SEARCH · Engineering Papers

Results for “Distributed training”

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 1,675 records · Page 93

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Classification and Localization of Fracture-Hit Events in Low-Frequency Distributed Acoustic Sensing Strain Rate with Convolutional Neural Networks

Summary Distributed acoustic sensing (DAS) has been used in the oil and gas industry as an advanced technology for surveillance and diagnostics. Operators use DAS to monitor hydraulic fracturing activities, examine well stimulation efficacy, and estimate complex fracture system geometries. Particularly, low-frequency DAS can detect geomechanical events such as fracture hits because hydraulic fractures propagate and create strain rate variations in the rock. Analysis of DAS data today is mostly done post-job and subject to interpretation methods. However, the continuous and dense data stream generated live by DAS poses the opportunity for more efficient and accurate real-time data-driven analysis. The objective of this study is to develop a machine learning-based workflow that can identify and locate fracture-hit events in simulated strain rate responses correlated with low-frequency DAS data. In this paper, “fracture hit” refers to a hydraulic fracture originating from a stimulated well intersecting an offset well. We start with building a single fracture propagation model to produce strain rate patterns observed at a hypothetical monitoring well. This model is used to generate two sets of strain rate responses with one set containing fracture-hit events. The labeled synthetic data are then used to train a custom convolutional neural network (CNN) model for identifying the presence of fracture-hit events. The same model is trained again for locating the event with the output layer of the model replaced with linear units. We achieved near-perfect predictions for both event classification and localization. These promising results prove the feasibility of using CNN for real-time event detection from fiber-optic sensing data. Additionally, we use edge detection techniques to recognize fracture-hit event patterns in strain rate images. The fracture-hit location can be identified using recognized pixels in the image. The accuracy of edge detection-based location identification is also plausible, but edge detection is dependent on the assumption of pattern shape and image quality, hence it is less robust compared to CNN models. This comparison further supports the need for CNN applications in image-based real-time fiber-optic sensing event detection.

Engineering↗

NASA NTRS2003

Early Petrologic Processes on the Ureilite Parent Body

We present a petrographic and petrologic analysis of 21 olivine-pigeonite ureilites, along with new experimental results on melt compositions predicted to be in equilibrium with ureilite compositions. We conclude that these ureilites are the residues of a partial melting/smelting event. Textural evidence preserved in olivine and pigeonite record the extent of primary smelting. In pigeonite cores, we observe fine trains of iron metal inclusions that formed by the reduction of olivine to pigeonite and metal during primary smelting. Olivine cores lack metal inclusions but the outer grain boundaries are variably reduced by a late-stage reduction event. The modal proportion of pigeonite and percentage of olivine affected by late stage reduction are inversely related and provide an estimation of the degree of primary smelting during ureilite petrogenesis. In our sample suite, this correlation holds for 16 of the 21 samples examined. Olivine-pigeonite-liquid phase equilibrium constraints are used to obtain temperature estimates for the ureilite samples examined. Inferred smelting temperatures range from approximately 1150 C to just over 1300 C and span the range of estimates published for ureilites containing two or more pyroxenes. Temperature is also positively correlated with modal percent pigeonite. Smelting temperature is inversely correlated with smelting depth--the hottest olivine-pigeonite ureilites coming from the shallowest depth in the ureilite parent body. The highest temperature samples also have oxygen isotopic signatures that fall toward the refractory inclusion-rich end of the carbonaceous chondrite-anhydrous mineral (CCAM) slope 1 mixing line. These temperature-depth variations in the ureilite parent body could have been created by a heterogeneous distribution of heat producing elements, which would indicate that isotopic heterogeneities existed in the material from which the ureilite parent body was assembled.

