Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “intelligence”

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 1,315 records · Page 73

Intelligent uranium fission converter for neutron production on the periphery of the nuclear reactor core (MARIA reactor in Swierk - Poland)

The multipurpose, high flux research reactor MARIA in Otwock - Swierk is an open-pool type, water and beryllium moderated and graphite reflected. There are two not occupied experimental H1 and H2 horizontal channels with complex of empty rooms beside them. Making use of these two channels is not in conflict with other research or commercial employing channels. They can work simultaneously, moreover commercial channels covers the cost of reactor working. Such conditions give beneficial possibility of creating epithermal neutron stand for researches in various field at the horizontal channel H2 of MARIA reactor (co-organization of research at H1 channel is additionally planned). At the front of experimental channels the neutron flux is strongly thermalized - neutrons with energies above 0.625 eV constitute only ∼2% of the total flux. This thermalized neutron flux will be used to achieve high flux of epithermal neutrons at the level of 2x10{sup 9} n cm{sup -2}s{sup -1} by uranium neutron converter (fast neutron production - conversion of reactor core thermal neutrons to fast neutrons - and then filtering, moderating and finally cutting of unwanted gamma radiation). The intelligent converter will be placed in the reactor pool, near the front of the H2 channel. It will replace one graphite block at the periphery of MARIA graphite reflector. The converter will consist of 20 fuel elements - low enriched uranium plates. A fuel plate will be a part which will measure 110 mm wide by 380 mm long and will consist of a thin layer of uranium sealed between two aluminium plates. These plates, once assembled, form the fuel element used in converter. The plates will be positioned vertically. There are several important requirements which should be taken into account at the converter design stage: -maximum efficiency of the converter for neutrons conversion, -cooling of the converter need to be integrated with the cooling circuit of the reactor pool and if needed equipped with self-cooling system (enhanced comparing to the cooling properties inherent with regular rector pool water flows), -proper cooling conditions can be ensured by an appropriate water flow, so the resistance to flow has to be optimised, -the requirement of the minimum resistance to water flow leads to the openwork design of the fuel element separator, which, on the other hand, has to be strong enough to ensure the needed strength for mechanical load due to the fuel weight and forces associated with the water flow, -the possibility of changing beam and flux qualities by rotating the converter or repositioning the converter plates by moving or replacing with another materials. In order to minimize the neutron activation of the fuel in the converter, the possibility was predicted to remove the converter and to replace it with an aluminium dummy for the time when the beam at the channel H2 is not used. This means that both, the converter and the dummy, have to be easily removable from the converter socket. There has to be also the place in the water pool, near the research stand or in technological pool, where the converter can be safely stored (this place have to be proper for operation with plates i.e. changing amount of plates). Thermal and neutron load of the fuel plates in the converter will be inhomogeneous. In order to equalize these loads, the converter should be designed in such way that it would be possible to change the order of fuel plates. Moreover replacing the amount of the plates gives the opportunity to obtain different fluxes of neutrons (quantitatively and qualitatively i.e. energetically). The project of the converter is based on Monte Carlo calculation concerning neutron production and on Computational Fluid Dynamics (CFD) i.e. modelling of converter for thermodynamical aspects. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Anomalous behavior detection by an artificial intelligence-enabled system with multiple correlated sensors

Multi-metric artificial intelligence (AI)/machine learning (ML) models for detection of anomalous behavior of a machine/system are disclosed. The multi-metric AI/ML models are configured to detect anomalous behavior of systems having multiple sensors that measure correlated sensor metrics such as coolant distribution units (CDUs). The multi-metric AI/ML models perform the anomalous system behavior detection in a manner that enables both a reduction in the amount of sensor instrumentation needed to monitor the system's operational behavior as well as a corresponding reduction in the complexity of the firmware that controls the sensor instrumentation. As such, AI-enabled systems and corresponding methods for anomalous behavior detection disclosed herein offer a technical solution to the technical problem of increased failure rates of existing multi-sensor systems, which is caused by the presence of redundant sensor instrumentation that necessitates complex firmware for controlling the sensor instrumentation.

