Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model prediction”

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 OSTI2020

Effects of stereoisomeric structure and bond location on the ignition and reaction pathways of hexenes

The current work presents new experimental autoignition and speciation data on the two cis-hexene isomers: cis-2-hexene and cis-3-hexene. The new data provide insights on the effects of carbon-carbon double bond location and stereoisomeric structures on ignition delay times and reaction pathways for linear hexene isomers. Experiments were performed using the University of Michigan rapid compression facility to determine ignition delay times from pressure-time histories. Stoichiometric (Φ = 1.0) mixtures at dilution levels of inert gas to O 2 = 7.5:1 (mole basis) were investigated at an average pressure of 11 atm and temperatures from 809 to 1052 K. Speciation experiments were conducted at T = 900 K for the two cis-hexene isomers, where fast-gas sampling and gas chromatography were used to identify and quantify the two cis-hexene isomers and stable intermediate species. The ignition delay time data showed negligible sensitivity to the location of the carbon-carbon double bond and the stereoisomeric structure (cis-trans), and the species data showed no correlation with the stereoisomeric structure, but there was a strong correlation of some of the measured species with the location of the double bond in the hexene isomer. In particular, 2-hexene showed strong selectivity to propene, acetaldehyde, and 1,3-butadiene, and 3-hexene showed selectivity to propanal. Model predictions of ignition delay times were in excellent agreement with the experimental data. Furthermore, there was generally good agreement for the model predictions of the species data for 2-hexene; however, the mechanism overpredicted some of the small aldehyde (C 2 -C 4 ) species for 3-hexene. Reaction pathway analysis indicates the hexenes are almost exclusively consumed by H-atom abstraction reactions at the conditions studied (P = 11 atm, T > 900 K), and not by C 3 -C 4 scission as observed in high-temperature (>1300 K) hexene ignition studies. Improved estimates for 3-hexene + OH reactions may improve model predictions for the species measured in this work.

42 ENGINEERING↗
DOE OSTI2023

Potential Cooling Energy Savings of Economizer Control and Artificial-Neural-Network-Based Air-Handling Unit Discharge Air Temperature Control for Commercial Building

Heating, ventilation, and air-conditioning (HVAC) systems play a significant role in building energy consumption, accounting for around 50% of total energy usage. As a result, it is essential to explore ways to conserve energy and improve HVAC system efficiency. One such solution is the use of economizer controls, which can reduce cooling energy consumption by using the free-cooling effect. However, there are various types of economizer controls available, and their effectiveness may vary depending on the specific climate conditions. To investigate the cooling energy-saving potential of economizer controls, this study employs a dry-bulb temperature-based economizer control approach. The dry-bulb temperature-based control strategy uses the outdoor air temperature as an indicator of whether free cooling can be used instead of mechanical cooling. This study also introduces an artificial neural network (ANN) prediction model to optimize the control of the HVAC system, which can lead to additional cooling energy savings. To develop the ANN prediction model, the EnergyPlus program is used for simulation modeling, and the Python programming language is employed for model development. The results show that implementing a temperature-based economizer control strategy can lead to a reduction of 7.6% in annual cooling energy consumption. Moreover, by employing an ANN-based optimal control of discharge air temperature in air-handling units, an additional 22.1% of cooling energy savings can be achieved. In conclusion, the findings of this study demonstrate that the implementation of economizer controls, especially the dry-bulb temperature-based approach, can be an effective strategy for reducing cooling energy consumption in HVAC systems. Additionally, using ANN prediction models to optimize HVAC system controls can further increase energy savings, resulting in improved energy efficiency and reduced operating costs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Topological structure of complex predictions

Abstract Current complex prediction models are the result of fitting deep neural networks, graph convolutional networks or transducers to a set of training data. A key challenge with these models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into a simplified topological view of the prediction landscape. The result is a map of the predictions that enables inspection of the model results with more specificity than dimensionality-reduction methods such as tSNE and UMAP. The methods scale up to large datasets across different domains. We present a case study of a transformer-based model previously designed to predict expression levels of a piece of DNA in thousands of genomic tracks. When the model is used to study mutations in the BRCA1 gene, our topological analysis shows that it is sensitive to the location of a mutation and the exon structure of BRCA1 in ways that cannot be found with tools based on dimensionality reduction. Moreover, the topological framework offers multiple ways to inspect results, including an error estimate that is more accurate than model uncertainty. Further studies show how these ideas produce useful results in graph-based learning and image classification.

