Search NASA⌕ Search

SEARCH · Search NASA

Results for “Training Analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 505 records · Page 28

MDLoader: A Hybrid Model-Driven Data Loader for Distributed Graph Neural Network Training

Scalable data management is essential for processing large scientific dataset on HPC platforms for distributed deep learning. In-memory distributed storage is preferred for its speed, enabling rapid, random, and frequent data access required by stochastic optimizers. Processes use one-sided or collective communication to fetch remote data, with optimal performance depending on (i) dataset characteristics, (ii) training scale, and (iii) interconnection network. Empirical analysis shows collective communication excels with larger mini-batch sizes and/or fewer processes, whereas one-sided communication outperforms at larger scales. We propose MDLoader, a hybrid in-memory data loader for distributed graph neural network training. MDLoader features a model-driven performance estimator that dynamically selects between one-sided and collective communication at the beginning of training using Tree of Parzen Estimators (TPE). Evaluations on NERSC Perlmutter and OLCF Summit show MDLoader outperforms single-backend loaders by up to 2.83 × and predicts the suitable communication method with 96.3% (Perlmutter) and 94.3% (Summit) success rate.

Bae, Jonghyun↗

Use of generic and site-specific underground research laboratories to support siting, design, and safety assessment - 15417

Under the auspices of the International Atomic Energy Agency (IAEA), nationally developed underground research laboratories (URLs) and associated research institutions are being offered for use by other nations. These facilities form an Underground Research Facilities (URF) Network for training in and demonstration of waste disposal technologies and the sharing of knowledge and experience related to geologic repository development, research, and engineering. In order to achieve its objectives, the URF Network regularly sponsors workshops and training events related to the knowledge base that is transferable between existing URL programs and to nations with an interest in developing a new URL. Toward that end, a three-day workshop was held in Albuquerque, New Mexico in October 2014 to identify and compare the understanding of URF Network members on the place and role of generic and site-specific URLs in the overall, iterative geological disposal development process, including repository siting, design, and post-closure safety assessment. Attention was also given to the need for URLs in salt host rock, since there is currently no such facility in operation in the world. This paper describes some of the outcomes of the workshop in the context of the general timeline for repository development and the evolving role of research, development, and demonstration (RD and D) activities in URLs. Of particular interest is the relationship between technology maturity, as measured by technology readiness level (TRL), and the stages or milestones in the repository development timeline. The long history of RD and D in worldwide URLs (> 40 years) can be argued to be the primary reason that nuclear waste disposal systems are currently at a high level of maturity. One of the key recommendations from the workshop was that an international, easily accessible knowledge base should soon be established to avoid the loss of important experiences and information obtained from existing and closed URLs. It was also recognized that a new generic URL in salt host rock would provide a number of benefits, but one should not be initiated until a national program specifically decides to site its repository in salt. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Neural Network and Regression Methods Demonstrated in the Design Optimization of a Subsonic Aircraft

The neural network and regression methods of NASA Glenn Research Center s COMETBOARDS design optimization testbed were used to generate approximate analysis and design models for a subsonic aircraft operating at Mach 0.85 cruise speed. The analytical model is defined by nine design variables: wing aspect ratio, engine thrust, wing area, sweep angle, chord-thickness ratio, turbine temperature, pressure ratio, bypass ratio, fan pressure; and eight response parameters: weight, landing velocity, takeoff and landing field lengths, approach thrust, overall efficiency, and compressor pressure and temperature. The variables were adjusted to optimally balance the engines to the airframe. The solution strategy included a sensitivity model and the soft analysis model. Researchers generated the sensitivity model by training the approximators to predict an optimum design. The trained neural network predicted all response variables, within 5-percent error. This was reduced to 1 percent by the regression method. The soft analysis model was developed to replace aircraft analysis as the reanalyzer in design optimization. Soft models have been generated for a neural network method, a regression method, and a hybrid method obtained by combining the approximators. The performance of the models is graphed for aircraft weight versus thrust as well as for wing area and turbine temperature. The regression method followed the analytical solution with little error. The neural network exhibited 5-percent maximum error over all parameters. Performance of the hybrid method was intermediate in comparison to the individual approximators. Error in the response variable is smaller than that shown in the figure because of a distortion scale factor. The overall performance of the approximators was considered to be satisfactory because aircraft analysis with NASA Langley Research Center s FLOPS (Flight Optimization System) code is a synthesis of diverse disciplines: weight estimation, aerodynamic analysis, engine cycle analysis, propulsion data interpolation, mission performance, airfield length for landing and takeoff, noise footprint, and others.