Singletary, S. J.↗

DOE OSTI2022

Online Power System Event Detection via Bidirectional Generative Adversarial Networks

Accurate and speedy detection of power system events is critical to enhancing the reliability and resiliency of power systems. Although supervised deep learning algorithms show great promise in identifying power system events, they require a large volume of high-quality event labels for training. This paper develops a bidirectional anomaly generative adversarial network (GAN)-based algorithm to detect power system events using streaming PMU data, which does not rely on a huge amount of event labels. By introducing conditional entropy constraint in the objective function of GAN and graph signal processing-based PMU sorting technique, our proposed algorithm significantly outperforms state-of-the-art event detection algorithms in terms of accuracy. To facilitate the adoption of the proposed algorithm, a prototype online platform is also developed using Apache Hadoop, Kafka, and Spark to enable real-time event detection. Here, the accuracy and computational efficiency of the proposed algorithm are validated using a large-scale real-world PMU dataset from the Eastern Interconnection of the United States.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS2006

Imagine Moving Off the Planet

Moving off the planet will be a defining moment of this century as landing on the Moon was in the last. For that to happen for humans to go where humans cannot go-- simulation is the sole solution. NASA supports simulation for life-cycle activities: design, analysis, test, checkout, operations, review and training. We contemplate time spans of a century and more, teams dispersed to different planets and the need for systems that endure or adapt as missions, teams and technology change. Without imagination such goals are impossible. But with imagination we can go outside our present perception of reality to think about and take action on what has been, is and, especially, what might be. Consciously maturing an imagined, possibly workable, idea through framing it to optimization to design, and building the product provides us with a new approach to innovation and simulation fidelity. We address options, analyze, test and make improvements in how we think and work. Each step includes increasingly exact information about costs, schedule, who will be needed, where, when and how. NASA i integrating such thinking into its Exploration Product Realization Hierarchy for simulation and analysis, test and verification, and stimulus response goals. Technically NASA follows a timeline of studies, analysis, definition, design, development and operations with concurrent documentation. We have matched this Product Realization Hierarchy with a continuum from image to realization that incorporates commitment, current and needed research and communication to ensure superior and creative problem solving as well as advances in simulation. One result is a new approach to collaborative systems. Another is a distributed observer network prototyped using game engine technology bringing advanced 3-D simulation of a simulation to the desktop enabling people to develop shared consensus of its meaning. Much of the value of simulation comes from developing in people their ability to make good decisions and reflexes supporting impressive achievement. Synthesizing imagination systematically into our work - and thus our success - is a challenge. NASA engineers have inventive minds, and the task is determining how best to enable them to devise the simulation and other innovations that will make a story so clear and so intellectually sound that people can carry out the mission for 50-100 years. This demands skills and knowledge traditionally under-respected and under-represented in technology organizations. But we are beginning to see that the process encourages efficiency and enables us to attain more effective results. We have to elicit imaginative, intelligent and effective ways to make better use than ever of the minds we have and will have available. We have to accept the challenge to accomplish tasks among dispersed interdisciplinary teams who must overcome changing priorities and technology, time and distance in order to maximize interactivity and innovation as never before. Attention to the process of innovation is a practical means to increase the efficiency of our intelligence. We have an obligation to reexamine and improve the process by which we approach and exercise innovation as we accept the charge to move off the planet.

Elfrey, Priscilla R.↗

NASA NTRS2020

Biomass Estimation from Simulated GEDI, ICESat-2 and NISAR Across Environmental Gradients in Sonoma County, California

