SEARCH · Engineering Papers

Results for “Performance Modeling”

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.

SourceResearch connectionFrom yearThrough year

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

At least 739 records · Page 41

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Exploring Flooded Fraction Prediction through Machine Learning Models Focusing on Medical Infrastructure in the Southeast U.S. Coastal Areas

Rising sea levels due to climate change increasingly threaten medical infrastructure through flooding. This study develops machine learning models to predict flood exposure for 11,508 medical facilities in the southeastern coastal regions of the United States by integrating datasets including meteorological, hydrological, topographic, and geological data, the Natural Risk Index, and historical flood records from NASA, HIFLD, and FEMA. Six regression models, namely Linear Regression, Support Vector Regression, Random Forest, k-Nearest Neighbors, XGBoost, and Artificial Neural Networks, are trained using 16 explanatory variables identified through literature review and correlation analysis. Data preprocessing employs the SMOGN for class imbalance and Winsorization for outliers. Model performance is evaluated using MAE, MSE, and RMSE, with Random Forest and XGBoost models achieving the highest performance (MSE of 2.58e-5 and 3.69e-5, respectively). This multifactorial approach allows the models to capture complex flood-influencing relationships, enhancing adaptability and performance across geographic regions. Future work focuses on expanding across the U.S. and developing a near real-time flood monitoring system.

Jihoon Chung↗

NASA NTRS1976

Dynamic modeling for evaluation of solar collector performance

Dynamic modeling is being developed to provide a tool for systematic analysis of performance characteristics in energy systems where time-dependent behavior is important. A dynamic model program designed to aid in the understanding of solar collector behavior over the full range of operating conditions was constructed and tested in the evaluation of a conceptual collector design.

Hamilton, C. L.↗

DOE OSTI2020

The importance of round-robin validation when assessing machine-learning-based vertical extrapolation of wind speeds

The extrapolation of wind speeds measured at a meteorological mast to wind turbine rotor heights is a key component in a bankable wind farm energy assessment and a significant source of uncertainty. Industry-standard methods for extrapolation include the power-law and logarithmic profiles. The emergence of machine-learning applications in wind energy has led to several studies demonstrating substantial improvements in vertical extrapolation accuracy in machine-learning methods over these conventional power-law and logarithmic profile methods. In all cases, these studies assess relative model performance at a measurement site where, critically, the machine-learning algorithm requires knowledge of the rotor-height wind speeds in order to train the model. This prior knowledge provides fundamental advantages to the site-specific machine-learning model over the power-law and log profiles, which, by contrast, are not highly tuned to rotor-height measurements but rather can generalize to any site. Furthermore, there is no practical benefit in applying a machine-learning model at a site where winds at the heights relevant for wind energy production are known; rather, its performance at nearby locations (i.e., across a wind farm site) without rotor-height measurements is of most practical interest. To more fairly and practically compare machine-learning-based extrapolation to standard approaches, we implemented a round-robin extrapolation model comparison, in which a random-forest machine-learning model is trained and evaluated at different sites and then compared against the power-law and logarithmic profiles. We consider 20 months of lidar and sonic anemometer data collected at four sites between 50 and 100 km apart in the central United States. We find that the random forest outperforms the standard extrapolation approaches, especially when incorporating surface measurements as inputs to include the influence of atmospheric stability. When compared at a single site (the traditional comparison approach), the machine-learning improvement in mean absolute error was 28 % and 23 % over the power-law and logarithmic profiles, respectively. Using the round-robin approach proposed here, this improvement drops to 20 % and 14 %, respectively. These latter values better represent practical model performance, and we conclude that round-robin validation should be the standard for machine-learning-based wind speed extrapolation methods.

