Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Predictive modelling”

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 757 records · Page 42
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

A search for dark matter produced in association with a dark Higgs boson decaying into a Higgs boson pair in 3b or 4b final states using pp collisions at $\sqrt{s}=13$ TeV with the ATLAS detector

A search is performed for dark matter particles produced in association with a resonant pair of Higgs bosons using 140 fb −1 of proton-proton collisions at a centre-of-mass energy of 13 TeV recorded by the ATLAS detector at the Large Hadron Collider. This signature is expected in some extensions of the Standard Model predicting the production of dark matter particles, and is interpreted in terms of a dark Higgs model containing a Z′ mediator in which the dark Higgs boson s decays into a pair of Higgs bosons. The dark Higgs boson is reconstructed through final states with at least three b-tagged jets, produced by the pair of Higgs boson decays, in events with significant missing transverse momentum consistent with the presence of dark matter. The observed data are found to be in good agreement with Standard Model predictions, constraining scenarios with dark Higgs boson masses within the range of 250 to 400 GeV and Z′ mediators up to 2.3 TeV.

Dark Energy and Dark Matter↗
DOE OSTI2026

Leveraging ARM Data to Improve Models for Predictive Understanding of Energy and Security Challenges

Extreme weather and natural hazards can disrupt the energy sector, affecting demand, generation, transmission, distribution, consumption and operational planning at regional and national scales. These disruptions stem from a broad range of atmospheric phenomena, including winter storms, freezing rain, wet snow loading, severe convection, flooding and landslides, wildfires, prolonged heat, and drought. Many of these same phenomena can also affect national security through impacts to transportation and infrastructure. To support the U.S. Department of Energy (DOE) focus on energy resilience and national security, the Atmospheric Radiation Measurement (ARM) User Facility is uniquely positioned to contribute measurement data, analyses, and modeling frameworks that can significantly improve predictive understanding of these hazards to mitigate their effects. To explore this opportunity, ARM convened a two-part virtual workshop in November 2025. The workshop engaged interdisciplinary experts in atmospheric science, energy systems, modeling, and operations. The goal of the meeting was to engage with these interdisciplinary experts to address three questions: • What are examples of atmospheric processes that represent significant risks to energy security or national security and where are those risks greatest? • What measurements or measurement strategies would improve ARM’s capacity to address these issues? • How can ARM and users of the ARM facility better work with the Energy Exascale Earth System Model (E3SM) and multi-sector modeling communities to apply ARM data to improving E3SM simulations of these phenomena? Participants were asked to submit white papers ahead of the meeting to initiate thinking on these themes and to help organize discussions. Workshop sessions were then organized around themes identified in the white papers. First from the white papers and then through subsequent discussions, workshop participants identified many examples that address the three questions listed above. Participants called out energy system vulnerabilities to weather phenomena such as the impact of freezing rain, strong winds, and excessive heat on power grids. They also noted the effects that weather phenomena could have on energy demand or supply (e.g., through effects of extreme temperatures). They called out security vulnerabilities such as impacts to crops from aerosol-borne pathogens and risks to industry due to melting permafrost in the Arctic. In all, over a dozen meteorological phenomena were linked to energy or security vulnerabilities. For many of the identified phenomena, participants pointed out where ARM was well poised to address issues (e.g., through measurements of cloud microphysics to inform studies of freezing rain) but also noted needs for additional measurements or modified measurement strategies. For example, adaptive scanning of severe weather would be valuable for probing winter storms or severe convection. Participants pointed out the value in integrating external observations with ARM measurements and with applying artificial intelligence (AI) to ARM observation analysis and they advocated for using model simulations to help optimize measurement strategies through Observing System Simulation Experiments (OSSEs). It was clear from the workshop that there are many ways that ARM observations can be used to mitigate energy and security concerns, but meeting participants were also asked to identify what they considered to be the greatest opportunities by ranking issues pertaining to the three workshop questions. This was accomplished through a survey administered to participants between the two virtual sessions. The highest-priority phenomena identified were winter storms, severe convection, and arctic processes. Discussion in the second session, therefore, focused primarily on these three areas, which were most fully developed in exploring ARM opportunities. Nevertheless, it was also clear that ARM has opportunities to contribute to all the identified topics. This report describes the workshop, including input from discussion and white papers (Sections 2 and 3) and a list of priority recommendations (section 4). Many other ideas for ARM contributions are discussed in individual white papers (Appendix D).

