Structural health monitoring via human-machine Interface
Bildiriler > Tam Metin Bildiri · 2014
Yazarlar: Mahmut PEKEDİS, DAVID MASCERANAS, GÜRSOY TURAN, HASAN CEYLAN, Emre ERCAN, CHARLES R FARRAR, Hasan YILDIZ
Sixth World Conference on Structural Control and Monitoring, İspanya, Barcelona, Uluslararası, Sözlü Sunum, Tam Metin Bildiri, 2014-2014, ss 167-171
Özet
<p>The current trend in structural health monitoring is to obtain vibrational data from the structure, process them via various numerical tools, and finally print out visual graphs for investigators. This strategy has been and is increasingly improving. The current study is an ongoing research that aims to monitor the health of structures within a different philosophy. Instead of interpreting the results visually, the investigator is physically connected to the machine (machine refers to computer). The signals are sent to the investigator with the developed graphical user interface by means of experimental haptic device including distributed vibration actuators. To examine the procedure a test is set up with a tower structure. The person's neurons are trained with the response of the well and ill-conditioned structure, where the structure's ill-conditioning is attained by means of changes in bolt load loss. After the training stage, the investigator is subjected to perceive the changes in the structural response. On the other hand, the health of the structure will be determined by using the investigator's sensing capability and neural network performance. As a result, the investigators were able to determine the damage with an averaged accuracy of 68.98 ± 30.91% and response time of 8.51± 3.22 seconds. </p>