Search NASA⌕ Search

SEARCH · Search NASA

Results for “feedback based control”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Tungsten control in long pulse operation: feedback from WEST to ITER

The full W environment that is now foreseen for ITER puts strong emphasis on experimental results obtained in present devices in similar conditions. In this context, the WEST tokamak is well equipped to bring key contributions to the preparation of ITER operation, thanks to its capability to perform long pulses in dominant electron heating, torque-free scheme based on RF systems, and its ITER-grade actively cooled divertor. Recent results of interest cover the understanding of tungsten contamination and the evaluation of conditioning methods, the feedback on the current ramp-up phase, and the ageing of the ITER divertor components in L-mode attached condition. Further, new directions are being explored, in particular low divertor temperature operation that should be the normal operating regime of ITER. We also report on tungsten peaking physics, and the role of light impurity content.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Application of deep learning methods for beam size control during user operation at the Advanced Light Source

Past research at the Advanced Light Source (ALS) provided a proof-of-principle demonstration that deep learning methods could be effectively employed to compensate for the significant perturbations to the transverse electron beam size induced by user-controlled adjustments of the insertion devices. However, incorporating these methods into the ALS’ daily operations has faced notable challenges. The complexity of the system’s operational requirements and the significant upkeep demands has restricted their sustained application during user operation. Here, we introduce the development of a more robust neural network (NN)-based algorithm that utilizes a novel online fine-tuning approach and its systematic integration into the day-to-day machine operations. Our analysis emphasizes the process of NN model selection, demonstrates the superior performance of the NN-based method over traditional feedback methods, and examines the effectiveness and resilience of the new algorithm during user-operation scenarios. Published by the American Physical Society 2024

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Uncertainty quantification and sensitivity analysis of a nuclear thermal propulsion reactor startup sequence

The research presented in this article describes progress in applying stochastic methods, uncertainty quantification, parametric studies, and variance-based sensitivity analysis (also known as Sobol sensitivity analysis) to a full-core model of a nuclear thermal propulsion (NTP) system simulated via the radiation transport code Griffin to simulate neutronics. Our goal is to develop a reduced-order (surrogate) model that can be rapidly sampled with perturbations to multiple input parameters. In this NTP system, reactivity and power feedback affect the rotation of control drums (CDs), which is itself controlled by a hybrid proportional-integral-derivative (PID) controller actuated by the power demand and reactivity feedback from the numerical model. This model uses reactor kinetic feedback (mean generation time [Λ] and effective delayed neutron fraction [ β eff ] from a transient Griffin simulation executed via Griffin’s improved quasi-static solver to provide the kinetic parameters) as inputs to functions that control the CD rotation angle. By investigating numerous stochastic approaches, we developed a dual-purpose surrogate model of the NTP system, using polynomial regression in the Multiphysics Object-Oriented Simulation Environment (MOOSE) Stochastic Tools Module (STM). The trained model can be rapidly sampled while simultaneously perturbing various input parameters, such as coefficients on the PID control or temperature (directly affecting the neutron cross section). The surrogate model delivers accurate (within 5%) results at speeds orders of magnitude faster (minutes, not days of computational time) than the base model. Once the surrogate model has been trained, distributions of the uncertain parameters can be changed at will to investigate the effects of perturbing multiple inputs as well as the effects of these inputs on the model output. For example, coefficients used in the PID control system may vary due to some type of physical interference, or uncertainty may exist in the temperature of the neutron cross sections in various regions of the reactor. A distribution can be placed on these parameters, and operational boundaries can be determined. The goal of this work is to support development of an advanced control system for operating CDs in a functioning NTP system. This work is a scoping study of the MOOSE STM.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗
DOE OSTI2026

CTRL-STEER: Closed-Loop Neuron Activation Control in Vision-Language-Action Models

Vision-Language-Action (VLA) models enable test-time behavioral steering via neuron-level interventions, but existing methods use fixed strengths and operate in open loop. This static modulation fails under evolving task dynamics, leading to overcorrection, oscillations, and reduced task success—especially for temporal attributes like speed. We propose CTRL-STEER, a control-theoretic framework that casts activation steering as closed-loop feedback with adaptive, time-varying interventions. Instead of assuming neurons encode temporal concepts, we steer along motion-aligned residual directions and regulate intervention magnitude via feedback. We instantiate this with both PID and reinforcement learning controllers that jointly optimize concept adherence and task success. Experiments on fine-tuned OpenVLA policies across four LIBERO suites show improved stability and a better steering–success trade-off over fixed-coefficient baselines, without retraining the base model.

