SEARCH · Engineering Papers

Results for “ML”

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 199 records · Page 11

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Machine learning approaches for intentional materials engineering

In this article, the development of nanoporous metals and metallic composites through dealloying processes presents significant opportunities in materials engineering. However, designing multicomponent precursor alloys and establishing corresponding processing methods that yield predictable compositions and nanostructures remain a complex challenge. This article explores how machine learning (ML)-augmented computational and experimental methodologies can tackle these challenges by predicting precursor alloy compositions, final nanoporous structures, and mechanical properties, while integrating ML-enabled autonomous experimentation for material design and quantification. We highlight recent advancements in applying ML to nanostructured materials design via dealloying and discuss how techniques from other nanomaterial designs can be adapted for improved control over morphological and compositional outcomes in nanoporous and nanocomposite materials. Furthermore, we explore the role of ML in autonomous synchrotron x-ray experimentation, enabling real-time feedback between modeling and experimental setups. ML-driven approaches to microstructure characterization and mechanical property prediction are also examined, with a focus on modeling and advanced imaging techniques such as three-dimensional nanotomography. Finally, this article outlines future directions for ML-enhanced materials science, emphasizing the exploration of high-dimensional parameter spaces and the incorporation of materials kinetics into processing and property evaluation, ultimately advancing the design of nanoporous structures and materials science.

36 MATERIALS SCIENCE↗

DOE OSTI2025

A Comparison of Machine Learning Methods of Association Tested on Dense Nodal Arrays

The association of phase picks to form events is one of the fundamental components of seismology. Large and dense sensor networks, such as >1000 geophone arrays (and distributed acoustic sensing), offer unique challenges in association due to the vast numbers of observations and high likelihood of errant picks. In addition, the large number of stations can greatly increase the time it takes to perform the association. For this reason, machine learning (ML) methods might provide a more optimal method of association for such networks. In this work, we examine how well ML methods (e.g., Gaussian mixture model association, PhaseLink, and Graph Earthquake Neural Interpretation Engine) can incorporate dense seismic arrays into regional networks and how well they handle the increasing numbers of stations. Here, we test their capabilities on two dense seismic deployments, one within Rock Valley Nevada (52 nodes and a 9-station sparse local network), and the LArge-n Seismic Survey in Oklahoma dense nodal array (>1800 vertical-component geophones). Processing data from these two different styles of dense seismic deployments allows testing of how the ML algorithms can merge array data with a broader regional network, how they deal with poorly picked phases, and how they handle anthropogenic noise. We compare the ML-associated bulletins to those obtained using the Rapid Earthquake Association and Location algorithm, a more traditional method of association. We find that there are very small differences in results between the methods for small networks (<100 stations) with low pick rates. For large networks (>1000), there are enough errant picks that some of the ML methods start to create false events out of noise. We also find that the ML methods vary in computation time significantly but are all faster than the traditional method tested here.

58 GEOSCIENCES↗

DOE OSTI2024

LLNL measurements of thermally irradiated HEU sample and saltwater-matrixed HEU sample

Two scintillation vials, kindly provided by the PNNL team, were received in the LLNL radiochemistry building on June 10, 2024; one containing approximately 2 mL dissolved thermally-irradiated HEU, and the other containing dried salt from irradiated seawater. A quick, semiquantitative screening count of the salt showed that the activation product activities were very low, with the highest activity being ~1 Bq 24 Na. The dissolved HEU solution was transferred to a Prindle vial (LLNL standard counting geometry) and weighed. Approximately 2 mL 3 M HNO 3 was added so that the solution completely covered the bottom of the vial and Gamanal software would be able to accurately generate an efficiency curve. This sample, called “PNNLFP24” is the irradiated HEU solution received, gravimetrically diluted by a factor of 1.7356 ± 0.0003, and was sent for quick gamma counting prior to further modification. Meanwhile the salt was quantitatively transferred to a 250 mL polyethylene bottle and dissolved in 160 mL 3 M HNO 3 . After counting, 50 µL PNNLFP24 was aliquoted for Resonance Ionization Mass Spectrometry (RIMS) analysis, and then 10.0 mL of the salt solution (6.03% of the total salt, gravimetrically) was added to the remaining PNNLFP24 solution to make “PNNLFPSW24”. After weighing, two 100 µL aliquots were removed for RIMS and DES, and 3 mL was aliquoted for microfluidic chemistry. The remaining “PNNLFPSW24” solution was weighed and proceeded for singles and coincidence counting on the MCBOS system.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Performance Evaluation of Intelligent Solar Control Software Through Hardware-in-the-Loop (CRADA Final Report)