Estimates of the magnitude and distribution of aboveground carbon in Earth’s forests remain uncertain, yet knowledge of forest carbon content at a global scale is critical for forest management in support of climate mitigation. In light of this knowledge gap, several upcoming spaceborne missions aim to map forest aboveground biomass, and many new biomass products are expected from these datasets. As these new missions host different technologies, each with relative strengths and weaknesses for biomass retrieval, as well as different spatial resolutions, consistently comparing or combining biomass estimates from these new datasets will be challenging. This paper presents a demonstration of an inter-comparison of biomass estimates from simulations of three NASA missions (GEDI, ICESat-2 and NISAR) over Sonoma county in California, USA. We use a high resolution, locally calibrated airborne lidar map as our reference dataset, and emphasize the importance of considering uncertainties in both reference maps and spaceborne estimates when conducting biomass product validation. GEDI and ICESat-2 were simulated from airborne lidar point clouds, while UAVSAR’s L-band backscatter was used as a proxy for NISAR. To estimate biomass for the lidar missions we used GEDI’s footprint-level biomass algorithms, and also adapted these for application to ICESat-2. For UAVSAR, we developed a locally trained biomass model, calibrated against the ALS reference map. Each mission simulation was evaluated in comparison to the local reference map at its native product resolution (25 m, 100m transect, and 1 ha) yielding RMSEs of 57%, 75%, and 89% for GEDI, NISAR, and ICESat-2 respectively. RMSE values increased for GEDI’s power beam during simulated daytime conditions (64%), coverage beam during nighttime conditions (72%), and coverage beam daytime conditions (87%). We also test the application of GEDI’s biomass modeling framework for estimation of biomass from ICESat-2, and fine that ICESat-2 yields reasonable biomass estimates, particularly in relatively short, open canopies. Results suggest that while all three missions will produce datasets useful for biomass mapping, tall, dense canopies such as those found in Sonoma County present the greatest challenges for all three missions, while steep slopes also prove challenging for single-date SAR based biomass retrieval. Our methods provide guidance for the inter-comparison and validation of spaceborne biomass estimates through the use of airborne lidar reference maps, and could be repeated with on-orbit estimates in any area with high quality field plot and ALS data. These methods allow for regional interpretations and filtering of multi-mission biomass estimates toward improved wall-to-wall biomass maps through data fusion.

GEDI↗

DOE OSTI2021

Stopping criteria for ending autonomous, single detector radiological source searches

While the localization of radiological sources has traditionally been handled with statistical algorithms, such a task can be augmented with advanced machine learning methodologies. The combination of deep and reinforcement learning has provided learning-based navigation to autonomous, single-detector, mobile systems. However, these approaches lacked the capacity to terminate a surveying/search task without outside influence of an operator or perfect knowledge of source location (defeating the purpose of such a system). Two stopping criteria are investigated in this work for a machine learning navigated system: one based upon Bayesian and maximum likelihood estimation (MLE) strategies commonly used in source localization, and a second providing the navigational machine learning network with a “stop search” action. A convolutional neural network was trained via reinforcement learning in a 10 m × 10 m simulated environment to navigate a randomly placed detector-agent to a randomly placed source of varied strength (stopping with perfect knowledge during training). The network agent could move in one of four directions (up, down, left, right) after taking a 1 s count measurement at the current location. During testing, the stopping criteria for this navigational algorithm was based upon a Bayesian likelihood estimation technique of source presence, updating this likelihood after each step, and terminating once the confidence of the source being in a single location exceeded 0.9. A second network was trained and tested with similar architecture as the previous but which contained a fifth action: for self-stopping. The accuracy and speed of localization with set detector and source initializations were compared over 50 trials of MLE-Bayesian approach and 1000 trials of the CNN with self-stopping. The statistical stopping condition yielded a median localization error of ~1.41 m and median localization speed of 12 steps. The machine learning stopping condition yielded a median localization error of 0 m and median localization speed of 17 steps. This work demonstrated two stopping criteria available to a machine learning guided, source localization system.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

