Search

This study investigates the influence of seismic activities on the optical synchronization system of the European X-ray Free-Electron Laser. We analyze the controller I/O data of phase-locked-loops in length-stabilized links, focusing on the response to earthquakes, ocean-generated microseism and civilization noise. By comparing the controller data with external data, we were able to identify disturbances and their effects on the control signals. Our results show that seismic events influence the stability of the phase-locked loops. Even earthquakes that are approximately \qty{5000}{\km} away cause remarkable fluctuations in the in-loop control signals. Ocean-generated microseism in particular has an enormous influence on the in-loop control signals due to its constant presence. The optical synchronization system is so highly sensitive that it can even identify vibrations caused by civilization, such as road traffic or major events like concerts or sport events. The phase-locked loops manages to eliminate more than 99% of the existing interference., Comment: submitted to Journal High Power Laser Science and Engineering

This paper introduces a machine learning-aided fault detection and isolation method applied to the case study of quench identification at the European X-Ray Free-Electron Laser. The plant utilizes 800 superconducting radio-frequency cavities in order to accelerate electron bunches to high energies of up to 17.5 GeV. Various faulty events can disrupt the nominal functioning of the accelerator, including quenches that can lead to a loss of the superconductivity of the cavities and the interruption of their operation. In this context, our solution consists in analyzing signals reflecting the dynamics of the cavities in a two-stage approach. (I) Fault detection that uses analytical redundancy to process the data and generate a residual. The evaluation of the residual through the generalized likelihood ratio allows detecting the faulty behaviors. (II) Fault isolation which involves the distinction of the quenches from the other faults. To this end, we proceed with a data-driven model of the k-medoids algorithm that explores different similarity measures, namely, the Euclidean and the dynamic time warping. Finally, we evaluate the new method and compare it to the currently deployed quench detection system, the results show the improved performance achieved by our method.

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., Comment: 5 pages, 1 figure, 15th International Particle Accelerator Conference

High-power multi-beam klystrons represent a key component to amplify RF to generate the accelerating field of the superconducting radio frequency (SRF) cavities at European XFEL. Exchanging these high-power components takes time and effort, thus it is necessary to minimize maintenance and downtime and at the same time maximize the device's operation. In an attempt to explore the behavior of klystrons using machine learning, we completed a series of experiments on our klystrons to determine various operational modes and conduct feature extraction and dimensionality reduction to extract the most valuable information about a normal operation. To analyze recorded data we used state-of-the-art data-driven learning techniques and recognized the most promising components that might help us better understand klystron operational states and identify early on possible faults or anomalies., Comment: 4 pages, 4 figures, 15, 15TH International Particle Accelerator Conference

Autonomous tuning of particle accelerators is an active and challenging field of research with the goal of enabling novel accelerator technologies cutting-edge high-impact applications, such as physics discovery, cancer research and material sciences. A key challenge with autonomous accelerator tuning remains that the most capable algorithms require an expert in optimisation, machine learning or a similar field to implement the algorithm for every new tuning task. In this work, we propose the use of large language models (LLMs) to tune particle accelerators. We demonstrate on a proof-of-principle example the ability of LLMs to successfully and autonomously tune a particle accelerator subsystem based on nothing more than a natural language prompt from the operator, and compare the performance of our LLM-based solution to state-of-the-art optimisation algorithms, such as Bayesian optimisation (BO) and reinforcement learning-trained optimisation (RLO). In doing so, we also show how LLMs can perform numerical optimisation of a highly non-linear real-world objective function. Ultimately, this work represents yet another complex task that LLMs are capable of solving and promises to help accelerate the deployment of autonomous tuning algorithms to the day-to-day operations of particle accelerators., Comment: 22 pages, 5 figures

Machine learning has emerged as a powerful solution to the modern challenges in accelerator physics. However, the limited availability of beam time, the computational cost of simulations, and the high-dimensionality of optimisation problems pose significant challenges in generating the required data for training state-of-the-art machine learning models. In this work, we introduce Cheetah, a PyTorch-based high-speed differentiable linear-beam dynamics code. Cheetah enables the fast collection of large data sets by reducing computation times by multiple orders of magnitude and facilitates efficient gradient-based optimisation for accelerator tuning and system identification. This positions Cheetah as a user-friendly, readily extensible tool that integrates seamlessly with widely adopted machine learning tools. We showcase the utility of Cheetah through five examples, including reinforcement learning training, gradient-based beamline tuning, gradient-based system identification, physics-informed Bayesian optimisation priors, and modular neural network surrogate modelling of space charge effects. The use of such a high-speed differentiable simulation code will simplify the development of machine learning-based methods for particle accelerators and fast-track their integration into everyday operations of accelerator facilities., Comment: 16 pages, 9 figures, 3 tables

