arXiv subjects

Thorsten Hellert

Publications and source records attributed to Thorsten Hellert.

14 recordsLinked to original sources

arXiv2026

Autonomous discovery of accelerator commissioning algorithms

Simulated commissioning has become essential for de-risking modern light-source design and commissioning, but the procedures being simulated are still designed entirely by human experts. Their labor-intensive redevelopment after lattice changes makes such studies hard to repeat and limits their use during early design iteration. This Letter demonstrates a closed research loop in which a language-model agent writes commissioning code, tests it in simulation, and improves the algorithm from the results. Applied to RF beam capture in the ALS-U accumulator-ring model, the loop substantially improves a working expert procedure and can construct a working one from a minimal starting point, with more capable models succeeding from less initial code. Extending the same framework to multiple objectives produces 16 non-dominated algorithms spanning physically distinct trade-offs between rapid beam capture and correction of seeded machine errors. This reframes commissioning studies from evaluating human-designed procedures toward a mode in which agents participate directly in discovering accelerator algorithms.

physics.acc-ph↗

arXiv2025

From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructure

Modern experimental platforms such as particle accelerators, fusion devices, telescopes, and industrial process control systems expose tens to hundreds of thousands of control and diagnostic channels accumulated over decades of evolution. Operators and AI systems rely on informal expert knowledge, inconsistent naming conventions, and fragmented documentation to locate signals for monitoring, troubleshooting, and automated control, creating a persistent bottleneck for reliability, scalability, and language-model-driven interfaces. We formalize semantic channel finding-mapping natural-language intent to concrete control-system signals-as a general problem in complex experimental infrastructure, and introduce a four-paradigm framework to guide architecture selection across facility-specific data regimes. The paradigms span (i) direct in-context lookup over curated channel dictionaries, (ii) constrained hierarchical navigation through structured trees, (iii) interactive agent exploration using iterative reasoning and tool-based database queries, and (iv) ontology-grounded semantic search that decouples channel meaning from facility-specific naming conventions. We demonstrate each paradigm through proof-of-concept implementations at four operational facilities spanning two orders of magnitude in scale-from compact free-electron lasers to large synchrotron light sources-and diverse control-system architectures, from clean hierarchies to legacy environments. These implementations achieve 90-97% accuracy on expert-curated operational queries.

cs.CL↗

arXiv2025

Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator

We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by two orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

physics.acc-ph↗

arXiv2025

Unsupervised Anomaly Detection in ALS EPICS Event Logs

This paper introduces an automated fault analysis framework for the Advanced Light Source (ALS) that processes real-time event logs from its EPICS control system. By treating log entries as natural language, we transform them into contextual vector representations using semantic embedding techniques. A sequence-aware neural network, trained on normal operational data, assigns a real-time anomaly score to each event. This method flags deviations from baseline behavior, enabling operators to rapidly identify the critical event sequences that precede complex system failures.

cs.LG↗

arXiv2025

Agentic System with Modal Logic for Autonomous Diagnostics

The development of intelligent agents, particularly those powered by language models (LMs), has shown a critical role in various environments that require intelligent and autonomous decision-making. Environments are not passive testing grounds, and they represent the data required for agents to learn and exhibit in very challenging conditions that require adaptive, complex, and autonomous capacity to make decisions. While the paradigm of scaling models and datasets has led to remarkable emergent capabilities, we argue that scaling the structure, fidelity, and logical consistency of agent reasoning within these environments is a crucial, yet underexplored, dimension of AI research. This paper introduces a neuro-symbolic multi-agent architecture where the belief states of individual agents are formally represented as Kripke models. This foundational choice enables them to reason about known concepts of \emph{possibility} and \emph{necessity} using the formal language of modal logic. In this work, we use immutable, domain-specific knowledge to make an informed root cause diagnosis, which is encoded as logical constraints essential for proper, reliable, and explainable diagnosis. In the proposed model, we show constraints that actively guide the hypothesis generation of LMs, effectively preventing them from reaching physically or logically untenable conclusions. In a high-fidelity simulated particle accelerator environment, our system successfully diagnoses complex, cascading failures by combining the powerful semantic intuition of LMs with the rigorous, verifiable validation of modal logic and a factual world model and showcasing a viable path toward more robust, reliable, and verifiable autonomous agents.

cs.AI↗

arXiv2025

Osprey: Production-Ready Agentic AI for Safety-Critical Control Systems

Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface for these tasks, but most existing approaches are not yet reliable or safe enough for production use. In this paper, we introduce Osprey, a framework for using agentic AI in large, safety-critical facility operations. Osprey is built around the needs of control rooms and addresses these challenges in four ways. First, it uses a plan-first orchestrator that generates complete execution plans, including all dependencies, for human review before any hardware is touched. Second, a coordination layer manages complex data flows, keeps data types consistent, and automatically downsamples large datasets when needed. Third, a classifier dynamically selects only the tools required for a given task, keeping prompts compact as facilities add capabilities. Fourth, connector abstractions and deployment patterns work across different control systems and are ready for day-to-day use. We demonstrate the framework through two case studies: a control-assistant tutorial showing semantic channel mapping and historical data integration, and a production deployment at the Advanced Light Source, where Osprey manages real-time operations across hundreds of thousands of control channels. These results establish Osprey as a production-ready framework for deploying agentic AI in complex, safety-critical environments.