17 WIND ENERGY↗

DOE OSTI2023

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Research & Experimental Medicine↗

NASA NTRS1989

Enhanced modeling features within TREETOPS

The original motivation for TREETOPS was to build a generic multi-body simulation and remove the burden of writing multi-body equations from the engineers. The motivation of the enhancement was twofold: (1) to extend the menu of built-in features (sensors, actuators, constraints, etc.) that did not require user code; and (2) to extend the control system design capabilities by linking with other government funded software (NASTRAN and MATLAB). These enhancements also serve to bridge the gap between structures and control groups. It is common on large space programs for the structures groups to build hi-fidelity models of the structure using NASTRAN and for the controls group to build lower order models because they lack the tools to incorporate the former into their analysis. Now the controls engineers can accept the hi-fidelity NASTRAN models into TREETOPS, add sensors and actuators, perform model reduction and couple the result directly into MATLAB to perform their design. The controller can then be imported directly into TREETOPS for non-linear, time-history simulation.

Vandervoort, R. J.↗

DOE OSTI2021

Modeling Profiles of Micrometeorological Variables in a Tropical Premontane Rainforest Using Multi-Layered CLM (CLM-ML)

This study updates the multi-layered Community Land Model (CLM-ml) for hillslopes and compares predictions from against observations collected in tropical montane rainforest, Costa Rica. Modifications are made in order to capture a wider array of vertical leaf area distributions, predict CO 2 profiles, account for soil respiration, and adjust wind forcings for difficult topographic settings. Test results indicate that the modified multi-layer CLM model can successfully replicate the shape of various micrometeorological profiles (humidity, CO 2 , temperature, and wind speed) under the canopy. In the single-layer models (CLM4.5 and CLM5), excessive day-to-night differences in leaf temperature and leaf wetness were originally noted, but CLM-ml significantly improved these issues, decreasing the amplitudes of diurnal cycles by 67% and 47%. Sub-canopy considerations, such as canopy shapes and turbulent transfer parameters, also played a significant role in model performance. More importantly, unlike single layer models, the results that CLM-ml produces can be compared to variables measured within the canopy to provide far more detailed diagnostic information. Further observations and model developments, aimed at reflecting surface heterogeneity, will be necessary to adequately capture the complexity and the features of the tropical montane rainforest.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Comparison of modular analytical wake models to the Lillgrund wind plant

Efficient and accurate wake models are required for wind plant performance modeling and the suite of engineering processes that support wind plant layout, control, and monitoring. Although many analytical and engineering wake models with low computational costs have been proposed, their ability to represent the power production of large wind plants in a wide range of atmospheric conditions is not completely understood. The following validation study reviews the underlying theory for analytical wake models, outlines quality control procedures for observational data, and compares model results with observational data from the Lillgrund Wind Plant. Lillgrund makes a valuable case study for wake modeling because of its regular arrangement and the relatively close spacing of constituent wind turbines, which lead to regular and significant wake interactions within the wind plant and the development of deep array flow conditions. Formulations for the velocity deficit, wake-added turbulence, and wake superposition methods are considered in a modular sense, yielding many possible configurations to represent wind turbine wakes, of which seven are examined in detail. Velocity deficit models that account for flow conditions in the near wake are better able to reproduce power production for wind turbines in the transitional region of the wind plant, where wind turbines experience as many as five wakes from upstream turbines. Finally, in the deep array, where power production reaches asymptotic values and wake statistics become quasi-periodic, wake superposition schemes become the largest driver in error reduction; using the linear or maximum wake superposition methods can reduce the relative root mean square error by as much as 40% in the deep array.

17 WIND ENERGY↗

DOE OSTI2024

Code Description for "Brief Communication: Monitoring snow depth using small, cheap, and easy-to-deploy ground surface temperature sensors"

Temporally continuous snow depth estimates are vital for understanding changing snow patterns and impacts on permafrost in the Arctic. We train a random forest machine learning model to predict snow depth from variability in ground surface temperature. To our knowledge, this is the first time that small ground surface temperature sensors have been used to estimate snow depth. The model performs well at sites where the model was trained and at pan-arctic evaluation sites (RMSE <= 0.15 m). Small temperature sensors are cheap and easy-to-deploy, so this technique enables spatially distributed and temporally continuous snowpack monitoring to an extent previously infeasible. The model is flexible and can be applied to datasets retroactively to retrieve snow depth estimates at additional sites. This code package includes a *.joblib file of the trained random forest model and a *.ipynb file showing how to clean input data, train the random forest model, and apply the model.