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2026

The Sensitivity of Variational Bayesian Neural Network Performance to Hyperparameters

In scientific applications, predictive modeling is often of limited use without accurate uncertainty quantification (UQ) to indicate when a model may be extrapolating or when more data needs to be collected. Bayesian Neural Networks (BNNs) produce predictive uncertainty by propagating uncertainty in neural network (NN) weights and offer the promise of obtaining not only an accurate predictive model but also accurate UQ. However, in practice, obtaining accurate UQ with BNNs is difficult due in part to the approximations used for model training (such as those made in variational inference) and in part to the need to choose a suitable set of hyperparameters; these hyperparameters outnumber those needed for traditional NNs and often have opaque effects on the results. We aim to shed light on the effects of hyperparameter choices for variational BNNs by performing a global sensitivity analysis of variational BNN performance under varying hyperparameter settings. Our results indicate that many of the hyperparameters interact with each other to affect both predictive accuracy and UQ. For improved usage of variational BNNs in real-world applications, we suggest that thorough hyperparameter tuning, including tuning of prior hyperparameters and loss function parameters, is essential for accurate UQ in variational BNNs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Evaluation of the Near-Surface Variables in the HRRR Weather Model Using Observations from the ARM SGP Site

Abstract The performance of version 4 of the NOAA High-Resolution Rapid Refresh (HRRR) numerical weather prediction model for near-surface variables, including wind, humidity, temperature, surface latent and sensible fluxes, and longwave and shortwave radiative fluxes, is examined over the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) region. The study evaluated the model’s bias and bias-corrected mean absolute error relative to the observations on different time scales. Forecasts of near-surface geophysical variables at five SGP sites (HRRR at 3-km scale) were found to agree well with observations, but some consistent observation–forecast differences also occurred. Sensible and latent heat fluxes are the most challenging variables to be reproduced. The diurnal cycle is the main temporal scale affecting observation–forecast differences of the near-surface variables, and almost all of the variables showed different biases throughout the diurnal cycle. Results show that the overestimation of downward shortwave and the underestimation of downward longwave radiative flux are the two major biases found in this study. The timing and magnitude of downward longwave flux, wind speed, and sensible and latent heat fluxes are also different with contributions from model representations, data assimilation limitations, and differences in scales between HRRR and SGP sites. The positive bias in downward shortwave and negative bias in longwave radiation suggests that the model is underestimating cloud fraction in the study domain. The study concludes by showing a brief comparison with version 3 of the HRRR and shows that version 4 has better performance in almost all near-surface variables. Significance Statement A correct representation of the near-surface variables is important for numerical weather prediction models. This study investigates the capability of the latest NOAA High-Resolution Rapid Refresh (HRRRv4) model in simulating the near-surface variables by comparing against the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) in situ observations. Among others, we find that the surface heat fluxes, such as sensible and latent heat fluxes, are the most difficult variables to be reproduced. This study also shows that the diurnal cycle has the dominant impact on the model’s performance, which means the majority of the outputted near-surface variables have the strong diurnal cycle in their bias errors.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Occupant Preference-Aware Load Scheduling for Resilient Communities

The load scheduling of resilient communities in the islanded mode is subject to many uncertainties such as weather forecast errors and occupant behavior stochasticity. To date, it remains unclear how occupant preferences affect the effectiveness of the load scheduling of resilient communities. This paper proposes an occupant thermal preference-aware load scheduler for resilient communities operating in the islanded mode. First, key resilience indicators are selected to quantify its impacts on the load scheduling of a resilient community. A deterministic model predictive control-based load scheduling framework is adopted as the baseline. Then, a chance-constrained controller is proposed to address the occupant-induced uncertainty in room temperature setpoints. Finally, the chance-constrained controller is compared with the deterministic controller on a virtual community testbed based on a real-world net-zero energy community in Florida, U.S. Results have shown that the proposed chance-constrained controller performs better in terms of serving occupants’ thermal preference and the required battery sizes compared to the deterministic controller with the presence of the assumed stochastic occupant behavior. This work indicates that it is necessary to consider the stochasticity of the occupant behavior when designing optimal load schedulers for resilient communities.

