SEARCH · Engineering Papers

Results for “Operator regression”

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 505 records · Page 28

All sources NASA NTRS DOE OSTI

NASA NTRS2009

Hybrid NN/SVM Computational System for Optimizing Designs

A computational method and system based on a hybrid of an artificial neural network (NN) and a support vector machine (SVM) (see figure) has been conceived as a means of maximizing or minimizing an objective function, optionally subject to one or more constraints. Such maximization or minimization could be performed, for example, to optimize solve a data-regression or data-classification problem or to optimize a design associated with a response function. A response function can be considered as a subset of a response surface, which is a surface in a vector space of design and performance parameters. A typical example of a design problem that the method and system can be used to solve is that of an airfoil, for which a response function could be the spatial distribution of pressure over the airfoil. In this example, the response surface would describe the pressure distribution as a function of the operating conditions and the geometric parameters of the airfoil. The use of NNs to analyze physical objects in order to optimize their responses under specified physical conditions is well known. NN analysis is suitable for multidimensional interpolation of data that lack structure and enables the representation and optimization of a succession of numerical solutions of increasing complexity or increasing fidelity to the real world. NN analysis is especially useful in helping to satisfy multiple design objectives. Feedforward NNs can be used to make estimates based on nonlinear mathematical models. One difficulty associated with use of a feedforward NN arises from the need for nonlinear optimization to determine connection weights among input, intermediate, and output variables. It can be very expensive to train an NN in cases in which it is necessary to model large amounts of information. Less widely known (in comparison with NNs) are support vector machines (SVMs), which were originally applied in statistical learning theory. In terms that are necessarily oversimplified to fit the scope of this article, an SVM can be characterized as an algorithm that (1) effects a nonlinear mapping of input vectors into a higher-dimensional feature space and (2) involves a dual formulation of governing equations and constraints. One advantageous feature of the SVM approach is that an objective function (which one seeks to minimize to obtain coefficients that define an SVM mathematical model) is convex, so that unlike in the cases of many NN models, any local minimum of an SVM model is also a global minimum.

Rai, Man Mohan↗

NASA NTRS2012

Improvement of Aerosol Optical Depth Retrieval from MODIS Spectral Reflectance over the Global Ocean Using New Aerosol Models Archived from AERONET Inversion Data and Tri-axial Ellipsoidal Dust Database

New over-ocean aerosol models are developed by integrating the inversion data from the Aerosol Robotic Network (AERONET) sun/sky radiometers with a database for the optical properties of tri-axial ellipsoid particles. The new aerosol models allow more accurate retrieval of aerosol optical depth (AOD) from the Moderate Resolution Imaging Spectroradiometer (MODIS) in the case of high AOD (AOD greater than 0.3). The aerosol models are categorized by using the fine-mode fraction (FMF) at 550 nm and the singlescattering albedo (SSA) at 440 nm from the AERONET inversion data to include a variety of aerosol types found around the globe. For each aerosol model, the changes in the aerosol optical properties (AOPs) as functions of AOD are considered to better represent aerosol characteristics. Comparisons of AODs between AERONET and MODIS for the period from 2003 to 2010 show that the use of the new aerosol models enhances the AOD accuracy with a Pearson coefficient of 0.93 and a regression slope of 0.99 compared to 0.92 and 0.85 calculated using the MODIS Collection 5 data. Moreover, the percentage of data within an expected error of +/-(0.03 + 0.05xAOD) is increased from 62 percent to 64 percent for overall data and from 39 percent to 51 percent for AOD greater than 0.3. Errors in the retrieved AOD are further characterized with respect to the Angstrom exponent (AE), scattering angle, SSA, and air mass factor (AMF). Due to more realistic AOPs assumptions, the new algorithm generally reduces systematic errors in the retrieved AODs compared with the current operational algorithm. In particular, the underestimation of fine-dominated AOD and the scattering angle dependence of dust-dominated AOD are significantly mitigated as results of the new algorithm's improved treatment of aerosol size distribution and dust particle nonsphericity.

aerosol optical depth↗

NASA NTRS2010

Objective Lightning Probability Forecasting for Kennedy Space Center and Cape Canaveral Air Force Station, Phase III