DOE OSTI2024

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling

Recent advances in differentiable modeling, a genre of physics-informed machine learning that trains neural networks (NNs) together with process-based equations, have shown promise in enhancing hydrological models' accuracy, interpretability, and knowledge-discovery potential. Current differentiable models are efficient for NN-based parameter regionalization, but the simple explicit numerical schemes paired with sequential calculations (operator splitting) can incur numerical errors whose impacts on models' representation power and learned parameters are not clear. Implicit schemes, however, cannot rely on automatic differentiation to calculate gradients due to potential issues of gradient vanishing and memory demand. Here we propose a “discretize-then-optimize” adjoint method to enable differentiable implicit numerical schemes for the first time for large-scale hydrological modeling. The adjoint model demonstrates comprehensively improved performance, with Kling–Gupta efficiency coefficients, peak-flow and low-flow metrics, and evapotranspiration that moderately surpass the already-competitive explicit model. Therefore, the previous sequential-calculation approach had a detrimental impact on the model's ability to represent hydrological dynamics. Furthermore, with a structural update that describes capillary rise, the adjoint model can better describe baseflow in arid regions and also produce low flows that outperform even pure machine learning methods such as long short-term memory networks. The adjoint model rectified some parameter distortions but did not alter spatial parameter distributions, demonstrating the robustness of regionalized parameterization. Despite higher computational expenses and modest improvements, the adjoint model's success removes the barrier for complex implicit schemes to enrich differentiable modeling in hydrology.

58 GEOSCIENCES↗

DOE OSTI2022

Learning functional priors and posteriors from data and physics

In this work, we develop a new Bayesian framework based on deep neural networks to be able to extrapolate in space-time using historical data and to quantify uncertainties arising from both noisy and gappy data in physical problems. Specifically, the proposed approach has two stages: (1) prior learning and (2) posterior estimation. At the first stage, we employ the physics-informed Generative Adversarial Networks (PI-GAN) to learn a functional prior either from a prescribed function distribution, e.g., Gaussian process, or from historical data and physics. At the second stage, we employ the Hamiltonian Monte Carlo (HMC) method to estimate the posterior in the latent space of PI-GANs. In addition, we use two different approaches to encode the physics: (1) automatic differentiation, used in the physicsinformed neural networks (PINNs) for scenarios with explicitly known partial differential equations (PDEs), and (2) operator regression using the deep operator network (DeepONet) for PDE-agnostic scenarios. We then test the proposed method for (1) meta-learning for one-dimensional regression, and forward/inverse PDE problems (combined with PINNs); (2) PDE-agnostic physical problems (combined with DeepONet), e.g., fractional diffusion as well as saturated stochastic (100-dimensional) flows in heterogeneous porous media; and (3) spatial-temporal regression problems, i.e., inference of a marine riser displacement field using experimental data from the Norwegian Deepwater Programme (NDP). The results demonstrate that the proposed approach can provide accurate predictions as well as uncertainty quantification given very limited scattered and noisy data, since historical data could be available to provide informative priors. In summary, the proposed method is capable of learning flexible functional priors, e.g., both Gaussian and non-Gaussian process, and can be readily extended to big data problems by enabling mini-batch training using stochastic HMC or normalizing flows since the latent space is generally characterized as low dimensional.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

Particle image velocimetry analysis with simultaneous uncertainty quantification using Bayesian neural networks

Particle image velocimetry (PIV) is an effective tool in experimental fluid mechanics for extracting flow fields from images. Recently, convolutional neural networks (CNNs) have been used to perform PIV analysis with accuracy on par with classical methods. Here we extend the use of CNNs to analyze PIV data while providing simultaneous uncertainty quantification on the inferred flow field. The method we apply in this paper is a Bayesian convolutional neural network (BCNN) which learns distributions of the CNN weights through variational Bayes. In order to demonstrate the utility of BCNNs for the PIV task, we compare the performance of three distinct BCNN models with simple architectures. The first network estimates flow velocity from image interrogation regions only. Our second model learns to infer velocity from both the image interrogation regions and interrogation region cross-correlation maps. Finally, our best performing network infers velocities from interrogation region cross-correlation maps only. We find that BCNNs using interrogation region cross-correlation maps as inputs perform better than those using interrogation windows only as inputs and discuss reasons why this may be the case. Additionally, we test the best performing BCNN on a full synthetic test image pair and a real image pair from the 1st International PIV Challenge. We show that ~98% of true particle displacements from the full synthetic image pair can be captured within the BCNN's 95% confidence intervals, and that the BCNN's performance on the real image pair is quantitatively similar to that of algorithms tested in the 1st International PIV Challenge. Finally, we show that BCNNs can be generalized to be used with multi-pass PIV algorithms with a moderate loss in accuracy, which may be overcome by future work on finetuning and training schemes. So to our knowledge, this is the first use of Bayesian neural networks to perform PIV.

