Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “automated experiments”

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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Evaluating Automated Face Identity-Masking Methods with Human Perception and a Deep Convolutional Neural Network

Face de-identification (or “masking”) algorithms have been developed in response to the prevalent use of video recordings in public places. Here, we evaluated the success of face identity masking for human perceivers and a deep convolutional neural network (DCNN). Eight de-identification algorithms were applied to videos of drivers’ faces, while they actively operated a motor vehicle. These masks were pre-selected to be applicable to low-quality video and to maintain coarse information about facial actions. Humans studied high-resolution images to learn driver identities and were tested on their recognition of active drivers in low-resolution videos. Faces in the videos were either unmasked or were masked by one of the eight algorithms. When participants were tested immediately after learning (Experiment 1), all masks reduced identification, with six of eight masks reducing identification to extremely poor performance. In a second experiment, two of the most effective masks were tested after a delay of 7 or 28 days. The delay did not further reduce identification of the masked faces. In all masked conditions, participants maintained stringent decision criteria, with low confidence in recognition, further indicating the effectiveness of the masks. Next, the DCNN performed an identity-matching task between high-resolution images and masked videos—a task analogous to that done by humans. The pattern of accuracy for the DCNN mirrored some, but not all, aspects of human performance, highlighting the need to test the effectiveness of identity masking for both humans and machines. The DCNN was also tested on its ability to match identity between masked and unmasked versions of the same video, based only on the face. DCNN performance for the eight masks offers insight into the nature of the information in faces that is coded in these networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

A review of machine learning in building load prediction

The surge of machine learning in recent years has been empowering engineer modeling in various fields. The decreasing hardware cost, increasing data accessibility, and advances of building automation system (BAS) allow the collection and storage of a significant amount of building operation data. The two facts provide great opportunities of applying machine learning to building energy systems modeling and analysis. There are a great number of research papers on this topic but there lacks a comprehensive and general review to summarize the current development, limitations, gaps and future trend. In this review paper series, machine learning techniques in building energy system modeling and analysis are reviewed under the organization and logic of the machine learning definition by Tom M. Mitchell: a computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. This paper is the first part of the review paper series, which focuses on building load prediction. First, the applications of building load prediction model (task T) are reviewed. Then, the modeling algorithms improving machine learning performance and accuracy (performance P) are reviewed. At the same time, the literature on the data perspective for modeling (experience E), including data engineering from sensors level to data level, pre-processing, feature extraction and selection, is reviewed. Finally, what is well-studied and what is lacking but with great potential are concluded; the gaps between present and future utilization of machine learning techniques are identified; the future trend and development are also predicted. The target readers of this paper are not only researchers from the building side who can get exposed to cutting edge machine learning tools, but also those from machine learning side who can understand the potential and challenge to apply machine learning in buildings.

Liang, Zhang↗
DOE OSTI2021

OBO Foundry in 2021: operationalizing open data principles to evaluate ontologies

Biological ontologies are used to organize, curate and interpret the vast quantities of data arising from biological experiments. While this works well when using a single ontology, integrating multiple ontologies can be problematic, as they are developed independently, which can lead to incompatibilities. The Open Biological and Biomedical Ontologies (OBO) Foundry was created to address this by facilitating the development, harmonization, application and sharing of ontologies, guided by a set of overarching principles. One challenge in reaching these goals was that the OBO principles were not originally encoded in a precise fashion, and interpretation was subjective. Here, we show how we have addressed this by formally encoding the OBO principles as operational rules and implementing a suite of automated validation checks and a dashboard for objectively evaluating each ontology’s compliance with each principle. This entailed a substantial effort to curate metadata across all ontologies and to coordinate with individual stakeholders. We have applied these checks across the full OBO suite of ontologies, revealing areas where individual ontologies require changes to conform to our principles. Our work demonstrates how a sizable, federated community can be organized and evaluated on objective criteria that help improve overall quality and interoperability, which is vital for the sustenance of the OBO project and towards the overall goals of making data Findable, Accessible, Interoperable, and Reusable (FAIR).