The AMU created new logistic regression equations in an effort to increase the skill of the Objective Lightning Forecast Tool developed in Phase II (Lambert 2007). One equation was created for each of five sub-seasons based on the daily lightning climatology instead of by month as was done in Phase II. The assumption was that these equations would capture the physical attributes that contribute to thunderstorm formation more so than monthly equations. However, the SS values in Section 5.3.2 showed that the Phase III equations had worse skill than the Phase II equations and, therefore, will not be transitioned into operations. The current Objective Lightning Forecast Tool developed in Phase II will continue to be used operationally in MIDDS. Three warm seasons were added to the Phase II dataset to increase the POR from 17 to 20 years (1989-2008), and data for October were included since the daily climatology showed lightning occurrence extending into that month. None of the three methods tested to determine the start of the subseason in each individual year were able to discern the start dates with consistent accuracy. Therefore, the start dates were determined by the daily climatology shown in Figure 10 and were the same in every year. The procedures used to create the predictors and develop the equations were identical to those in Phase II. The equations were made up of one to three predictors. TI and the flow regime probabilities were the top predictors followed by 1-day persistence, then VT and Ll. Each equation outperformed four other forecast methods by 7-57% using the verification dataset, but the new equations were outperformed by the Phase II equations in every sub-season. The reason for the degradation may be due to the fact that the same sub-season start dates were used in every year. It is likely there was overlap of sub-season days at the beginning and end of each defined sub-season in each individual year, which could very well affect equation performance.

Crawford, Winifred C.↗

DOE OSTI2021

Assessing the Energy Resilience of Office Buildings: Development and Testing of a Simplified Metric for Real Estate Stakeholders

Increasing concern over higher frequency extreme weather events is driving a push towards a more resilient built environment. In recent years there has been growing interest in understanding how to evaluate, measure, and improve building energy resilience, i.e., the ability of a building to provide energy-related services in the event of a local or regional power outage. In addition to human health and safety, many stakeholders are keenly interested in the ability of a building to allow continuity of operations and minimize business disruption. Office buildings are subject to significant economic losses when building operations are disrupted due to a power outage. We propose “occupant hours lost” (OHL) as a means to measure the business productivity lost as the result of a power outage in office buildings. OHL is determined based on indoor conditions in each space for each hour during a power outage, and then aggregated spatially and temporally to determine the whole building OHL. We used quasi-Monte Carlo parametric energy simulations to demonstrate how the OHL metric varies due to different building characteristics across different climate zones and seasons. The simulation dataset was then used to develop simple regression models for assessing the impact of ten key building characteristics on OHL. The most impactful were window-to-wall ratio and window characteristics. The regression models show promise as a simple means to assess and screen for resilience using basic building characteristics, especially for non-critical facilities where it may not be viable to conduct detailed engineering analysis.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA NTRS2001

The Statistical Consulting Center for Astronomy (SCCA)

The process by which raw astronomical data acquisition is transformed into scientifically meaningful results and interpretation typically involves many statistical steps. Traditional astronomy limits itself to a narrow range of old and familiar statistical methods: means and standard deviations; least-squares methods like chi(sup 2) minimization; and simple nonparametric procedures such as the Kolmogorov-Smirnov tests. These tools are often inadequate for the complex problems and datasets under investigations, and recent years have witnessed an increased usage of maximum-likelihood, survival analysis, multivariate analysis, wavelet and advanced time-series methods. The Statistical Consulting Center for Astronomy (SCCA) assisted astronomers with the use of sophisticated tools, and to match these tools with specific problems. The SCCA operated with two professors of statistics and a professor of astronomy working together. Questions were received by e-mail, and were discussed in detail with the questioner. Summaries of those questions and answers leading to new approaches were posted on the Web (www.state.psu.edu/ mga/SCCA). In addition to serving individual astronomers, the SCCA established a Web site for general use that provides hypertext links to selected on-line public-domain statistical software and services. The StatCodes site (www.astro.psu.edu/statcodes) provides over 200 links in the areas of: Bayesian statistics; censored and truncated data; correlation and regression, density estimation and smoothing, general statistics packages and information; image analysis; interactive Web tools; multivariate analysis; multivariate clustering and classification; nonparametric analysis; software written by astronomers; spatial statistics; statistical distributions; time series analysis; and visualization tools. StatCodes has received a remarkable high and constant hit rate of 250 hits/week (over 10,000/year) since its inception in mid-1997. It is of interest to scientists both within and outside of astronomy. The most popular sections are multivariate techniques, image analysis, and time series analysis. Hundreds of copies of the ASURV, SLOPES and CENS-TAU codes developed by SCCA scientists were also downloaded from the StatCodes site. In addition to formal SCCA duties, SCCA scientists continued a variety of related activities in astrostatistics, including refereeing of statistically oriented papers submitted to the Astrophysical Journal, talks in meetings including Feigelson's talk to science journalists entitled "The reemergence of astrostatistics" at the American Association for the Advancement of Science meeting, and published papers of astrostatistical content.

