Time-Efficient Convolutional Neural Network-Assisted Brillouin Optical Frequency Domain Analysis

Karapanagiotis, Christos; Wosniok, Aleksander; Hicke, Konstantin; Krebber, Katerina

doi:10.3390/s21082724

Cited by 12 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has the advantage that no ultra-fast electronics are required, which, on the one hand, has a positive impact on the system's cost but, on the other hand, increases the measurement time significantly. For this reason, a machine learning method for time-efficient BOFDA measurements was proposed [69,167].…”

Section: Machine Learning Applied In Brillouin Frequency Domain Sensorsmentioning

confidence: 99%

“…Specifically, machine learning algorithms have been employed to enhance the measurement accuracy and shorten the signal processing time without increasing the system's cost [40,66,67]. Machine learning has also contributed to enhanced spatial resolution in BOTDA systems [68] and shorter measurement times in BOFDA systems [69]. Furthermore, the problem of temperature and strain cross-sensitivity has been addressed using machine learning in both BOTDA and BOFDA systems [70][71][72][73].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approaches in Brillouin Distributed Fiber Optic Sensors

Karapanagiotis

Krebber

2023

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Machine Learning Applied In Brillouin Frequency Domain Sensorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning Approaches in Brillouin Distributed Fiber Optic Sensors

Karapanagiotis

Krebber

2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, the strain and temperature can be indirectly measured through BOFDA technology. Compared with other distributed fiber optic sensing technologies, the advantages of BOFDA are its high precision and high resolution [24]. The testing accuracy of BOFDA can reach 2 µε or 0.1 • C, its spatial resolution can reach 0.2 m, its dynamic range can exceed 20 dB, and a distributed fine decomposition of strain and temperature can be realised.…”

Section: Bofda Pipeline Leak Testing Principlementioning

confidence: 99%

Multi-physical field joint monitoring of buried gas pipeline leakage based on BOFDA

Zhang

Liu²,

Yao³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Determining the leakage location in an underground gas pipeline is a serious technical problem. Distributed fiber optic testing technology based on Brillouin optical frequency domain analysis (BOFDA) can be used for monitoring the change in the strain and temperature of the surrounding media caused by the gas leakage. In this study, a point source leakage model was built. The distributed fiber optic strain and actively heated fiber optic were installed around the pipeline to monitor the gas pipeline leakage. Variations in the strain and temperature characteristics of the pipeline under different gas pressure conditions were found to be in the range of -392–402 με and 3.5 ℃ during the 1.0 MPa gas leakage, respectively. When the soil model was loaded with a gas leakage pressure of 0.3–1.0 MPa, a significant variation in strain and temperature was noticed. The copper mesh actively heated fiber optic can effectively identify the location of the leak. Meanwhile, the heating rate of the actively heated fiber optic cables in different media environments were obtained and ranked from fast to slow: air, followed by general soil, followed by leakage soil. This led to the generation of new technology to detect the leakage location of buried gas pipelines through actively heated optical cables.

show abstract

“…Practice has shown that correlation methods are quite effective in studying signals with low SNR. Another noteworthy method is machine learning [ 34 , 35 , 36 , 37 ]. These are artificial intelligence methods used to obtain the correct characteristic feature which is not a direct solution to the problem but is a learning input through applied solutions to many other similar problems.…”

Section: Introductionmentioning

confidence: 99%

Improving Prediction Accuracy and Extraction Precision of Frequency Shift from Low-SNR Brillouin Gain Spectra in Distributed Structural Health Monitoring

Nordin

Abdullah

Zan

et al. 2022

Sensors

View full text Add to dashboard Cite

In this paper, we studied the possibility of increasing the Brillouin frequency shift (BFS) detection accuracy in distributed fibre-optic sensors by the separate and joint use of different algorithms for finding the spectral maximum: Lorentzian curve fitting (LCF, including the Levenberg–Marquardt (LM) method), the backward correlation technique (BWC) and a machine learning algorithm, the generalized linear model (GLM). The study was carried out on real spectra subjected to the subsequent addition of extreme digital noise. The precision and accuracy of the LM and BWC methods were studied by varying the signal-to-noise ratios (SNRs) and by incorporating the GLM method into the processing steps. It was found that the use of methods in sequence gives a gain in the accuracy of determining the sensor temperature from tenths to several degrees Celsius (or MHz in BFS scale), which is manifested for signal-to-noise ratios within 0 to 20 dB. We have found out that the double processing (BWC + GLM) is more effective for positive SNR values (in dB): it gives a gain in BFS measurement precision near 0.4 °C (428 kHz or 9.3 με); for BWC + GLM, the difference of precisions between single and double processing for SNRs below 2.6 dB is about 1.5 °C (1.6 MHz or 35 με). In this case, double processing is more effective for all SNRs. The described technique’s potential application in structural health monitoring (SHM) of concrete objects and different areas in metrology and sensing were also discussed.

show abstract

Time-Efficient Convolutional Neural Network-Assisted Brillouin Optical Frequency Domain Analysis

Cited by 12 publications

References 29 publications

Machine Learning Approaches in Brillouin Distributed Fiber Optic Sensors

Machine Learning Approaches in Brillouin Distributed Fiber Optic Sensors

Multi-physical field joint monitoring of buried gas pipeline leakage based on BOFDA

Improving Prediction Accuracy and Extraction Precision of Frequency Shift from Low-SNR Brillouin Gain Spectra in Distributed Structural Health Monitoring

Contact Info

Product

Resources

About