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2024

ML based control systems for nuclear physics experiments

The Experimental Physics Software and Computing Infrastructure (EPSCI) group at Jefferson Lab is leading the use of machine learning (ML) to enhance control systems in nuclear physics experiments. Collaborating closely with domain experts and data scientists, we have developed an ML-based control system that uses a Gaussian process to dynamically adjust the high voltage of the GlueX Central Drift Chamber. This results in stable detector performance by adapting to environmental changes, thereby reducing the offline calibration effort. Furthermore, we are developing ML-driven systems for optimizing the polarization of photon beams and polarized cryotargets. These systems will maintain the optimal microwave frequency in cryogenic targets and make real-time adjustments to diamond radiators for polarized photon sources, tasks traditionally handled by human operators. By automating these functions, we aim to optimize the polarization, reduce downtime, and minimize human error. This talk will highlight the development of reliable ML-based control systems and the policies to ensure they are both effective and trustworthy.

Jeske, Torri↗
DOE OSTI2026

Machine Learning-Based Anomaly Detection for PMT Data Quality Monitoring in the SBN and DUNE

Maintaining high-quality detector data is essential for achieving the scientific objectives of the Short-Baseline Neutrino (SBN) Program at Fermilab. Current data quality monitoring (DQM) procedures rely primarily on threshold-based metrics and manual inspection of detector monitoring plots, making the detection of subtle or gradually developing anomalies both time-consuming and dependent on expert interpretation. This project developed and evaluated a machine-learning workflow for automatically identifying anomalous photomultiplier tube (PMT) channels in the Short-Baseline Near Detector (SBND) using optical-hit amplitude data. A Python-based analysis program was developed to process ROOT files, extract statistical features describing individual PMT amplitude distributions, and generate feature vectors for anomaly detection. These features were used to train an Isolation Forest model using data representing normal detector operation. The trained model was subsequently applied to independent detector runs to identify channels exhibiting statistically unusual behavior relative to the learned reference response. To support expert interpretation, the workflow generated complementary diagnostic products, including anomaly score distributions, normalized amplitude comparisons, decision-tree visualizations, and principal component analysis (PCA) projections. This project demonstrated the feasibility of integrating unsupervised machine learning into detector data-quality monitoring and developed a complete workflow for automated PMT performance assessment to aid expert-driven review. Beyond its technical contributions, the VFP appointment fostered a research collaboration between Aurora University and Fermilab and provided direct workforce development benefits by training the visiting faculty member in detector-scale machine-learning methods that are now being incorporated into undergraduate coursework and research. The methodology developed here provides a foundation for future applications to ProtoDUNE and other liquid argon time projection chamber (LArTPC) detectors, contributing to ongoing efforts to improve detector reliability, reduce manual monitoring requirements, and enable scalable data quality monitoring for future large-scale neutrino experiments, including the Deep Underground Neutrino Experiment (DUNE).

Colón Santana, Juan A. [Unlisted, US, IL]↗
DOE OSTI2021

High Flux Isotope Reactor Low-Enriched Uranium Low Density Silicide Fuel Design Parameters

High Flux Isotope Reactor (HFIR) highly enriched uranium (HEU) to low-enriched uranium (LEU) conversion activities are ongoing as part of the Department of Energy (DOE) National Nuclear Security Administration (NNSA)’s nuclear nonproliferation mission. Design activities studying the conversion of HFIR from HEU to LEU fuel explored different fuel design features and shapes with a low density uranium-silicide dispersion (U 3 Si 2 -Al) fuel, which has a uranium density of 4.8 gU/cm 3 . The goal of these studies is to generate several HFIR LEU fuel designs of varying fuel fabrication complexity that meet the current HEU performance metrics and safety requirements. The documented designs will serve as references for fuel fabrication and qualification activities. Recent advancements in modeling and simulation tools enable quick prototyping of fuel designs. Shift, a Monte Carlo neutron transport and depletion tool optimized for high-performance computing (HPC) architectures, is used for efficient fuel cycle and performance metrics calculations. The HFIR Steady State Heat Transfer Code (HSSHTC) is used to vet the thermal safety margin. Also, a new automation tool that connects all fuel design analysis steps, named Python HFIR Analysis and Measurement Engine (PHAME), has been developed to expedite the design study in an efficient and reproducible manner. Leveraging these tools, several candidate fuel designs were selected for varying fabrication complexity. This report provides design feature details for four selected HFIR LEU low density U 3 Si 2 -Al fuel designs and their corresponding performance and safety metrics. Nominal, best-estimate design parameters and irradiation conditions, including fission rate densities, power densities, heat fluxes, and cumulative fission densities are provided for candidate fuel designs relevant to framing irradiation experiments to support fuel qualification efforts. Simulations show that the low density U 3 Si 2 -Al, with design features to enhance safety, can meet HEU core performance metrics and safety requirements if the reactor power is increased from 85 MW (HEU) to 95 MW (LEU) and if the active fuel length is increased from 50.80 cm (HEU) to 55.88 cm (LEU).

