Automated piecewise linear regression for analyzing structural health monitoring data

H. Garg; K. Yang; A. G. Cohn; D. Borman; S. V. Nanukuttan; P. A. M. Basheer

doi:10.14359/51740370

Automated piecewise linear regression for analyzing structural health monitoring data

H. Garg
, K. Yang
, A. G. Cohn
, D. Borman
, S. V. Nanukuttan
, P. A. M. Basheer

School of Natural and Built Environment

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

The recent increased interest in structural health monitoring (SHM)
related to material performance has necessitated the application
of advanced data analysis techniques for interpreting the realtime
data in decision-making. Currently, an accurate and efficient
approach for the timely analyses of large volumes of uncertain
sensor data is not well-established. This paper proposes an automated
clustering-based piecewise linear regression (ACPLR)-SHM
methodology for handling, smoothing, and processing large data
sets. It comprises two main stages, where the gaussian weighted
moving average (GWMA) filter is used to smooth noisy data
obtained from electrical resistance sensors, and piecewise linear
regression (PLR) predicts material properties for assessing the
performance of concrete in service. The obtained values of stabilized
resistance and derived values of diffusion coefficients using
this methodology have clearly demonstrated the benefit of applying
ACPLR to the sensor data, thereby classifying the performance of
different types of concrete in service environments.

Original language	English
Pages (from-to)	93-104
Journal	ACI Materials Journal
Volume	121
Issue number	2
DOIs	https://doi.org/10.14359/51740370
Publication status	Published - 01 Mar 2024

Bibliographical note

Original data came from the DfI - QUB project led by S Nanukuttan. Sensor Installation and 3 years of data collection carried out by S Nanukuttan as part of R2920CIV. Lead author is a PhD student of S Nanukuttan.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities

Keywords

artificial intelligence
automated clustering-based piecewise linear regression
diffusion coefficient
electrical resistance
in-service performance
structural health monitoring

Access to Document

10.14359/51740370Licence: Unspecified

Cite this

@article{95945cf27029483b83339cb0a8790e7b,

title = "Automated piecewise linear regression for analyzing structural health monitoring data",

abstract = "The recent increased interest in structural health monitoring (SHM) related to material performance has necessitated the application of advanced data analysis techniques for interpreting the realtime data in decision-making. Currently, an accurate and efficient approach for the timely analyses of large volumes of uncertain sensor data is not well-established. This paper proposes an automated clustering-based piecewise linear regression (ACPLR)-SHM methodology for handling, smoothing, and processing large data sets. It comprises two main stages, where the gaussian weighted moving average (GWMA) filter is used to smooth noisy data obtained from electrical resistance sensors, and piecewise linear regression (PLR) predicts material properties for assessing the performance of concrete in service. The obtained values of stabilized resistance and derived values of diffusion coefficients using this methodology have clearly demonstrated the benefit of applying ACPLR to the sensor data, thereby classifying the performance of different types of concrete in service environments.",

keywords = "artificial intelligence, automated clustering-based piecewise linear regression, diffusion coefficient, electrical resistance, in-service performance, structural health monitoring",

author = "H. Garg and K. Yang and Cohn, \{A. G.\} and D. Borman and Nanukuttan, \{S. V.\} and Basheer, \{P. A. M.\}",

note = "Original data came from the DfI - QUB project led by S Nanukuttan. Sensor Installation and 3 years of data collection carried out by S Nanukuttan as part of R2920CIV. Lead author is a PhD student of S Nanukuttan.",

year = "2024",

month = mar,

day = "1",

doi = "10.14359/51740370",

language = "English",

volume = "121",

pages = "93--104",

journal = "ACI Materials Journal",

issn = "0889-325X",

publisher = "American Concrete Institute",

number = "2",

}

TY - JOUR

T1 - Automated piecewise linear regression for analyzing structural health monitoring data

AU - Garg, H.

AU - Yang , K.

AU - Cohn, A. G.

AU - Borman, D.

AU - Nanukuttan, S. V.

AU - Basheer, P. A. M.

N1 - Original data came from the DfI - QUB project led by S Nanukuttan. Sensor Installation and 3 years of data collection carried out by S Nanukuttan as part of R2920CIV. Lead author is a PhD student of S Nanukuttan.

PY - 2024/3/1

Y1 - 2024/3/1

N2 - The recent increased interest in structural health monitoring (SHM) related to material performance has necessitated the application of advanced data analysis techniques for interpreting the realtime data in decision-making. Currently, an accurate and efficient approach for the timely analyses of large volumes of uncertain sensor data is not well-established. This paper proposes an automated clustering-based piecewise linear regression (ACPLR)-SHM methodology for handling, smoothing, and processing large data sets. It comprises two main stages, where the gaussian weighted moving average (GWMA) filter is used to smooth noisy data obtained from electrical resistance sensors, and piecewise linear regression (PLR) predicts material properties for assessing the performance of concrete in service. The obtained values of stabilized resistance and derived values of diffusion coefficients using this methodology have clearly demonstrated the benefit of applying ACPLR to the sensor data, thereby classifying the performance of different types of concrete in service environments.

AB - The recent increased interest in structural health monitoring (SHM) related to material performance has necessitated the application of advanced data analysis techniques for interpreting the realtime data in decision-making. Currently, an accurate and efficient approach for the timely analyses of large volumes of uncertain sensor data is not well-established. This paper proposes an automated clustering-based piecewise linear regression (ACPLR)-SHM methodology for handling, smoothing, and processing large data sets. It comprises two main stages, where the gaussian weighted moving average (GWMA) filter is used to smooth noisy data obtained from electrical resistance sensors, and piecewise linear regression (PLR) predicts material properties for assessing the performance of concrete in service. The obtained values of stabilized resistance and derived values of diffusion coefficients using this methodology have clearly demonstrated the benefit of applying ACPLR to the sensor data, thereby classifying the performance of different types of concrete in service environments.

KW - artificial intelligence

KW - automated clustering-based piecewise linear regression

KW - diffusion coefficient

KW - electrical resistance

KW - in-service performance

KW - structural health monitoring

U2 - 10.14359/51740370

DO - 10.14359/51740370

M3 - Article

SN - 0889-325X

VL - 121

SP - 93

EP - 104

JO - ACI Materials Journal

JF - ACI Materials Journal

IS - 2

ER -

Automated piecewise linear regression for analyzing structural health monitoring data

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this