Akritas, Michael↗

DOE OSTI2024

Photovoltaic Inverter Failure Mechanism Estimation Using Unsupervised Machine Learning and Reliability Assessment

This article introduces a data-driven approach to assessing failure mechanisms and reliability degradation in outdoor photovoltaic (PV) string inverters. The manufacturer's stated PV inverter lifetime can vary due to the impact of operating site conditions. To address limitations in degradation estimation through accelerated testing, condition monitoring, or degradation modeling, we propose a machine learning (ML) oriented approach. Utilizing data from a 1.4 MW PV power plant operational since 2016, with 46 string PV inverters tied to the grid, we employ the unsupervised one-class support vector machine ML technique to analyze inverter and sensor data, capable of classifying humidity cycling and temperature fluctuations as dominant failure mechanisms. Utilizing the anomaly alert relationship and alert details specific to the inverter, the level of PV inverter output is considered as its availability or available reliability. Subsequently, a continuous Markov model is applied to six-month alert data, revealing an average stated reliability of 20% after 20 years of continuous operation. These results support recommendations for time-bound preventive measures to enhance PV inverter reliability under diverse outdoor conditions. Furthermore, the approach provides a nondestructive, top–down, and generalized method for analyzing any commercial PV inverter exposed to outdoor conditions, contingent on the availability of relevant data.

14 SOLAR ENERGY↗

NASA NTRS1975

The use of hand-held 35 mm color infrared imagery for estimates of suspended solids - A progress report

A cost-effective aerial surveillance technique is proposed for detection and identification of suspended solids which would be operational for both governmental monitoring organizations and private individuals operating catfish farms. Sixteen catfish ponds were flown daily for seven days using two hand-held 35 mm cameras with both Kodachrome X and Ektachrome infrared film. Hue, value, and chroma designations were recorded for each pond on each date by three interpreters, and the accepted color was that recorded by at least two of the interpreters, or if there was a three hue range, the median was accepted. Relations between suspended solids and color designations were analyzed graphically, and chroma was discarded due to an apparent lack of correlation. The data obtained were then analyzed by multiple regression. Significant correlations were revealed between hue and value and total and inorganic suspended solids. If perfected, this technique could be developed to sufficent accuracy for large-scale reconnaissance surveys to monitor the quality of rivers and streams.

Miller, W. F.↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗

NASA NTRS2016

Prediction of Weather Impacts on Airport Arrival Meter Fix Capacity

This paper introduces a data driven model for predicting airport arrival capacity with a look-ahead time 2-8 hour forecast. The model is suitable for air traffic flow management by explicitly investigating the impact of convective weather on airport arrival meter fix throughput. Estimation of the arrival airport capacity under arrival meter fix flow constraints due to severe weather is an important part of Air Traffic Management (ATM). Airport arrival capacity can be reduced if one or more airport arrival meter fixes are partially or completely blocked by convective weather. When the predicted airport arrival demands exceed the predicted available airport's arrival capacity for a sustained period, Ground Delay Program (GDP) operations will be triggered by ATM system. Serious imbalances between demand and capacity occur most frequently when the airport capacity is severely degraded due to either bad airport terminal surface weather or inclement convective weather around airport arrival fixes. A model that predicts the weather-impacted airport arrival meter fix throughput may help ATM personnel to plan GDP operations more efficiently. This paper identifies the characteristics of air traffic flow across arrival meter fixes at Newark Liberty International Airport (EWR). The proposed approach, based on machine-learning methods, is developed to predict the weather impacted EWR arrival Meter Fix (MF) throughput. Sector forecast coverage is used to envision the weather impact on airport arrival MF flow, and the validation is accomplished by using Convective Weather Avoidance Model (CWAM) 0.5 to 2-hour and Collaborative Convective Forecast Product (CCFP) 4 to 8-hour look-ahead forecast data for the period of April-September in 2014. Furthermore, the regression tree ensemble learning of random forests approach for translating a sector forecast coverage model to an EWR arrival meter fix throughput model is examined. The results suggest that ATM decision makers in charge of MF flow control and GDP planning may benefit from adopting the airport arrival meter capacity prediction models to estimate the inclement weather impacts.