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Software Development for Data Visualization and Analysis of PN-Diodes & MOSFET Devices

The U.S. Department of Energy has a broad mission to ensure the nation’s security by addressing ongoing environmental challenges, developing novel energy production technologies, and mitigating nuclear security concerns. These efforts benefit from developing more effective semiconductor materials and devices. The research discussed in this report aims to further the development of these new electronics by improving implementations of vertical device structures, which offer theoretically better performance compared to lateral structures. Specifically, it reviews the background and development of a new and easy-to-use program for data processing and analysis from experiments run on vertical gallium nitride power devices. Current vertical structures fall short in critical performance metrics, such as On-Resistance and Breakdown Voltage, due to poor management of the device’s electric field. Junction termination extensions, or JTEs, are a field management technique that increases a device’s resilience to expected failure modes by controlling its surface electric fields. Each JTE design requires significant experimental validation, consisting of hundreds of tested devices, each outputting an enormous set of data points. The new software includes multiple methods of filtering large sets of device testing data to identify and remove flawed devices, automate device analyses, and provide statistical breakdowns for four metrics used to define the effectiveness of the JTE and the current carrying capacity of the device. These results can then be related back to fabrication techniques and device design, and in the future, be combined with processing simulations to further improve our understanding of the JTE mechanisms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Parametric and Sensitivity Analysis of a Steam Generator Model Using Python and Machine-Learning Tools

For this study, we used Python and machine-learning tools to perform a comprehensive parametric and sensitivity analysis on a steam generator (SG) model. (The Python model was based on a previously completed MATLAB framework for the Holtec SMR-160 SG.) We investigated the influence of various input parameters (e.g., heat transfer coefficient [HTC], Nusselt number, and heat exchanger effectiveness) on the system’s output. With machine-learning tools such as the Risk Analysis Virtual Environment (RAVEN), which was developed at Idaho National Laboratory, we were then able to perform an automated analysis of the SG inputs’ effect on the HTC. The analysis results give valuable insights into the performance and optimization of SG systems. We found the inlet mass flow rate (MFR) to have the greatest impact on the HTC, followed closely by the inlet temperature, and then pressure. Shifting of the input parameters causes the location of the maximum HTC along the SG length to change incrementally. The cold leg (CL) MFR was also found to impact the HTC magnitude as well as the location of the maximum HTC. At between 0.4–0.9 of the total SG length, the input parameters experience maximum impact on the HTC, leading us to suggest that sensors be efficiently placed on the SG so as to closely and effectively monitor thermal-hydraulic properties during reactor operation. We also found that the sensitivity data calculated manually agrees with the RAVEN – based data, confirming the same range of maximum sensitivity. However, the RAVEN-based analysis showed that cold leg pressure and hot leg temperature have a greater impact on the heat transfer coefficient than the mass flow rate, implying that a manual sensitivity study taking only two samples is not accurate.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2025

Packaging HEP Heterogeneous Mini-apps for Portable Benchmarking and Facility Evaluation on Modern HPCs