47 OTHER INSTRUMENTATION↗

DOE OSTI2022

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems: Preprint

We present the PowerGridworld software package to provide users with a light-weight, modular, and customizable framework for creating power systems-focused, multi-agent gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). While many frameworks exist for training multi-agent (MA) RL policies, none exist to rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning multi-agent RL policies using both OpenAI's MADDPG and RLLib's PPO algorithms where, in both cases, at least some subset of agents incorporate elements of the power flow solution at each time step as part of their reward (negative cost) structures.

MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Performance Comparison of Clipping Detection Techniques in AC Power Time Series

In this research, a variety of methods were developed to detect clipping periods in AC power time series. AC power data streams associated with 36 unique systems across the United States were collected, and data points representing clipping periods were manually labeled by experts. Using this data set for training and validation, novel logic-based and machine learning (ML) approaches were developed to classify time series values as clipping or non-clipping. These approaches were compared to the RdTools method for detecting clipping periods. The logic-based and ML XGBoost approaches achieved F-scores of 85.0 and 77.6, respectively, when cross-validated against the manually labeled data, as compared to the current RdTools approach (F-score of 56.4), indicating a significant improvement at detecting clipping periods. Additionally, the effects of each clipping filter when evaluating system degradation rates were assessed, using 31 unique systems across the United States. Results indicate that estimated system degradation rate can vary based on the type of clipping filter used, by up to 0.6% degradation rate for some cases.

clipping↗

NASA NTRS2001

Overview and Scientific Agenda of Global Precipitation Mission

This paper addresses the status of the Global Precipitation Mission (GPM) currently planned for launch in the 2007-2008 time frame. The GPM notional design involves a 9-member satellite constellation, one of which wilt be an advanced TRMM-like "core" satellite carrying a dual-frequency Ku-Ka band radar (DFPR) and a TMI-like radiometer. The other eight members of the constellation will be considered daughters of the core satellite, each carrying some type of passive microwave radiometer measuring across the 10.7 - 85 GHz ,frequency range - likely to include a combination of lightweight satellites and co-existing operational/Experimental satellites carrying passive microwave radiometers (i.e., SSM/I and AMSR-E & -F). The constellation is designed to provide no worse than 3-hour sampling at any spot on the globe using sun-synchronous orbit architecture for the daughter satellites, with the core satellite providing relevant measurements on internal cloud-precipitation microphysical processes and the "training-calibrating" information for retrieval algorithms used on daughter satellite measurements. The GPM is organized internationally, currently involving a partnership between NASA in the US, NASDA in Japan, and ESA in Europe (representing the European community nations). The mission is expected to involve additional international participants, sister agencies to the mainstream space agencies, and a diverse collection scientists from academia, government, and the private sector, A critical element in understanding the scientific thinking which has motivated the GPM project is an understanding of what scientific problems TRMM has and has not been able to address and at what scales. The TRMM satellite broke important scientific ground because it carried to space an array of rain-sensitive instruments, two of which were specifically designed for physical precipitation retrieval. These were the 9-channel TRMM Microwave Imager (TMI) and the 13.8 GHz Precipitation Radar (PR). By the same token, because TRMM is a single satellite in a low inclination, low altitude, non-sun-synchronous orbit, it cannot provide global coverage or regular diurnal sampling. These features are essential for many current scientific inquiries involving physical processes of climate and the global water cycle, the modeling of hydrometeorological-biogeochemical cycling, and coupled land-atmosphere/ocean-atmosphere exchanges. Moreover, TRMM has not been able to retrieve explicit properties of the drop size distribution (DSD), a final major barrier to making accurate rain measurements, because the single frequency TRMM radar cannot measure differential reflectivity. which is a minimal requirement for attacking rain retrieval within the framework of extinction cross-section-dependency. GPM is expected to surmount much of the DSD retrieval problem because its core satellite wilt have the capacity to make differential reflectivity measurements with its Ku-Ka band radar (13.6 - 35 GHz) called DFPR - being developed by NASDA/CRL in Japan. This paper will provide an overview of the above issues as well as present a discussion on the expected measurement improvements.

