Filtern
Dokumenttyp
- Vortrag (7)
- Zeitschriftenartikel (6)
- Forschungsdatensatz (3)
- Beitrag zu einem Tagungsband (2)
Sprache
- Englisch (16)
- Deutsch (1)
- Mehrsprachig (1)
Schlagworte
- Artificial neural networks (18) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (7)
Wavelength-scanning distributed acoustic sensing for structural monitoring and seismic applications
(2019)
We introduce wavelength-scanning coherent optical time domain reflectometry (WS-COTDR) for dynamic vibration sensing along optical fibers. The method is based on spectral shift computation from Rayleigh backscatter spectra. Artificial neural networks (ANNs) are used for fast and high-resolution strain computation from raw measurement data. The applicability of the method is demonstrated for vibration monitoring of a reinforced concrete bridge. We demonstrate another application example for quasi-static and dynamic measurement of ground deformation and surface wave propagation along a dark fiber in a telecommunication cable.
Wavelength-scanning distributed acoustic sensing for structural monitoring and seismic applications
(2019)
We introduce wavelength-scanning coherent optical time domain reflectometry (WS-COTDR) for dynamic vibration sensing along optical fibers. The method is based on spectral shift computation from Rayleigh backscatter spectra. Artificial neural networks (ANNs) are used for fast and high-resolution strain computation from raw measurement data. The applicability of the method is demonstrated for vibration monitoring of a reinforced concrete bridge. We demonstrate another application example for quasi-static and dynamic measurement of ground deformation and surface wave propagation along a dark fiber in a telecommunication cable.
The use of artificial neural networks (ANNs) is demonstrated for efficient real-time data processing in optical fiber sensing applications. Using ANN-based algorithms, two orders of magnitude improved computation time and improved measurement resolution is achieved for distributed strain sensing using the wavelength-scanning coherent optical time domain reflectometry technique.
AI-reflectivity is a code based on artificial neural networks trained with simulated reflectivity data that quickly predicts film parameters from experimental X-ray reflectivity curves. This project has a common root with (ML-reflectivity)[https://github.com/schreiber-lab/ML-reflectivity] and evolved in parallel. Both are linked to the following publication:
Fast Fitting of Reflectivity Data of Growing Thin Films Using Neural Networks A. Greco, V. Starostin, C. Karapanagiotis, A. Hinderhofer, A. Gerlach, L. Pithan, S. Liehr, F. Schreiber, S. Kowarik (2019). J. Appl. Cryst.
For an online live demonstration using a pre-trained network have a look at github.
Distributed acoustic sensing (DAS) over tens of kilometers of fiber optic cables is well-suited for monitoring extended railway infrastructures. As DAS produces large, noisy datasets, it is important to optimize algorithms for precise tracking of train position, speed, and the number of train cars, The purpose of this study is to compare different data analysis strategies and the resulting parameter uncertainties. We present data of an ICE 4 train of the Deutsche Bahn AG, which was recorded with a commercial DAS system. We localize the train signal in the data either along the temporal or spatial direction, and a similar velocity standard deviation of less than 5 km/h for a train moving at 160 km/h is found for both analysis methods, The data can be further enhanced by peak finding as well as faster and more flexible neural network algorithms. Then, individual noise peaks due to bogie clusters become visible and individual train cars can be counted. From the time between bogie signals, the velocity can also be determined with a lower standard deviation of 0.8 km/h, The analysis methods presented here will help to establish routines for near real-time Train tracking and train integrity analysis.
Industry 4.0 is all about interconnectivity, sensor-enhanced process control, and data-driven systems. Process analytical technology (PAT) such as online nuclear magnetic resonance (NMR) spectroscopy is gaining in importance, as it increasingly contributes to automation and digitalization in production. In many cases up to now, however, a classical evaluation of process data and their transformation into knowledge is not possible or not economical due to the insufficiently large datasets available. When developing an automated method applicable in process control, sometimes only the basic data of a limited number of batch tests from typical product and process development campaigns are available. However, these datasets are not large enough for training machine-supported procedures. In this work, to overcome this limitation, a new procedure was developed, which allows physically motivated multiplication of the available reference data in order to obtain a sufficiently large dataset for training machine learning algorithms. The underlying example chemical synthesis was measured and analyzed with both application-relevant low-field NMR and high-field NMR spectroscopy as reference method. Artificial neural networks (ANNs) have the potential to infer valuable process information already from relatively limited input data. However, in order to predict the concentration at complex conditions (many reactants and wide concentration ranges), larger ANNs and, therefore, a larger Training dataset are required. We demonstrate that a moderately complex problem with four reactants can be addressed using ANNs in combination with the presented PAT method (low-field NMR) and with the proposed approach to generate meaningful training data.
Data set of low-field NMR spectra of continuous synthesis of nitro-4’-methyldiphenylamine (MNDPA). 1H spectra (43 MHz) were recorded as single scans.
Two different approaches for the generation of artificial neural networks training data for the prediction of reactant concentrations were used: (i) Training data based on combinations of measured pure component spectra and (ii) Training data based on a spectral model.
Synthetic low-field NMR spectra
First 4 columns in MAT-files represent component areas of each reactant within the synthetic mixture spectrum.
Xi (“pure component spectra dataset”)
Xii (“spectral model dataset”)
Experimental low-field NMR spectra from MNDPA-Synthesis
This data set represents low-field NMR-spectra recorded during continuous synthesis of nitro-4’-methyldiphenylamine (MNDPA). Reference values from high-field NMR results are included.
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.