Wang, Yao X.↗

DOE OSTI2021

A surrogate-model-based approach for estimating the first and second-order moments of offshore wind power

Power curve, the functional relationship that governs the process of converting a set of weather variables experienced by a wind turbine into electric power, is widely used in the wind industry to estimate power output for planning and operational purposes. Existing methods for power curve estimation have three main limitations: (i) they mostly rely on wind speed as the sole input, thus ignoring the secondary, yet possibly significant effects of other environmental factors, (ii) they largely overlook the complex marine environment in which offshore turbines operate, potentially compromising their value in offshore wind energy applications, and (ii) they solely focus on the first-order properties of wind power, with little (or null) information about the variation around the mean behavior, which is important for ensuring reliable grid integration, asset health monitoring, and energy storage, among others. In light of that, this study investigates the impact of several wind-and wave-related factors on offshore wind power variability, with the ultimate goal of accurately predicting its first two moments. Further, our approach couples OpenFAST—a multi-physics wind turbine simulator—with Gaussian Process (GP) regression to reveal the underlying relationships governing offshore weather-to-power conversion. We first find that a multi-input power curve which captures the combined impact of wind speed, direction, and air density, can provide double-digit improvements, in terms of prediction accuracy, relative to univariate methods which rely on wind speed as the sole explanatory variable (e.g. the standard method of bins). Wave-related variables are found not important for predicting the average power output, but interestingly, appear to be extremely relevant in describing the fluctuation of the offshore power around its mean. Tested on real-world data collected at the New York/New Jersey bight, our proposed multi-input models demonstrate a high explanatory power in predicting the first two moments of offshore wind generation, testifying their potential value to the offshore wind industry.

17 WIND ENERGY↗

DOE OSTI2022

Combined full shape analysis of BOSS galaxies and eBOSS quasars using an iterative emulator

ABSTRACT Standard full-shape clustering analyses in Fourier space rely on a fixed power spectrum template, defined at the fiducial cosmology used to convert redshifts into distances, and compress the cosmological information into the Alcock–Paczynski parameters and the linear growth rate of structure. In this paper, we propose an analysis method that operates directly in the cosmology parameter space and varies the power spectrum template accordingly at each tested point. Predictions for the power spectrum multipoles from the TNS model are computed at different cosmologies in the framework of $\Lambda \rm {CDM}$. Applied to the final eBOSS QSO and LRG samples together with the low-z DR12 BOSS galaxy sample, our analysis results in a set of constraints on the cosmological parameters Ωcdm, H0, σ8, Ωb, and ns. To reduce the number of computed models, we construct an iterative process to sample the likelihood surface, where each iteration consists of a Gaussian process regression. This method is validated with mocks from N-body simulations. From the combined analysis of the (e)BOSS data, we obtain the following constraints: σ8 = 0.877 ± 0.049 and $\Omega _{\rm m}=0.304^{+0.016}_{-0.010}$ without any external prior. The eBOSS quasar sample alone shows a 3.1σ discrepancy compared to the Planck prediction.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

Quantification of Lanthanides in a Molten Salt Reactor Surrogate Off-Gas Stream Using Laser-Induced Breakdown Spectroscopy