Serebryakov, Sergey↗

Development of a Smart Signal Detection Method for Cyclic Voltammetry via Artificial Neural Intelligence

The electrorefiner (ER) is the heart of pyroprocessing technology which is a high-temperature method for separating uranium from Used Nuclear Fuel (UNF). It is important to improve this technology with respect to nuclear materials detection and accountability. Artificial Neural Intelligence (ANI) is a novel data analysis and simulation method that can be applied to electrochemical data sets. This computational code, which has been performed using the commercial software MATLAB, can be trained to generalize adequate electrical current and potential simulated data sets for the unseen data with a high accuracy of prediction. For this purpose, a massive collection of cyclic voltammetry (CV) data sets by Hoover (2014), for 0.5, 1, 2.5, and 5 wt% of zirconium chloride in LiCl-KCl molten salt with different scan rates at 773 K has been considered. The computer is trained via ANI to predict the unseen data after providing suitable hidden layers and validation numbers. In addition, this work can trace the CV plot for a blind condition by interpolating between two simulated data set. The different hidden layers with various neurons (from 5 to 30) at several validation numbers (from 5 to 30) has been studied and the average percent error between experimental and theoretical data for 0.5 wt% with 200 and 450 mV/s has been calculated. Preliminary results demonstrate that if the number of hidden layers increases from one to three, the average error falls down from 44% to around 8%. The best condition which gives a minimum average percent error has been discovered and the simulated CV graph has been compared with the experimental data. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Intelligent Pixel Detectors: Towards a Radiation Hard ASIC with On-Chip Machine Learning in 28 nm CMOS

Detectors at future high energy colliders will face enormous technical challenges. Disentangling the unprecedented numbers of particles expected in each event will require highly granular silicon pixel detectors with billions of readout channels. With event rates as high as 40 MHz, these detectors will generate petabytes of data per second. To enable discovery within strict bandwidth and latency constraints, future trackers must be capable of fast, power efficient, and radiation hard data-reduction at the source. We are developing a radiation hard readout integrated circuit (ROIC) in 28nm CMOS with on-chip machine learning (ML) for future intelligent pixel detectors. We will show track parameter predictions using a neural network within a single layer of silicon and hardware tests on the first tape-outs produced with TSMC. Preliminary results indicate that reading out featurized clusters from particles above a modest momentum threshold could enable using pixel information at 40 MHz.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Understanding the High Energy Higgs Sector with the CMS Experiment and Artificial Intelligence

This dissertation describes efforts towards understanding the Higgs boson at the highest energies humanly accessible, using the CMS experiment at the Large Hadron Collider and advances in artificial intelligence (AI) and machine learning (ML). We present searches for resonant and nonresonant Higgs-boson (H) pair production in the all-hadronic two beauty-quark and two vector boson (V) final state, using a novel strategy to measure the quartic HHVV coupling and search for new Higgs-like bosons. By targeting highly Lorentz-boosted Higgs pairs, we probe effects of potential new physics in the high energy Higgs sector, which could hold answers to fundamental mysteries of nature such as baryon asymmetry. To enable these and future searches, we introduce as well significant developments in AI/ML, including in the identification of boosted H$\rightarrow$VV decays with deep transformer networks and advances in AI-accelerated fast simulations of the CMS detector. The latter notably includes the development of the first, highly performant generative models for point-cloud data in high energy physics, which have the potential to improve CMS' computational efficiency by up to three orders of magnitude. We also highlight novel solutions to the important and challenging problems of calibrating and validating these ML techniques. Finally, we present new approaches to search for new physics in a model-agnostic manner, using physics-informed ML methods equivariant to Lorentz transformations. The quartic HHVV coupling is observed (expected) to be constrained to $[-0.04, 2.05]$ ($[0.05, 1.98]$) at the 95% confidence level relative to the standard model prediction, representing the second-most sensitive measurement of this coupling by CMS to date. Exclusion limits on the production cross section of new heavy resonances decaying to two Higgs-like bosons are expected to be as low as 0.3 fb for high resonance masses.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Synthesis Methodology for Intelligent Memory Interfaces in Accelerator Systems

