AI Assisted Experiment Control and Calibration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910338797010944 |
|---|---|
| author | Britton, Thomas Goodrich, Michael Jarvis, Naomi Jeske, Torri Kalra, Nikhil Lawrence, David McSpadden, Diana |
| author_facet | Britton, Thomas Goodrich, Michael Jarvis, Naomi Jeske, Torri Kalra, Nikhil Lawrence, David McSpadden, Diana |
| contents | Final report for the AI Assisted Experiment Control and Calibration project. This project integrated AI/ML into the controls and calibration of a production detector system in the GlueX spectrometer, a large scale Nuclear Physics detector in experimental Hall-D at Jefferson Lab. The AI/ML model predicted calibration constants for a Central Drift Chamber using environmental information available prior to taking the data. The device controls were then automatically adjusted so that the calibration values needed for post-processing of the data were much more stable and quicker to determine. Integration into a production system required guardrails and policy choices to ensure safety of the equipment and the data quality. The project sought to apply similar technology to other detectors. Those efforts are also described here. This documents many of the details of the project. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13261 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI Assisted Experiment Control and Calibration Britton, Thomas Goodrich, Michael Jarvis, Naomi Jeske, Torri Kalra, Nikhil Lawrence, David McSpadden, Diana Instrumentation and Detectors Nuclear Experiment Final report for the AI Assisted Experiment Control and Calibration project. This project integrated AI/ML into the controls and calibration of a production detector system in the GlueX spectrometer, a large scale Nuclear Physics detector in experimental Hall-D at Jefferson Lab. The AI/ML model predicted calibration constants for a Central Drift Chamber using environmental information available prior to taking the data. The device controls were then automatically adjusted so that the calibration values needed for post-processing of the data were much more stable and quicker to determine. Integration into a production system required guardrails and policy choices to ensure safety of the equipment and the data quality. The project sought to apply similar technology to other detectors. Those efforts are also described here. This documents many of the details of the project. |
| title | AI Assisted Experiment Control and Calibration |
| topic | Instrumentation and Detectors Nuclear Experiment |
| url | https://arxiv.org/abs/2402.13261 |