Bayesian optimization has emerged as a highly effective tool for the safe online optimization of systems, due to its high sample efficiency and noise robustness. To further enhance its efficiency, reduced physical models of the system can be incorporated into the optimization process, accelerating it. These models are able to offer an approximation of the actual system, and evaluating them is significantly cheaper. The similarity between the model and reality is represented by additional hyperparameters, which are learned within the optimization process. Safety is a crucial criterion for online optimization methods such as Bayesian optimization, which has been addressed by recent works that provide safety guarantees under the assumption of known hyperparameters. In practice, however, this does not apply. Therefore, we extend the robust Gaussian process uniform error bounds to meet the multi-task setting, which involves the calculation of a confidence region from the hyperparameter posterior distribution utilizing Markov chain Monte Carlo methods. Subsequently, the robust safety bounds are employed to facilitate the safe optimization of the system, while incorporating measurements of the models. Simulation results indicate that the optimization can be significantly accelerated for expensive to evaluate functions in comparison to other state-of-the-art safe Bayesian optimization methods, contingent on the fidelity of the models., Comment: Submitted to L4DC 2024

Accelerator physics relies on numerical algorithms to solve optimization problems in online accelerator control and tasks such as experimental design and model calibration in simulations. The effectiveness of optimization algorithms in discovering ideal solutions for complex challenges with limited resources often determines the problem complexity these methods can address. The accelerator physics community has recognized the advantages of Bayesian optimization algorithms, which leverage statistical surrogate models of objective functions to effectively address complex optimization challenges, especially in the presence of noise during accelerator operation and in resource-intensive physics simulations. In this review article, we offer a conceptual overview of applying Bayesian optimization techniques towards solving optimization problems in accelerator physics. We begin by providing a straightforward explanation of the essential components that make up Bayesian optimization techniques. We then give an overview of current and previous work applying and modifying these techniques to solve accelerator physics challenges. Finally, we explore practical implementation strategies for Bayesian optimization algorithms to maximize their performance, enabling users to effectively address complex optimization challenges in real-time beam control and accelerator design.

Navigating the landscape of particle accelerators has become increasingly challenging with recent surges in contributions. These intricate devices challenge comprehension, even within individual facilities. To address this, we introduce PACuna, a fine-tuned language model refined through publicly available accelerator resources like conferences, pre-prints, and books. We automated data collection and question generation to minimize expert involvement and make the data publicly available. PACuna demonstrates proficiency in addressing intricate accelerator questions, validated by experts. Our approach shows adapting language models to scientific domains by fine-tuning technical texts and auto-generated corpora capturing the latest developments can further produce pre-trained models to answer some intricate questions that commercially available assistants cannot and can serve as intelligent assistants for individual facilities.

In this paper, we show a textual analysis of past ICALEPCS and IPAC conference proceedings to gain insights into the research trends and topics discussed in the field. We use natural language processing techniques to extract meaningful information from the abstracts and papers of past conference proceedings. We extract topics to visualize and identify trends, analyze their evolution to identify emerging research directions, and highlight interesting publications based solely on their content with an analysis of their network. Additionally, we will provide an advanced search tool to better search the existing papers to prevent duplication and easier reference findings. Our analysis provides a comprehensive overview of the research landscape in the field and helps researchers and practitioners to better understand the state-of-the-art and identify areas for future research.

This article introduces a method to detect anomalies in the log data generated by control system nodes at the European XFEL accelerator. The primary aim of this proposed method is to provide operators a comprehensive understanding of the availability, status, and problems specific to each node. This information is vital for ensuring the smooth operation. The sequential nature of logs and the absence of a rich text corpus that is specific to our nodes poses significant limitations for traditional and learning-based approaches for anomaly detection. To overcome this limitation, we propose a method that uses word embedding and models individual nodes as a sequence of these vectors that commonly co-occur, using a Hidden Markov Model (HMM). We score individual log entries by computing a probability ratio between the probability of the full log sequence including the new entry and the probability of just the previous log entries, without the new entry. This ratio indicates how probable the sequence becomes when the new entry is added. The proposed approach can detect anomalies by scoring and ranking log entries from European XFEL nodes where entries that receive high scores are potential anomalies that do not fit the routine of the node. This method provides a warning system to alert operators about these irregular log events that may indicate issues.

