Gaussian Process-Based Particle-Filtering Approach for Real-Time Damage Prediction with Application

Rajesh Kumar Neerukatti, Masoud Yekani Fard, Aditi Chattopadhyay

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A prognostic model capable of predicting temporal damage evolution is essential to prevent catastrophic failure of structures. Data driven techniques, such as neural networks and support vector machines, are widely used for prediction of damage in a variety of aerospace and civil applications. Most of the available techniques cannot be applied for real-time prediction because they assume the measured value to be the true value, which is often not true. They also require training data from a similar set of experiments based on which predictions are made, which may not always be available. In this paper, the authors propose a novel integrated approach that intelligently combines particle filter updating with a fully probabilistic Gaussian process model to predict complex physical phenomena (e.g., temporal local pier scour) considering both measurement and prediction uncertainties. In this example, the measurement model is obtained using radio frequency identification (RFID) sensors and the state space model is the Gaussian process-based prognosis model. The performance of the algorithm was tested using corrupt training data. Different scenarios are presented with application to predicting local scour near bridge piers, which is a highly stochastic phenomenon with training data mostly unavailable. The algorithm is used to make predictions using corrupt training data. The results indicate that the proposed approach predicts the scour depth accurately under varying field conditions.

Original languageEnglish (US)
Article number04016080
JournalJournal of Aerospace Engineering
Volume30
Issue number1
DOIs
StatePublished - Jan 1 2017

Fingerprint

Scour
Bridge piers
Piers
Radio frequency identification (RFID)
Support vector machines
Neural networks
Sensors
Experiments

Keywords

  • Data analysis
  • Gaussian process
  • Particle filter
  • Prognosis
  • Structural safety
  • Temporal scour

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Materials Science(all)
  • Aerospace Engineering
  • Mechanical Engineering

Cite this

Gaussian Process-Based Particle-Filtering Approach for Real-Time Damage Prediction with Application. / Neerukatti, Rajesh Kumar; Yekani Fard, Masoud; Chattopadhyay, Aditi.

In: Journal of Aerospace Engineering, Vol. 30, No. 1, 04016080, 01.01.2017.

Research output: Contribution to journalArticle

@article{25f3f82aed754bef99cd3c6c1c5959d0,
title = "Gaussian Process-Based Particle-Filtering Approach for Real-Time Damage Prediction with Application",
abstract = "A prognostic model capable of predicting temporal damage evolution is essential to prevent catastrophic failure of structures. Data driven techniques, such as neural networks and support vector machines, are widely used for prediction of damage in a variety of aerospace and civil applications. Most of the available techniques cannot be applied for real-time prediction because they assume the measured value to be the true value, which is often not true. They also require training data from a similar set of experiments based on which predictions are made, which may not always be available. In this paper, the authors propose a novel integrated approach that intelligently combines particle filter updating with a fully probabilistic Gaussian process model to predict complex physical phenomena (e.g., temporal local pier scour) considering both measurement and prediction uncertainties. In this example, the measurement model is obtained using radio frequency identification (RFID) sensors and the state space model is the Gaussian process-based prognosis model. The performance of the algorithm was tested using corrupt training data. Different scenarios are presented with application to predicting local scour near bridge piers, which is a highly stochastic phenomenon with training data mostly unavailable. The algorithm is used to make predictions using corrupt training data. The results indicate that the proposed approach predicts the scour depth accurately under varying field conditions.",
keywords = "Data analysis, Gaussian process, Particle filter, Prognosis, Structural safety, Temporal scour",
author = "Neerukatti, {Rajesh Kumar} and {Yekani Fard}, Masoud and Aditi Chattopadhyay",
year = "2017",
month = "1",
day = "1",
doi = "10.1061/(ASCE)AS.1943-5525.0000680",
language = "English (US)",
volume = "30",
journal = "Journal of Aerospace Engineering",
issn = "0893-1321",
publisher = "American Society of Civil Engineers (ASCE)",
number = "1",

}

TY - JOUR

T1 - Gaussian Process-Based Particle-Filtering Approach for Real-Time Damage Prediction with Application

AU - Neerukatti, Rajesh Kumar

AU - Yekani Fard, Masoud

AU - Chattopadhyay, Aditi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - A prognostic model capable of predicting temporal damage evolution is essential to prevent catastrophic failure of structures. Data driven techniques, such as neural networks and support vector machines, are widely used for prediction of damage in a variety of aerospace and civil applications. Most of the available techniques cannot be applied for real-time prediction because they assume the measured value to be the true value, which is often not true. They also require training data from a similar set of experiments based on which predictions are made, which may not always be available. In this paper, the authors propose a novel integrated approach that intelligently combines particle filter updating with a fully probabilistic Gaussian process model to predict complex physical phenomena (e.g., temporal local pier scour) considering both measurement and prediction uncertainties. In this example, the measurement model is obtained using radio frequency identification (RFID) sensors and the state space model is the Gaussian process-based prognosis model. The performance of the algorithm was tested using corrupt training data. Different scenarios are presented with application to predicting local scour near bridge piers, which is a highly stochastic phenomenon with training data mostly unavailable. The algorithm is used to make predictions using corrupt training data. The results indicate that the proposed approach predicts the scour depth accurately under varying field conditions.

AB - A prognostic model capable of predicting temporal damage evolution is essential to prevent catastrophic failure of structures. Data driven techniques, such as neural networks and support vector machines, are widely used for prediction of damage in a variety of aerospace and civil applications. Most of the available techniques cannot be applied for real-time prediction because they assume the measured value to be the true value, which is often not true. They also require training data from a similar set of experiments based on which predictions are made, which may not always be available. In this paper, the authors propose a novel integrated approach that intelligently combines particle filter updating with a fully probabilistic Gaussian process model to predict complex physical phenomena (e.g., temporal local pier scour) considering both measurement and prediction uncertainties. In this example, the measurement model is obtained using radio frequency identification (RFID) sensors and the state space model is the Gaussian process-based prognosis model. The performance of the algorithm was tested using corrupt training data. Different scenarios are presented with application to predicting local scour near bridge piers, which is a highly stochastic phenomenon with training data mostly unavailable. The algorithm is used to make predictions using corrupt training data. The results indicate that the proposed approach predicts the scour depth accurately under varying field conditions.

KW - Data analysis

KW - Gaussian process

KW - Particle filter

KW - Prognosis

KW - Structural safety

KW - Temporal scour

UR - http://www.scopus.com/inward/record.url?scp=85009121750&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009121750&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)AS.1943-5525.0000680

DO - 10.1061/(ASCE)AS.1943-5525.0000680

M3 - Article

VL - 30

JO - Journal of Aerospace Engineering

JF - Journal of Aerospace Engineering

SN - 0893-1321

IS - 1

M1 - 04016080

ER -