Computer Science↗
DOE OSTI2020

A Genome-Based Model to Predict the Virulence of Pseudomonas aeruginosa Isolates

ABSTRACT: Variation in the genome of Pseudomonas aeruginosa , an important pathogen, can have dramatic impacts on the bacterium’s ability to cause disease. We therefore asked whether it was possible to predict the virulence of P. aeruginosa isolates based on their genomic content. We applied a machine learning approach to a genetically and phenotypically diverse collection of 115 clinical P. aeruginosa isolates using genomic information and corresponding virulence phenotypes in a mouse model of bacteremia. We defined the accessory genome of these isolates through the presence or absence of accessory genomic elements (AGEs), sequences present in some strains but not others. Machine learning models trained using AGEs were predictive of virulence, with a mean nested cross-validation accuracy of 75% using the random forest algorithm. However, individual AGEs did not have a large influence on the algorithm’s performance, suggesting instead that virulence predictions are derived from a diffuse genomic signature. These results were validated with an independent test set of 25 P. aeruginosa isolates whose virulence was predicted with 72% accuracy. Machine learning models trained using core genome single-nucleotide variants and whole-genome k-mers also predicted virulence. Our findings are a proof of concept for the use of bacterial genomes to predict pathogenicity in P. aeruginosa and highlight the potential of this approach for predicting patient outcomes. IMPORTANCE Pseudomonas aeruginosa is a clinically important Gram-negative opportunistic pathogen. P. aeruginosa shows a large degree of genomic heterogeneity both through variation in sequences found throughout the species (core genome) and through the presence or absence of sequences in different isolates (accessory genome). P. aeruginosa isolates also differ markedly in their ability to cause disease. In this study, we used machine learning to predict the virulence level of P. aeruginosa isolates in a mouse bacteremia model based on genomic content. We show that both the accessory and core genomes are predictive of virulence. This study provides a machine learning framework to investigate relationships between bacterial genomes and complex phenotypes such as virulence.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Traffic safety analysis and model updating for freeways using Bayesian method

Freeway crash prediction models are the basic of traffic safety research, yet crash occurrence and the influencing factors change over time. In order to make sure the implemented safety models fit the current traffic environment, this study conducts a comparative analysis of 2017 and 2020 datasets collected from freeways in Suzhou, China. Herein, considering the spatial correlation among analysis units and the hierarchical data structure, a Bayesian conditional autoregressive negative binomial (CAR-NB) model and a Bayesian hierarchical CAR-NB (HCAR-NB) model were used to explore the safety influencing factors, and a traditional NB model was developed for further comparison. To update the HCAR-NB model from 2017 to 2020, Bayesian inference with informative priors was used to improve its goodness of fit and efficiency. Preliminary results showed that 1) the HCAR-NB model outperformed the NB model and CAR-NB model in prediction accuracy, and 2) the number of crashes was significantly correlated with average speed, speed variance, road segment length, number of lanes, and presence of ramps. The potential for safety improvement (PSI) method was applied to the modeling results to identify hotspots for the two years. The results confirmed that the hotspots spatiotemporally shifted among the freeways. The proposed crash prediction model and updating method are expected to assist implementation of informed countermeasures for freeway safety improvement.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Computational model for predicting the performance of fluid-powered longiudinal piston modules and motors.

A Matlab-based computational model line code has been developed for predicting the performance of fluid-powered longitudinal piston modules and motors. A system of equations has been developed based upon applying the conservation of mass to a control volume defined by a reciprocating piston. The method results in a differential equation that predicts the pressure gradient in the control volume as a function of rotor rotation angle. The model uses an integration scheme to predict the pressure state in the control volume. The orifice equation is used to predict the flowrate in and out of the control volume. From the resulting solution the torque and speed characteristics of the motor configuration can be predicted, optimized, or tailored for a specific requirement.SAND2019-13983 M Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Taylor, Michael↗
DOE OSTI2020

Application of an Erosion Wear Model to Predict Wear of Hammer Milling Components

