Filtern
Erscheinungsjahr
- 2022 (4) (entfernen)
Dokumenttyp
- Beitrag zu einem Tagungsband (4) (entfernen)
Sprache
- Englisch (4)
Schlagworte
- Distributed fiber sensing (2)
- Structural health monitoring (2)
- Acoustic sensing (1)
- Artificial neural networks (1)
- BOFDA (1)
- Distributed Brillouin sensing (1)
- Distributed acoustic sensing (1)
- I-OFDR (1)
- Leakage detection (1)
- Machine learning (1)
Organisationseinheit der BAM
In this paper, a cost-efficient distributed fiber optic measurement system based on Rayleigh scattering is presented. The distributed digital incoherent optical frequency domain reflectometry (I-OFDR) method is developed for detection of significantly large strain in the range from 3 % up to 10 % as required by end users. For this purpose, a vector network analyzer used in the I-OFDR is replaced by a compact and cost-effective digital data acquisition system. This digital emitting/receiving unit enables the recording of the complex transfer function carrying information about the local deformations along the entire sensing fiber.
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.