Recent research has highlighted the potential for solar to act as a zero-marginal-cost and zero-emission flexibility resource on the bulk power system when operated with advanced control systems. To increase the performance of these systems, leading technologies, including machine learning (ML) and hierarchical inverter set point allocation, have been developed by Latimer Controls, Inc. to estimate the headroom of large PV plants for grid operation and control; however, these technologies lack comprehensive validation under real-world application scenarios. Latimer Controls, Inc. received two voucher awards for research at a national laboratory from the Department of Energy American Made Solar Prize Round 6. The National Renewable Energy Laboratory (NREL) was selected to collaborate with Latimer staff to conduct a performance evaluation of Latimer PV control software. The NREL team will develop a hardware-in-the-loop (HIL) testbed to perform testing and validation of the Latimer PV control technology in a de-risked yet realistic testbed environment. Latimer and NREL worked together to analyze the test data, draw conclusions from the results, and disseminate the resulting scientific findings. In this CRADA work, we propose to test and validate the real-world application of the Latimer Control solution in an HIL environment. We evaluate the performance of different flexible solar technologies in responding to automatic generation control signals in a closed-loop fashion. In particular, a data-driven potential high limit (PHL) estimation is developed for large solar plants to accurately estimate their headroom so that they have fast and short-time regulation and control capability to participate in grid services and respond to grid signals in real time (e.g., AGC). This PHL estimation algorithm is embedded in a hardware power plant controller (PPC) and tested with an IEEE-39 bus system model developed in RTDS. To account for the varying cloud conditions and diverse inverter dispatches, we developed a 135-MW PV plant with detailed modeling of 27 individual PV modules and inverters using RTDS. The real-world communications used in such big plants, such as ModBus TCP/IP for inverter level and DNP3 for plant level, were developed to emulate the real-world applications in big PV plants. The ML-based PHL estimation method is tested under nine separate weather scenarios against the ‘reference-control’ solution, hereafter referred to as the baseline solution. The baseline method reserves a subset of inverters (reference group) to operate at their PHL at all times and dispatches only the remaining inverters (control group) at curtailed levels to fulfill the flexibility need. Despite being successfully piloted by NREL in California in 2017 and Chile in 2020, there exist two gaps in the state of the art to fully unlock the flexibility of PV plants: a. There is a trade-off between the PHL estimation accuracy and the flexibility range. b. There lacks granularity in the PHL estimation to capture the variation across inverters. The Latimer solution seeks to address these gaps by applying machine learning methods to improve PHL estimation accuracy while accounting for variability at every inverter. Performance metrics were taken from the 2023 Georgia Power CARES utility-scale RFP. The results demonstrate that the ML-based approach outperforms the traditional baseline method in PHL estimation accuracy for 7 of 9 scenarios. The average PHL error across the nine scenarios was 7.40% for the ML-based method, 2.06% less than the 9.46% PHL error average across scenarios that was exhibited by the baseline method. Additionally, the PHL error was below 5% for at least 95% of the testing interval for 3 of 9 tested intervals with the ML approach, whereas it did not achieve this metric for any of the baseline tests. Overall, simulation results indicate the superior performance of an ML-based approach compared to the conventional baseline reference-control approach, showcasing its potential to support grid stability and operational efficiency. This laboratory HIL testing using real PPC, representative power system simulation models in real-time with detailed PV plant and inverter models, and real-world communication protocols gives us confidence that this machine learning based PHL estimation algorithm works well in the hardware PPC and therefore de-risks future field commissioning. The end goal of this project is to advance grid technology to address the grid operation challenges brought by solar plant’s variability and uncertainties in power generation.