A workable analytical erosion model that relates critical hammermill process parameters (hammermill geometry and rotational speed) to critical material attributes of inorganic mineral species in feedstock (density, size, and aspect ratio) and substrate (hardness, toughness, and fatigue ductility) was applied to model wear (more specifically, change in the shape of hammers) in hammer milling operations. Results of the model were compared to experimental observations of the shape of hammers used in the INL Stage 1 Vermeer hammermill. Results showed good agreement between predicted and measured shape of the hammer, and that a quality-by-design (QbD) approach can be developed to predict component reliability based on scientific engineering principles in lieu of trial-and-error approaches.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Modeling Chemo-Mechanics with Electrolyte Infiltration to Quantify Degradation of Cathode Particles

One of the main goals in modeling lithium-ion batteries is to improve/predict longevity and resilience of new chemistries. To that end, this talk investigates the formation of stress-induced fracture within polycrystalline cathode particles and the impact on capacity loss. Physically based cathode aging dynamics is simulated in a 3D, continuum-level chemo-mechanical model. The model captures anisotropic Li diffusion within a single polycrystalline particle comprised of hundreds to thousands of randomly oriented grains. A recent addition to this model includes electrolyte infiltration, which occurs when the electrolyte seeps into surface cracks within the particle. The model predicts that particle fracture is primarily due to non-ideal grain interactions with slight dependence on high-rate charge demands. Essentially, when neighboring grains are misaligned, they expand a different rates relative to one another leading to high stresses and ultimately the formation of intraparticle cracks. The model predicts that small particles with large grains develop significantly less damage than larger particles with small grains. Finally, the model predicts most of the chemo-mechanical damage accumulates in the first charge after formation. This chemo-mechanical "damage saturation" effect indicates that initial particle fracture occurs within the first few cycles, while long-term cathode degradation is not solely chemo-mechanically induced. The principle contribution of this research is the use of an anisotropic chemo-mechanical model to test how particle geometry affect capacity fade, which predicts that particle size has a stronger effect on capacity fade than grain size and ultimately that small particles with large grains have the least capacity fade.

cathode↗
DOE OSTI2021

Model Based Predictive Control for Frequency Support in Multi-port Autonomous Reconfigurable Solar Plants

Primary frequency support functionality can be an added advantage for any new grid integrated power electronics resource. With increased penetration of power electronics resources, inertial and primary frequency response capabilities are decreasing. In this research paper, an advanced model-based predictive control (MBPC) algorithm for providing frequency support to a new topology of integrated photovoltaic(PV), batterybased energy storage systems (ESS), and high-voltage direct current (HV dc) systems called multi-port autonomus reconfigurable solar (MARS) plants is based on the synchronverter-based control. The simulation of MARS-HV dc system with proposed control strategy is simulated and validated for MARS connected to low short circuit ratio (SCR) grids in PSCAD/EMTDC simulation environment. The control algorithm proposed showcases better performance in terms of frequency nadir improvement and frequency steady state improvemnt with respect to no frequency control.

Marthi, Phani Ratna Vanamali↗
DOE OSTI2020

A statistical model to predict ignition probability

Ignition capability is a critical design constraint for aeronautical gas turbines. However the current trend toward overall lean burn is detrimental to the engine ignition and relight and the ignition system must be adapted to ensure a fast and reliable light-round in all circumstances. As ignition is a stochastic phenomenon, the optimization of an ignition system requires to build ignition probability maps, which is difficult and costly with either experiment or numerical simulation as both require many tests. Here, this work proposes a model to predict the ignition probability map, knowing only flow statistics in non-reacting conditions, i.e., with only one test. The originality of the model is to construct statistics of the flame kernel trajectory, which are then combined with local flow indicators to evaluate the ignition probability at the considered sparking location. Application to a swirled burner operated in premixed, non-premixed and spray combustion modes illustrates the model concepts and demonstrates its ability to recover the experimental ignition map with good accuracy.

42 ENGINEERING↗
DOE OSTI2022

Language models for the prediction of SARS-CoV-2 inhibitors

The COVID-19 pandemic highlights the need for computational tools to automate and accelerate drug design for novel protein targets. We leverage deep learning language models to generate and score drug candidates based on predicted protein binding affinity. We pre-trained a deep learning language model (BERT) on ∼9.6 billion molecules and achieved peak performance of 603 petaflops in mixed precision. Our work reduces pre-training time from days to hours, compared to previous efforts with this architecture, while also increasing the dataset size by nearly an order of magnitude. For scoring, we fine-tuned the language model using an assembled set of thousands of protein targets with binding affinity data and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro and PLpro. We utilized a genetic algorithm approach for finding optimal candidates using the generation and scoring capabilities of the language model. Our generalizable models accelerate the identification of inhibitors for emerging therapeutic targets.