Domain-specific systems improve the performance of a specific set of applications compared to general-purpose processing systems by deploying custom hardware accelerators. These hardware accelerators are generated using high-level synthesis (HLS) tools. The HLS tools enable a comprehensive design space exploration to optimize the compute performance of the generated accelerators. However, they often ignore the challenges of implementing the accelerators in a system-on-chip, particularly how the accelerators access memory. Our work introduces a buffering system design that improves accelerators' memory accesses by intelligently employing burst transactions to prefetch useful data from external memory to on-chip local buffers. Our design is dynamic, parametric, and transparent to the accelerators generated by HLS tools. We derive the buffering system parameters using appropriate compiler-based analysis passes and memory channel latency constraints. The proposed buffering system design results in, on average, 8.8x performance improvements while lowering memory channel utilization on average by 53.2% for a set of PolyBench kernels.

Limaye, Ankur M. (ORCID:0000000194062584)↗

Artificial Intelligence for Event Reconstruction and Higgs Physics at CMS and Future Colliders

This dissertation charts a trajectory in which advances in artificial intelligence (AI) play a central role in pushing the high-energy physics frontier, complementing progress driven by higher collision energies and larger colliders. The discovery potential of the LHC and future colliders relies on accurate reconstruction of increasingly complex particle collision events. In the CMS experiment, this task is performed by the particle-flow (PF) algorithm. This dissertation presents the first implementation of a machine-learning-based particle-flow (MLPF) reconstruction in the CMS detector based on transformer architectures. In simulated top quark--antiquark pair (ttbar) events under LHC Run~3 (2023--2024) conditions, MLPF improves jet energy resolution by 10--20\% compared to standard PF for jets with transverse momentum between 30--100\GeV. Runtime performance is evaluated using simulated multijet events, with a median inference time of 20\unit{ms} per event on an NVIDIA L4 GPU, compa red to approximately 110\unit{ms} for standard PF. The MLPF algorithm is also validated on Run~3 collision data, representing the first data-validated ML-based reconstruction pipeline at any LHC experiment. We then extend MLPF toward future electron--positron colliders and introduce the first full-simulation cross-detector transfer learning workflow for PF reconstruction. The model is pre-trained on simulated events from the Compact Linear Collider detector (CLICdet) and fine-tuned on the CLIC-like detector (CLD) proposed for the Future Circular Collider (FCC). This approach achieves up to a 40\% improvement in jet energy resolution over rule-based reconstruction while reducing the required training dataset size by an order of magnitude, demonstrating the potential of AI to accelerate detector development and optimization. This dissertation also demonstrates how modern AI techniques enhance the sensitivity of LHC physics analyses. A CMS search for highly Lorentz-boosted Higgs bosons decaying to \textrm{W} boson pairs is presented, focusing on the single-lepton final state. A dedicated fine-tuning strategy for \ParT yields an approximately 70\% increase in expected sensitivity relative to the baseline model. The analysis uses proton--proton collision data at a center-of-mass energy of \ensuremath{\sqrt{s}=13\TeV} collected by CMS between 2016 and 2018, corresponding to an integrated luminosity of 138\ensuremath{\ \mathrm{fb}^{-1}}. The expected significance of the search is $1.86\sigma$, with an observed signal strength of $-0.19^{+0.48}_{-0.46}$. Finally, explainable AI techniques are applied to the MLPF and \ParticleNet algorithms using layerwise relevance propagation, showing that both models base their predictions on physically meaningful features consistent with our physics intuition. Together, these results demonstrate how advanced AI methods can enhance reconstruction, analysis sensitivity, and interpretability, shaping the next era of experimental parti cle physics.

