A DATA DRIVEN STRUCTURAL HEALTH MONITORING APPROACH INTEGRATING COGNITIVE CONCEPTS

Burcu GUNES

Makale detayları

A DATA DRIVEN STRUCTURAL HEALTH MONITORING APPROACH INTEGRATING COGNITIVE CONCEPTS

Yazarlar:

Burcu GUNES

Yayıncı:

İstanbul Technical University

Dergi:

The Journal of Cognitive Systems 2018 Vol.3 Issue 1, pp.17-20

Belge Tipi:

Makale

Yayın Tarihi:

11/2018

Belge Dili:

İngilizce

Document ID (Org No.):

2000664904

Sıklık:

İki Yıllık

pISSN:

2548-0650

Özet:

 


The most
crucial step of the structural health monitoring (SHM) methodology is the
detection stage where a decision on the existence of damage has to be made.
Without a very detailed and refined finite element model of the system, data
driven approaches have the potential for rapid assessment of the structure at
the damage detection stage of the more encompassing SHM problem. Change in the
dynamic properties of structures offers a real-time structural health
monitoring technique which detects damage at low cost and with little or no
human intervention. Whether the changes in the identified parameters are due to
the onset of damage or due to factors introducing non-linearity to the system,
such as closing and opening of micro-cracks in concrete structures,
environmental conditions or noise present in the data is a challenge that needs
to be faced. This study presents a pattern recognition type of approach that
will help with the distinction of true and false positives. The first step of
the model-free methodology includes the linearity check of the system. The
recorded vibration measurements recorded from the structure is divided into
time segments and with each data set modal parameters are identified. The
variability of the identification results are used as a measure for the
existence of confounding factors that may mask accumulation of damage
revelation. An ‘expert’ knowledge gained through this allows better treatment
of the uncertainties in the problem and mimic the human decision process. The
results of the numerical simulations are promising for the effectiveness of the
procedure to minimize ‘false negative’ identifications.

.

Makale detayları

A DATA DRIVEN STRUCTURAL HEALTH MONITORING APPROACH INTEGRATING COGNITIVE CONCEPTS

Yazarlar: Burcu GUNES

Yayıncı: İstanbul Technical University

Dergi: The Journal of Cognitive Systems 2018 Vol.3 Issue 1, pp.17-20

Belge Tipi: Makale

Yayın Tarihi: 11/2018

Belge Dili: İngilizce

Document ID (Org No.): 2000664904

Sıklık: İki Yıllık

pISSN: 2548-0650

Sayı

Yazarlar:

Burcu GUNES

Yayıncı:

İstanbul Technical University

Dergi:

The Journal of Cognitive Systems 2018 Vol.3 Issue 1, pp.17-20

Belge Tipi:

Makale

Yayın Tarihi:

11/2018

Belge Dili:

İngilizce

Document ID (Org No.):

2000664904

Sıklık:

İki Yıllık

pISSN:

2548-0650