Blanchard, Andrew E.↗
DOE OSTI2023

Dimensionally reduced machine learning model for predicting single component octanol–water partition coefficients

Abstract MF-LOGP, a new method for determining a single component octanol–water partition coefficients ( $$LogP$$ LogP ) is presented which uses molecular formula as the only input. Octanol–water partition coefficients are useful in many applications, ranging from environmental fate and drug delivery. Currently, partition coefficients are either experimentally measured or predicted as a function of structural fragments, topological descriptors, or thermodynamic properties known or calculated from precise molecular structures. The MF-LOGP method presented here differs from classical methods as it does not require any structural information and uses molecular formula as the sole model input. MF-LOGP is therefore useful for situations in which the structure is unknown or where the use of a low dimensional, easily automatable, and computationally inexpensive calculations is required. MF-LOGP is a random forest algorithm that is trained and tested on 15,377 data points, using 10 features derived from the molecular formula to make $$LogP$$ LogP predictions. Using an independent validation set of 2713 data points, MF-LOGP was found to have an average $$RMSE$$ RMSE = 0.77 ± 0.007, $$MAE$$ MAE = 0.52 ± 0.003, and $${R}^{2}$$ R 2 = 0.83 ± 0.003. This performance fell within the spectrum of performances reported in the published literature for conventional higher dimensional models ( $$RMSE$$ RMSE = 0.42–1.54, $$MAE$$ MAE = 0.09–1.07, and $${R}^{2}$$ R 2 = 0.32–0.95). Compared with existing models, MF-LOGP requires a maximum of ten features and no structural information, thereby providing a practical and yet predictive tool. The development of MF-LOGP provides the groundwork for development of more physical prediction models leveraging big data analytical methods or complex multicomponent mixtures. Graphical Abstract

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Generative large language models for predictive maintenance planning

Maintenance planning and the generation of necessary components for tasks can prove time-consuming and complex. Automating the creation of recurring or similar tasks by leveraging previous planning packages and data, while uncovering insights to automate planning package generation, presents an opportunity to conserve valuable time and resources. This work aims to harness the textual and probabilistic capabilities of large language models (LLMs) to automate the generation of planning packages. Utilizing diverse data sources ranging from raw data to handwritten text, both singular and collaborative LLMs are trained and tested. Results demonstrate their capability to generate essential planning package components, effectively replicating the statistical patterns in the data. This demonstrates the use of these tools inside a digital asset for automated planning. This work outlines a methodology for constructing datasets, a training suite, and evaluation methods for LLM-based textual and conversational planning tools utilized in an asset digital twin. Results indicate that the fine-tuned models generate estimated planning information within the statistical ranges observed in real maintenance data. The models achieve high accuracy (>90%) in document question-answering and instruction generation tasks. Furthermore, the conversational retrieval-augmented generation (RAG) assistant system achieves 100% document retrieval accuracy, while conversational information capture exceeds 98% across the majority of work-package assistant modules.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Shell Predictive Battery Life Models (SPBLM) [SWR-20-35]

Battery life models to predict the capacity fade and resistance growth of lithium-ion batteries from various manufacturers with different chemistries. The battery life model is trained on experimental test data, and accounts for calendar and cycling aging mechanisms as functions of cell environmental conditions and use. The battery life model is then used to predict capacity fade and resistance growth under any arbitrary aging scenario.