14 SOLAR ENERGY↗

DOE OSTI2025

wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation

As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multipleefforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of synthesized ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680 000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75% percentile within several percent of the synthesized resources on the synthetic test dataset.

Hawks, Benjamin G. [Fermilab]↗

DOE OSTI2026

Describing Point Defect Topology in 2D Energy Materials Through Computer Vision

Point defects such as vacancies and impurity atoms strongly impact the performance of 2D materials. Traditional efforts often rely on manual detection, a process that is time-intensive, prone to human error, and challenging to scale. Here we leverage machine learning (ML) methods to identify and quantify vacancies within 2D transition metal carbides (Ti3C2, MXenes), aiming to expedite detection while improving accuracy. MXenes exhibit valuable defect-defined electrochemical properties, but we currently lack statistical understanding of defect topology needed to fully harness these materials. Here we employ a convolutional neural network for semantic segmentation of experimental MXene images, opening an opportunity to conduct a rigorous statistical study on defect hierarchy while investigating local relaxation in the lattice. We show how the integration of ML can yield fundamental insight into point defects, providing a powerful tool that will play an increasingly crucial role in the future of materials science. ML is often not just a matter of straightforward application, and pretrained models proved ineffective in this case. Instead, we trained our own neural network (NN) and applied data augmentation techniques and fine-tuning to the training dataset. Since labeled microscopy data is often scarce, we developed training data from a previously published wide-frame MXene image, using customized Gaussian fitting to locate atomic positions. Our trained model was then applied to a large dataset of experimental images, enabling a statistical study of defect configurations across three samples prepared with different HF etchant concentrations (5%, 9.1%, and 12.5%), as shown in Fig. 1. This also allowed us to investigate local strain around vacancies, though we find that we are limited by the precision of measurements using high-angle annular dark field (HAADF) images, as shown in Fig. 2. This study demonstrates how ML enables large-scale, quantitative analysis of atomic defects - an otherwise infeasible task with traditional methods. While our NN was specialized for Ti3C2 MXenes, the pipeline we developed provides a foundation for future ML models tailored to other materials. Ultimately, we envision embedding the NN onto the microscope to give real-time feedback to the user. To make this a reality, continued work is necessary to fully understand the NN's capabilities and limitations. This study gets one step closer to our goals of automated experimentation moving away from traditional methods of manual labeling. As ML capabilities advance, we hope to continue adapting and applying these techniques in microscopy.

2D materials↗

DOE OSTI2025

Uncertainty-Based Design: Finite Element and Explainable Machine Learning Modeling of Carbon–Carbon Composites for Ultra-High Temperature Solar Receivers

Design under uncertainty has significantly grown in research developments during the past decade. Additionally, machine learning (ML) and explainable ML (XML) have offered various opportunities to provide reliable predictable models. The current article investigates the use of finite element modeling (FEM), ML and XML predictions, and uncertain-based design of carbon-carbon (C-C) composites for use in ultra-high temperatures. A C-C composite concentrating solar power (CSP) as a microvascular receiver is considered as a case study. These C-C composites are fiber composites with directly integrated carbonized microchannels to form a lightweight, high-absorptivity material that includes an embedded microvascular network of channels. The topology of these microchannels is engineered to optimize heat transfer to a supercritical carbon dioxide (sCO2) heat transfer fluid. The mechanical characterization of C-C composites is highly challenging. Thus, designing every component made of C-C composites for ultra-high temperature applications needs an uncertainty-based analysis. As a part of a comprehensive project on the development of a novel carbonized microvascular C-C composite, this paper explores C-C composite sensitivity analysis, FEM, ML prediction, and XML analysis. The resulting composite can then be carbonized and coated with an oxidation-resistant coating to form a thermally efficient and mechanically robust C-C composite. An ANSYS 3-D-FE model was used to analyze the CSP’s stress/strain. To consider the variability in the mechanical and thermal properties of C-C composites, various mechanical properties are considered as the ANSYS FEM’s input. A synthetic dataset from 730 ANSYS runs was produced to feed into the ML and XML algorithms for uncertainty analysis and prediction. The ML and XML algorithms could accurately predict the CSP stresses/strains.