Babu, Abhijith [Florida International University, ↗
DOE OSTI2025

Employing MACS/ViBRANT as a Surrogate MARVEL Reactor for Startup Reactivity Tuning and Supervisory Control Processes

Advanced nuclear reactors are a key part of the future of nuclear energy both in the United States and globally. They offer unique benefits for various energy-demanding applications, including use in remote locations, compact size, modular manufacturing, remote monitoring, low and/or variable power rating operation, and reliance on novel technologies to enhance operational safety. To achieve economic feasibility, advanced reactors must significantly reduce their workforces in comparison with the current fleet. Achieving this reduction will occur through reducing staff workloads using technology to achieve autonomous or semi-autonomous operations, demonstrated by comprehensive testing and validation activities. These operations will require both software and hardware platforms during the design and testing phases. While simulations are useful during the design phase, their performance can significantly deviate during actual deployment on hardware. This report presents the outcomes of a collaborative technical initiative between the U.S. Department of Energy (DOE) Microreactor Program (MRP) and Advanced Sensors and Instrumentation (ASI) Program. The collaboration utilized the Microreactor Automated Control System (MACS) hardware platform to bridge the gap between theoretical reactor design and actual startup and control operations. Two key use cases were investigated: facilitating the startup testing period and demonstrating supervisory control. The first use case details the key Microreactor Applications Research Validation and Evaluation (MARVEL) reactor startup physics testing activities conducted using the MACS platform. These activities included drum worth measurements, shutdown margin assessment, temperature feedback analysis, and scram time evaluation, as well as unique testing that would apply to the MARVEL reactor to demonstrate the testing methodologies in a low-risk environment. The MACS platform, serving as a surrogate representation of the MARVEL reactor, proved instrumental in performing these tests. The exercise revealed aspects that led to optimized processes, refined hardware design, and enhanced base software capabilities. By maturing methods and technologies in this manner, the initiative promises to reduce wasted time in the actual on-site reactor deployment effort, thereby saving significant time and resources. The second use case focuses on the development and implementation of supervisory control methods aimed at managing core tilt, which can result from asymmetrical operations or manufacturing imperfections in fuel rods or reactivity control devices. A key objective was to assess and compare the use of artificial intelligence (AI) for supervisory control. The effort aimed to define the role of supervisory control to enhance performance without risking control instability. This effort explored three distinct approaches: rules-based (RB) methods, optimization techniques, and reinforcement learning (RL) algorithms. Each approach was evaluated for its ease of implementation, its usability, and its effectiveness in responding to asymmetries in neutron flux. Comparative analysis of these approaches provided valuable insights into their applicability and effectiveness, offering a robust framework for advanced reactor operations. Together, these two use cases highlight the potential of hardware test beds to help streamline the design, operation, and control of advanced nuclear reactors. This collaborative effort underscores the importance of continued innovation and experimentation in achieving the next generation of safe, reliable, and economically viable nuclear energy solutions.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Dynamically Learning Incentives for Load Control

As electrical generation becomes more distributed and volatile, and loads become more uncertain, controllability of distributed energy resources (DERs), regardless of their ownership status, will be necessary for grid reliability. Grid operators lack direct control over end-users' grid interactions, such as energy usage, but incentives can influence behavior -- for example, an end-user that receives a grid-driven incentive may adjust their consumption or expose relevant control variables in response. A key challenge in studying such incentives is the lack of data about human behavior, which usually motivates strong assumptions, such as distributional assumptions on compliance or rational utility-maximization. In this paper, we propose a general incentive mechanism in the form of a constrained optimization problem -- our approach is distinguished from prior work by modeling human behavior (e.g., reactions to an incentive) as an arbitrary unknown function. We propose feedback-based optimization algorithms to solve this problem that each leverage different amounts of information and/or measurements. We show that each converges to an asymptotically stable incentive with (near)-optimality guarantees given mild assumptions on the problem. Finally, we evaluate our proposed techniques in voltage regulation simulations on standard test beds. We test a variety of settings, including those that break assumptions required for theoretical convergence (e.g., convexity, smoothness) to capture realistic settings. In this evaluation, our proposed algorithms are able to find near-optimal incentives even when the reaction to an incentive is modeled by a theoretically difficult (yet realistic) function.

