A DATA DRIVEN STRUCTURAL HEALTH MONITORING APPROACH INTEGRATING COGNITIVE CONCEPTS

Year 2018, Volume: 3 Issue: 1, 17 - 20, 01.12.2018

Burcu Gunes

Abstract

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.

Keywords

Data Driven Damage Detection, Structural Health Monitoring, Cognitive, Cognitive Concepts

References

• [1] S. W. Doebling, C. R. Farrar and M. B. Prime, “A summary review of vibration-based damage identification methods.” Shock Vib. Dig., Vol. 302, 1998, pp. 91–105.
• [2] S. W. Doebling, C. R. Farrar, M. B. Prime, and D. Shevits, “Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review.” Los Alamos National Laboratory Rep. No. LA-13070-MS, 1996, Los Alamos, N.M.
• [3] H. Sohn, C. R. Farrar, F. M. Hemez, D. D. Shunk, D. W. Stinemates, and B. R. Nadler, 2003. “Review of structural health monitoring literature: 1996-2001.” Report No. LA-13976-MS, Los Alamos National Laboratory, 2003, Los Alamos, N.M.
• [4] K. Worden and C. R. Farrar, Structural Health Monitoring: A Machine Learning Perspective, 2013.
• [5] M. Gordan, H. A. Razak, I. Zubaidah and K. Ghaedi, “Recent Developments in Damage Identification of Structures Using Data Mining.” Latin American Journal of Solids and Structures, Vol. 14, No. 13, 2017, pp. 2373-2401.
• [6] R. E. Kalman, “Mathematical description of linear dynamical systems.” SIAM J. Control Optim., Vol. 1, No. 2, 1963, pp. 152–192.
• [7] J. N. Juang and R. S. Pappa, “An eigensystem realization algorithm for modal parameter identification and model reduction.” J. Guid. Control Dyn., Vol. 8, No. 5, 1985, pp. 620–627.
• [8] J. N. Juang, Applied system identification, Prentice-Hall, Englewood Cliffs, 1994, N.J.
• [9] Y. K. Wen, "Method for random vibration of hysteretic systems." Journal of Engineering Mechanics. American Society of Civil Engineers, Vol. 102, No. 2, 1976, pp. 249–263.