Wang, Jing↗
DOE OSTI2025

Challenges in predicting protein-protein interactions of understudied viruses: Arenavirus-human interactions

Understanding protein-protein interactions (PPIs) between viruses and host organisms is crucial for uncovering infection mechanisms and identifying potential therapeutic targets. The ability to generalize PPI predictive models across understudied viruses presents a significant challenge. In this work, we use arenavirus-human PPIs to illustrate the difficulties associated with model generalization, which are compounded by a lack of both positive and negative data. We employ a Transfer Learning approach to investigate arenavirus-human PPIs by utilizing models trained on better-studied virus-human and human-human PPIs. Additionally, we curate and assess four types of negative sampling datasets to evaluate their impact on model performance. Despite the overall high accuracies (93–99 %) and AUPRC scores (0.8–0.9) appearing promising, further analysis indicates that these performance metrics can be misleading due to data leakage, data bias, and overfitting, especially concerning under-represented viral proteins. We reveal these gaps and assess the impact of data imbalance using standard k-fold cross-validation and Independent Blind Testing with a Balanced Dataset, resulting in a drop in accuracy below 50 %. We propose a viral protein-specific evaluation framework that categorizes viral proteins into majority and minority classes based on their representation in the dataset, enabling comparison of model performance across these groups using balanced accuracies. This framework offers a more robust evaluation of model generalizability, addressing biases inherent in standard evaluation techniques and paving the way for more reliable PPI prediction models for understudied viruses.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Studies of new Higgs boson interactions through nonresonant $HH$ production in the $ b\overline{b}\gamma \gamma $ final state in $pp$ collisions at $ \sqrt{s} $ = 13 TeV with the ATLAS detector

A search for nonresonant Higgs boson pair production in the $ b\overline{b}\gamma \gamma $ final state is performed using 140 fb –1 of proton-proton collisions at a centre-of-mass energy of 13 TeV recorded by the ATLAS detector at the CERN Large Hadron Collider. This analysis supersedes and expands upon the previous nonresonant ATLAS results in this final state based on the same data sample. The analysis strategy is optimised to probe anomalous values not only of the Higgs (H) boson self-coupling modifier κλ but also of the quartic HHVV (V = W, Z) coupling modifier κ 2V . No significant excess above the expected background from Standard Model processes is observed. An observed upper limit μHH < 4.0 is set at 95% confidence level on the Higgs boson pair production cross-section normalised to its Standard Model prediction. The 95% confidence intervals for the coupling modifiers are –1.4 < κ λ < 6.9 and –0.5 < κ 2V < 2.7, assuming all other Higgs boson couplings except the one under study are fixed to the Standard Model predictions. The results are interpreted in the Standard Model effective field theory and Higgs effective field theory frameworks in terms of constraints on the couplings of anomalous Higgs boson (self-)interactions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

A mechanistic, multiscale model for predicting Pd penetration in TRISO fuels using BISON

TRistructural ISOtropic (TRISO) particles use silicon carbide (SiC) as the primary structural member and barrier against metallic fission product (FP) release. palladiums (PDs), produced by fission in the fuel kernel, can diffuse to and chemically interact with the SiC layer, degrading its structural integrity and ability to contain radioactive FPs. Existing temperature-dependent correlations for predicting Pd penetration rely on experimental data with significant scatter due to varying conditions, potentially complicating ongoing fuel qualification and licensing efforts for advanced reactors that would subject TRISO fuels to operating conditions outside of those examined in the experiments. A mechanistic model of Pd production, transport, and reaction is developed in this work to better understand and predict PD attack of SiC in TRISO particles. molecular dynamicss (MDs) simulations are utilized to calculate the Pd diffusivity in SiC grain bulk and grain boundaries. A mesoscale phase-field diffusion model, informed by the MD diffusivities, is used to develop a reduced order model (ROM) for the effect of SiC microstructure on the Pd penetration rate. The engineering scale BISON model calculates Pd production and transport, utilizing the ROM to predict penetration rates consistent with experimental data. This novel mechanistic ROM captures the effect of temperature, microstructure, and irradiation history on Pd penetration. In conclusion, these new capabilities are expected to support ongoing qualification and licensing efforts associated with near-term TRISO-fueled reactor applications.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

