPublished - Apr 2020
  • Data-driven condition assessment
  • Environmental and Operational Variability (EOV)
  • Gaussian Process (GPs) Vector AutoRegressive (GP-VAR) models
  • Structural Health Monitoring (SHM)
  • Wind energy infrastructure
  • APA
  • Author
  • BIBTEX
  • Harvard
  • Standard
  • RIS
  • Vancouver

Avendaño-Valencia, L. D., & Chatzi, E. N. (2020). Multivariate GP-VAR models for robust structural identification under operational variability. Probabilistic Engineering Mechanics, 60, [103035]. https://doi.org/10.1016/j.probengmech.2020.103035

Avendaño-Valencia, Luis David ; Chatzi, Eleni N. / Multivariate GP-VAR models for robust structural identification under operational variability. In: Probabilistic Engineering Mechanics. 2020 ; Vol. 60.

@article{949900577bbe4f6b880d780bdb80dbd2,

title = "Multivariate GP-VAR models for robust structural identification under operational variability",

abstract = "While the concept of structural monitoring has been around for a number of decades, it remains under-exploited in practice. A main driver for this shortcoming lies in the difficulty to robustly and autonomously interpret the information that is extracted from dynamic data. This hindrance in properly deciphering the collected information may be attributed to the uncertainty that is inherent in i) the finite set of measured data, ii) the models employed for capturing the manifested dynamics, and more importantly, iii) the susceptibility of these systems to variations in Environmental and Operational Parameters (EOPs). In previous work of the authors, a Gaussian Process (GP) time-series approach has been introduced, which serves as a hierarchical input–output method to account for the influence of EOPs on structural response. This in turn enables a robust structural identification. In this scheme, the short-term dynamics are modeled by means of linear-in-the-parameters time-series models, while EOV dependence – acting on a long-term time scale – is achieved via GP regression of the model coefficients on measured EOPs. This work corresponds to a further advancement on this modeling approach, corresponding to its generalization to the vector response case. Particularly, the problem of global identification here is solved via an Expectation–Maximization algorithm tailored to the GP time-series model structure. Moreover, an EOP-dependent innovations covariance matrix is integrated in the model, which helps to capture variation in the vibration power. The resulting model does not only have the capability to represent the long-term response of a structure under variable EOPs, but also facilitates the enhanced tracking of modal quantities in contrast to traditional operational modal analysis techniques. The proposed approach is exemplified on the identification of the vibration response of a simulated wind turbine blade at different points along the blade axis in the flap-wise direction, under variability of both the acting wind speeds and ambient temperatures.",

keywords = "Data-driven condition assessment, Environmental and Operational Variability (EOV), Gaussian Process (GPs) Vector AutoRegressive (GP-VAR) models, Structural Health Monitoring (SHM), Wind energy infrastructure",

author = "Avenda{\~n}o-Valencia, {Luis David} and Chatzi, {Eleni N.}",

year = "2020",

(Video) Damage Quantification in Laminated Composites using Gaussian Process Regression Model

month = apr,

doi = "10.1016/j.probengmech.2020.103035",

language = "English",

volume = "60",

journal = "Probabilistic Engineering Mechanics",

issn = "0266-8920",

publisher = "Elsevier",

}

Avendaño-Valencia, LD & Chatzi, EN 2020, 'Multivariate GP-VAR models for robust structural identification under operational variability', Probabilistic Engineering Mechanics, vol. 60, 103035. https://doi.org/10.1016/j.probengmech.2020.103035

Multivariate GP-VAR models for robust structural identification under operational variability. / Avendaño-Valencia, Luis David; Chatzi, Eleni N.

(Video) GPSS 2021: Kernel design

In: Probabilistic Engineering Mechanics, Vol. 60, 103035, 04.2020.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Multivariate GP-VAR models for robust structural identification under operational variability

AU - Avendaño-Valencia, Luis David

AU - Chatzi, Eleni N.

PY - 2020/4

Y1 - 2020/4

N2 - While the concept of structural monitoring has been around for a number of decades, it remains under-exploited in practice. A main driver for this shortcoming lies in the difficulty to robustly and autonomously interpret the information that is extracted from dynamic data. This hindrance in properly deciphering the collected information may be attributed to the uncertainty that is inherent in i) the finite set of measured data, ii) the models employed for capturing the manifested dynamics, and more importantly, iii) the susceptibility of these systems to variations in Environmental and Operational Parameters (EOPs). In previous work of the authors, a Gaussian Process (GP) time-series approach has been introduced, which serves as a hierarchical input–output method to account for the influence of EOPs on structural response. This in turn enables a robust structural identification. In this scheme, the short-term dynamics are modeled by means of linear-in-the-parameters time-series models, while EOV dependence – acting on a long-term time scale – is achieved via GP regression of the model coefficients on measured EOPs. This work corresponds to a further advancement on this modeling approach, corresponding to its generalization to the vector response case. Particularly, the problem of global identification here is solved via an Expectation–Maximization algorithm tailored to the GP time-series model structure. Moreover, an EOP-dependent innovations covariance matrix is integrated in the model, which helps to capture variation in the vibration power. The resulting model does not only have the capability to represent the long-term response of a structure under variable EOPs, but also facilitates the enhanced tracking of modal quantities in contrast to traditional operational modal analysis techniques. The proposed approach is exemplified on the identification of the vibration response of a simulated wind turbine blade at different points along the blade axis in the flap-wise direction, under variability of both the acting wind speeds and ambient temperatures.