High Energy Physics (HEP) experiments are making increasing use of GPUs and GPU dominated High Performance Computer facilities. Both the software and hardware of these systems are rapidly evolving, creating challenges for experiments to make informed decisions as to where they wish to devote resources. In its first phase, the High Energy Physics Center for Computational Excellence (HEP-CCE) produced portable versions of a number of heterogeneous HEP mini-apps, such as p2r, FastCaloSim, Patatrack and the WireCell Toolkit, that exercise a broad range of GPU characteristics, enabling cross platform and facility benchmarking and evaluation. However, these miniapps still require a significant amount of manual intervention to deploy on a new facility. We present our work in developing turn-key deployments of these mini-apps, where by means of containerization and automated configuration and build techniques such as Spack, we are able to quickly test new hardware, software, environments and entire facilities with minimal user intervention, and then track performance metrics over time.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

Cryogenic Performance of the SPT-SLIM Receiver

The South Pole Telescope Shirokoff Line Intensity Mapper (SPT-SLIM) is a millimeter-wave line-intensity mapping experiment, deployed on the South Pole Telescope (SPT) during the 2024-2025 Austral Summer season. This pathfinder experiment serves to demonstrate the on-sky operation of multi-pixel on-chip spectrometer technology. We present on the cryogenic performance of the SPT-SLIM receiver for this Year 1 observing campaign. The SPT-SLIM receiver utilizes an Adiabatic Demagnetization Referigerator (ADR) for cooling the focal plane of superconducting filterbank spectrometers to a temperature of 150mK. We demonstrate stable thermal performance of the focal plane module during observing operations in line with thermal modelling, enabling a cryogenic operation efficiency above 80%. We also report on the receiver control system design utilizing the Observatory Control System (OCS) platform for automated cryogenic operation on the SPT.

Young, Matthew [Fermilab]↗
DOE OSTI2025

Design and Performance of the SPT-SLIM Receiver Cryostat

The South Pole Telescope Shirokoff Line Intensity Mapper (SPT-SLIM) is a millimeter-wavelength line-intensity mapping experiment, which was deployed on the South Pole Telescope (SPT) during the 2024-2025 Austral summer season. This pathfinder experiment serves to demonstrate the on-sky operation of multi-pixel on-chip spectrometer technology. We report on the cryogenic performance of the SPT-SLIM receiver for the first year of commissioning observations. The SPT-SLIM receiver utilizes an Adiabatic Demagnetization Refrigerator (ADR) for cooling the focal plane of superconducting filterbank spectrometers to a temperature of 150 mK. We demonstrate stable thermal performance of the focal plane module during observations consistent with thermal modeling, enabling a cryogenic operating efficiency above 80%. We also report on the receiver control system design utilizing the Observatory Control System (OCS) platform for automated cryogenic operation on the SPT.

Young, M. R. [Fermilab; Chicago U., KICP]↗
DOE OSTI2024

Modernizing the Legacy Fission Wire Measurement System for the Advanced Test Reactor-Critical Facility

Operational lifetime extensions of existing research reactors have emphasized the need for refurbishment, replacements, and upgrades to supporting equipment and instrumentation. The Advanced Test Reactor (ATR) at Idaho National Laboratory (INL), which entered service in 1967, has recently completed the sixth core internals change-out and has scheduled operations until at least 2040. Reactor maintenance and operational risk management is critically important in the research reactor community, however supporting measurement systems sometimes get overlooked when maintenance is planned. The Fission Wire Measurement System (FWMS) is a custom measurement system designed in the 1960s to measure the beta-particle activity of irradiated uranium-aluminum fission wires. This measurement is conducted to determine the fission rate profile of the Advanced Reactor Test Critical (ATR-C) facility. The ATR-C is an open-pool, low-power test reactor that was purpose driven to resemble ATR and is used to qualify experiment configurations and verify core models prior to full-power experiment irradiations in ATR. A power distribution measurement in ATR-C uses uranium-aluminum wires that are distributed throughout the ATR-C core to validate simulation and modeling results. These measurements require 340 to 1500 wires to be irradiated and measured within a 12-hour window. The activity of the wires is measured in the required time with the FWMS, which was put into service in 1965 at the Radiation Measurements Laboratory (RML). The system consists of 4 measurement channels and one reference channel, each with a 2-pi proportional gas flow detector and the measurement channels each have an automated sample changer. This legacy system is crucial to the continued operations of ATR and has undergone some minor hardware upgrades since 1965, however the system presently relies on custom control boards, custom gas ion chambers, analog amplifiers/discriminators, and a user interface (UI) for the system written in outdated code. Much of the equipment and software is custom with no commercial replacements or support and limited documentation. The existing control software requires an operating system that is no longer supported, creating more vulnerabilities to continued operations. A project is underway with a third-party vendor to design, build, and document a new control and data acquisition system (CDAS) for the FWMS. The new upgrade will replace the control system, computer, UI, sample changer motors, and main power supply while maintaining the interface with existing detector hardware. The upgraded system will be operated in parallel with the current hardware and software to conduct validation testing. This equipment upgrade demonstrates the commitment at ATR to ensuring successful operations and potential future research reactors at INL.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2023