This work investigates and applies machine learning paradigms seldom seen in analytical spectroscopy for quantification of gallium in cerium matrices via processing of laser-plasma spectra. Ensemble regressions, support vector machine regressions, Gaussian kernel regressions, and artificial neural network techniques are trained and tested on cerium-gallium pellet spectra. A thorough hyperparameter optimization experiment is conducted initially to determine the best design features for each model. The optimized models are evaluated for sensitivity and precision using the limit of detection (LoD) and root mean-squared error of prediction (RMSEP) metrics, respectively. Gaussian kernel regression yields the superlative predictive model with an RMSEP of 0.33% and an LoD of 0.015% for quantification of Ga in a Ce matrix. This study concludes that these machine learning methods could yield robust prediction models for rapid quality control analysis of plutonium alloys.

Rao, Ashwin P. (ORCID:0000000319312568)↗
DOE OSTI2026

Structural coherence model for predicting molten salt thermal conductivity informed by the pair distribution function

To enable thermal behavior prediction and design optimization of molten salt reactors, thermal conductivity of molten salts must be characterized in terms of salt composition and temperature. Current theoretical models fail to provide consistent approximations for all halide mixtures, particularly actinide-bearing melts. This study aims to link the short-range order structure of molten salts to the mean free path of energy carriers through a simple structural coherence model informed by the partial pair distribution function. The proposed method is used to predict the thermal conductivity of 33 alkali and alkaline earth halide salts. Predictions approximate experimental measurements with a mean absolute error of 15.7% for dissociating, complexing, and actinide salts, including unary LiCl, NaCl, and MgCl 2 as well as mixtures LiF–NaF–KF (FLiNaK), LiF–BeF 2 (FLiBe), and NaCl–UCl 3 . The work provides evidence for the validity of energy carrier descriptions of molecular-level heat transfer in molten salts, with implications for improved theories of liquid energy transport in general.

Actinide mixtures↗
DOE OSTI2020

MHD stability and disruptions in the SPARC tokamak

SPARC is being designed to operate with a normalized beta of $β_N$ = 1.0, a normalized density of $n_G$ = 0.37 and a safety factor of $q_{95}$ ≈ 3.4, providing a comfortable margin to their respective disruption limits. Further, a low beta poloidal $β_p$ = 0.19 at the safety factor $\textit{q}$ = 2 surface reduces the drive for neoclassical tearing modes, which together with a frozen-in classically stable current profile might allow access to a robustly tearing-free operating space. Although the inherent stability is expected to reduce the frequency of disruptions, the disruption loading is comparable to and in some cases higher than that of ITER. The machine is being designed to withstand the predicted unmitigated axisymmetric halo current forces up to 50 MN and similarly large loads from eddy currents forced to flow poloidally in the vacuum vessel. Runaway electron (RE) simulations using GO+CODE show high flattop-to-RE current conversions in the absence of seed losses, although NIMROD modelling predicts losses of ~80 %; self-consistent modelling is ongoing. A passive RE mitigation coil designed to drive stochastic RE losses is being considered and COMSOL modelling predicts peak normalized fields at the plasma of order 10 –2 that rises linearly with a change in the plasma current. Massive material injection is planned to reduce the disruption loading. A data-driven approach to predict an oncoming disruption and trigger mitigation is discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

