Engineering topics

Kuklev, Nikita [Fermilab]

Publications and source records attributed to Kuklev, Nikita [Fermilab].

8 records

DOE OSTI2026

APOLLO: a facility-scale differentiable virtual accelerator for Fermilab

As the design complexity of modern accelerators grows, there is more interest in using advanced simulations that have fast execution time or yield additional insights like gradients. The FAST/IOTA facility has been working on implementing and experimentally validating an end-to-end digital twin that is both fast and gradient-aware, allowing for rapid prototyping of new software and experiments with minimal beam time costs. Our framework integrates physics and ML codes for linac and ring simulation through a set of generic interfaces between surrogate and physics-based sections. To reproduce device inputs and outputs, system state is exposed as a deterministic discrete event simulator. Because Fermilab is undergoing control system transition, both EPICS and ACNET frontends are supported. Recently, we have begun transitioning to a new community lattice standard, PALS, as well as developing standardized infrastructure for data ingest and normalization to prepare for model calibration during FAST proton injector commissioning. We discuss implementation details as well as challenges, and future plans to extend modelling to main complex proton accelerators like PIPII and Booster.

Kuklev, Nikita [Fermilab]↗

DOE OSTI2026

Optimization and stabilization of Fermilab Booster using hybrid Bayesian/RL framework

PIPII project will raise Fermilab Booster intensity and ramp rate. Beam losses will limit average power and are hard to simulate. Presently, Booster uses operator-guided empirical tuning. This task is challenging due to high dimensionality, multiple objectives, critical safety constraints, and drifts. We developed a synergistic suite of Bayesian optimization (BO) and reinforcement learning (RL) tools to optimize and stabilize beam losses. First, active learning was used to build a rough model. Data was collected parasitically using two novel safety constraint types – nonlinear input space restrictions (based on optics model), and uncertainty constraints (to stop bad steps/beam aborts). We then applied online multi-objective BO with scalarized objectives and fitting to improve/rebalance losses, increasing safety margins by 25%. Using BO model as a safety veto, we tried several on/off-policy RL agents for long term stabilization; SAC had best performance. We found that adding contextual (state) information further improved performance, eventually integrating key knobs like linac phase and temperature into the parameter space. Long term testing is ongoing to enable operational use.

Kuklev, Nikita [Fermilab]↗

DOE OSTI2026

Online multi-objective Bayesian optimization of injection efficiency and beam lifetime with skew quadrupoles at NSLS-II

At NSLS-II, the vertical emittance of electron beam is typically blown up to ~30 pm with a coupling wave to increase beam lifetime during user operation. As more and more insertion devices are added to the storage ring, injection efficiency to the ring drops noticeably in certain machine states, apparently due to degraded dynamic apertures. To help alleviate this issue, we have recently performed online multi-objective Bayesian optimization to increase injection efficiency while maintaining beam lifetime, by adjusting the strengths of 15 skew quadrupoles in non-dispersive sections. We report the results of this optimization effort.

Hidaka, Yoshiteru [Brookhaven]↗

DOE OSTI2026

APS upgrade: Commissioning the world’s first light source based on swap-out injection

The Advanced Photon Source (APS) has recently completed a major upgrade, replacing its 25-year-old storage ring with a cutting-edge hybrid seven-bend achromat lattice enhanced by six additional reverse bends. The new design achieves a natural emittance of 42 pm-rad, enabling the production of X-rays up to 500 times brighter than those generated by the original APS. A key innovation of the upgrade is the implementation of a swap-out injection scheme, which replaces entire depleted bunches instead of performing traditional top-up injection. This approach enables on-axis injection to accommodate for the reduced dynamic aperture resulting from strong focusing. This paper outlines the commissioning process, shares initial operating experience with swap-out injection, and presents performance data for new systems such as the bunch-lengthening cavity.