Daghigh, Vahid (ORCID:0000000298941620)↗

NASA NTRS2002

Heterogeneous responses of human limbs to infused adrenergic agonists: a gravitational effect?

Unlike quadrupeds, the legs of humans are regularly exposed to elevated pressures relative to the arms. We hypothesized that this "dependent hypertension" would be associated with altered adrenergic responsiveness. Isoproterenol (0.75-24 ng x 100 ml limb volume-1 x min-1) and phenylephrine (0.025-0.8 microg x 100 ml limb volume-1 x min-1) were infused incrementally in the brachial and femoral arteries of 12 normal volunteers; changes in limb blood flow were quantified by using strain-gauge plethysmography. Compared with the forearm, baseline calf vascular resistance was greater (38.8 +/- 2.5 vs. 26.9 +/- 2.0 mmHg x 100 ml x min x ml-1; P < 0.001) and maximal conductance was lower (46.1 +/- 11.9 vs. 59.4 +/- 13.4 ml x ml-1 x min-1 x mmHg-1; P < 0.03). Vascular conductance did not differ between the two limbs during isoproterenol infusions, whereas decreases in vascular conductance were greater in the calf than the forearm during phenylephrine infusions (P < 0.001). With responses normalized to maximal conductance, the half-maximal response for phenylephrine was significantly less for the calf than the forearm (P < 0.001), whereas the half-maximal response for isoproterenol did not differ between limbs. We conclude that alpha1- but not beta-adrenergic-receptor responsiveness in human limbs is nonuniform. The relatively greater response to alpha1-adrenergic-receptor stimulation in the calf may represent an adaptive mechanism that limits blood pooling and capillary filtration in the legs during standing.

Clinical Trial↗

NASA NTRS2000

Validation of real-time three-dimensional echocardiography for quantifying left ventricular volumes in the presence of a left ventricular aneurysm: in vitro and in vivo studies

OBJECTIVES: To validate the accuracy of real-time three-dimensional echocardiography (RT3DE) for quantifying aneurysmal left ventricular (LV) volumes. BACKGROUND: Conventional two-dimensional echocardiography (2DE) has limitations when applied for quantification of LV volumes in patients with LV aneurysms. METHODS: Seven aneurysmal balloons, 15 sheep (5 with chronic LV aneurysms and 10 without LV aneurysms) during 60 different hemodynamic conditions and 29 patients (13 with chronic LV aneurysms and 16 with normal LV) underwent RT3DE and 2DE. Electromagnetic flow meters and magnetic resonance imaging (MRI) served as reference standards in the animals and in the patients, respectively. Rotated apical six-plane method with multiplanar Simpson's rule and apical biplane Simpson's rule were used to determine LV volumes by RT3DE and 2DE, respectively. RESULTS: Both RT3DE and 2DE correlated well with actual volumes for aneurysmal balloons. However, a significantly smaller mean difference (MD) was found between RT3DE and actual volumes (-7 ml for RT3DE vs. 22 ml for 2DE, p = 0.0002). Excellent correlation and agreement between RT3DE and electromagnetic flow meters for LV stroke volumes for animals with aneurysms were observed, while 2DE showed lesser correlation and agreement (r = 0.97, MD = -1.0 ml vs. r = 0.76, MD = 4.4 ml). In patients with LV aneurysms, better correlation and agreement between RT3DE and MRI for LV volumes were obtained (r = 0.99, MD = -28 ml) than between 2DE and MRI (r = 0.91, MD = -49 ml). CONCLUSIONS: For geometrically asymmetric LVs associated with ventricular aneurysms, RT3DE can accurately quantify LV volumes.