Bachand, Claire↗

DOE OSTI2023

Assessing the Influence of Climate on the Spatial Pattern of West Nile Virus Incidence in the United States

West Nile virus (WNV) is the leading cause of mosquito-borne disease in humans in the United States. Since the introduction of the disease in 1999, incidence levels have stabilized in many regions, allowing for analysis of climate conditions that shape the spatial structure of disease incidence. Our goal was to identify the seasonal climate variables that influence the spatial extent and magnitude of WNV incidence in humans. We developed a predictive model of contemporary mean annual WNV incidence using U.S. county-level case reports from 2005 to 2019 and seasonally averaged climate variables. We used a random forest model that had an out-of-sample model performance of R 2 =0.61. Our model accurately captured the V-shaped area of higher WNV incidence that extends from states on the Canadian border south through the middle of the Great Plains. It also captured a region of moderate WNV incidence in the southern Mississippi Valley. The highest levels of WNV incidence were in regions with dry and cold winters and wet and mild summers. The random forest model classified counties with average winter precipitation levels <23.3 mm/month as having incidence levels over 11 times greater than those of counties that are wetter. Among the climate predictors, winter precipitation, fall precipitation, and winter temperature were the three most important predictive variables. We consider which aspects of the WNV transmission cycle climate conditions may benefit the most and argued that dry and cold winters are climate conditions optimal for the mosquito species key to amplifying WNV transmission. Our statistical model may be useful in projecting shifts in WNV risk in response to climate change.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2023

The 2021 Blind PVPMC Modeling Intercomparison

This document provides the instructions for participating in the 2021 blind photovoltaic (PV) modeling intercomparison organized by the PV Performance Modeling Collaborative (PVPMC). It describes the system configurations, metadata, and other information necessary for the modeling exercise. The practical details of the validation datasets are also described. The datasets were published online in open access in April 2023, after completing the analysis of the results.

14 SOLAR ENERGY↗

DOE OSTI2023

An extended focused assessment with sonography in trauma ultrasound tissue-mimicking phantom for developing automated diagnostic technologies

Medical imaging-based triage is critical for ensuring medical treatment is timely and prioritized. However, without proper image collection and interpretation, triage decisions can be hard to make. While automation approaches can enhance these triage applications, tissue phantoms must be developed to train and mature these novel technologies. Here, we have developed a tissue phantom modeling the ultrasound views imaged during the enhanced focused assessment with sonography in trauma exam (eFAST). The tissue phantom utilized synthetic clear ballistic gel with carveouts in the abdomen and rib cage corresponding to the various eFAST scan points. Various approaches were taken to simulate proper physiology without injuries present or to mimic pneumothorax, hemothorax, or abdominal hemorrhage at multiple locations in the torso. Multiple ultrasound imaging systems were used to acquire ultrasound scans with or without injury present and were used to train deep learning image classification predictive models. Performance of the artificial intelligent (AI) models trained in this study achieved over 97% accuracy for each eFAST scan site. We used a previously trained AI model for pneumothorax which achieved 74% accuracy in blind predictions for images collected with the novel eFAST tissue phantom. Grad-CAM heat map overlays for the predictions identified that the AI models were tracking the area of interest for each scan point in the tissue phantom. Overall, the eFAST tissue phantom ultrasound scans resembled human images and were successful in training AI models. Tissue phantoms are critical first steps in troubleshooting and developing medical imaging automation technologies for this application that can accelerate the widespread use of ultrasound imaging for emergency triage.