To enable the deployment of molten salt reactor technology, the development of off-gas treatment systems and advanced monitoring tools capable of operating with high temperatures and radiation fields while delivering near real-time information is necessary. Here, we aim to fulfill this requirement and proposes laser-induced breakdown spectroscopy (LIBS) for monitoring molten salt aerosol streams. A sheath gas measuring method was developed to protect optical elements from aerosol particles and to ensure a relatively constant aerosol stream for measurement. An aqueous system was studied to demonstrate the utility of LIBS for monitoring possible fission products in an aerosol stream: Gd, Nd, and Sm up to 2000 parts per million (ppm). A calibration model was built using partial least squares (PLS) regression with five, six, and nine latent variables for Gd, Nd, and Sm, respectively. This calibration model successfully estimated the concentrations of three test samples, which were validated with inductively charged plasma optical emission spectroscopy measurements at a 99.9% confidence interval. To enhance these models, a genetic algorithm was used to filter the spectra before entering the PLS model, thereby limiting the spectral features being regressed to those with greater correlations to concentration. This allowed for the number of latent variables used in the PLS models to be reduced to four, three, and three for Gd, Nd, and Sm, respectively. Finally, the genetic algorithm-filtered PLS models were used to predict the concentrations of the aerosol stream on a real-time dataset and resulted in a 73%, 18%, and 25% improvement in root mean squared error of prediction compared to the original PLS models developed.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Uncertainty quantification and sensitivity analysis for SPERT III E-core reactivity measurement benchmarking

The Special Power Excursion Reactor Test (SPERT) III E-core experiment is important because it provides critical data on reactor behavior under significant reactivity insertions, which is essential for validating computer simulations and ensuring the safety of modern light water reactors. Its design similarities to contemporary reactors make it a valuable resource for understanding and mitigating extreme hazards in nuclear operations. The current study details the application of formal parametric uncertainty quantification and sensitivity analysis to a model of the SPERT-III E-core model for zero power reactivity benchmarking. Additionally, the reactivity impact from various modeling assumptions is quantified. Overall, an conservative estimate for an uncertainty in k$_{\text{eff}}$ of $\pm$1257 was observed. A less conservative, more realistic, uncertainty estimate of $\pm$1096 pcm can be justified by the potential for various parametric uncertainties to become negligible when sampled independently across the ~1400 pins in the core. The experimental results fall within both of these uncertainty bounds. Standardized regression coefficient as well as Sobol indices are used to identify the guide tube thicknesses as the primary contributors to the uncertainty in k$_{\text{eff}}$. Overall, this study provides information on how the uncertainties in input parameters and modeling methods impact simulated k$_{\text{eff}}$ values and can be used to aid model building efforts for future code validation with the SPERT-III E-core experiment.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

SymbolNet: neural symbolic regression with adaptive dynamic pruning for compression

Abstract Compact symbolic expressions have been shown to be more efficient than neural network (NN) models in terms of resource consumption and inference speed when implemented on custom hardware such as field-programmable gate arrays (FPGAs), while maintaining comparable accuracy (Tsoi et al 2024 EPJ Web Conf. 295 09036). These capabilities are highly valuable in environments with stringent computational resource constraints, such as high-energy physics experiments at the CERN Large Hadron Collider. However, finding compact expressions for high-dimensional datasets remains challenging due to the inherent limitations of genetic programming (GP), the search algorithm of most symbolic regression (SR) methods. Contrary to GP, the NN approach to SR offers scalability to high-dimensional inputs and leverages gradient methods for faster equation searching. Common ways of constraining expression complexity often involve multistage pruning with fine-tuning, which can result in significant performance loss. In this work, we propose S y m b o l N e t , a NN approach to SR specifically designed as a model compression technique, aimed at enabling low-latency inference for high-dimensional inputs on custom hardware such as FPGAs. This framework allows dynamic pruning of model weights, input features, and mathematical operators in a single training process, where both training loss and expression complexity are optimized simultaneously. We introduce a sparsity regularization term for each pruning type, which can adaptively adjust its strength, leading to convergence at a target sparsity ratio. Unlike most existing SR methods that struggle with datasets containing more than O ( 10 ) inputs, we demonstrate the effectiveness of our model on the LHC jet tagging task (16 inputs), MNIST (784 inputs), and SVHN (3072 inputs).