AB - While the concept of structural monitoring has been around for a number of decades, it remains under-exploited in practice. A main driver for this shortcoming lies in the difficulty to robustly and autonomously interpret the information that is extracted from dynamic data. This hindrance in properly deciphering the collected information may be attributed to the uncertainty that is inherent in i) the finite set of measured data, ii) the models employed for capturing the manifested dynamics, and more importantly, iii) the susceptibility of these systems to variations in Environmental and Operational Parameters (EOPs). In previous work of the authors, a Gaussian Process (GP) time-series approach has been introduced, which serves as a hierarchical input–output method to account for the influence of EOPs on structural response. This in turn enables a robust structural identification. In this scheme, the short-term dynamics are modeled by means of linear-in-the-parameters time-series models, while EOV dependence – acting on a long-term time scale – is achieved via GP regression of the model coefficients on measured EOPs. This work corresponds to a further advancement on this modeling approach, corresponding to its generalization to the vector response case. Particularly, the problem of global identification here is solved via an Expectation–Maximization algorithm tailored to the GP time-series model structure. Moreover, an EOP-dependent innovations covariance matrix is integrated in the model, which helps to capture variation in the vibration power. The resulting model does not only have the capability to represent the long-term response of a structure under variable EOPs, but also facilitates the enhanced tracking of modal quantities in contrast to traditional operational modal analysis techniques. The proposed approach is exemplified on the identification of the vibration response of a simulated wind turbine blade at different points along the blade axis in the flap-wise direction, under variability of both the acting wind speeds and ambient temperatures.

KW - Data-driven condition assessment

KW - Environmental and Operational Variability (EOV)

(Video) 2021 SMI Conference - Session 8: Flexible Bayesian Approaches for Imaging Analysis

KW - Gaussian Process (GPs) Vector AutoRegressive (GP-VAR) models

KW - Structural Health Monitoring (SHM)

KW - Wind energy infrastructure

U2 - 10.1016/j.probengmech.2020.103035

DO - 10.1016/j.probengmech.2020.103035

M3 - Journal article

VL - 60

JO - Probabilistic Engineering Mechanics

JF - Probabilistic Engineering Mechanics

SN - 0266-8920

M1 - 103035

ER -

Avendaño-Valencia LD, Chatzi EN. Multivariate GP-VAR models for robust structural identification under operational variability. Probabilistic Engineering Mechanics. 2020 Apr;60. 103035. https://doi.org/10.1016/j.probengmech.2020.103035

(Video) DSI | MuyGPs: Scalable Gaussian Process Hyperparameter Estimation Using Local Cross-Validation
(Video) Overview of GPy

Videos

1. Timeseries Variability Features
(Rubin Observatory)
2. Sudipto Banerjee: High-dimensional Bayesian geostatistics
(Centre International de Rencontres Mathématiques)
3. ICTP 2015: Qingyun Duan (BNU China) - Parametric Uncertainty of Large Geophysical Models
(UTIG UT Institute for Geophysics)
4. Utility-Owned Distributed Generation Models
(Clean Energy Solutions Center)
5. Reverse Stress Testing Using AI with Microsoft & Axioma
(Ai4)
6. Tutorial on From Covariance Matrices to Covariance Operators: Data Representation from Finite t...
(ComputerVisionFoundation Videos)

You might also like

Latest Posts

Article information

Author: Aracelis Kilback

Last Updated: 09/12/2022

Views: 6724

Rating: 4.3 / 5 (44 voted)

Reviews: 83% of readers found this page helpful

Author information

Name: Aracelis Kilback

Birthday: 1994-11-22

Address: Apt. 895 30151 Green Plain, Lake Mariela, RI 98141

Phone: +5992291857476

Job: Legal Officer

Hobby: LARPing, role-playing games, Slacklining, Reading, Inline skating, Brazilian jiu-jitsu, Dance

Introduction: My name is Aracelis Kilback, I am a nice, gentle, agreeable, joyous, attractive, combative, gifted person who loves writing and wants to share my knowledge and understanding with you.