NASA Discipline Cardiopulmonary↗

NASA NTRS1998

Deposition and dispersion of 1-micrometer aerosol boluses in the human lung: effect of micro- and hypergravity

We performed bolus inhalations of 1-micrometer particles in four subjects on the ground (1 G) and during parabolic flights both in microgravity (microG) and in approximately 1.6 G. Boluses of approximately 70 ml were inhaled at different points in an inspiration from residual volume to 1 liter above functional residual capacity. The volume of air inhaled after the bolus [the penetration volume (Vp)] ranged from 200 to 1,500 ml. Aerosol concentration and flow rate were continuously measured at the mouth. The deposition, dispersion, and position of the bolus in the expired gas were calculated from these data. For Vp >/=400 ml, both deposition and dispersion increased with Vp and were strongly gravity dependent, with the greatest deposition and dispersion occurring for the largest G level. At Vp = 800 ml, deposition and dispersion increased from 33.9% and 319 ml in microG to 56.9% and 573 ml at approximately 1.6 G, respectively (P < 0.05). At each G level, the bolus was expired at a smaller volume than Vp, and this volume became smaller with increasing Vp. Although dispersion was lower in microG than in 1 G and approximately 1.6 G, it still increased steadily with increasing Vp, showing that nongravitational ventilatory inhomogeneity is partly responsible for dispersion in the human lung.

Parabolic Flight↗

NASA NTRS2013

A Parameter Estimation Scheme for Multiscale Kalman Smoother (MKS) Algorithm Used in Precipitation Data Fusion

A new approach is presented in this paper to effectively obtain parameter estimations for the Multiscale Kalman Smoother (MKS) algorithm. This new approach has demonstrated promising potentials in deriving better data products based on data of different spatial scales and precisions. Our new approach employs a multi-objective (MO) parameter estimation scheme (called MO scheme hereafter), rather than using the conventional maximum likelihood scheme (called ML scheme) to estimate the MKS parameters. Unlike the ML scheme, the MO scheme is not simply built on strict statistical assumptions related to prediction errors and observation errors, rather, it directly associates the fused data of multiple scales with multiple objective functions in searching best parameter estimations for MKS through optimization. In the MO scheme, objective functions are defined to facilitate consistency among the fused data at multiscales and the input data at their original scales in terms of spatial patterns and magnitudes. The new approach is evaluated through a Monte Carlo experiment and a series of comparison analyses using synthetic precipitation data. Our results show that the MKS fused precipitation performs better using the MO scheme than that using the ML scheme. Particularly, improvements are significant compared to that using the ML scheme for the fused precipitation associated with fine spatial resolutions. This is mainly due to having more criteria and constraints involved in the MO scheme than those included in the ML scheme. The weakness of the original ML scheme that blindly puts more weights onto the data associated with finer resolutions is overcome in our new approach.

multiscale↗

NASA NTRSDate not supplied

Phenomena Portal: Large- Scale Visual Exploration of Atmospheric Phenomena

The Earth science community is experiencing a high influx of remote sensing data due to recent advancements in sensor technology. This enables the community to extend their research on a larger scale than ever before. Unfortunately, traditional data processing techniques do not scale well to these new, high volume data sources. State-of-the-art machine learning (ML) pipelines have been proven to overcome these burdens in various other fields but are underexploited within the physical sciences community. Moreover, ML is reliant on labeled data, which is currently sparsely available, owing to the fact that ML adoption is still in the early stages within the Earth and atmospheric science communities. To address these issues, we developed the Phenomena Portal, a visual exploration tool that uses ML to detect various atmospheric phenomena on a global scale. This allows the Earth and atmospheric science communities to view trends of occurrences of phenomena, identify potential relationships between them, and analyze spatiotemporal patterns over time. These detections can also serve as initial labeled data for ML research pertaining to the respective phenomena. The tool also incorporates feedback from subject matter experts to further improve the model detection accuracy, thereby facilitating human-in-the-loop. This presentation will provide an overview of the ML model development and cloud deployment. We also discuss the capabilities of the user interface for displaying the detections.

Muthukumaran Ramasubramanian↗

NASA NTRSDate not supplied

Artificial Neural Networks to Predict Cognitive Impairment of Rodents Subjected to Space Radiation