demand response↗
DOE OSTI2026

Impact of impurities on peeling–ballooning modes and turbulence in tokamak plasmas

This study investigates the impact of various impurity species on peeling–ballooning (PB) modes and microturbulence in tokamak plasmas through the extension of traditional two-fluid and gyro-landau-fluid (GLF) models. By incorporating finite Larmor radius (FLR) effects, the analysis provides a comprehensive understanding of impurity-driven impact and its interaction with plasma turbulence. Depending on charge state and local plasma conditions, heavy impurities may exhibit gyro-radii larger than those of main ions, which are captured in the extended GLF model presented. Following the presentation of modified two-fluid equations incorporating impurity effects, we systematically analyze the distinctions between impurity and main ion dynamics and their resultant feedback mechanisms on plasma behavior. Derivation of the linear dispersion relation enables quantification of impurity-mediated modifications to: plasma vorticity, diamagnetic drift and gyroviscous effects, electron Hall physics, and FLR effects. BOUT++ – based linear simulations corroborate this formalism, demonstrating systematic stabilization of PB modes upon impurity seeding. And then operational implications for practical impurity control strategies in tokamak devices are proposed. The results underscore the necessity of impurity management to maintain stability and optimize plasma confinement, with specific focus on how FLR effects contribute to transport dynamics. This work paves the way for enhanced modeling and simulation efforts, supporting the development of strategies to control impurity-induced turbulence and improve overall reactor performance.

BOUT++ simulation↗
DOE OSTI2025

Grid Forming Control Tuning for a Hybrid Inverter-Based Resource Power Plant

A hybrid inverter-based resource (IBR) power plant consists of grid-following (GFL) and grid-forming inverter-based resources (GFM-IBR) connected in parallel. Here, this research focuses on how to design and tune GFM's control parameters to ensure stable operation of the hybrid power plant for weak and strong grid conditions. We consider two design cases: one where the GFL-IBR does not provide frequency support, and one where it does. It is found that the GFM's power-frequency synchronizing system can lose stability when the power-frequency droop constant is large and/or the grid is strong. Additionally, if the GFL has its frequency support enabled, oscillation stability worsens. To explain the mechanism of the interactions, we construct a feedback system for the synchronizing loop, which consists of the GFM's power-frequency droop control that generates the GFM's synchronizing angle, the GFL's phase-locked loop that measures the voltage phase angle, the GFL's frequency-power control that generates its power order, and the rest of the system. The feedback system is effective in illustrating the potential stability risks. Successful design ensures that the hybrid power plant can operate smoothly and ride through grid disturbances.

feedback systems↗
DOE OSTI2025

Advancing \textit{otsdaq}: Enhancements for Usability, Accuracy, and Robustness

High-energy physics (HEP) experiments require data acquisition (DAQ) systems that can orchestrate complex detector operations, high data throughput, and responsive, real-time feedback to operators. Traditional DAQ stacks, which are often bespoke, command-line driven and highly specific, impose large learning curves on users. The Off-The-Shelf Data Acquisition (\textit{otsdaq}) framework was created to address these issues by offering a highly customizable and scalable browser-based ’desktop’ environment, in which experiment-specific control and monitoring applications can be easily deployed and integrated. Although the initial development of the \textit{otsdaq} software was aimed at the Fermilab Test Beam Facility, \textit{otsdaq} is now being leveraged for broader deployment, including the upcoming Mu2e experiment, where real-time monitoring of field-programmable gate array (FPGA)-based Data Transfer Controllers (DTCs), Clock and Fanout (CFO) boards, and several other subsystems are critical. We contribute a set of targeted improvements to \textit{otsdaq}: bitmap visualization functionality for configured data, improved and corrected delta-based DTC throughput metrics, version control (VC)-backed source navigation for console messages, custom navigation hooks to eliminate disruptive user interface glitches, and copy-to-clipboard support for macro execution history. These changes improve usability, reduce debugging time, and increase accuracy in performance data as Mu2e moves toward commissioning.