Tsoi, Ho Fung (ORCID:0000000225502184)↗

DOE OSTI2025

Multi-physics Topology OPtimization and Additive Manufacturing for High-temperature Heat Exchangers

This research significantly advances the understanding of high-temperature heat exchanger design through an integrated approach that combines topology optimization (TO), triply periodic minimal surface (TPMS) structures, additive manufacturing (AM) and thermohydraulic testing. Each of these components contributes uniquely to a unified, high-performance design, fabrication and testing workflow. Topology optimization serves as the foundation of the design methodology by providing a systematic way to determine the most effective material layout for separating hot and cold fluids while maximizing thermal performance. The researchers introduced a novel three-material optimization framework using two density fields to represent hot fluid, cold fluid, and solid domains. This approach enables automated discovery of optimal shapes and flow paths that cannot be intuitively designed, especially under constraints imposed by manufacturing technologies. Furthermore, constraints such as minimal wall thickness and overhang angles were embedded into the optimization process, ensuring that resulting designs are not only thermally efficient but also manufacturable using modern additive techniques. In parallel, the study delves into the use of Gyroid-based TPMS geometries for constructing the core of the heat exchanger. TPMS structures are known for their high surface area, excellent fluid mixing capabilities, and minimal pressure drop characteristics. The researchers applied a data-driven modeling framework using Heteroscedastic Sparse Gaussian Process Regression (HSGPR) combined with genetic algorithms. This allowed for the rapid evaluation and optimization of key geometric parameters such as frequency, iso-value, and phase shift. The result was a set of Gyroid structures tailored for high heat transfer and low flow resistance, demonstrating clear improvements over conventional straight-channel designs. After the designing process, additive manufacturing played a critical role by turning these highly complex, optimized geometries into physical components. Utilizing Laser Powder Bed Fusion (LPBF) with Haynes 282, the study demonstrated the feasibility of fabricating these heat exchangers at high precision. Post-processing methods, including dilation-erosion operations, were applied to ensure local features adhered to self-supporting constraints. The fabricated structures were then subjected to thermohydraulic testing under conditions representative of supercritical CO 2 Brayton cycles, validating the predicted performance and confirming the viability of the full design-to-fabrication pipeline. Finally, thermohydraulic testing across the above studies served as a crucial experimental validation of advanced heat exchanger. Under consistent high-temperature and high-pressure conditions using supercritical CO 2 , the testing demonstrated that both TO and Gyroid-based TPMS designs significantly outperformed conventional straight-channel HXs. The TO design achieved a 115% increase in UA and NTU and a 27.6% boost in gravimetric power density, while the data-driven optimized Gyroid design delivered a 166% increase in UA and NTU and improved effectiveness from 68.7% to 86.1%. These results validate the simulation models, confirm the manufacturability of complex geometries under AM constraints, and provide key insights into design-performance trade-offs, thereby advancing the development of high-efficiency, compact heat exchangers for extreme environments.

36 MATERIALS SCIENCE↗

NASA NTRS2010

Predictability of Top of Descent Location for Operational Idle-Thrust Descents

To enable arriving aircraft to fly optimized descents computed by the flight management system (FMS) in congested airspace, ground automation must accurately predict descent trajectories. To support development of the trajectory predictor and its uncertainty models, commercial flights executed idle-thrust descents at a specified descent speed, and the recorded data included the specified descent speed profile, aircraft weight, and the winds entered into the FMS as well as the radar data. The FMS computed the intended descent path assuming idle thrust after top of descent (TOD), and the controllers and pilots then endeavored to allow the FMS to fly the descent to the meter fix with minimal human intervention. The horizontal flight path, cruise and meter fix altitudes, and actual TOD location were extracted from the radar data. Using approximately 70 descents each in Boeing 757 and Airbus 319/320 aircraft, multiple regression estimated TOD location as a linear function of the available predictive factors. The cruise and meter fix altitudes, descent speed, and wind clearly improve goodness of fit. The aircraft weight improves fit for the Airbus descents but not for the B757. Except for a few statistical outliers, the residuals have absolute value less than 5 nmi. Thus, these predictive factors adequately explain the TOD location, which indicates the data do not include excessive noise.

Stell, Laurel L.↗

DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