Smith, Eric A.↗

DOE OSTI2025

Designing Future Energy Systems with Generative AI

Energy systems are experiencing various changes that impact the distribution, use, and reliability of energy. Local utilities and municipalities must respond and adapt to these changes, moving towards a future energy system with modernized infrastructure and other targeted investments and policy decisions. However, planning for and enacting these advancements requires significant effort from experts and engineers to develop strategies that ensure a reliable and secure energy future. This includes characterizing the current energy infrastructure, identifying areas for development, and engaging with local community members. Emerging generative artificial intelligence techniques can alleviate pain points and help support the development of the next generation of energy systems. Here, in this article, we highlight on-going generative AI work in the areas of atmospheric modeling, building energy management, and distribution network design, and we propose a vision for the role of generative AI that considers opportunities and identifies challenges inherent to this technology.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2025

Performance Evaluation of Vertical Federated Machine Learning Against Adversarial Threats on Wide-Area Control System: Preprint

Federated machine learning (FL) is gaining significant popularity to develop cybersecurity solutions in power grids because of its advanced capability to support decentralized data handing at local devices, its privacy preservation, and its low-bandwidth requirement. However, the evolving adversarial machine learning (AML) threats raise significant concerns for the cybersecurity of FL architectures. The FL-based split neural network (SplitNN) achieves high performance through the decentralized training of local neural network models while preserving data privacy across multiple entities. In this paper, we propose a methodology for evaluating the performance of a vertical FLbased anomaly detector against different types of AML attacks, including denial-of-service attacks, adversarial data injection attacks, and replay attacks on the trained local models deployed in the grid network. For a case study, we consider the modified IEEE 13-bus system, and we develop SplitNN-based binary and multiclass classification models to detect, locate, and identify different types of data integrity attacks on the volt-watt control with two pooling layers: maximum pooling and AvgPool. Our experimental results, computed through performance metrics, reveal that the severity of these AML attacks varies with the integrated pooling mechanism, the type of classification model, and the nature of the cyberattack. Further, the AML attacks negatively impacted the prediction time per sample for the pretrained SplitNN during the online testing.

adversarial threats↗

NASA NTRS2021

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

This research uses machine-learned computational analyses to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is from a rodent model exposed to ≤ 15 cGy of individual Galactic Cosmic Radiation (GCR) ions: 4He, 16O, 28Si, 48Ti, or 56Fe, expected for a Lunar or Mars mission. This work investigates rats at a subject-based level and uses performance scores taken before irradiation to predict impairment in Attentional Set-shifting (ATSET) data post-irradiation. Here, the worst performing rats of the control group define the impairment thresholds based on population analyses via cumulative distribution functions, leading to the labeling of impairment for each subject. 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 Machine Learning (ML) classifiers such as the Gaussian Naïve Bayes, Support Vector Machine, and Artificial Neural Networks identifies rats that have a higher tendency for impairment after GCR exposure. The algorithms employ the experimental prescreenperformance scores as multidimensional input features to predict each rodent’s susceptibility to cognitive impairment due to space radiation exposure. The receiver operating characteristic and the precision-recall curves of the ML models show a better prediction of impairment when 56Feis the ion in question in both SD and CD stages. They, however, do not depict impairment due to 4Hein SD and 28Siin CD, suggesting no dose-dependent impairment response in these cases. One key finding of our study is that prescreen performance scores can be used to predict the ATSET performance impairments. This result is significant to crewed space missions as it supports the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. Future research can focus on constructing ML ensemble methods to integrate the findings from the methodologies implemented in this study for morerobust predictionsof cognitive decrements due to space radiation exposure.

