Filtern
Dokumenttyp
- Beitrag zu einem Tagungsband (3)
- Vortrag (3)
- Zeitschriftenartikel (2)
- Buchkapitel (1)
- Dissertation (1)
Sprache
- Englisch (10) (entfernen)
Schlagworte
- BOFDA (10) (entfernen)
Organisationseinheit der BAM
- 8.6 Faseroptische Sensorik (10) (entfernen)
Eingeladener Vortrag
- nein (3)
We present our achievements in the development of distributed fiber optic sensing systems based on Brillouin optical frequency-domain analysis for structural health monitoring. The focus of the applications is on the gapless monitoring of geotechnical structures, large area infrastructures and electrical grids. The work includes the latest use of machine learning algorithms to reduce measurement time by coexistent increasing the measurement accuracy.
We present our research on the development of a Brillouin optical frequency-domain analysis (BOFDA) using a perfluorinated graded-index polymer optical fiber (PFGI-POF) as a sensing fiber. The described works include investigations both on the selection of the setup components with respect to mode coupling effects and on the impact of the humidity cross-sensitivity. The suitability of the developed POF-based BOFDA is proved by a distributed measurement on an 86 m long PFGI-POF recorded with the spatial resolution of 6 m.
We present our research on the development of a Brillouin optical frequency-domain analysis (BOFDA) using a perfluorinated graded-index polymer optical fiber (PFGI-POF) as a sensing fiber. The described works include investigations both on the selection of the setup components with respect to mode coupling effects and on the impact of the humidity cross-sensitivity. The suitability of the developed POF-based BOFDA is proved by a distributed measurement on an 86 m long PFGI-POF recorded with the spatial resolution of 6 m.
The substantial progresses in fiber-optic communications in combination with the increasing economic and political interest in structural health monitoring have led to a commercial establishment of distributed Brillouin sensing. The sensor systems, mainly based on the time-domain techniques, have been successfully implemented in the areas such as pipeline leak detection, geohazard effects, and ground movement detection.
This chapter introduces a further advancement in the area of Brillouin sensing in the frequency domain. The so-called Brillouin optical frequency-domain analysis (BOFDA) offers crucial perspectives in terms of dynamic range and cost efficiency.
The main principle of the frequency-domain approach takes advantage of the reversibility between the time and frequency domain given by a Fourier transform in the analysis of linear systems. The hereby presented overview gives a summary of the benefits and challenges of frequency-domain measurements closely tied to the narrowband recording of the complex transfer function. This function relates the counterpropagating pump and probe laser light along the sensor fiber providing the pulse response of the measurement system by applying the inverse Fourier transform (IFT). The strain or temperature distribution can be then determined from the retrieved Brillouin frequency shift (BFS) profile along the fiber.
In this thesis, a distributed Brillouin sensor in perfluorinated polymer optical fibers utilizing BOFDA is presented. These commercially available polymer fibers offer beneficial characteristics for sensing applications such as higher break down strain up to 100 %, minimal bending radii below 2 mm, higher sensitivity to temperature and lower sensitivity to strain compared to their silica equivalent.
The chosen wavelength of operation at 1319 nm corresponds to lower fiber propagation loss (< 37 dB/km) compared to other approaches at 1550 nm (150 - 250 dB/km). A 86 m PFGI-POF was successfully measured by BOFDA with spatial resolution of 3.4 m.
The findings related to humidity influences can serve as a basis for future distributed humidity sensors not only limited to stimulated Brillouin backscattering.
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.
This paper presents reported machine learning approaches in the field of Brillouin distributed fiber optic sensors (DFOSs). The increasing popularity of Brillouin DFOSs stems from their capability to continuously monitor temperature and strain along kilometer-long optical fibers, rendering them attractive for industrial applications, such as the structural health monitoring of large civil infrastructures and pipelines. In recent years, machine learning has been integrated into the Brillouin DFOS signal processing, resulting in fast and enhanced temperature, strain, and humidity measurements without increasing the system’s cost. Machine learning has also contributed to enhanced spatial resolution in Brillouin optical time domain analysis (BOTDA) systems and shorter measurement times in Brillouin optical frequency domain analysis (BOFDA) systems. This paper provides an overview of the applied machine learning methodologies in Brillouin DFOSs, as well as future perspectives in this area.
We report, to our knowledge for the first time on simultaneous distributed temperature and strain sensing in a standard telecom optical fiber using a machine learning assisted Brillouin frequency domain analysis (BOFDA) system. The well-known temperature and strain cross-sensitivity problem is addressed by developing a BOFDA system with a high signal-to-noise ratio and applying machine learning. The spectrum consists of four highly resolved peaks, whose Brillouin frequency shifts are extracted and serve as features for the machine learning algorithms. The spectra result from a 450-m standard SMF-28 optical fiber, and particularly from a segment of 30 m. This fiber segment is coiled around a stretcher and placed in a climate chamber. The applied temperature and strain values range from 20 °C to 40 °C and from 0 µɛ to 1380 µɛ, respectively. The total measurement time to achieve a high SNR and resolve four peaks with a spatial resolution of 6 m is 16 min. To discriminate temperature and strain effects, simple frequentist and more sophisticated Bayesian-based algorithms are employed with the powerful Gaussian process regression (GPR) delivering the best performance in terms of temperature and strain errors, which are found to be 2 °C and 45 µɛ, respectively. These errors are calculated using leave-one-out cross-validation, so that an unbiased estimation of the sensor’s performance is provided.
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.