How AI Predicts the Untrained and Unseen

Focus Area: Model predictability improvements (Primary); Data optimization (secondary); Data complexity insights (secondary). The Scientific Challenge: If we believe that a future under extreme conditions will look very differently from today, we can likely agree that ML/AI models trained on past and present datasets will not be adequate to make reliable predictions into the future. This is true for water cycling, as well as biogeochemistry and other Earth system components and behaviors. Additionally, ML/AI models are inherently non-physical. Despite the flourishing success of ML/AI in many applications, such as computer vision, natural language process, and gaming, even the most sophisticated AI models don’t understand the very basic physical laws. Therefore, a natural question is: Can we trust ML/AI based predictions of Earth system behaviors that are fundamentally driven by physical laws? So, are physics models with meticulous process representation a better choice? Not exactly. Physical models, when firmly rooted in first principles, work great at predicting behaviors of systems with a well-defined set of boundary conditions and variables. However, as a complex system, the number of parameters and the degree of complexity and dynamics in processes, coupling, and scale dependent emergent behaviors make the Earth system behaviors very challenging to predict with physical models composed of deterministic laws. In addition, due to the lack of fundamental understandings, physical models often implement empirical correlations derived from observations with biases from locality of data generation. Because correlation is not necessarily causation or comply with first principles, scaling of model predictions beyond locality is often invalid. Beyond the limitation of models, physics or AI, our knowledge of the Earth system is limited by the lack of observational technologies and resources. Insufficient data density, dimensionality and diversity only offer a sliced (or projected) view of the Earth system, e.g. Plato’s Cave analogy, limiting our capability to better understand and represent fundamental processes in models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Low responsiveness of machine learning models to critical or deteriorating health conditions

Machine learning (ML) based mortality prediction models can be immensely useful in intensive care units. Such a model should generate warnings to alert physicians when a patient’s condition rapidly deteriorates, or their vitals are in highly abnormal ranges. Before clinical deployment, it is important to comprehensively assess a model’s ability to recognize critical patient conditions. We develop multiple medical ML testing approaches, including a gradient ascent method and neural activation map. We systematically assess these machine learning models’ ability to respond to serious medical conditions using additional test cases, some of which are time series. Guided by medical doctors, our evaluation involves multiple machine learning models, resampling techniques, and four datasets for two clinical prediction tasks. We identify serious deficiencies in the models’ responsiveness, with the models being unable to recognize severely impaired medical conditions or rapidly deteriorating health. For in-hospital mortality prediction, the models tested using our synthesized cases fail to recognize 66% of the injuries. In some instances, the models fail to generate adequate mortality risk scores for all test cases. Our study identifies similar kinds of deficiencies in the responsiveness of 5-year breast and lung cancer prediction models. Using generated test cases, we find that statistical machine-learning models trained solely from patient data are grossly insufficient and have many dangerous blind spots. Most of the ML models tested fail to respond adequately to critically ill patients. How to incorporate medical knowledge into clinical machine learning models is an important future research direction.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

In Situ X-ray Radiography and Computational Modeling to Predict Grain Morphology in $\beta$-Titanium during Simulated Additive Manufacturing

The continued development of metal additive manufacturing (AM) has expanded the engineering metallic alloys for which these processes may be applied, including beta-titanium alloys with desirable strength-to-density ratios. To understand the response of beta-titanium alloys to AM processing, solidification and microstructure evolution needs to be investigated. In particular, thermal gradients (Gs) and solidification velocities (Vs) experienced during AM are needed to link processing to microstructure development, including the columnar-to-equiaxed transition (CET). In this work, in situ synchrotron X-ray radiography of the beta-titanium alloy Ti-10V-2Fe-3Al (wt.%) (Ti-1023) during simulated laser-powder bed fusion (L-PBF) was performed at the Advanced Photon Source at Argonne National Laboratory, allowing for direct determination of Vs. Two different computational modeling tools, SYSWELD and FLOW-3D, were utilized to investigate the solidification conditions of spot and raster melt scenarios. The predicted Vs obtained from both pieces of computational software exhibited good agreement with those obtained from in situ synchrotron X-ray radiography measurements. The model that accounted for fluid flow also showed the ability to predict trends unobservable in the in situ synchrotron X-ray radiography, but are known to occur during rapid solidification. A CET model for Ti-1023 was also developed using the Kurz–Giovanola–Trivedi model, which allowed modeled Gs and Vs to be compared in the context of predicted grain morphologies. Both pieces of software were in agreement for morphology predictions of spot-melts, but drastically differed for raster predictions. The discrepancy is attributable to the difference in accounting for fluid flow, resulting in magnitude-different values of Gs for similar Vs.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Flux effects in precipitation under irradiation simulation of Fe-Cr alloys

