| Paper | Title | Page |
|---|---|---|
| TUPDP113 | A Flexible EPICS Framework for Sample Alignment at Neutron Beamlines | 836 |
|
||
|
Funding: This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Science under Award Number DE-SC0021555. RadiaSoft has been developing a flexible front-end framework, written in Python, for rapidly developing and testing automated sample alignment IOCs at Oak Ridge National Laboratory. We utilize YAML-formatted configuration files to construct a thin abstraction layer of custom classes which provide an internal representation of the external hardware within a controls system. The abstraction layer takes advantage of the PCASPy and PyEpics libraries in order to serve EPICS process variables & respond to read/write requests. Our framework allows users to build a new IOC that has access to information about the sample environment in addition to user-defined machine learning models. The IOC then monitors for user inputs, performs user-defined operations on the beamline, and reports on its status back to the control system. Our IOCs can be booted from the command line, and we have developed command line tools for rapidly running and testing alignment processes. These tools can also be accessed through an EPICS GUI or in separate Python scripts. This presentation provides an overview of our software structure and showcases its use at two beamlines at ORNL. |
||
| DOI • | reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TUPDP113 | |
| About • | Received ※ 06 October 2023 — Revised ※ 22 October 2023 — Accepted ※ 04 December 2023 — Issued ※ 16 December 2023 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| TUPDP114 | Machine Learning Based Noise Reduction of Neutron Camera Images at ORNL | 841 |
|
||
|
Funding: This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Science under Award Number DE-SC0021555. Neutron cameras are utilized at the HB2A powder diffractometer to image the sample for alignment in the beam. Typically, neutron cameras are quite noisy as they are constantly being irradiated. Removal of this noise is challenging due to the irregular nature of the pixel intensity fluctuations and the tendency for it to change over time. RadiaSoft has developed a novel noise reduction method for neutron cameras that inscribes a lower envelope of the image signal. This process is then sped up using machine learning. Here we report on the results of our noise reduction method and describe our machine learning approach for speeding up the algorithm for use during operations. |
||
| DOI • | reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TUPDP114 | |
| About • | Received ※ 07 October 2023 — Revised ※ 22 October 2023 — Accepted ※ 11 December 2023 — Issued ※ 16 December 2023 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| TUPDP116 | Machine Learning Based Sample Alignment at TOPAZ | 851 |
|
||
|
Funding: This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Science under Award Number DE-SC0021555. Neutron scattering experiments are a critical tool for the exploration of molecular structure in compounds. The TOPAZ single crystal diffractometer at the Spallation Neutron Source studies these samples by illuminating samples with different energy neutron beams and recording the scattered neutrons. During the experiments the user will change temperature and sample position in order to illuminate different crystal faces and to study the sample in different environments. Maintaining alignment of the sample during this process is key to ensuring high quality data are collected. At present this process is performed manually by beamline scientists. RadiaSoft in collaboration with the beamline scientists and engineers at ORNL has developed a new machine learning based alignment software automating this process. We utilize a fully-connected convolutional neural network configured in a U-net architecture to identify the sample center of mass. We then move the sample using a custom python-based EPICS IOC interfaced with the motors. In this talk we provide an overview of our machine learning tools and show our initial results aligning samples at ORNL. |
||
| DOI • | reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TUPDP116 | |
| About • | Received ※ 06 October 2023 — Accepted ※ 05 December 2023 — Issued ※ 11 December 2023 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |