Translator Disclaimer
Presentation + Paper
12 April 2017 A new method for detection of fatigue cracking in steel bridge girders using self-powered wireless sensors
Author Affiliations +
Development of fatigue cracking is affecting the structural performance of many of welded steel bridges in the United States. This paper presents a support vector machine (SVM) method for the detection of distortion-induced fatigue cracking in steel bridge girders based on the data provided by self-powered wireless sensors (SWS). The sensors have a series of memory gates that can cumulatively record the duration of the applied strain at a specific threshold level. Each sensor output has been characterized by a Gaussian cumulative density function. For the analysis, extensive finite element simulations were carried out to obtain the structural response of an existing highway steel bridge girder (I-96/M- 52) in Webberville, Michigan. The damage states were defined based on the length of the crack. Initial damage indicator features were extracted from the sensor output distribution at different data acquisition nodes. Subsequently, the SVM classifier was developed to identify multiple damage states. A data fusion model was proposed to increase the classification performance. The results indicate that the models have acceptable detection performance, specific ally for cracks larger than 10 mm. The best classification performance was obtained using the information from a group of sensors located near the damage zone.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hassene Hasni, Amir H. Alavi, Pengcheng Jiao, and Nizar Lajnef "A new method for detection of fatigue cracking in steel bridge girders using self-powered wireless sensors", Proc. SPIE 10168, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2017, 101680Q (12 April 2017);

Back to Top