Mohammed, A. [Unlisted, US]↗
DOE OSTI2025

Baseband Digital Network Analyzer Upgrade for LLRF Controllers

Digital Network Analyzers (DNA) have been implemented in many Low-Level Radio Frequency (LLRF) systems, notably NSLS-II and CERN, to help tune feedback loops. DNA characterizes feedback loops by measuring the frequency-dependent magnitude and phase transfer functions. It enables the measurement of open loop gains, gain/phase margins, and loop delays to help fine-tune feedback loops. An FPGA-based DNA has been developed and integrated into the current Relativistic Heavy Ion Collider (RHIC) LLRF infrastructure. Its performance has been tested with an implementation of one-turn delay feedback (OTFB) on the bench to maximize gain and stability. The DNA has been used to characterize a RHIC 28 MHz cavity in a RHIC Accelerator Physics Experiment (APEX) to test transient beam loading compensation strategies.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Dynamic modelling and control strategy of a temperature-driven metal hydride cooling system for buildings

A temperature-driven coupled metal hydride (MH) based thermal energy storage (TES) system can allow to shave and shift the peak energy demand in buildings. The high energy density and long-term (seasonal) energy storage capability are its major advantages over other energy storage methods. The dynamic nature of the MH operation, however, requires controlled hydrogen transfer between the coupled MHs at a rate needed to meet the building's transient load. While temperature-driven MH systems are studied in the literature, their application in buildings and control are scarcely reported. Here, this paper presents a control-based dynamic modeling of the temperature-driven coupled MH-TES system for building cooling applications. The dynamic model is developed in MATLAB(R) Simulink environment, considering the thermodynamic and kinetic behaviors of the MH systems. Based on a preliminary analysis of a property database of over 337 hydrides, we select around 1600 MH pairs suitable for building cooling applications. Each of these MH pairs is studied for their performance using the dynamic model, and among all, Zr 0.76 Ti 0.24 Ni 1.16 Mn 0.63 V 0.14 Fe 0.18 -Ti 0.85 Zr 0.15 Cr 1.2 Mn 0.8 MH pair showed fast dynamics along with high coefficient of performance (COP) of 0.71. A parametric investigation is performed on this MH pair to understand the effect of operating temperatures. Finally, three proportional-integral (PI) feedback controllers are investigated to regulate the temperature, pressure and mass exchange between the coupled MH pairs. The developed PI controller is sufficiently capable of rejecting the signal noise from the hydrogen flow and internal heat exchange processes with root mean square error of 5.78 W between reference and actual cooling load.

08 HYDROGEN↗
DOE OSTI2026

Microsecond-latency feedback at a particle accelerator by online reinforcement learning on hardware

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution due to their ability to dynamically adapt to changing environments and consider delayed consequences. In many real-world applications, RL policies must produce actions in real time, often within microseconds to milliseconds, imposing significant constraints on system latency and computational overhead that conventional machine learning libraries are not designed to handle. To control phenomena in real time at these timescales, RL needs to be deployed on-the-edge, namely on dedicated hardware located near the system it controls, without relying on a host CPU or cloud-based inference. In this work we present the design and deployment of an experience accumulator system in a particle accelerator. In this system, deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of phenomena like beam instabilities. The training uses the collected data offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator, a synchrotron light source, where the system was used to control artificially induced horizontal betatron oscillations in real-time, with a control loop period of just 2.7 μs. The results showed a performance comparable to the commercial feedback system available at the accelerator, demonstrating the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, a seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.