60 APPLIED LIFE SCIENCES↗

NASA NTRS1996

A priori testing of subgrid-scale models for the velocity-pressure and vorticity-velocity formulations

Subgrid-scale models for Large Eddy Simulation (LES) in both the velocity-pressure and the vorticity-velocity formulations were evaluated and compared in a priori tests using spectral Direct Numerical Simulation (DNS) databases of isotropic turbulence: 128(exp 3) DNS of forced turbulence (Re(sub(lambda))=95.8) filtered, using the sharp cutoff filter, to both 32(exp 3) and 16(exp 3) synthetic LES fields; 512(exp 3) DNS of decaying turbulence (Re(sub(Lambda))=63.5) filtered to both 64(exp 3) and 32(exp 3) LES fields. Gaussian and top-hat filters were also used with the 128(exp 3) database. Different LES models were evaluated for each formulation: eddy-viscosity models, hyper eddy-viscosity models, mixed models, and scale-similarity models. Correlations between exact versus modeled subgrid-scale quantities were measured at three levels: tensor (traceless), vector (solenoidal 'force'), and scalar (dissipation) levels, and for both cases of uniform and variable coefficient(s). Different choices for the 1/T scaling appearing in the eddy-viscosity were also evaluated. It was found that the models for the vorticity-velocity formulation produce higher correlations with the filtered DNS data than their counterpart in the velocity-pressure formulation. It was also found that the hyper eddy-viscosity model performs better than the eddy viscosity model, in both formulations.

Winckelmans, G. S.↗

NASA NTRS2021

Mass Inferencing Model Creation And Deployment To Lunar Excavation Robot, RASSOR

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) Excavator is a teleoperated mobile robotic platform with a unique space regolith excavation capability. This research project developed functionality for inferencing regolith mass ingested during RASSOR operation, enhancing RASSOR’s ability to successfully complete ISRU missions. Radio wave propagation time to the Moon and back is ~2.56 seconds. Though teleoperation is possible with this delay, autonomous capability that enables RASSOR to plan and execute excavation missions intelligently and efficiently is preferred. To teleoperate or run autonomously, it is crucial for the quantity of regolith mass ingested by RASSOR to be available as a system state for efficient operation (e.g. knowledge of whether drums are full informs the task of highest priority, whether it be continuing to dig, or returning to a processing plant to offload regolith). A configurable data reduction and analysis pipeline was created to allow for straightforward incorporation of new data, such as that from lunar excavation, to improve model performance in new environments. Four distinct modeling approaches were employed in developing a mass inferencing approach that could work on RASSOR. All four models take in system states and output a mass prediction for each set of the robot’s bucket drums. Initial results from deployment to RASSOR and testing in a simulated lunar environment show that the models have <10% mean error during robot operation. Future work includes refinement of a model that estimates regolith mass in real-time during excavation as well as further testing of the developed models on the hardware.

ROS↗

DOE OSTI2023

De-Risking Large-Scale PV Systems Through Data Analytics

Large-scale photovoltaic system performance analysis is being conducted within the US Department of Energy's-sponsored PV Fleet Performance Data Initiative. This collaboration with commercial PV system owners collects and evaluates PV field performance data, and provides reports on aggregated results. Drawing on over 2200 sites across the US and over 24,000 separate PV inverters we have collected in excess of 8.3 gigawatts (GW) of performance data, representing 6-7% of the entire US installed PV capacity. A mixture of utility-scale and large commercial systems are represented, averaging 4.1 megawatts (MW) in size and 5 years in age. Initial results show average system degradation rates at -0.75% / year, which is slightly higher than historically reported module-level values of -0.5%/year. We also found that the availability of systems averaged 97.7%, which is lower than the typical 99% uptime assumed by many project economic forecasts. Given these results, we compared monthly performance with expected production values, based on satellite weather data and a simple PVWatts performance model. We found that systems were performing within 10% of monthly expectation over 90% of the time, with a fleet average vs expected monthly value of 0.994. We also evaluated the impact of extreme weather events on system performance, and found a range of short-term and longer-term performance effects ranging from grid outage, system downtime, module damage and accelerated long-term degradation rate.

analysis↗

DOE OSTI2025

Fuel Bonding and its Impact on Axial Gas Communication Behavior in Light-Water Reactor Fuel Rods