Mokhtar, Farouk [UC, San Diego]↗

Artificial Intelligence Thermostat to Detect Faults

Residential air conditioners and heat pumps often experience faults due to inadequate maintenance, which can severely reduce efficiency or even cause system failure. Common issues include dirty or clogged air filters and refrigerant leaks. These problems degrade performance and increase energy use and operating costs. This study presents a smart thermostat with embedded artificial intelligence to detect such faults and alert homeowners when maintenance is needed. The thermostat uses low-cost measurements—including return-air temperature, relative humidity, supply-air temperature, outdoor-air temperature, and condenser subcooling—to identify abnormal operations. Because different faults produce distinct response patterns, tailored algorithms are developed to recognize characteristic fault signatures. The investigation is built on a detailed co-simulation platform that couples EnergyPlus with the DOE/ORNL Heat Pump Design Model (HPDM). EnergyPlus represents the building’s dynamic environment, while HPDM is a high-fidelity, hardware-based model that can simulate fault-free performance as well as a wide range of faults, including gradual degradation such as minor refrigerant leakage. This platform provides a virtual training and testing environment that helps distinguish fault-induced behavior from normal operation and supports development of robust diagnostic algorithms. Using this framework, a Dynamic Bayesian Network was developed to identify two common faults—gradual refrigerant charge loss and indoor airflow blockage—and the AI-embedded thermostat was verified through annual building simulations.

Shen, Bo [ORNL] (ORCID:0000000336600393)↗

U.S. Department of Energy Competitiveness Improvement Project 2024 Technology Commercialization Awardee: Intelligent Energy Systems

This fact sheet describes the 2024 Competitiveness Improvement Project (CIP) award received by Intelligent Energy Systems for technology commercialization. The U.S. Department of Energy's (DOE's) CIP awards cost-shared subcontracts and technical support to manufacturers of small and medium-sized wind turbines. Managed by NLR on behalf of DOE's Wind Energy Technologies Office, CIP helps advance wind energy as a cost-effective, distributed-generation technology option.

17 WIND ENERGY↗

Holistic Interactions of Shallow Clouds, Aerosols, and Land-Ecosystems (HI-SCALE): National Geospatial-Intelligence Agency Calibration Target Placements Field Campaign Report

The purpose of our research has been to develop a capability of simulating image collection from any sensor so as to account for sensor configuration, ground spectral radiance, and atmospheric contributions. Atmosphere is arguably the most difficult aspect of the image pipeline to accurately characterize and integrate into an image simulation. Some of the reasons for this include the highly variable spatial content of different absorbing and scattering species in the atmosphere. Additionally, the interaction of land and atmosphere can significantly impact the total radiation budget, especially in the southern Great Plains.

54 ENVIRONMENTAL SCIENCES↗

Artificial intelligence based analysis of nanoindentation load–displacement data using a genetic algorithm

In this work, we developed an automated tool, Nanoindentation Neo package for the analysis of nanoindentation load–displacement curves using a Genetic Algorithm (GA) applied to the Oliver-Pharr method (Oliver et al.,1992). For some materials, such as polycrystalline isotropic graphites, Least Squares Fitting (LSF) of the unload curve can produce unrealistic fit parameters. These graphites exhibit sharply peaked unloading curves not easily fit using the LSF, which tends to overestimate the indenter tip geometry parameter. To tackle this problem, we extended our general materials characterization tool Neo for EXAFS analysis (Terry et al., 2021) to fit nanoindentation data. Nanoindentation Neo automatically processes and analyzes nanoindentation data with minimal user input while producing meaningful fit parameters. GA, a robust metaheuristic method, begins with a population of temporary solutions using model parameters called chromosomes; from these we evaluate a fitness value for each solution, and select the best solutions to mix with random solutions producing the next generation. A mutation operator then modifies existing solutions by random perturbations, and the optimal solution is selected. We tested the GA method using Silica and Al reference standards. We fit samples of graphite and a high entropy alloy (HEA) consisting of BCC and FCC phases.

42 ENGINEERING↗

Monitoring river flow status using low-cost wildlife camera and image segmentation artificial intelligence

Continuous measurement and monitoring of surface water coverage in non-perennial streams are essential for understanding the exchange fluxes between surface and subsurface waters under both inundated and non-inundated conditions. In this study, a wildlife camera photo-based framework was developed to monitor small stream water inundation, depth, discharge, and velocity. Two advanced machine learning models, YOLOv8 and Mask2Former, were utilized to efficiently analyze images captured by wildlife cameras. The accuracy of the framework was validated against on-site depth measurements at six sites in the Yakima River Basin, along with the gage height, discharge, and velocity data from four USGS sites. This approach facilitates long-term, continuous monitoring and quantification of river intermittency and water availability with high precision and low cost, thereby advancing river ecosystem research and management.

machine learning↗