cs.MA↗

arXiv2025

eLog analysis for accelerators: status and future outlook

This work demonstrates electronic logbook (eLog) systems leveraging modern AI-driven information retrieval capabilities at the accelerator facilities of Fermilab, Jefferson Lab, Lawrence Berkeley National Laboratory (LBNL), SLAC National Accelerator Laboratory. We evaluate contemporary tools and methodologies for information retrieval with Retrieval Augmented Generation (RAGs), focusing on operational insights and integration with existing accelerator control systems. The study addresses challenges and proposes solutions for state-of-the-art eLog analysis through practical implementations, demonstrating applications and limitations. We present a framework for enhancing accelerator facility operations through improved information accessibility and knowledge management, which could potentially lead to more efficient operations.

hep-ex↗

arXiv2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show three examples, where we demonstrate the viability of such architecture.

physics.acc-ph↗

arXiv2024

PhysBERT: A Text Embedding Model for Physics Scientific Literature

The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 million arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific tasks including the effectiveness in fine-tuning for specific physics subdomains.

physics.comp-ph↗

arXiv2024

Towards Unlocking Insights from Logbooks Using AI

Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL, and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, enable macro-analysis for root cause analysis, and facilitate problem-solving automation.

physics.acc-ph↗

arXiv2018

Detuning related coupler kick variation of a superconducting nine-cell 1.3 GHz cavity

Superconducting TESLA-type cavities are widely used to accelerate electrons in long bunch trains, such as in high repetition rate free electron lasers. The TESLA cavity is equipped with two higher order mode couplers and a fundamental power coupler (FPC), which break the axial symmetry of the cavity. The passing electrons therefore experience axially asymmetrical coupler kicks, which depend on the transverse beam position at the couplers and the rf phase. The resulting emittance dilution has been studied in detail in the literature. However, the kick induced by the FPC depends explicitly on the ratio of the forward to the backward traveling waves at the coupler, which has received little attention. The intention of this paper is to present the concept of discrete coupler kicks with a novel approach of separating the field disturbances related to the standing wave and a reflection dependent part. Particular attention is directed to the role of the penetration depth of the FPC antenna, which determines the loaded quality factor of the cavity. The developed beam transport model is compared to dedicated experiments at FLASH and European XFEL. Both the observed transverse coupling and detuning related coupler kick variations are in good agreement with the model. Finally, the expected trajectory variations due to coupler kick variations at European XFEL are investigated and results of numerical studies are presented.

physics.acc-ph↗

arXiv2018

Higher-order mode-based cavity misalignment measurements at the free-electron laser FLASH

At the Free-Electron Laser in Hamburg (FLASH) and the European X-Ray Free-Electron Laser, superconducting TeV-energy superconducting linear accelerator (TESLA)-type cavities are used for the acceleration of electron bunches, generating intense free-electron laser (FEL) beams. A long rf pulse structure allows one to accelerate long bunch trains, which considerably increases the efficiency of the machine. However, intrabunch-train variations of rf parameters and misalignments of rf structures induce significant trajectory variations that may decrease the FEL performance. The accelerating cavities are housed inside cryomodules, which restricts the ability for direct alignment measurements. In order to determine the transverse cavity position, we use a method based on beam-excited dipole modes in the cavities. We have developed an efficient measurement and signal processing routine and present its application to multiple accelerating modules at FLASH. The measured rms cavity offset agrees with the specification of the TESLA modules. For the first time, the tilt of a TESLA cavity inside a cryomodule is measured. The preliminary result agrees well with the ratio between the offset and angle dependence of the dipole mode which we calculated with eigenmode simulations.

physics.acc-ph↗

arXiv2017

Efficient model for low-energy transverse beam dynamics in a nine-cell 1.3 GHz cavity

FLASH and the European XFEL are SASE-FEL user facilities, at which superconducting TESLA cavities are operated in a pulsed mode to accelerate long bunch-trains. Several cavities are powered by one klystron. While the low-level rf system is able to stabilize the vector sum of the accelerating gradient of one rf station sufficiently, the rf parameters of individual cavities vary within the bunch-train. In correlation with misalignments, intrabunch-train trajectory variations are induced. An efficient model is developed to describe the effect at low beam energy, using numerically adjusted transfer matrices and discrete coupler kick coefficients, respectively. Comparison with start-to-end tracking and dedicated experiments at the FLASH injector will be shown. The short computation time of the derived model allows for comprehensive numerical studies on the impact of misalignments and variable rf parameters on the transverse intra-bunch-train beam stability at the injector module. Results from both, statistical multibunch performance studies and the deduction of misalignments from multibunch experiments are presented.

physics.acc-ph↗

arXiv2017

Analysis of multibunch free electron laser operation

At the SASE-FEL user facilities FLASH and European XFEL, superconducting TESLA type cavities are used for acceleration of the driving electron bunches. The high achievable duty cycle allows for operating with long bunch trains, hence considerably increasing the efficiency of the machine. However, multibunch free electron lasers (FEL) operation requires longitudinal and transverse stability within the bunch train. The purpose of this work is to investigate the intra-bunch-train transverse dynamics at FLASH and European XFEL. Key relationships of superconducting rf cavity operation and the resulting impact on the intrabunch-train trajectory variation are described. The observed trajectory variation during multibunch user runs at FLASH is analyzed and related to both, intrabunch-train variations of the rf and the following impact on the multibunch FEL performance.

physics.acc-ph↗