The increasing amount of data being generated in different areas of science and technology require novel and efficient techniques of processing, going beyond traditional concepts. In this paper, we numerically study the information processing capabilities of semiconductor lasers subject to delayed optical feedback. Based on the recent concept of reservoir computing, we show that certain tasks, which are inherently hard for traditional computers, can be efficiently tackled by such systems. Major advantages of this approach comprise the possibility of simple and low-cost hardware implementation of the reservoir and ultrafast processing speed. Experimental results corroborate the numerical predictions.
Along temperature, humidity is one of the principal environmental factors that plays an important role in various application areas. Presented work investigates possibility of distributed fiberoptic humidity monitoring based on humidity-induced strain measurement in polyimide (PI)-coated optical fibers. Characterization of relative humidity (RH) and temperature response of four different commercial PI- and one acrylate-coated fiber was performed using optical backscattering reflectometry (OBR). The study addresses issues of temperature-humidity cross-sensitivity, fiber response stability, repeatability, and the influence of annealing. Acrylate-coated fiber exhibited rather unfavorable nonlinear RH response with strong temperature dependence, which makes it unsuitable for humidity sensing applications. On the other hand, humidity response of PI-coated fibers showed good linearity with fiber sensitivity slightly decreasing at rising temperatures. In the tested range, temperature sensitivity of the fibers remained humidity independent. Thermal annealing was shown to considerably improve and stabilize fiber RH response. Based on performed analysis, a 20 m sensor using the optimal PI-coated fibers was proposed and constructed. The sensor uses dual sensing fiber configuration for mutual decoupling and simultaneous measurement of temperature and RH variations. Using OBR, distributed dual temperature-RH monitoring with cm spatial resolution was demonstrated for the first time.
We present results demonstrating several beneficial effects on distributed fiber optic vibration sensing (DVS) functionality and performance resulting from utilizing standard single mode optical fiber (SMF) with femtosecond laser-inscribed equally-spaced simple scattering dots. This modification is particularly useful when using traditional single-wavelength amplitude-based coherent optical time domain reflectometry (C-OTDR) as sensing method. Local sensitivity is increased in quasi-distributed interferometric sensing zones which are formed by the fiber segments between subsequent pairs of the scattering dots. The otherwise nonlinear transfer function is overwritten with that of an ordinary two-beam interferometer. This linearizes the phase response to monotonous temperature variations. Furthermore, sensitivity fading is mitigated and the demodulation of low-frequency signals is enabled. The modification also allows for the quantitative determination of local temperature gradients directly from the C-OTDR intensity traces. The dots’ reflectivities and thus the induced attenuation can be tuned via the inscription process parameters. Our approach is a simple, robust and cost-effective way to gain these sensing improvements without the need for more sophisticated interrogator technology or more complex fiber structuring, e.g., based on ultra-weak FBG arrays. Our claims are substantiated by experimental evidence.
We report, to our knowledge for the first time, on distributed relative humidity sensing in silica polyimide-coated optical fibers using Brillouin optical frequency domain analysis (BOFDA). Linear regression, which is a simple and well-interpretable algorithm in machine learning and statistics, is utilized. The algorithm is trained using as features the Brillouin frequency shifts and linewidths of the fiber’s multipeak Brillouin spectrum. To assess and improve the effectiveness of the regression algorithm, we make use of machine learning concepts to estimate the model’s uncertainties and select the features that contribute most to the model’s performance. In addition to relative humidity, the model is also able to simultaneously provide distributed temperature information addressing the well-known cross-sensitivity effects.
In this paper, we present a collection of machine learning assisted distributed fiber optic sensors (DFOS) for applications in the field of infrastructure monitoring. We employ advanced signal processing based on artificial neural networks (ANNs) to enhance the performance of the dynamic DFOS for strain and vibration sensing. Specifically, ANNs in comparison to conventional and computationally expensive correlation and linearization algorithms, deliver lower strain errors and speed up the signal processing allowing real time strain monitoring. Furthermore, convolutional neural networks (CNNs) are used to denoise the dynamic DFOS signal and enable useable sensing lengths of up to 100 km. Applications of the machine learning assisted dynamic DFOS in road traffic and railway infrastructure monitoring are demonstrated. In the field of static DFOS, machine learning is applied to the well-known Brillouin optical frequency domain analysis (BOFDA) system. Specifically, CNN are shown to be very tolerant against noisy spectra and contribute towards significantly shorter measurement times. Furthermore, different machine learning algorithms (linear and polynomial regression, decision trees, ANNs) are applied to solve the well-known problem of cross-sensitivity in cases when temperature and humidity are measured simultaneously. The presented machine learning assisted DFOS can potentially contribute towards enhanced, cost effective and reliable monitoring of infrastructures.