Online tuning of real-world plants is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods, such as Reinforcement Learning-trained Optimisation (RLO) and Bayesian optimisation (BO), hold great promise for achieving outstanding plant performance and reducing tuning times. Which algorithm to choose in different scenarios, however, remains an open question. Here we present a comparative study using a routine task in a real particle accelerator as an example, showing that RLO generally outperforms BO, but is not always the best choice. Based on the study's results, we provide a clear set of criteria to guide the choice of algorithm for a given tuning task. These can ease the adoption of learning-based autonomous tuning solutions to the operation of complex real-world plants, ultimately improving the availability and pushing the limits of operability of these facilities, thereby enabling scientific and engineering advancements., Comment: 17 pages, 8 figures, 2 tables

The problem of robust controller synthesis for plants affected by structured uncertainty, captured by integral quadratic constraints, is discussed. The solution is optimized towards a worst-case white noise rejection specification, which is a generalization of the standard $\mathcal{H}_2$-norm to the robust setting including possibly non-LTI uncertainty. Arbitrary structural constraints can be imposed on the control solution, making this method suitable for distributed systems. The nonsmooth optimization algorithm used to solve the robust synthesis problem operates directly in the frequency domain, eliminating scalability issues for complex systems and providing local optimality certificates. The method is evaluated using a literature example and a real-world system using a novel implementation of a robust $\mathcal{H}_2$-performance bound., Comment: 6 pages, 4 figures, accepted for IFAC World Congress 2023. Shortened to satisfy submission page limit (removed one numerical example and compressed remaining text)

A distributed model predictive control scheme is developed for tracking piecewise constant references where the terminal set is reconfigured online, whereas the terminal controller is computed offline. Unlike many standard existing schemes, this scheme yields large feasible regions without performing offline centralized computations. Although the resulting optimal control problem (OCP) is a semidefinite program (SDP), an SDP scalability method based on diagonal dominance is used to approximate the derived SDP by a second-order cone program. The OCPs of the proposed scheme and its approximation are amenable to distributed optimization. Both schemes are evaluated using a power network example and compared to a scheme where the terminal controller is reconfigured online as well. It is found that fixing the terminal controller results in better performance, noticeable reduction in computational cost and similar feasible region compared to the case in which this controller is reconfigured online.

A novel approach to detect anomalies in superconducting radio-frequency cavities is presented, based on the parity space method with the goal to detect quenches and distinguish them from other anomalies. The model-based parity space method relies on analytical redundancy and generates a residual signal computed from measurable RF waveforms. The residual is a sensitive indicator of deviation from the model and provides different signatures for different types of anomalies. This new method not only helps with detecting faults, but also provides a catalogue of unique signatures, based on the detected fault. The method was experimentally verified at the European X-ray Free Electron Laser (EuXFEL). Various types of anomalies incorrectly detected as quenches by the current quench detection system are analysed using this new approach.

We present an online stochastic model predictive control framework for demand charge management for a grid-connected consumer with attached electrical energy storage. The consumer we consider must satisfy an inflexible but stochastic electricity demand, and also receives a stochastic electricity inflow. The optimization problem formulated solves a stochastic cost minimization problem, with given weather forecast scenarios converted into forecast demand and inflow. We introduce a novel weighting scheme to account for cases where the optimization horizon spans multiple demand charge periods. The optimization scheme is tested in a setting with building demand and photovoltaic array inflow data from a real office building. The simulation study allows us to compare various design and modeling alternatives, ultimately proposing a policy based on causal affine decision rules., Comment: 8 pages, 7 figures

Various efforts have been devoted to developing stabilizing distributed Model Predictive Control (MPC) schemes for tracking piecewise constant references. In these schemes, terminal sets are usually computed offline and used in the MPC online phase to guarantee recursive feasibility and asymptotic stability. Maximal invariant terminal sets do not necessarily respect the distributed structure of the network, hindering the distributed implementation of the controller. On the other hand, ellipsoidal terminal sets respect the distributed structure, but may lead to conservative schemes. In this paper, a novel distributed MPC scheme is proposed for reference tracking of networked dynamical systems where the terminal ingredients are reconfigured online depending on the closed-loop states to alleviate the aforementioned issues. The resulting non-convex infinite-dimensional problem is approximated using a quadratic program. The proposed scheme is tested in simulation where the proposed MPC problem is solved using distributed optimization.