Simulating Catalysis with Realistic Pellet Geometries Using Mesoflow: A Case Study of Catalytic Propane Dehydrogenation

We present a case study of catalytic propane dehydrogenation with our open-source multiphysics solver, Mesoflow. The solver was developed to simulate reactive flow coupled to heterogeneous catalytic reactions and deactivation in the context of complex, mesoscale geometry. The method leverages cartesian block-structured adaptive mesh refinement to capture realistic catalyst microstructural features acquired directly from X-ray computed tomography data. A kinetic model for propane dehydrogenation and catalyst deactivation was developed based on temporal analysis of products (TAP) reactor experiments. The TAP reactor experiments allow for precise characterization of intrinsic kinetic reaction steps which are implemented into Mesoflow simulations to model the spatial and temporal evolution of reactants, products, and catalyst active sites. The short-term and long-term deactivation behavior is studied by using XCT data collected from fresh and aged catalyst pellets, which exhibit different microstructural features. This study employs time-splitting algorithms to connect disparate reaction and flow timescales, enabling the simulations to achieve realistic deactivation timescales on the order of minutes while the flow time-scales for small particles (100 microns) are several milliseconds. We also introduce a flexible automated python script that writes the necessary files to construct a Mesoflow simulation from user-created chemical mechanisms. We will also introduce a few new features that are added to Mesoflow such as higher order schemes, implicit chemistry integrators and the ability to run on AMD and NVIDIA graphics-processing-units.

AMReX↗
DOE OSTI2025

Packaging HEP Heterogeneous Mini-apps for Portable Benchmarking and Facility Evaluation on Modern HPCs

High Energy Physics (HEP) experiments are making increasing use of GPUs and GPU dominated High Performance Computer facilities. Both the software and hardware of these systems are rapidly evolving, creating challenges for experiments to make informed decisions as to where they wish to devote resources. In its first phase, the High Energy Physics Center for Computational Excellence (HEP-CCE) produced portable versions of a number of heterogeneous HEP mini-apps, such as \ptor, FastCaloSim, Patatrack and the WireCell Toolkit, that exercise a broad range of GPU characteristics, enabling cross platform and facility benchmarking and evaluation. However, these mini-apps still require a significant amount of manual intervention to deploy on a new facility. We present our work in developing turn-key deployments of these mini-apps, where by means of containerization and automated configuration and build techniques such as Spack, we are able to quickly test new hardware, software, environments and entire facilities with minimal user intervention, and then track performance metrics over time.