Hopkins, Dale A.↗

Pilot personality and crew coordination - Implications for training and selection

It is contended that past failures to find linkages between performance and personality were due to a combination of premature performance evaluation, inadequate statistical modeling, and/or the reliance on data gathered in contrived as opposed to realistic situations. The goal of the research presented is to isolate subgroups of pilots along performance-related personality dimensions and to document limits on the impact of crew coordination training between the groups. Three different profiles were identified through cluster analysis of personality scales that replicated across samples and predicted attitude change following training in crew coordination.

Chidester, Thomas R.↗

Python codes for the paper - "Trade-offs in the latent representation of microstructure evolution"

SAND2024-00946O Python codes used in "Trade-offs in the latent representation of microstructure evolution," a manuscript accepted for publication in Acta Materialia, are part of a repository. The code was developed to perform analysis of microstructure evolution. The repository consists of two main directories: models, which train and test models such as autoencoders and diffusion maps, and analysis, which analyzes microstructures. Source code is used to perform dimensionality reduction of microstructure data for analysis of its evolution in time. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Dingreville, Remi↗

Establishing High-Quality Prostate Brachytherapy Using a Phantom Simulator Training Program

Purpose: To design and implement a unique training program that uses a phantom-based simulator to teach the process of prostate brachytherapy (PB) quality assurance and improve the quality of education. Methods and Materials: Trainees in our simulator program were practicing radiation oncologists, radiation oncology residents, and fellows of the American Brachytherapy Society. The program emphasized 6 core areas of quality assurance: patient selection, simulation, treatment planning, implant technique, treatment evaluation, and outcome assessment. Using the Iodine 125 ({sup 125}I) preoperative treatment planning technique, trainees implanted their ultrasound phantoms with dummy seeds (ie, seeds with no activity). Pre- and postimplant dosimetric parameters were compared and correlated using regression analysis. Results: Thirty-one trainees successfully completed the simulator program during the period under study. The mean phantom prostate size, number of seeds used, and total activity were generally consistent between trainees. All trainees met the V100 >95% objective both before and after implantation. Regardless of the initial volume of the prostate phantom, trainees' ability to cover the target volume with at least 100% of the dose (V100) was not compromised (R=0.99 pre- and postimplant). However, the V150 had lower concordance (R=0.37) and may better reflect heterogeneity control of the implant process. Conclusions: Analysis of implants from this phantom-based simulator shows a high degree of consistency between trainees and uniformly high-quality implants with respect to parameters used in clinical practice. This training program provides a valuable educational opportunity that improves the quality of PB training and likely accelerates the learning curve inherent in PB. Prostate phantom implantation can be a valuable first step in the acquisition of the required skills to safely perform PB.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Air Transport by Gliders : Some Technical Observations

This short analysis may be useful in determining the real tactical possibilities of "glider trains" and in adopting the course to be followed in possible studies of these questions. In this analysis most prominent are: (a) the power required for the train in level flight; (b) its speed; (c) climb; and (d) the type of airplane best suited for towing as well as design requirements for transport gliders.

Stepniewski, Wieslaw↗

Rapid Inverse Parameter Inference Using Physics-Informed Neural Network

As Li-ion batteries become more essential in today's economy, tools need to be developed to accurately and rapidly diagnose a battery's internal state-of-health. Using a Li-ion battery's (high-rate) voltage response, it is proposed to determine a battery's internal state through Bayesian calibration. However, Bayesian calibration is notoriously slow and requires thousands of model runs. To accelerate parameter inference using Bayesian calibration, a surrogate model is developed to replace the underlying physics-based Li-ion model. Developing a surrogate model for rapid Bayesian calibration analysis is discussed for both the single particle model (SPM) and the pseudo two-dimensional (P2D) model. Surrogate models are constructed using physics-informed neural networks (PINNs) that encode the influence of internal properties on observed voltage responses. In practice, a neural network can be trained by: 1) using simulation results of the physics-based model (i.e., a data-loss approach); 2) using the residuals of the governing equations themselves (i.e., a physics-loss approach); or 3) using a combination of simulation results and governing equation residuals. In the present work, PINNs are developed using a variety of training losses and neural network architectures. In this analysis, it is shown that a PINN surrogate model can be reliably trained with only physics-informed loss. However, using a coupled data-informed and physics-loss approach produced the most accurate PINNs.