In this paper, a novel distributed model predictive control (MPC) scheme with asymmetric adaptive terminal sets is developed for the regulation of large-scale systems with a distributed structure. Similar to typical MPC schemes, a structured Lyapunov matrix and a distributed terminal controller, respecting the distributed structure of the system, are computed offline. However, in this scheme, a distributed positively invariant terminal set is computed online and updated at each time instant taking into consideration the current state of the system. In particular, we consider ellipsoidal terminal sets as they are easy to compute for large-scale systems. The size and the center of these terminal sets, together with the predicted state and input trajectories, are considered as decision variables in the online phase. Determining the terminal set center online is found to be useful specifically in the presence of asymmetric constraints. Finally, a relaxation of the resulting online optimal control problem is provided. The efficacy of the proposed scheme is illustrated in simulation by comparing it to a recent distributed MPC scheme with adaptive terminal sets.

This paper presents scalable controller synthesis methods for heterogeneous and partially heterogeneous systems. First, heterogeneous systems composed of different subsystems that are interconnected over a directed graph are considered. Techniques from robust and gain-scheduled controller synthesis are employed, in particular the full-block S-procedure, to deal with the decentralized system part in a nominal condition and with the interconnection part in a multiplier condition. Under some structural assumptions, we can decompose the synthesis conditions into conditions that are the size of the individual subsystems. To solve these decomposed synthesis conditions that are coupled only over neighboring subsystems, we propose a distributed method based on the alternating direction method of multipliers. It only requires nearest-neighbor communication and no central coordination is needed. Then, a new classification of systems is introduced that consists of groups of homogeneous subsystems with different interconnection types. This classification includes heterogeneous systems as the most general and homogeneous systems as the most specific case. Based on this classification, we show how the interconnected system model and the decomposed synthesis conditions can be formulated in a more compact way. The computational scalability of the presented methods with respect to a growing number of subsystems and interconnections is analyzed, and the results are demonstrated in numerical examples., Comment: 16 pages, 7 figures, journal paper

We present an approximate method for solving nonlinear control problems over long time horizons, in which the full nonlinear model is preserved over an initial part of the horizon, while the remainder of the horizon is modeled using a linear relaxation. As this approximate problem may still be too large to solve directly, we present a Benders decomposition-based solution algorithm that iterates between solving the nonlinear and linear parts of the horizon. This extends the Dual Dynamic Programming approach commonly employed for optimization of linearized hydro power systems. We prove that the proposed algorithm converges after a finite number of iterations, even when the nonlinear initial stage problems are solved inexactly. We also bound the suboptimality of the split-horizon method with respect to the original nonlinear problem, in terms of the properties of a map between the linear and nonlinear state-input trajectories. We then apply this method to a case study concerning a multiple reservoir hydro system, approximating the nonlinear head effects in the second stage using McCormick envelopes. We demonstrate that near-optimal solutions can be obtained in a shrinking horizon setting when the full nonlinear model is used for only a short initial section of the horizon. For this example, the approach is shown to be more practical than both conventional dynamic programming and a multi-cell McCormick envelope approximation from literature., Comment: 10 pages, 9 figures

In this paper, we propose a distributed model predictive control (DMPC) scheme for linear time-invariant constrained systems which admit a separable structure. To exploit the merits of distributed computation algorithms, the stabilizing terminal controller, value function and invariant terminal set of the DMPC optimization problem need to respect the loosely coupled structure of the system. Although existing methods in the literature address this task, they typically decouple the synthesis of terminal controllers and value functions from the one of terminal sets. In addition, these approaches do not explicitly consider the effect of the current state of the system in the synthesis process. These limitations can lead the resulting DMPC scheme to poor performance since it may admit small or even empty terminal sets. Unlike other approaches, this paper presents a unified framework to encapsulate the synthesis of both the stabilizing terminal controller and invariant terminal set into the DMPC formulation. Conditions for Lyapunov stability and invariance are imposed in the synthesis problem in a way that allows the value function and invariant terminal set to admit the desired distributed structure. We illustrate the effectiveness of the proposed method on several examples including a benchmark spring-mass-damper problem.