Smith, Kandler↗
DOE OSTI2023

Bayesian-Motivated Probabilistic Model of Hurricane-Induced Multimechanism Flood Hazards

Multimechanism floods (MMFs) are caused by the simultaneous occurrence of more than one flood mechanism such as storm surge, precipitation, tides, and waves. MMFs can lead to more severe or differing impacts than single-mechanism floods. As a result, comprehensive risk assessments require the ability to assess the multivariate probabilistic behaviors of hazards from MMFs. Here this study introduces a novel Bayesian-motivated approach for the probabilistic assessment of hurricane-induced hazards from the combination of the surge, precipitation, tides, and river antecedent flow. A Bayesian network (BN) is developed to capture the physical (conditional) relationship between variables and facilitate the generation of a hazard curve for river discharge that captures the contributions from multiple flood drivers. A case study located along the Delaware River is used to illustrate the proposed approach. Five computationally efficient representative predictive models are developed to estimate the conditional distributions required for the BN as a means of demonstrating the overall framework. The predictive models used in this study act as placeholders and can be replaced with more sophisticated and high-fidelity models depending on the desired accuracy level. While the predictive models are intended to be representative and illustrative, the model performance is evaluated using three historical storms that affected the area. Overall, the proposed framework is shown to be transparent, effective, and adaptable.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Data to Accompany: PM2.5 is insufficient to explain personal PAH exposure

Fine particulate matter (PM2.5) air quality index (AQI) data from outdoor stationary monitors and Hazard Mapping System (HMS) smoke density data from satellites are often used as proxies for personal chemical exposure. Silicone wristbands can quantify more individualized exposure data than stationary air monitors or smoke satellites. However, it is not understood how these proxy measurements compare to chemical data measured from wristbands. We hypothesized that predictive models for personal chemical exposure would be significantly improved by expanding beyond stationary PM2.5 AQI data or satellite HMS data to also include environmental and behavioral information. In Eugene, Oregon, participants wore daily wristbands, carried a phone that recorded locations, and answered daily questionnaires for a seven-day period in multiple seasons. We gathered publicly available daily PM2.5 AQI data and HMS data. We analyzed wristbands for 94 organic chemicals, including 53 polycyclic aromatic hydrocarbons (PAHs). Wristband chemical detections and concentrations, behavioral variables (e.g., time spent indoors), and environmental conditions (e.g., PM2.5 AQI) significantly differed between seasons. Machine learning models were fit to predict personal chemical exposure using PM2.5 AQI only, HMS only, and a multivariate feature set including PM2.5 AQI, HMS, and other environmental and behavioral information. On average, the multivariate models increased predictive accuracy by approximately 70% compared to either the AQI model or the HMS model for all chemicals modeled. This study provides evidence that PM2.5 AQI data alone or HMS data alone is insufficient to explain personal chemical exposures. Our results identify additional key predictors of personal chemical exposure.

Bramer, Lisa M↗
DOE OSTI2022

Examination of stiff ion temperature gradient mode physics in simulations of DIII-D H-mode transport

A systematic evaluation of gyrokinetic and gyrofluid model predictions of ion temperature gradient (ITG) stability and transport using parameters from DIII-D high confinement mode (H-mode) plasmas has been performed. The nonlinear CGYRO code is used to make the gyrokinetic predictions, and the quasilinear TGLF model for the corresponding gyrofluid predictions. The assessments are made at three radii (normalized toroidal flux ρtor = 0.4, 0.55, and 0.7) in three different plasma scenarios with varying levels of neutral beam heating and torque. For each of the nine cases (3 radii × 3 scenarios) considered, ITG turbulence is found to be the dominant long-wavelength instability and transport mechanism. The inclusions of both transverse magnetic fluctuations and dynamic fast beam ions are stabilizing for all cases considered, with strongest effects seen at ρor = 0.4 where the fast ion population and normalized plasma pressure β = 2μ0nT/B2 are highest. The further inclusion of parallel magnetic fluctuations does not have a meaningful impact on the ITG turbulence in these scenarios, but does destabilize (in combination with fast ions) new high-frequency instabilities at ρtor = 0.4 in the high power scenarios. In each case the linear and nonlinear ITG critical gradients are predicted to be lower than the measured ITG scale lengths and their associated uncertainties. Inclusion of equilibrium flow shear in the transport predictions generally leads to an upshift in effective critical gradient rather than a qualitative change in the predicted stiffness, with stronger responses typically seen in the gyrokinetic predictions than in the gyrofluid results. However, in most cases these upshifted gradients still remain below the measured values and their uncertainties. Although the predicted critical gradients are below the measured gradients, both models predicted flux-matching gradients consistent with measured values in six of the nine cases considered, with no clear systematic over- or underprediction. Thus, while the experimental ion temperature profiles do not appear to be closely pinned to the ITG critical gradient, both gyrokinetic and gyrofluid models are able to accurately match the measured gradients reasonably well in most cases.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