Recent development in artificial neural network based distributed fiber optic sensors

Lalam, Nageswara; Ng, Wai Pang

doi:10.1109/csndsp49049.2020.9249588

Cited by 7 publications

(4 citation statements)

References 36 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been many approaches for simultaneous sensing: using two fibers or double core fibers [3], [4], hybrid systems using Rayleigh and Brillouin scatterings [5], [6]or combination of Brillouin and Raman scatterings [7], or using few mode fibers [8], however, each has their own type of limitations either suffer with large measurement errors, or interrogation technique is complex and expensive. Specially designed fibers with multiple (or two) acoustic modes and having single mode operation can be used for multi (or two)-parameter sensing.…”

Section: Introductionmentioning

confidence: 99%

Brillouin scattering-based simultaneous and discriminative strain and temperature sensing with double Brillouin peak fibers

Bhatta,

Lalam,

Buric

et al. 2024

Optical Fibers and Sensors for Medical Diagnostics, Treatment, and Environmental Applications XXIV

View full text Add to dashboard Cite

This paper introduces a double-parameter distributed fiber sensing system that utilizes stimulated Brillouin scattering in a specialized fiber, distinguished by two gain peaks in its scattering spectrum with nearly identical intensity levels. Employing this specialty fiber in a Brillouin optical time domain analysis system, we conduct a comprehensive analysis highlighting their efficacy in the simultaneous measurement of strain and temperature. These fibers are characterized by a significant temperature coefficient disparity (~0.2 MHz/℃) between the two peaks, and similar large peak gain amplitudes resulting minimal Brillouin frequency shift uncertainties, thereby substantially reducing strain and temperature measurement errors. We evaluated strain and temperature coefficients of 47 kHz/με, 1.15 MHz/°C for the first peak, and 51 kHz/με, 1.37 MHz/°C for the second one, which were then applied in the simultaneous measurement of strain and temperature under various conditions, including an applied strain of 1220 με at temperatures of 62 ℃ and 72℃. The results indicate a significant enhancement in measurement accuracy, reducing errors to ~17 με and ~ 0.9 °C in terms of strain and temperature respectively. Additionally, strain and temperature errors due to the impact of the variance of Brillouin frequency shift uncertainty between two peaks are explored. This study underscores the potential of the proposed double-Brillouin peak fiber in critical applications such as long-distance natural gas pipeline monitoring, where precise and distinct measurements of strain and temperature are paramount.

show abstract

Section: Introductionmentioning

confidence: 99%

Brillouin scattering-based simultaneous and discriminative strain and temperature sensing with double Brillouin peak fibers

Bhatta,

Lalam,

Buric

et al. 2024

Optical Fibers and Sensors for Medical Diagnostics, Treatment, and Environmental Applications XXIV

View full text Add to dashboard Cite

show abstract

“…While these techniques have been effective to some extent, they are limited in their ability to provide realtime, and continuous monitoring. In recent years, distributed optical fiber sensor systems have emerged as promising tools for the continuous monitoring of pipelines, offering advantages in terms of sensitivity, coverage, and real-time data acquisition [3,4]. Distributed optical fiber sensing is based on the principle of measuring changes in the optical properties of the fiber caused by external stimuli along its length.…”

Section: Introductionmentioning

confidence: 99%

Distributed optical fiber sensor systems: application to natural gas pipeline monitoring

Lalam,

Bhatta,

Buric

et al. 2024

Optical Waveguide and Laser Sensors III

View full text Add to dashboard Cite

Distributed fiber optic sensing is a cutting-edge technology that has found extensive applications in the monitoring of pipelines. Among them, distributed acoustic sensors, phase-sensitive optical time domain reflectometry (Φ-OTDR) is a versatile technology that can continuously detect external perturbations and provide spatial and real-time information along the kilometer lengths of sensing fiber. Considering the low backscattering level of standard single-mode fiber as fiber under test, a Rayleigh-enhanced optical fiber embedded within the tight-buffered cable is demonstrated in field testing. We analyzed the increased backscattering fiber cable's vibration performance to the conventional single-mode telecom fiber using a custom-built Φ-OTDR interrogator system. Thereafter, using a 4-inch steel pipeline with a flow rate of 5, 10, 15, and 20 ft/s and a fixed pressure level of 1000 psi, we field-tested the sensor system for monitoring natural gas pipeline acoustic vibrations. We also field-tested the Brillouin optical time domain analysis (BOTDA) system for pipeline hoop strain monitoring under various pressure conditions. The pilot-scale testing results presented in this study suggested that pipeline operators can accurately perform flow monitoring, leak detection, and pressure monitoring for pipeline integrity monitoring.

show abstract

“…These methods require a large number of data points, expensive computation, and are sensitive to measurement noise. Recently, the use of artificial neural networks (ANN) has been adopted for the analysis of OTDR data, enabling real-time applications and enhancing robustness to noise [4,5].…”

Section: Introductionmentioning

confidence: 99%

Spatially Resolved Strain Measurement at Meter Scale Using a Carbon Fiber Based Strain Sensor and Artificial Neural Networks

Wieja,

Steinbild,

Ehrig

et al. 2023

10th ECCOMAS Thematic Conference on Smart Structures and Materials

View full text Add to dashboard Cite

Life cycle optimization, maintenance planning and adaptive control systems in fiberreinforced structures such as aircraft wings require the monitoring of loads and stresses during operation. State of the art systems using strain gauges can measure strains at limited numbers of discrete points, while systems based on fiber optic time domain reflectometry require complex and cost intensive evaluation units. A novel sensor based on electrical time domain reflectometry (ETDR) allows to acquire information about the spatial distribution of strain along a fractured carbon fiber (CF) embedded in a composite structure. This sensor concept has been investigated in previous studies with specimens up to 60 mm in length. Based on this work, a demonstrator with an improved sensor layout and two embedded sensors of 1 m length is developed. A shallow feed-forward network and a convolutional neural network are compared regarding their ability to infer strain profiles from measured ETDR reflectograms. The simultaneous evaluation of two sensors with a convolutional neural network allowed the inference of strain distributions with a good generalization ability.

show abstract

Recent development in artificial neural network based distributed fiber optic sensors

Cited by 7 publications

References 36 publications

Brillouin scattering-based simultaneous and discriminative strain and temperature sensing with double Brillouin peak fibers

Brillouin scattering-based simultaneous and discriminative strain and temperature sensing with double Brillouin peak fibers

Distributed optical fiber sensor systems: application to natural gas pipeline monitoring

Spatially Resolved Strain Measurement at Meter Scale Using a Carbon Fiber Based Strain Sensor and Artificial Neural Networks

Contact Info

Product

Resources

About