FPGA↗
DOE OSTI2024

Promoting Sustainable Transportation Modes: A Systematic Review of Behavior-Change Strategies

In previous studies, many travel-behavior-change strategies often relied on single behavior determinants or psychological theories, overlooking the incorporation of sociopsychological theories for guidance in their design. Integrating these theories could offer consistent guidance for program developers and enhance intervention effectiveness. This paper systematically reviews interventions targeting travel-behavior change, with a focus on self-determination theory and its principles of satisfying individuals’ competence, autonomy, and relatedness needs for enacting change. Additionally, experiment design methods, including randomized controlled trials and quasi-experimental designs, are reviewed and discussed. Key findings highlight the effectiveness of personalized interventions and integrating feedback with goal-setting strategies. Given the limited direct references to sociopsychological theories in existing studies, we explore relevant sociopsychological theories applicable to travel-behavior-change programs to provide examples of how strategies could be designed based on them. This review contributes valuable insights into the development of strategies for changing travel behavior, offering a theoretical framework for researchers and practitioners to guide intervention design, experimentation, and evaluation. In conclusion, leveraging these theories not only facilitates reproducibility but also provides a standardized approach for transportation demand management program developers.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Hydrology controls thermokarst and alters carbon cycling and methane emissions in peatlands near the southern limit of permafrost

Permafrost peatlands store vast amounts of frozen carbon across northern landscapes. When ground ice melts, surface subsidence produces thermokarst landforms that expand wetlands at the edges of permafrost plateaus. Thermokarst represents an accelerating climate feedback, but uncertainties remain about how ground ice, hydrology, and vegetation interact to shape landscape change and carbon fluxes. We extended the process-based model ecosys to simulate thermokarst dynamics in laterally coupled 2D transects at a well-characterized boreal peatland site in Canada’s Northwest Territories. After benchmarking against site observations, we varied ground ice content and hydrologic boundary conditions across ranges typical near the southern permafrost limit. Simulations revealed distinct degradation regimes governed by the elevation difference between the frost table and the external water table. Rates of lateral retreat, the thaw-driven encroachment of wetlands into adjacent plateaus, ranged from 0 to >2 m yr −1 under identical weather forcing, consistent with observations and highlighting the strong role of WT and ground ice. Simulated vegetation dynamics indicate that black spruce mortality cannot be explained by anoxia alone, pointing to additional stressors such as root damage, pathogens, or physical destabilization. Despite large hydrologic shifts, net ecosystem CO 2 exchange remained a slight sink after collapse, while methane (CH 4 ) emissions rose by one to two orders of magnitude. As a result, lateral retreat substantially increases the greenhouse warming potential of permafrost peatlands (1.7 million km 2 in area), with simulated emissions of 0.1–10 Mt CO 2 -eq decade −1 depending on hydrology and retreat rates. These results underscore the need to account for both ground ice and hydrologic dynamics when assessing thermokarst-driven climate feedbacks.

carbon cycling↗
DOE OSTI2025

Nonvariational ADAPT algorithm for quantum simulations

We explore a nonvariational quantum state preparation approach combined with the ADAPT operator selection strategy in the application of preparing the ground state of a desired target Hamiltonian. In this algorithm, energy gradient measurements determine both the operators and the gate parameters in the quantum circuit construction. We compare this nonvariational algorithm with ADAPT-VQE and with feedback-based quantum algorithms in terms of the rate of energy reduction, the circuit depth, and the measurement cost in molecular simulation. We find that, despite using deeper circuits, this new algorithm reaches chemical accuracy at a similar measurement cost to ADAPT-VQE. Since it does not rely on a classical optimization subroutine, it may provide robustness against circuit parameter errors due to imperfect control or gate synthesis.

Tang'S, Ho Lun [Virginia Polytechnic Inst. and Sta↗
DOE OSTI2025

Closed-loop control of active nematic flows

Stabilizing and shaping autonomous flows of active fluids is a fundamental challenge and a prerequisite for applications. We embed a light-responsive microtubule-based nematic in a proportional-integral control loop that adjusts the applied light intensity in response to real-time measurements of the spatially averaged flow speed. The self-regulating hardware/software/wetware system maintains a target flow speed against external or internal perturbations, including protein aging and aggregation, sample-to-sample variability, and temperature variation. Varying the controller’s gains reveals antagonistic roles between feedback and intrinsic processes, leading to nontrivial dynamics observed in fluctuation spectra. In particular, oscillations emerge from the interplay between the controller, motor binding kinetics, and active hydrodynamic relaxation. Accounting for the underlying binding timescale, our coarse-grained model and nematohydrodynamics simulations corroborate these observations. This work provides insight into the coupled dynamics of controlled active matter, laying the foundation for spatiotemporal patterning of active stress to generate and stabilize new dynamical configurations.

