JACoW logo

Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.


BiBTeX citation export for TUPOST009: Online Correction of Laser Focal Position Using FPGA-Based ML Models

@inproceedings{einstein-curtis:ipac2022-tupost009,
  author       = {J.A. Einstein-Curtis and S.K. Barber and C.E. Berger and S.J. Coleman and N.M. Cook and J.P. Edelen and J. van Tilborg},
% author       = {J.A. Einstein-Curtis and S.K. Barber and C.E. Berger and S.J. Coleman and N.M. Cook and J.P. Edelen and others},
% author       = {J.A. Einstein-Curtis and others},
  title        = {{Online Correction of Laser Focal Position Using FPGA-Based ML Models}},
  booktitle    = {Proc. IPAC'22},
% booktitle    = {Proc. 13th International Particle Accelerator Conference (IPAC'22)},
  pages        = {857--860},
  eid          = {TUPOST009},
  language     = {english},
  keywords     = {laser, network, FPGA, controls, electron},
  venue        = {Bangkok, Thailand},
  series       = {International Particle Accelerator Conference},
  number       = {13},
  publisher    = {JACoW Publishing, Geneva, Switzerland},
  month        = {07},
  year         = {2022},
  issn         = {2673-5490},
  isbn         = {978-3-95450-227-1},
  doi          = {10.18429/JACoW-IPAC2022-TUPOST009},
  url          = {https://jacow.org/ipac2022/papers/tupost009.pdf},
  abstract     = {{High repetition-rate, ultrafast laser systems play a critical role in a host of modern scientific and industrial applications. We present a prototype diagnostic and correction scheme for controlling and determining laser focal position at 10 s of Hz rate by utilizing fast wavefront sensor measurements from multiple positions to train a focal position predictor. This predictor is used to determine corrections for actuators along the beamline to provide the desired correction to the focal position on millisecond timescales. Our initial proof-of-principle demonstrations leverage pre-compiled data and pre-trained networks operating ex-situ from the laser system. We then discuss the application of a high-level synthesis framework for generating a low-level hardware description of ML-based correction algorithms on FPGA hardware coupled directly to the beamline. Lastly, we consider the use of remote computing resources, such as the Sirepo scientific framework* , to actively update these correction schemes and deploy models to a production environment.}},
}