Sajaev, Vadim [Argonne, PHY]↗

DOE OSTI2025

APOLLO: a facility-scale differentiable virtual accelerator at Fermilab FAST/IOTA

As the design complexity of modern accelerators grows, there is more interest in using advanced simulations that have fast execution time or yield additional insights like gradients. The FAST/IOTA facility has been working on implementing and experimentally validating an end-to-end digital twin that is both fast and gradient-aware, allowing for rapid prototyping of new software and experiments with minimal beam time costs. Our framework integrates physics and ML codes for linac and ring simulation through a set of generic interfaces between surrogate and physics-based sections. To reproduce device inputs and outputs, system state is exposed as a deterministic event loop in a specialized discrete event simulator architecture. Because Fermilab is undergoing control system transition, several APIs were implemented as final user interfaces - a fully asynchronous EPICS soft IOC, a gRPC-based Data Pool Manager (DPM), and legacy ACNET protocols. We discuss implementation details as well as challenges handling live data assimilation and future plans to extend modelling to main complex proton accelerators like PIPII and Booster.

Kuklev, Nikita [Fermilab]↗

DOE OSTI2025

Xopt and Badger: a machine learning ecosystem for real-time accelerator control and optimization

Machine learning (ML)-based black-box optimization algorithms have demonstrated significant improvements in accelerator optimization speed, often by orders of magnitude. However, deploying these algorithms in real-time facility control remains challenging due to the specialized expertise and infrastructure required. To bridge this gap, we introduce the Xopt ecosystem, a versatile suite of tools designed to make advanced ML-based optimization accessible to the broader accelerator community. This ecosystem includes Xopt, a modular Python framework that facilitates the integration of ML-based optimization algorithms with arbitrary control problems, and Badger, a graphical user interface built on top of Xopt, which enables seamless deployment of ML algorithms in real-time control systems. The Xopt ecosystem has been successfully applied towards solving challenging real-time control problems at leading international accelerator facilities, including SLAC, LBNL, Argonne, Fermilab, BNL, DESY, and ESRF, demonstrating its effectiveness in real-world optimization tasks. In this presentation, we provide an overview of Xopt’s capabilities and illustrate its impact through case studies from SLAC accelerator facilities including LCLS, LCLS-II, and FACET-II.

Roussel, Ryan [SLAC]↗

DOE OSTI2025

Unified differentiable digital twin for the IOTA/FAST facility

As the design complexity of modern accelerators grows, there is more interest in using advanced simulations that have fast execution time or produce insights about accelerator state. One notable example of additional information are gradients of physical observables with respect to design parameters produced by differentiable simulations. The IOTA/FAST facility has recently begun a program to implement and experimentally validate a unified start-to-end differentiable digital twin to serve as a virtual accelerator test stand, allowing for rapid prototyping of new software and experiments with minimal beam time costs. In this contribution we will discuss our plans and progress. Specifically, we will cover the selection and benchmarking of both physics and ML codes, the development of generic interfaces between device models and surrogate or physics-based sections, and the export of the parameters through either a deterministic event loop or a fully asynchronous EPICS soft input/output controller. We will also discuss challenges in model calibration and uncertainty quantification, as well as future plans to support larger proton accelerators like PIPII and Booster.

Kuklev, Nikita [Fermilab]↗

DOE OSTI2025

Fermilab Booster loss modelling and rebalancing using Bayesian methods

Fermilab Booster is being upgraded for the PIP-II project to support 20Hz ramp rate at higher intensities. Loss trip limits determine the achievable peak power. To meet PIP-II requirements, losses need to be halved as compared to current levels. Losses primarily occur at injection and transition crossing, with both gradually increasing and threshold-like intensity-dependent behaviors. The existing simulation models are not yet good enough for quantitative loss predictions. In practice, it will be necessary to tune up the Booster using iterative methods and operator intuition. In this paper we present an effort to systematically model Booster losses using active learning (Bayesian exploration) techniques, and subsequently to rebalance them for higher trip limit margins. We first created several sets of spatially and temporally isolated orbit and optics knobs, and trained Gaussian process models for each beam loss monitor as well as beam current. This is a complex task due to safety and timing requirements – we discuss mitigations such as uncertainty constraints and approximate fitting. Once models are stable, we perform large-scale single and multi-objective tuning using scalarized objectives made up of critical beam loss locations. Our results demonstrate significant rebalancing of losses, increasing trip margins, as well as an overall improvement in beam transmission efficiency. We are exploring how to combine existing simulations with experimental data and automate the collection procedure so that more advanced surrogate models can be created over time.

Kuklev, Nikita [Fermilab]↗