Atif, Mohammad [Brookhaven] (ORCID:000000026889770↗
DOE OSTI2022

Data Mining – Image Analysis of Radiography for Zr Redistribution

The research effort described in this report represents a first attempt to investigate the radial redistribution of Zr in ternary fuel alloys U-xPu-10Zr (x = 0, 8, 19) irradiated in the in-reactor fuel experiments during the operation of the U.S. Department of Energy’s (DOE’s) Experimental Breeder Reactor II (EBR-II) at Idaho National Laboratory (INL) using methods of image processing on post-irradiation neutron radiographs. Approximately 130,000 metal fuel pins were irradiated in EBR-II during its 30 years of operation to develop and characterize existing and prospective fuels. For many of the metal fuel irradiation experiments, neutron radiography imaging was performed historically now allowing application of modern image analysis techniques to characterize fuel behavior, such as fuel swelling, fluff formation, and now, fuel alloy constituent redistribution. The redistribution of fuel components depends on the temperature field, radially, within the fuel. Specifically, Zr is expected to redistribute radially towards the center of the pin, as well as towards the outer zones. Currently, direct imaging of a pin cross-section through optical methods or scanning electron microscopy (SEM) is used to study the constituents’ redistribution, which is very time-consuming and can only be applied to a limited number of pins. An automated image processing technique allowing for the investigation of fuel radial redistribution zones would significantly accelerate data analysis. In general, if the fuel temperature is hot enough, three redistribution zones are expected, corresponding to the main fuel components (e.g., U, Pu, Zr). While more assessment will be performed in fiscal year (FY)-2023, it seems possible to differentiate the pins according to their fuel composition using image analysis techniques on neutron radiographs of metallic fuel pins based on the analysis to date.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Integration and Demonstration of Monitoring, Modeling, and Prediction of DV-1 Amendment Performance at the Bench Scale: DV-1 Amendment Demonstration

During fiscal years 2024 and 2025, the U.S. Department of Energy’s Hanford Field Office commissioned Pacific Northwest National Laboratory to conduct applied research aimed at reducing the cost, time, and uncertainty associated with in situ treatment of vadose zone contaminants at the Hanford Site. This report outlines the integration of three key research efforts into a meso-scale demonstration designed to advance field-scale solutions that aim to (1) optimize the delivery of chemical amendments to contaminated soils, (2) reduce uncertainty in amendment delivery performance assessment using advanced monitoring techniques, and (3) provide real-time insights into when and where amendment-induced precipitation reactions occur in the subsurface. To achieve these objectives, the tank-scale (~ 1 cubic meter) Geophysical Imaging of Flow and Transport (GIFT) system was developed. GIFT enables experimental testing of amendment delivery while incorporating automated multi-modal monitoring approaches, including pressure measurements, direct fluid sampling, and remote time-lapse geophysical imaging. The data generated from these monitoring techniques will serve as inputs for a generative artificial-intelligence-driven digital twin – a numerical simulation model designed to honor observed data while quantifying uncertainty in simulation accuracy. Using this simulator, researchers will refine an amendment injection strategy to maximize delivery efficiency within a low-permeability soil zone. Monitoring data will be interpreted through simulated outputs to enhance understanding of the injection process. The efficacy of this integrated approach will be evaluated through direct sampling at the conclusion of the experiment.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Neural message-passing for objective-based uncertainty quantification and optimal experimental design

Various real-world scientific applications involve the mathematical modeling of complex uncertain systems with numerous unknown parameters. Accurate parameter estimation is often practically infeasible in such systems, as the available training data may be insufficient and the cost of acquiring additional data may be high. In such cases, based on a Bayesian paradigm, we can design robust operators retaining the best overall performance across all possible models and design optimal experiments that can effectively reduce uncertainty to enhance the performance of such operators maximally. While objective-based uncertainty quantification (objective-UQ) based on MOCU (mean objective cost of uncertainty) provides an effective means for quantifying uncertainty in complex systems, the high computational cost of estimating MOCU has been a challenge in applying it to real-world scientific/engineering problems. In this work, we propose a novel scheme to reduce the computational cost for objective-UQ via MOCU based on a data-driven approach. We adopt a neural message-passing model for surrogate modeling, incorporating a novel axiomatic constraint loss that penalizes an increase in the estimated system uncertainty. As an illustrative example, we consider the optimal experimental design (OED) problem for uncertain Kuramoto models, where the goal is to predict the experiments that can most effectively enhance robust synchronization performance through uncertainty reduction. We show that our proposed approach can accelerate MOCU-based OED by four to five orders of magnitude, without any visible performance loss compared to the state-of-the-art. The proposed approach applies to general OED tasks, beyond the Kuramoto model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation

The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs approaches expert-authored reference procedures on the benchmark (F1-score > 0.89) on challenging multi-plate syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