Filtern
Dokumenttyp
Sprache
- Englisch (3)
Referierte Publikation
- ja (3) (entfernen)
Schlagworte
- Artificial neural networks (3) (entfernen)
Organisationseinheit der BAM
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.
X-ray reflectivity (XRR) is a powerful and popular scattering technique that can give valuable insight into the growth behavior of thin films. This study Shows how a simple artificial neural network model can be used to determine the thickness, roughness and density of thin films of different organic semiconductors [diindenoperylene, copper(II) phthalocyanine and alpha-sexithiophene] on silica from their XRR data with millisecond computation time and with minimal user input or a priori knowledge. For a large experimental data set of 372 XRR curves, it is shown that a simple fully connected model can provide good results with a mean absolute percentage error of 8–18% when compared with the results obtained by a genetic least mean squares fit using the classical Parratt formalism. Furthermore, current drawbacks and prospects for improvement are discussed.
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.