Filtern
Dokumenttyp
- Zeitschriftenartikel (6)
- Beitrag zu einem Tagungsband (4)
- Vortrag (3)
- Posterpräsentation (1)
Sprache
- Englisch (14)
Schlagworte
- Fiber optics sensors (14) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (3)
Brillouin Optical Frequency Domain Analysis (BOFDA) is a powerful and well-established method for static distributed sensing of temperature and strain. Recently, we demonstrated a BOFDA system based on convolutional neural network which shortens the measurement time considerably. In this paper, we apply leave-one-out cross validation to evaluate the generalization performance and provide an unbiased and reliable machine learning model for a time-efficient BOFDA system.
Brillouin Optical Frequency Domain Analysis (BOFDA) is a powerful and well-established method for static distributed sensing of temperature and strain. Recently, we demonstrated a BOFDA system based on convolutional neural network which shortens the measurement time considerably. In this paper, we apply leave-one-out cross validation to evaluate the generalization performance and provide an unbiased and reliable machine learning model for a time-efficient BOFDA system.
Distributed humidity fiber-optic sensor based on BOFDA using a simple machine learning approach
(2022)
We report, to our knowledge for the first time, on distributed relative humidity sensing in silica polyimide-coated optical fibers using Brillouin optical frequency domain analysis (BOFDA). Linear regression, which is a simple and well-interpretable algorithm in machine learning and statistics, is utilized. The algorithm is trained using as features the Brillouin frequency shifts and linewidths of the fiber’s multipeak Brillouin spectrum. To assess and improve the effectiveness of the regression algorithm, we make use of machine learning concepts to estimate the model’s uncertainties and select the features that contribute most to the model’s performance. In addition to relative humidity, the model is also able to simultaneously provide distributed temperature information addressing the well-known cross-sensitivity effects.
Short presentation of the PhD project in machine learning based Brillouin distributed sensing. Machine learning can be used to enhance the performance of BOFDA and reduce considerably the measurement time. Apart from this, ML can also be used to extract more information from the Brillouin gain spectrum in order to render the temperature and strain discrimination possible
We present, to our knowledge for the first time, a 100-km Brillouin Optical Frequency-Domain Analysis (BOFDA) employing a 200-km fiber loop. Compared to our previous publication, enhanced sensor length, sensor accuracy and spatial resolution are presented. The performance improvements are achieved by applying distributed Raman amplification (DRA) and a digital high-pass filter. We report on temperature measurements over sensing distances of 75 km and 100 km both with a 12.5-m spatial resolution. Temperature changes of 5 °C have been measured along 75 km sensing fiber. A temperature change of 30 °C has been detected at 99.5 km.
We demonstrate (and are the first to do so) 63 km Brillouin Optical Frequency-Domain Analysis (BOFDA) for temperature and strain monitoring using a 100 km fiber loop. The use of BOFDA for long-range applications can be considered a novel approach, as previous investigations focused on the utilization of Brillouin Optical Time-Domain Reflectometry and Analysis (BOTDR and BOTDA, respectively). At 51.7 km, a 100 m hotspot (37 °C) was detected without using distributed Raman amplification or image processing.
Distributed vibration sensing in optical fibers opened entirely new opportunities and penetrated various sectors from security to seismic monitoring. Here, we demonstrate a most simple and robust approach for dynamic strain measurement using wavelength-scanning coherent optical time domain reflectometry (C-OTDR). Our method is based on laser current modulation and Rayleigh backscatter shift correlation. As opposed to common single-wavelength phase demodulation techniques, also the algebraic sign of the strain change is retrieved. This is crucial for the intended applications in structural health monitoring and modal analysis. A linear strain response down to 47.5 pε and strain noise of 100 pε/√Hz is demonstrated for repetition rates in the kHz range. A field application of a vibrating bridge is presented. Our approach provides a cost-effective high-resolution method for structural vibration analysis and geophysical applications.
We propose the use of alternating pulse wavelengths in a direct-detection coherent optical time domain reflectometry (C-OTDR) setup not only to measure strain and temperature changes but also to determine the correct algebraic sign of the change. The sign information is essential for the intended use in distributed mode shape analysis of civil engineering structures. Correlating relative backscatter signal shifts in the temporal/signal domain allows for measuring with correct magnitude and sign. This novel approach is simulated, experimentally implemented and demonstrated for temperature change measurement at a spatial resolution of 1 m.