Filtern
Erscheinungsjahr
Dokumenttyp
- Beitrag zu einem Tagungsband (11)
- Beitrag zu einem Sammelband (4)
- Zeitschriftenartikel (3)
- Vortrag (3)
- Posterpräsentation (2)
Sprache
- Englisch (22)
- Mehrsprachig (1)
Schlagworte
- Fibre optic sensors (23) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (3)
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.
Grouted connections are intensively used in offshore rigs, platforms as well as jacket and monopile offshore wind turbine structures. Being located in remote offshore conditions, these connections can experience considerable adverse loading during their lifetimes. Degradation was reported inside similar connections, which were installed in the last three decades. Grouting in the offshore sites may often be proven difficult, which eventually leads to reduced load-bearing capacity of connections in the long run. Thus, repair and rehabilitation of such connections should be planned ahead to minimize operational delays and costs. In this study, scaled grouted connections were manufactured using a novel mould, whose integrity were monitored using digital image correlation (DIC). The connections were loaded under static load to visualize the main failure pattern using distributed fibre optic sensors and acoustic emission (AE) analysis. Grouted connections were then repaired using a cementitious injectable grout. The effectiveness of the grout injection was monitored using dye penetration technique. Finally, specimens are reloaded to identify the potential of such repair for grouted connections.
We present a technique for distributed temperature gradient sensing in real-time along an optical fiber utilizing simple amplitude-based direct-detection coherent optical time domain reflectometry (C-OTDR) and a special sensing fiber. Our technique enables us to determine phase changes or low-frequency variations of the C-OTDR signal stemming from temperature variations. The distinct feature of the used sensing fiber is its structuring with equidistant strongly scattering dots. Consecutive pairs of these scatterers form the dominant local interferometers, effectively overwriting the otherwise highly nonlinear transfer function of common optical fiber. This enables a quasi-phase-resolved evaluation of perturbation responses originating from temperature changes at sensor positions between the scatterers. Using our method, we show the measurement of a nonlinear temperature transient from a heating process with a maximum temperature gradient of 0.8 °C over 20 s and a total temperature increase of 28.4 °C. This method requires almost no post-processing and can be used for simultaneous distributed vibration sensing (DVS) and quantification of local temperature gradients in a single fiber, e.g., for the use in condition monitoring of infrastructure or industrial installations.
We present a technique for distributed temperature gradient sensing in real-time along an optical fiber utilizing simple amplitude-based direct-detection coherent optical time domain reflectometry (C-OTDR) and a special sensing fiber. Our technique enables us to determine phase changes or low-frequency variations of the C-OTDR signal stemming from temperature variations. The distinct feature of the used sensing fiber is its structuring with equidistant strongly scattering dots. Consecutive pairs of these scatterers form the dominant local interferometers, effectively overwriting the otherwise highly nonlinear transfer function of common optical fiber. This enables a quasi-phase-resolved evaluation of perturbation responses originating from temperature changes at sensor positions between the scatterers. Using our method, we show the measurement of a nonlinear temperature transient from a heating process with a maximum temperature gradient of 0.8 °C over 20 s and a total temperature increase of 28.4 °C. This method requires almost no post-processing and can be used for simultaneous distributed vibration sensing (DVS) and quantification of local temperature gradients in a single fiber, e.g., for the use in condition monitoring of infrastructure or industrial installations.
In the last century external gas pressure cable systems with 64/110 kV operating voltage have proven to form a reliable way for the transportation of electrical
energy in larger cities all over the world. The beginning of their development reaches back to the 1930s. The dielectric used in these thermally stable cables consists of a mass impregnated cable paper insulation that requires the absence of partial discharges as a prerequisite for continuous operation. In this contribution two test set-ups for advanced lab testing of external gas pressure cable specimens were established. Two specimens of different aging state were subjected to various electrical voltage levels and frequencies as well as different temperatures. Simultaneously dissipation factor measurement and partial discharge detection were applied. Finally the specimens’ relationships between dissipation factor, partial discharge level, temperature, impregnation mass to paper ratio, water content and external gas pressure were discussed.
Distributed Fibre Optic Acoustic and Vibration Sensors for Industrial Monitoring Applications
(2017)
We investigate the usability of distributed fibre optic acoustic sensing (DAS) for innovative and advanced monitoring applications in industrial and civil infrastructure installations. In this paper, we report on our ongoing application-oriented research activities regarding the utilization of DAS based on coherent optical time-domain reflectometry (C-OTDR) for condition monitoring of a variety of infrastructures. Specifically, our research presented here aims at acoustic condition monitoring of and fault detection in pipelines and industrial piping systems, at acoustic condition monitoring of rollers in industrial conveyor belt installations, and at acoustic condition monitoring of and threat detection in extensive submarine power cables, respectively. Furthermore, we show a method to mitigate the effect of sensitivity fading of C-OTDR based DAS due to unstable environmental conditions via the modification of the sensor fibre. This can help to provide a continuous adequate sensor functionality for a number of different industrial monitoring applications.
Condition monitoring of industrial infrastructures using distributed fibre optic acoustic sensors
(2017)
Distributed fibre optic acoustic sensing (DAS) can serve as an excellent tool for real-time condition Monitoring of a variety of industrial and civil infrastructures. In this paper, we portray a subset of our current Research activities investigating the usability of DAS based on coherent optical time-domain reflectometry (C-OTDR) for innovative and demanding condition Monitoring applications. Specifically, our application-oriented Research presented here aims at acoustic and vibrational condition monitoring of pipelines and piping systems, of rollers in industrial heavy-duty conveyor belt systems and of extensive submarine power cable installations, respectively.
Online condition monitoring of submarine power cables helps to avert failures and damages produced by mechanical impacts. We report, to our knowledge for the first time, on investigations regarding the feasibility of distributed fiber optic acoustic sensors based on C-OTDR, with the sensor fibres being embedded in the cable, to detect vibrations due to mechanical disturbances along the cable. We present first results of sensing experiments where acoustic signals are transmitted through water to simulate the corresponding submarine conditions. Furthermore, we show results evaluating the usefulness of fibre commonly embedded in existing power cable designs for our sensing purposes.
Distributed fibre optic acoustic sensing for condition and structural health monitoring applications
(2017)
We present current and previous research projects and activities at BAM related to distributed fibre optic acoustic sensing (DAS) for condition monitoring purposes. Furthermore, we show the experimental capabilities of our DAS equipment and portray other BAM competences in fibre optic sensing that could be combined with DAS.