Highly Dense FBG Temperature Sensor Assisted with Deep Learning Algorithms

In this paper, we demonstrate the application of deep neural networks (DNNs) for processing the reflectance spectrum from a fiberoptic temperature sensor composed of densely inscribed fiber Bragg gratings (FBG). Such sensors are commonly avoided in practice since close arrangement of short FBGs results in distortion of the spectrum caused by mutual interference between gratings. In our work the temperature sensor contained 50 FBGs with the length of 0.95 mm, edge-to-edge distance of 0.05 mm and arranged in the 1500–1600 nm spectral range. Instead of solving the direct peak detection problem for distorted signal, we applied DNNs to predict temperature distribution from entire reflectance spectrum registered by the sensor. We propose an experimental calibration setup where the dense FBG sensor is located close to an array of sparse FBG sensors. The goal of DNNs is to predict the positions of the reflectance peaks of the reference sparse FBG sensors from the reflectance spectrum of the dense FBG sensor. We show that a convolution neural network is able to predict the positions of FBG reflectance peaks of sparse sensors with mean absolute error of 7.8 pm that is slightly higher than the hardware reused interrogator equal to 5 pm. We believe that dense FBG sensors assisted with DNNs have a high potential to increase spatial resolution and also extend the length of a fiber optical sensors.

Download Full-text

Temperature Effect on Fiber Optical Sensors for Dry Cast Storage Health Monitoring

Volume 6A: Materials and Fabrication ◽

10.1115/pvp2015-45623 ◽

2015 ◽

Cited By ~ 1

Author(s):

Bin Lin ◽

Lingyu Yu ◽

Victor Giurgiutiu

Keyword(s):

Temperature Effect ◽

Health Monitoring ◽

Optical Sensors ◽

High Frequency ◽

Ultrasonic Waves ◽

Laser Source ◽

Reflective Spectrum ◽

Fiber Optical ◽

Fiber Optical Sensors ◽

Fbg Sensors

The increasing number, size, and complexity of nuclear facilities deployed worldwide are increasing the need to maintain readiness and develop innovative sensing materials to monitor important to safety structures (ITS). Assessing and supporting next generation nuclear materials management and safeguards for future U.S. fuel cycles with minimum human intervention is of paramount importance. Technologies for the diagnosis and prognosis of a nuclear system, such as dry cast storage system (DCSS), can improve verification of the health of the structure that can eventually reduce the likelihood of inadvertently failure of a component. In the past decades, an extensive sensor technology development has been used for structural health monitoring (SHM). Fiber optical sensors have emerged as one of the major SHM technologies developed particularly for temperature and strain measurements. However, the fiber optical sensors and sensing system has not been developed with adequate solutions and guideline for DCSS applications. This paper presents an experimental study of temperature effect on fiber Bragg grating (FBG) sensors. The reflective spectrum of FBG sensors on the structure was measured with a tunable laser source. The shift of FBG reflective spectrum reflected the thermal expansion on the structure. The shift of the spectrum due to the temperature effect was correlated to the temperature changes. In addition, the FBG sensing methodology including high frequency guided ultrasonic waves (GUW) under different temperatures were also performed to check the performance of high frequency, small strain sensing. The potential of FBG sensors for DCSS applications was explored. The paper ends with conclusions and suggestions for further work.

Download Full-text

Needle tip force estimation by deep learning from raw spectral OCT data

International Journal of Computer Assisted Radiology and Surgery ◽

10.1007/s11548-020-02224-w ◽

2020 ◽

Vol 15 (10) ◽

pp. 1699-1702

Author(s):

M. Gromniak ◽

N. Gessert ◽

T. Saathoff ◽

A. Schlaefer

Keyword(s):

Deep Learning ◽

Optical Sensors ◽

Mean Absolute Error ◽

Absolute Error ◽

Optical Signal ◽

Needle Placement ◽

Force Estimation ◽

Spectral Oct ◽

Fiber Optical ◽

Fiber Optical Sensors

Abstract Purpose Needle placement is a challenging problem for applications such as biopsy or brachytherapy. Tip force sensing can provide valuable feedback for needle navigation inside the tissue. For this purpose, fiber-optical sensors can be directly integrated into the needle tip. Optical coherence tomography (OCT) can be used to image tissue. Here, we study how to calibrate OCT to sense forces, e.g., during robotic needle placement. Methods We investigate whether using raw spectral OCT data without a typical image reconstruction can improve a deep learning-based calibration between optical signal and forces. For this purpose, we consider three different needles with a new, more robust design which are calibrated using convolutional neural networks (CNNs). We compare training the CNNs with the raw OCT signal and the reconstructed depth profiles. Results We find that using raw data as an input for the largest CNN model outperforms the use of reconstructed data with a mean absolute error of 5.81 mN compared to 8.04 mN. Conclusions We find that deep learning with raw spectral OCT data can improve learning for the task of force estimation. Our needle design and calibration approach constitute a very accurate fiber-optical sensor for measuring forces at the needle tip.

Download Full-text

Modelling Light Transmission in a Fiber-Optical Reflection System

Nonlinear Analysis Modelling and Control ◽

10.15388/na.2004.9.1.15170 ◽

2004 ◽

Vol 9 (1) ◽

pp. 55-63

Author(s):

V. Kleiza

Keyword(s):

Optical Sensors ◽

Light Transmission ◽

External Cavity ◽

Linear Displacement ◽

Fiber System ◽

Light Emitting ◽

Optical Media ◽

Reflected Light ◽

Fiber Optical ◽

Fiber Optical Sensors

Light transmission in the reflection fiber system, located in external optical media, has been investigated for application as sensors. The system was simulated by different models, including external cavity parameters such as the distance between light emitting and receiving fibers and mirror positioning distance. The sensitivity to a linear displacement of the sensors was studied as a function of the distance between the tips of the light emitting fiber and the center of the pair reflected light collecting fibers, by positioning a mirror. Physical fundamentals and operating principles of the advanced fiber optical sensors were revealed.

Download Full-text