Axial gas communication concerns the flow along the axial axis of nuclear fuel rods during ramp and loss of coolant accident (LOCA) conditions. During power ramps, the higher linear heat generation rate may cause fuel-to-clad gap closure that may prevent transport of released fission gases to the plenum. Upon reduction in power the gas then can communicate to the plenum. This phenomenon has been experimentally observed by short power dips during ramp experiments completed at the Risø reactor. At higher burnups it is observed that the UO2 fuel and Zircaloy cladding forms a chemical bond. This bond results in complete closure of the gap. When these high burnup rods are subjected to a LOCA, the bond has implications on both the mechanical response (i.e., ballooning) of the cladding and subsequent fuel relocation and axial gas communication. In the LOCA scenario, gas communication is of interest in two different regimes: 1) pre-rupture communication from the plenum towards the lower pressure ballooning area and 2) the post-rupture depressurization of the plenum to the external system pressure. In both regimes the presence of a fuel-to-cladding bond will impact the rate of depressurization. In this work we present a fuel-to-clad bonding model that is coupled to an existing axial gas communication model framework in the BISON fuel performance code. The effect of considering the bond on fuel performance modeling predictions is presented through comparisons to existing experimental data. Experiments considered include several rods from the Halden IFA-650 test series. An evaluation on a full-length rod that explores the combined effect of plenum size and bonding status on axial gas communication behavior is also presented.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2022

Generalizability analysis of tool condition monitoring ensemble machine learning models

Tool condition monitoring (TCM) is an essential research area for the optimization and automation of metal machining processes, and could help manufacturers reduce costs, production time, machine downtime, energy use, and part scrappage. However, TCM systems developed in prior studies have struggled to reach the high level of generalizability which is necessary for industrial applications. This study addresses TCM system generalizability to new machining conditions, how variations in machining and environmental conditions may be used to improve model generalizability, and ensemble machine learning techniques for TCM. Further, milling tool life experiments were conducted using various machining conditions, and the processes' sound, spindle power, and axial load signals were collected. Different machine learning models were evaluated for the prediction of tool wear levels, including four individual models and five ensemble models. Changes in cutting speed were found to display a large effect on model performance, while the chip load showed some effect, and the feed rate had little effect. A simulated noise data augmentation technique for model improvement is applied within TCM for the first time, and resulted in increased model generalizability and reduced overfitting. Across several performance metrics the extremely randomized trees ensemble machine learning model generally performed the best for this application, achieving a leave-one-group-out cross validation accuracy score of 92.4 %, a 10-fold cross validation score of 98.9 %, and an averaged accuracy across 11 generalizability tests of 87.3 %.

42 ENGINEERING↗

NASA NTRS2000

Analytic Guided-Search Model of Human Performance Accuracy in Target- Localization Search Tasks

Current models of human visual search have extended the traditional serial/parallel search dichotomy. Two successful models for predicting human visual search are the Guided Search model and the Signal Detection Theory model. Although these models are inherently different, it has been difficult to compare them because the Guided Search model is designed to predict response time, while Signal Detection Theory models are designed to predict performance accuracy. Moreover, current implementations of the Guided Search model require the use of Monte-Carlo simulations, a method that makes fitting the model's performance quantitatively to human data more computationally time consuming. We have extended the Guided Search model to predict human accuracy in target-localization search tasks. We have also developed analytic expressions that simplify simulation of the model to the evaluation of a small set of equations using only three free parameters. This new implementation and extension of the Guided Search model will enable direct quantitative comparisons with human performance in target-localization search experiments and with the predictions of Signal Detection Theory and other search accuracy models.

Eckstein, Miguel P.↗

NASA NTRS1990

Update transport - A new technique for update synchronization in replicated database systems

A fully distributed approach to update synchronization is presented where each site completely executes every update. This approach has several features-higher resiliency to different kinds of failures, higher parallelism, improved response to user requests, and low communication overhead. A fully distributed algorithm for concurrency control obtained by rehashing a previously published semidistributed algorithm into the fully distributed model of update execution is presented. A performance model of replicated database systems is presented and used to study the performance of the proposed algorithm and its semidistributed version. The results of the performance study reveal that the proposed approach can substantially improve the performance at the cost of moderate input/output overhead.

Singhal, Mukesh↗