Bayesian calibration↗

Model Predictive Control of Integrated Gasification Combined Cycle Power Plants

The primary project objectives were to understand how the process design of an integrated gasification combined cycle (IGCC) power plant affects the dynamic operability and controllability of the process. Steady-state and dynamic simulation models were developed to predict the process behavior during typical transients that occur in plant operation. Advanced control strategies were developed to improve the ability of the process to follow changes in the power load demand, and to improve performance during transitions between power levels. Another objective of the proposed work was to educate graduate and undergraduate students in the application of process systems and control to coal technology. Educational materials were developed for use in engineering courses to further broaden this exposure to many students. ASPENTECH software was used to perform steady-state and dynamic simulations of an IGCC power plant. Linear systems analysis techniques were used to assess the steady-state and dynamic operability of the power plant under various plant operating conditions. Model predictive control (MPC) strategies were developed to improve the dynamic operation of the power plants. MATLAB and SIMULINK software were used for systems analysis and control system design, and the SIMULINK functionality in ASPEN DYNAMICS was used to test the control strategies on the simulated process. Project funds were used to support a Ph.D. student to receive education and training in coal technology and the application of modeling and simulation techniques.

01 COAL, LIGNITE, AND PEAT↗

Proteomics investigation of endogenous S-nitrosylation in Arabidopsis

Highlights: Black-Right-Pointing-Pointer Identification and quantification of nitrosothiols. Black-Right-Pointing-Pointer A first dataset of endogenously nitrosylated cysteines in Arabidopsis cells. Black-Right-Pointing-Pointer Nitrosothiols display apolar motifs not located in close vicinity of cysteines. Black-Right-Pointing-Pointer Salt stress alters the endogenous nitrosylation of specific cysteines in Arabidopsis. -- Abstract: S-Nitrosylation emerges as an important protein modification in many processes. However, most data were obtained at the protein level after addition of a NO donor, particularly in plants where information about the cysteines nitrosylated in these proteins is scarce. An adapted work-flow, combining the classical biotin switch method and labeling with isotope-coded affinity tags (ICAT), is proposed. Without addition of NO donor, a total of 53 endogenous nitrosocysteines was identified in Arabidopsis cells, in proteins belonging to all cell territories, including membranes, and covering a large panel of functions. This first repertoire of nitrosothiols in plants enabled also preliminary structural description. Three apolar motifs, not located in close vicinity of cysteines and accounting for half the dataset, were detected and are proposed to complement nitrosylation prediction algorithms, poorly trained with plant data to date. Analysis of changes induced by a brief salt stress showed that NaCl modified the nitrosylation level of a small proportion of endogenously nitrosylated proteins and did not concern all nitrosothiols in these proteins. The possible role of some NO targets in the response to salt stress was discussed.

60 APPLIED LIFE SCIENCES↗

Exponential concentration in quantum kernel methods

Kernel methods in Quantum Machine Learning (QML) have recently gained significant attention as a potential candidate for achieving a quantum advantage in data analysis. Among other attractive properties, when training a kernel-based model one is guaranteed to find the optimal model’s parameters due to the convexity of the training landscape. However, this is based on the assumption that the quantum kernel can be efficiently obtained from quantum hardware. In this work we study the performance of quantum kernel models from the perspective of the resources needed to accurately estimate kernel values. We show that, under certain conditions, values of quantum kernels over different input data can be exponentially concentrated (in the number of qubits) towards some fixed value. Thus on training with a polynomial number of measurements, one ends up with a trivial model where the predictions on unseen inputs are independent of the input data. We identify four sources that can lead to concentration including expressivity of data embedding, global measurements, entanglement and noise. For each source, an associated concentration bound of quantum kernels is analytically derived. Lastly, we show that when dealing with classical data, training a parametrized data embedding with a kernel alignment method is also susceptible to exponential concentration. Our results are verified through numerical simulations for several QML tasks. Altogether, we provide guidelines indicating that certain features should be avoided to ensure the efficient evaluation of quantum kernels and so the performance of quantum kernel methods.