Radiation-enhanced precipitation of Cr-rich α’ in irradiated Fe-Cr alloys, which results in hardening and embrittlement, depends on the irradiating particle and the displacement per atom (dpa) rate. Here, we utilize a Cahn-Hilliard phase-field based approach, that includes simple models for nucleation, irradiating particle and rate dependent radiation-enhanced diffusion and cascade mixing to simulate α’ evolution under neutrons, heavy ions, and electron irradiations. Different irradiating particles manifest very different cascade mixing efficiencies. The model was calibrated using neutron data. For cascade inducing neutron/heavy-ion dpa rates at 300 °C between 10-8 and 10-6 dpa/s the model predicts approximately constant number density, decreasing radius, decreasing α’ Cr composition, and lower α’ volume fraction. The model then predicts a dramatic transition to no α’ formation above approximately 10-5 dpa/s, while electron irradiation, with weak mixing, had little effect at dpa rates up to 10-3 dpa/s. These model predictions are consistent with experiments. We explain the results in terms of the flux dependence of the radiation enhanced diffusion, cascade mixing, and their ratio, which all vary significantly in relevant flux ranges for neutron and cascade inducing ion irradiations. These results show that both cascade mixing and radiation enhanced diffusion must be accounted for when attempting to emulate neutron-irradiation effects using accelerated ion irradiations.

Ke, Jia-Hong↗
DOE OSTI2022

The Natural and Accelerated Evolution of EVA Adhesion Through Intermediate Exposures

Ethylene vinyl acetate (EVA) encapsulants comprise the majority of the encapsulants currently in use; much work has been done to understand and model the adhesive characteristics of EVA-encapsulated modules, but limited work has provided reliable insight into adhesion during the intermediate stages of exposure, limiting the ability to validate model predictions in this range. We provide the adhesion energy measurements for EVA adhesion after nearly six years of field aging and 10 000 h of accelerated aging. Both field and accelerated aging reveal a distinct plateau that emerges during the intermediate exposure periods (after one year in the field and after 1000 h in a chamber). At 10 000 h, adhesion within accelerated aged minimodules falls to a level generally seen after long-term field exposures (>15 years). Previous modeling predicted that adhesion would steadily decrease over the lifetime of a module, but these current results uncover an intermediate plateauing trend that is important to accurately modeling the evolution of adhesion and predicting adhesive failure. Based on these findings, three key model refinements concerning the rate of UV-radical formation and subsequent β-scission, the rate and acceleration of hydrolytic depolymerization, and the profile of the plasticity contribution over time are implemented and discussed.

14 SOLAR ENERGY↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗
DOE OSTI2020

Engine-in-the-Loop Study of a Hierarchical Predictive Online Controller for Connected and Automated Heavy-Duty Vehicles

This paper presents a cohesive set of engine-in-the-loop (EIL) studies examining the use of hierarchical model-predictive control for fuel consumption minimization in a class-8 heavy-duty truck intended to be equipped with Level-1 connectivity/automation. This work is motivated by the potential of connected/automated vehicle technologies to reduce fuel consumption in both urban/suburban and highway scenarios. The authors begin by presenting a hierarchical model-predictive control scheme that optimizes multiple chassis and powertrain functionalities for fuel consumption. These functionalities include: vehicle routing, arrival/departure at signalized intersections, speed trajectory optimization, platooning, predictive optimal gear shifting, and engine demand torque shaping. The primary optimization goal is to minimize fuel consumption, but the hierarchical controller explicitly accounts for other key objectives/constraints, including operator comfort and safe inter-vehicle spacing. This work is experimentally experimentally validated via a sequence of EIL studies intended for evaluating the computational costs and fuel savings associated with these algorithms. These EIL studies involve the closed-loop validation of the proposed control strategies, both individually and combined. These studies show that this hierarchy of algorithms is capable of running online, with the round-trip communication delay inherent in EIL simulation being one of the key factors affecting the EIL results. Moreover, the EIL studies are encouraging, both in terms of the successful hierarchical integration of the underlying algorithms and also in the resulting fuel savings seen in the EIL tests. In particular, the EIL results suggest that an aggressive overall goal of reducing vehicle fuel consumption by 15-20% or more is potentially achievable, especially in urban/suburban scenarios.

33 ADVANCED PROPULSION SYSTEMS↗