Filtern
Dokumenttyp
- Zeitschriftenartikel (10)
- Vortrag (5)
- Beitrag zu einem Tagungsband (2)
- Forschungsdatensatz (2)
- Posterpräsentation (1)
Schlagworte
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (5)
Artificial intelligence (AI), machine learning, and neural networks have revolutionized fields such as self-driving cars or machine translation. Indeed, AI has progressed so far that scientists such as Stephen Hawking now fear that it may destroy humankind altogether. So, let’s get started and use AI in surface science.
Here we train neural networks to use raw measurement data as input and immediately return the desired output parameters. We discuss the example of X-ray reflectivity measurements of ultrathin films, which contain reciprocal space information and must traditionally be fitted with dynamic scattering theory. Instead, we train the neural network with simulated X-ray data of multilayer structures and then apply it to measurement data. The neural network yields high accuracy results, is robust against noise, and performs significantly faster than fitting algorithms in real-time experiments. The presented neural network data analysis is becoming increasingly attractive, because free software has become very accessible and specialized computer chips (NPU) are currently being rolled out.
We demonstrate the use of a 3D printed radial collimator in X-ray powder diffraction and surface sensitive grazing incidence X-ray diffraction. We find a significant improvement in the overall Signal to background ratio of up to 100 and a suppression of more than a factor 3⋅10⁵ for undesirable Bragg reflections generated by the X-ray “transparent” windows of the sample environment.
The background reduction and the removal of the high intensity signals from the windows, which limit the detector’s dynamic range, enable significantly higher sensitivity in experiments within sample environments such as vacuum chambers and gas- or liquid-cells. Details of the additively manufactured steel collimator geometry, alignment strategies using X-ray fluorescence, and data analysis are also briefly discussed. The flexibility and affordability of 3D prints enable designs optimized for specific detectors and sample environments, without compromising the degrees of freedom of the diffractometer.
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.
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.
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.
The influence of size effects on the thermoelectric properties of thin platinum films is investigated and compared to the bulk. Structural properties, like the film thickness and the grain size, are varied. We correlate the electron mean free path with the temperature dependence of the electrical conductivity and the absolute Seebeck coefficient SPt of platinum. A measurement platform was developed as a standardized method to determine SPt and show that SPt,film is reduced compared to SPt,bulk. Boundary and surface scattering reduce the thermodiffusion and the phonon drag contribution to SPt,film by nearly the same factor. We discuss in detail on behalf of a model, which describes the temperature dependence of the absolute Seebeck coefficient, the influence of size effects of electron-phonon and phonon-phonon interaction on SPt.
Fiber Optic sensing @BAM
(2017)