INTRODUCTION We use artificial neural networks (ANNs) as an example machine learning (ML) tool to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is attentional set-shifting (ATSET) test scores from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 28Si, or 56Fe, expected for a Lunar or Mars mission [1]. This work investigates rats at a subject-based level and uses applied dose and performance scores taken before irradiation to predict whether a rat will be impaired when irradiated. The results of this study are significant to crewed space missions as they support the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. METHODS Data used in this work are scores from the ATSET, a multi-stage constrained cognitive flexibility test [2]. Our computational model utilizes the number of attempts to reach the criterion to pass a stage as a behavioral performance measure for rats. We use the post-irradiation scores, generate thresholds from cumulative distribution plots of non-irradiated rats, and calculate the percent of irradiated rats whose scores fall below the threshold to infer how each radiation type/dose affects a population. Rats scoring above the threshold are labeled impaired while the others are non-impaired. We then employ ANNs as a typical ML technique, and use each subject’s individual scores taken before radiation along with the applied dose, to predict their personal susceptibility to cognitive impairment due to space radiation exposure. RESULTS AND CONCLUSION A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing ML classifiers such as ANNs identifies rats that have a higher tendency for impairment after GCR exposure [1]. The receiver operating characteristic (ROC) and the precision-recall (PR) curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD (Figure 1) and CD stages. They, however, do not depict impairment due to 4He in SD (Figure 1) and 28Si in CD, suggesting no dose-dependent impairment response in these cases. In this work, “good” prediction pertains to “better-than-random-chance”, due to the limited sample size and the high inter- and intra-individual variabilities in response to brain stimulation paradigms, as applicable to both animals and humans. More behavioral tests and biomarkers should be investigated on the same subjects, to be fed to the ML models to capture the agents responsible for performance alterations of some individuals versus others.

machine learning↗

NASA NTRSDate not supplied

Machine Learning Models to Predict Cognitive Impairment of Rodents Subjected to Space Radiation

machine learning↗

NASA NTRS2022

Coevolution of Machine Learning and Process-Based Modelling to Revolutionize Earth and Environmental Sciences: A Perspective

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in EES, (1) nowcasting and prediction, (2) scenario analysis, and (3) diagnostic learning. The paper ponders over a ‘coevolutionary’ approach to model building, shifting away from a borrowing to a co-creation culture, to develop a generation of models that leverage the unique strengths of ML such as scalability to big data and high-dimensional mapping, while remaining faithful to process-based knowledge base and principles of model explainability and interpretability, and therefore, falsifiability.

Saman Razavi↗

NASA NTRSDate not supplied

Machine Learning based Aircraft Performance Model Estimation for Trajectory Prediction

The accurate prediction of aircraft trajectory by ground-based decision support tools is a critical component of air traffic management in the US National Airspace System (NAS). Accurate predictions of where the aircraft will be in the future or when they will arrive at specific locations (e.g., fixes) is a key enabler for sequencing and efficient arrival management of flights. Traditional physics based aircraft trajectory prediction relies on a simplified point-mass total energy model whose parameters are referred to as Aircraft Performance Model (APM) parameters. Even though the performance coefficients and weight of an aircraft are a vital part of the aircraft performance model’s predictions and accuracy, these coefficients are proprietary in nature and therefore, unavailable to decision-support tools. Current approaches freeze some coefficients to default base of aircraft data (BADA) values and optimize others. However, the APM parameters are highly coupled by the flight dynamics and prioritizing one parameter over others leads to bias and skewed predictions. To alleviate this problem, we provide a combined optimization framework to predict all the critical (thrust, drag and weight) APM parameters. This paper is focused on training Machine Learning (ML) models that map historical flights to optimized APM parameters that provide the best fit (in terms of prediction error). Our dataset obtained from NASA’s Sherlock data warehouse is comprised of thousands of historical flights and includes weather and track data collected from 2019. Using different subsets of relevant features (e.g., aircraft type), we trained several ML models to estimate the aircraft’s take off weight, drag polar coefficients (both parasitic and lift induced), and thrust settings (multiplier applied to the maximum engine thrust). The chosen flights are from three of the most common aircraft types (B738, B737, and A320) arriving at four airports (LAX, DEN, MSP, and DFW). Our ML approach is comprised of two different solutions: 1- using a subset of features that are known prior to the flight departure and do not change during flight (such as engine type, current temperature at departure & destination airports, aircraft type) and 2 - using a subset of temporal features of the flight trajectory (such as cruise altitude, Mach, airspeed, and rate of climb) in addition to the pre-departure features from the first solution. The labels or target variables are the APM parameters that were obtained by an optimized ordinary differential equations (ODE) fitting process (applied to individual flights). The ODE-fitting is very time intensive and is therefore performed offline. Thus, training an ML model to learn the relationship between the flight features and ODE-generated labels enables faster estimation of the APM parameters and is therefore amenable to real-time prediction. Various ML models including linear regression, random forest, XGBoost, and neural network were trained, and the results are compared. After model validation and hyperparameter-tuning, we observed that the Random Forest model outperformed the other three models by the overall mean square error (MSE) of 2% for the first solution and 1.5% for the second solution. Finally, the ML-derived parameters are compared against default BADA APM parameters using NASA’s Autonomy Development toolkit (ADK) simulation software. The simulation results for one of each aircraft type is shown and discussed.