97 MATHEMATICS AND COMPUTING↗

Processing of microencapsulated dyes for the visual inspection of fibre reinforced plastics

The evaluation of damages caused during processing, assembly or usage of fibre reinforced plastics is still a challenge. The use of inspection technology like ultrasonic scanning enables a detailed damage analysis but requires high investments and trained staff. Therefore, the visual inspection method is widely used. A drawback of this method is the difficult identification of barely visible damages, which can already be detrimental for the structural integrity. Therefore an approach is undertaken to integrate microencapsulated dyes into the laminates of fibre reinforced plastic parts to highlight damages on the surface. In case of a damage, the microcapsules rupture which leads to a release of the dye and a visible bruise on the part surface. To enable a wide application spectrum for this technology the microcapsules must be processable without rupturing with established manufacturing processes for fibre reinforced plastics. Therefore the incorporation of microcapsules in the filament winding, prepreg autoclave and resin transfer moulding (RTM) process is investigated. The results show that the use of a carrier medium is a feasible way to incorporate the microcapsules into the laminate for all investigated manufacturing processes. Impact testing of these laminates shows a bruise formation on the specimen surface which correlates with the impact energy level. This indicates a microcapsule survival during processing and shows the potential of this technology for damage detection and characterization.

36 MATERIALS SCIENCE↗

A Metabolomics Assay to Diagnose Citrus Huanglongbing Disease and to Aid in Assessment of Treatments to Prevent or Cure Infection

Citrus greening disease, or Huanglongbing (HLB), has devastated citrus crops globally in recent years. The causal bacterium, ‘ Candidatus Liberibacter asiaticus’, presents a sampling issue for qPCR diagnostics and results in a high false negative rate. In this work, we compared six metabolomics assays to identify HLB-infected citrus trees from leaf tissue extracted from 30 control and 30 HLB-infected trees. A liquid chromatography-mass spectrometry-based assay was most accurate. A final partial least squares-discriminant analysis (PLS-DA) model was trained and validated on 690 leaf samples with corresponding qPCR measures from three citrus varieties (Rio Red grapefruit, Hamlin sweet orange, and Valencia sweet orange) from orchards in Florida and Texas. Trees were naturally infected with HLB transmitted by the insect vector Diaphorina citri. In a randomized validation set, the assay was 99.9% accurate to classify diseased from nondiseased samples. This model was applied to samples from trees receiving plant defense-inducer compounds or biological treatments to prevent or cure HLB infection. From two trials, HLB-related metabolite abundances and PLS-DA scores were tracked longitudinally and compared with those of control trees. We demonstrate how our assay can assess tree health and the efficacy of HLB treatments and conclude that no trialed treatment was efficacious.

Plant Sciences↗

Simple, low-cost and accurate data-driven geophysical forecasting with learned kernels

Modelling geophysical processes as low-dimensional dynamical systems and regressing their vector field from data is a promising approach for learning emulators of such systems. We show that when the kernel of these emulators is also learned from data (using kernel flows, a variant of cross-validation), then the resulting data-driven models are not only faster than equation-based models but are easier to train than neural networks such as the long short-term memory neural network. In addition, they are also more accurate and predictive than the latter. When trained on geophysical observational data, for example the weekly averaged global sea-surface temperature, considerable gains are also observed by the proposed technique in comparison with classical partial differential equation-based models in terms of forecast computational cost and accuracy. When trained on publicly available re-analysis data for the daily temperature of the North American continent, we observe significant improvements over classical baselines such as climatology and persistence-based forecast techniques. Although our experiments concern specific examples, the proposed approach is general, and our results support the viability of kernel methods (with learned kernels) for interpretable and computationally efficient geophysical forecasting for a large diversity of processes.

