Filtern
Erscheinungsjahr
- 2022 (4) (entfernen)
Dokumenttyp
- Beitrag zu einem Tagungsband (4) (entfernen)
Sprache
- Englisch (4)
Schlagworte
Organisationseinheit der BAM
- 8 Zerstörungsfreie Prüfung (4) (entfernen)
This contribution introduces an investigation of a large-scale prestressed concrete bridge model (“BLEIB” structure at the BAM-TTS open air test site) by means of on-site cooperative measurements. This bridge has an external post-tensioning system and has been instrumented with the ultrasonic transducers, temperature sensors and optical fibers for Distributed Acoustic Sensing (DAS). Our experiment was designed to test the suitability of the novel 6C sensors developed within the framework of the GIOTTO project – the IMU50. The IMU50 sensor enables vibration measurements in translation along three axes and rotation around three axes. The geophone sensors were considered for complementary measurements of vertical velocity response. In the experiment, several perturbations were achieved by controlling the external influence factors such as loading and prestressing changes. The aim of the integrated measurement strategy was to fully observe the results of the condition change and to verify the effectiveness of multiple sensors for bridge monitoring.
In the last few years, the use of machine learning has emerged in the field of distributed fiber optic sensors as a promising approach to enhance their performance and provide new capabilities. In this study, we use machine learning for simultaneous measurements of temperature and humidity in polyimide (PI)-coated optical fibers based on Brillouin Brillouin optical frequency domain analysis (BOFDA). Different non-linear machine learning algorithms are employed, namely polynomial regression, decision trees and artificial neural networks (ANNs), and their discrimination performance is benchmarked against that of the conventional linear regression. The performance is evaluated using leave-one-out cross-validation to ensure that the models are reliable and able to generalize well on new data. We show that nonlinear machine learning algorithms outperform the conventional linear regression and thus could pave the way towards simultaneous cost-effective temperature and humidity distributed sensing, which has the potential to find attractive new applications in the field of civil and geotechnical engineering, from structural health monitoring of dikes and bridges to subsea cables and long pipelines corrosion detection.