RadiaSoft LLC, Boulder, Colorado, USA
BNL, Upton, New York, USA
Synchrotron radiation beamlines transport X-rays from the electron beam source to the experimental sample. Precise alignment of the beamline optics is required to achieve adequate beam properties at the sample. This process is often done manually and can be quite time consuming. Further, we would like to know the properties at the sample in order to provide metadata for X-ray experiments. Diagnostics may provide some of this information but important properties may remain unmeasured. In order to solve both of these problems, we are developing tools to create fast online models (also known as digital twins). For this purpose, we are creating reduced models that fit into a hierarchy of X-ray models of varying degrees of complexity and runtime. These are implemented within a software framework called Sirepo-Bluesky* that allows for the computation of the model from within a Bluesky session which may control a real beamline. This work is done in collaboration with NSLS-II. We present the status of the software development and beamline measurements including results from the TES beamline. Finally, we present an outlook for continuing this work and applying it to more beamlines at NSLS-II and other synchrotron facilities around the world.
*https://github.com/NSLS-II/sirepo-bluesky
RadiaSoft LLC, Boulder, Colorado, USA
LBNL, Berkeley, California, USA
High repetition-rate, ultrafast laser systems play a critical role in a host of modern scientific and industrial applications. We present a diagnostic and correction scheme for controlling and determining laser focal position by utilizing fast wavefront sensor measurements from multiple positions to train a focal position predictor. This predictor and additional control algorithms have been integrated into a unified control interface and FPGA-based controller on beamlines at the Bella facility at LBNL. An optics section is adjusted online to provide the desired correction to the focal position on millisecond timescales by determining corrections for an actuator in a telescope section along the beamline. Our initial proof-of-principle demonstrations leveraged pre-compiled data and pre-trained networks operating ex-situ from the laser system. A framework for generating a low-level hardware description of ML-based correction algorithms on FPGA hardware was coupled directly to the beamline using the AMD Xilinx Vitis AI toolchain in conjunction with deployment scripts. 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.
* M.S. Rakitin et al., "Sirepo: an open-source cloud-based software interface for X-ray source and optics simulations" Journal of Synchrotron Radiation25, 1877-1892 (Nov 2018).
RadiaSoft LLC, Boulder, Colorado, USA
SLAC, Menlo Park, California, USA
The industrial and medical accelerator industry is an ever-growing field with advancements in accelerator technology enabling its adoption for new applications. As the complexity of industrial accelerators grows so does the need for more sophisticated control systems to regulate their operation. Moreover, the environment for industrial and medical accelerators is often harsh and noisy as opposed to the more controlled environment of a laboratory-based machine. This environment makes control more challenging. Additionally, instrumentation for industrial accelerators is limited making it difficult at times to identify and diagnose problems when they occur. RadiaSoft has partnered with SLAC to develop new machine learning methods for control and anomaly detection for industrial accelerators. Our approach is to develop our methods using simulation models followed by testing on experimental systems. Here we present initial results using simulations of a room temperature s-band system.
RadiaSoft LLC, Boulder, Colorado, USA
BNL, Upton, New York, USA
Robust and reliable quench detection for superconducting magnets is increasingly important as facilities push the boundaries of intensity and operational runtime. RadiaSoft has been working with Brookhaven National Lab on quench detection and prediction for superconducting magnets installed in the RHIC storage rings. This project has analyzed several years of power supply and beam position monitor data to train automated classification tools and automated quench precursor determination based on input sequences. Classification was performed using supervised multilayer perceptron and boosted decision tree architectures, while models of the expected operation of the ring were developed using a variety of autoencoder architectures. We have continued efforts to maximize area under the receiver operating characteristic curve for the multiple classification problem of real quench, fake quench, and no-quench events. We have also begun work on long short-term memory (LSTM) and other recurrent architectures for quench prediction. Examinations of future work utilizing more robust architectures, such as variational autoencoders and Siamese models, as well as methods necessary for uncertainty quantification will be discussed.
RadiaSoft LLC, Boulder, Colorado, USA
BNL, Upton, New York, USA
The design, execution, and analysis of light source experiments requires the use of sophisticated simulation, controls and data management tools. Existing workflows require significant specialization to accommodate specific beamline operations and data pre-processing steps necessary for more intensive analysis. Recent efforts to address these needs at the National Synchrotron Light Source II (NSLS-II) have resulted in the creation of the Bluesky data collection framework, an open-source library for coordinating experimental control and data collection. Bluesky provides high level abstraction of experimental procedures and instrument readouts to encapsulate generic workflows. We present a prototype data analysis platform for integrating data collection with real time analysis at the beamline. Our application leverages Bluesky in combination with a flexible run engine to execute user configurable Python-based analyses with customizable queueing and resource management. We discuss initial demonstrations to support X-ray photon correlation spectroscopy experiments and future efforts to expand the platform’s features.