58 GEOSCIENCES↗

Underwater Fish Detection using Deep Learning for Water Power Applications

Clean energy from oceans and rivers is becoming a reality with the development of new technologies like tidal and instream turbines that generate electricity from naturally flowing water. These new technologies are being monitored for effects on fish and other wildlife using underwater video. Methods for automated analysis of underwater video are needed to lower the costs of analysis and improve accuracy. We have trained a deep learning model, YOLO, to recognize fish in underwater video using three very different datasets recorded at real-world water power sites. Training and testing with examples from all three datasets resulted in a mean average precision (MAP) score of 0.5392. To test how well a model could generalize to new datasets, the model was trained using examples from only two of the datasets and then tested on examples from all three datasets. The resulting model could not recognize fish in the dataset that was not part of the training set. The MAP scores on the other two datasets that were included in the training set were higher than the scores achieved by the model trained on all three datasets. These results indicate that different methods are needed in order to produce a trained model that can generalize to new data sets such as those encountered in real world applications.

fish detection, underwater video, marine and hydro↗

Neuro-Spark: A Submicrosecond Spiking Neural Networks Architecture for In-Sensor Filtering

Neuro-Spark, which is a new neuromorphic architecture with a field-programmable gate array (FPGA) implementation for ultrafast spiking neural network (SNN) inference at the edge, facilitates smart-pixel in-sensor filtering for high-energy physics experiments at the Large Hadron Collider (LHC). Utilizing the evolutionary optimization for neuromorphic systems (EONS) training method, we generate compact SNN models with 91% signal efficiency, akin to convolutional neural networks but with half the parameters. However, deploying near the detector poses a challenge because the SNN must handle a sustained input data rate exceeding 1013 GB/s. To overcome this, we propose a novel hardware architecture that uses high-level synthesis to construct a tuned architecture for the EONS-trained SNN. In addition to the analysis and validation with an AMD Xilinx Artix-A7 FPGA, our solution consumes only ç24% of FPGA LUT and flipflops. We also introduce an innovative quantization method that reduces FPGA resource utilization by ç15% without compromising accuracy. Our FPGA implementation achieves computing latency of ç10 ns for smart-pixel application inference on an edge FPGA.

Miniskar, Narasinga Rao↗

Dynamic Role-Based Access Control Policy for Smart Grid Applications: An Offline Deep Reinforcement Learning Approach

Role-based access control (RBAC) is adopted in the information and communication technology domain for authentication purposes. However, due to a very large number of entities within organizational access control (AC) systems, static RBAC management can be inefficient, costly, and can lead to cybersecurity threats. In this paper, a novel hybrid RBAC model is proposed, based on the principles of offline deep reinforcement learning (RL) and Bayesian belief networks. The considered framework utilizes a fully offline RL agent, which models the behavioral history of users as a Bayesian belief-based trust indicator. Thus, the initial static RBAC policy is improved in a dynamic manner through off-policy learning while guaranteeing compliance of the internal users with the security rules of the system. By deploying our implementation within the smart grid domain and specifically within a Distributed Energy Resources (DER) ecosystem, we provide an end-to-end proof of concept of our model. Finally, detailed analysis and evaluation regarding the offline training phase of the RL agent are provided, while the online deployment of the hybrid RL-based RBAC model into the DER ecosystem highlights its key operation features and salient benefits over traditional RBAC models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Emerging Technologies for Privacy Preservation in Energy Systems

This study explores the intersection of digitalization and privacy within the energy sector, focusing on the emerging challenges and opportunities presented by integrating Distributed Energy Resources (DERs) and advanced metering infrastructure. The need for robust digital privacy measures has become crucial as the energy industry evolves towards a more decentralized, digitalized, and decarbonized future. This study delves into four cutting-edge privacy-preserving technologies—Homomorphic Encryption (HE), Secure Multiparty Computation (SMPC), Differential Privacy (DP), and Federated Learning (FL)—each offering unique solutions to safeguard consumer data by increasing digital connectivity and data exchange. Through a detailed examination of these methods, the study explains how each technology operates, its applications within the energy sector, and the specific privacy challenges it addresses. Homomorphic Encryption allows for secure computations on encrypted data, enabling data analysis without compromising privacy. Secure Multiparty Computation enables collaborative data analysis across different entities while protecting the confidentiality of the inputs. Differential Privacy introduces randomness into the assembled data set, preventing the identification of individual records in statistical databases. Lastly, Federated Learning offers a paradigm shift in data analysis, where machine learning models are trained at the edge, minimizing the centralization of sensitive data. The research underscores the significance of implementing these privacy-enhancing technologies to comply with strict data protection regulations, foster consumer trust, and enhance the security of the energy infrastructure. By providing a comprehensive overview of these methodologies and their practical implications for the energy sector, this study aims to contribute to the ongoing discourse on digital privacy, offering insights into how the energy industry can navigate the complexities of data privacy in the digital age.

Cali, Umit↗