Nishiyama, Katsu [Brandeis Univ., Waltham, MA (Uni↗
DOE OSTI2025

Multiphysics Modeling of Microreactors with NEAMS codes, and Validation Based on KRUSTY Reactivity Insertion

The NEAMS Multiphysics Applications team continues to assess code usability and functionality for microreactor design and safety analyses, while demonstrating that NEAMS tools capture both steady-state and transient behavior across distinct microreactor concepts. In FY2025, the team advanced full-core, high-fidelity, multiphysics models that solve more complex problems and strengthen verification/validation for several microreactor systems: heat-pipe microreactor (HPMR), gas-cooled microreactor (GCMR), and the KRUSTY experiment. These models employ the MOOSE MultiApp/Transfers architecture with Griffin for neutronics, BISON for heat conduction/thermomechanics, Sockeye for heat pipes, SAM/THM for coolant channels and loops, and SWIFT for hydride behavior, with meshes generated via the MOOSE Reactor Module. The graphite models available in the Grizzly code were also investigated for future analyses. For the HPMR, a Na-HPMR variant was constructed to align with recently validated heat-pipe experiments and Sockeye’s LCVF capability, enabling mechanistic heat-pipe transients and startup modeling. The Na-HPMR will serve as the primary model for HPMR investigations in upcoming tasks. The load-following and single heat-pipe failure scenarios (Griffin/BISON/Sockeye), which were previously modeled for the K-HPMR, were replicated for the Na-HPMR, showing strong negative temperature feedback and highly localized thermal effects, respectively, while the startup case captured vapor-front progression and heat-removal activation. Solid mechanics was added to the previously built K-HPMR full-core model in BISON, showing minimal impact on steady-state reactivity yet enabling stress-field predictions that prepare the path for full-core TRISO performance analyses. For the GCMR, automated steady-state and four transient scenarios were executed using Griffin/BISON/SAM/SWIFT. Results confirm robust inherent safety: power collapses promptly in loss-of-cooling events, the inlet-temperature drop settles to a new equilibrium, and a single-channel blockage yields only a ~30 K local fuel-temperature rise with <0.4% power decrease. SWIFT-predicted hydrogen redistribution affects reactivity during both steady-state and transient conditions, underscoring its importance. A Brayton-cycle balance of plant (BOP) model in SAM/THM demonstrated stable startup behavior, and xenon-driven reactivity during load following was analyzed. To improve TRISO-compact temperature fidelity, a fast multiscale Heat Source Decomposition (HSD) treatment was implemented. Against heterogeneous benchmarks, HSD reduces underprediction of kernel temperatures and lowers predicted peak powers in reactivity-insertion transients compared to previous homogenized models. KRUSTY warm-critical validation progressed from FY2024 baselines: the 15Ȼ insertion shows excellent agreement in peak power (~2% high) and temperature trends, and the 30Ȼ case was automated via a feedback controller that maintained power near 3 kW for ~150 s with close agreement to data. The successful modeling of the warm critical tests has laid a strong foundation for simulating more complex nuclear system tests in the years ahead. Throughout FY2025, developer feedback was provided (e.g., MOOSE batch mesh generation, distributed pre-split meshes, Griffin sweeper on displaced meshes), several new models were contributed to the Virtual Test Bed, and an OECD-NEA WPRS multiphysics benchmark based on the HPMR was initiated to enable broader cross-comparison and best-practice development with the nuclear community at large.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

ORCHID: Orchestrated Retrieval-Augmented Classification of High-Risk Property with Intelligent Decision-Making

High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We propose ORCHID, a modular agentic framework for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy based outputs that can be audited. Small cooperating agents—retrieval, description refiner, classifier, validator, and feedback logger—coordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an "Item to Evidence to Decision" loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts—illustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