Aida Sharif Rohani↗

NASA NTRSDate not supplied

Operational Modal Analysis of the Artemis I Dynamic Rollout Test and Wet Dress Rehearsal

NASA has developed an expendable heavy lift launch vehicle capability, the Space Launch System (SLS), to support lunar and deep space exploration. The uncrewed Artemis I was the first flight of this new launch vehicle and tested critical systems for the upcoming crewed Artemis II flight to the moon. Accelerations were recorded at a multitude of locations on Artemis, the Mobile Launcher (ML), and the Crawler Transporter (CT)during the rollout of Artemis I from the Vehicle Assembly Building (VAB) to Launch Pad 39B March 2022 and is referred to as the Artemis I Dynamic Rollout Test (DRT). While Artemis I was at Launch Pad 39B, the Wet Dress Rehearsal (WDR) was performed to demonstrate launch readiness and acceleration measurements were also recorded. Finally, Artemis I rolled back from Launch Pad 39B to the VAB in April 2022, where acceleration measurements were also recorded and is referred to as the rollback portion of DRT. Because the forces during rollout and at the launch pad acting on Artemis I, the ML, and the CT are not directly measurable, Operational Modal Analysis (OMA) techniques, instead of traditional Experimental Modal Analysis (EMA) techniques, were used to identify modal characteristics. The OMA analysis of DRT and WDR directly builds upon the lessons learned from the OMA analysis of an earlier rollout of the ML from the VAB. DRT and WDR dynamic characteristics will be used to support SLS Integrated Modal Test finite element model correlation efforts and Exploration Ground System ML and CT finite element model verification and validation, which are part of the Building Block approach the Space Launch System program has implemented. The dynamic characteristics extracted from DRT as well as the rollout acceleration time histories themselves will be used in the development of generic rollout forcing functions that will provide refined estimates of the Artemis IV rollout forces, which will have the heavier and larger SLS Block 1B launch vehicle and Mobile Launcher 2 (ML-2). This paper briefly describes Artemis I, the ML, and the CT physical characteristics, DRT rollout/rollback and WDR data collection, the challenges in implementing OMA techniques due in part to the CT harmonics, and how these challenges were overcome to obtain the Artemis I DRT configuration and WDR configuration modal characteristics.

Apollo↗

NASA NTRSDate not supplied

Runway Sign Classifier: A DAL C Certifiable Machine Learning System

In recent years, the remarkable progress of Machine Learning (ML) technologies within the domain of Artificial Intelligence (AI) systems has presented unprecedented opportunities for the aviation industry, paving the way for further advancements in automation, including the potential for single pilot or fully autonomous operation of large commercial airplanes. However, ML technology faces major incompatibilities with existing airborne certification standards, such as ML model traceability and explainability issues or the inadequacy of traditional coverage metrics. Certification of ML-based airborne systems using current standards is problematic due to these challenges. This paper presents a case study of an airborne system utilizing a Deep Neural Network (DNN) for airport sign detection and classification. Building upon our previous work, which demonstrates compliance with Design Assurance Level (DAL) ”D”, we upgrade the system to meet the more stringent requirements of Design Assurance Level ”C”. To achieve DAL C, we employ an established architectural mitigation technique involving two redundant and dissimilar Deep Neural Networks. The application of novel ML-specific data management techniques further enhances this approach. This work is intended to illustrate how the certification challenges of ML-based systems can be addressed for medium criticality airborne applications.

Flight Software↗