space radiation↗

NASA NTRSDate not supplied

A Decision Support System for Extravehicular Operations Under Significant Communication Latency

Humanity hopes to perform extravehicular activities (EVAs) on the surface of Mars; however, several technical and operational challenges must first be overcome. Foremost among these challenges is managing a significant communication latency between Earth and Mars. Current and historical paradigms of EVA operations have required near-real-time communication between the crewmember(s) and Earth-based mission control. Nextgeneration operational paradigms for supporting deep space exploration will necessitate a distributed decision authority system, including delayed Earth-based mission control, the onplanet extravehicular crewmember(s), and intermediate mission support from intravehicular (IV) crewmember(s) within real-time communication range. This latter group is of particular interest: they must provide operations support without the plentiful resources available to mission control on Earth. Thus, NASA is developing the Personalized EVA Informatics and Decision Support (PersEIDS) software platform. PersEIDS is designed to bolster operator situational awareness and offload operator workload by automatically tracking and projecting consumables usage over an EVA timeline, providing real-time probabilistic safety assessments and recommending alternative EVA timeline(s) when the active timeline is not expected to be completed under consumables limits. The PersEIDS concept of operations, use cases, and models will be presented. A limited version of PersEIDS was demonstrated during a three-day-long study where each day a roughly four-hour-long simulated Martian EVA was performed in virtual reality at the NASA Johnson Space Center. The first day was a control trial without PersEIDS support; the second and third days represented different levels of decision support provided by PersEIDS to the IV crewmember acting as mission control. With PersEIDS support, the IV crewmember was able to manage the mission to completion faster and with more remaining consumables; however, additional testing is required to understand confounding factors, e.g., training bias.

Mars↗

NASA NTRSDate not supplied

PersEIDS: A Biomedical Decision Support System for Extravehicular Operations Under Significant Communication Latency

Mars↗

DOE OSTI2023

Demonstrate FARM supervisory capabilities for a thermal energy storage problem for the DETAIL facility: IES Simulation Ecosystem Control System Development

The goal of the power dispatch problem for an Integrated Energy System (IES) is to adjust the power output and the heat flow of each component to maximize the profitability of the whole unit. Facilities that can integrate real-time digital signals, mock nuclear power, thermal energy storage and industrial heat use via high-temperature electrolysis were constructed at INL to support the research activities. The Dynamic Energy Technology and Integration Laboratory (DETAIL) houses the Microreactor Agile Non-nuclear Experimental Test Bed (MAGNET) and the Thermal Energy Distribution System (TEDS). In this report, the hierarchical control system architecture proposed in June 2023 milestone for the flexible operation of DETAIL facility is finalized and demonstrated. A brief description of the components and the corresponding Dymola models from the HYRBID repository is first provided. Then, the current control strategy is presented. In particular, the approach for generating the set-point trajectories to be fed to the PI controllers is analyzed, and its limits were identified. To preserve safe operation over both long-time and real-time horizons, the integration of a Supervisory Control layer embedding a modified version of FARM (Feasible Actuator Range Modifier) module is proposed. FARM is a component of the RAVEN-based FORCE framework designed to support HERON module at optimizing the operation of IES units. The proposed control system for DETAIL foresees FARM to be applied twice, i.e., the original version (“FARM-Validator”) aiding the solution of the power dispatch problem, and a modified version (“FARM-Supervisory”) coordinating the PID controllers. Despite the kernel of the two modules is the same, their tasks are quite different. The former intervenes at the beginning of each hour to prevent constraint violations over long time periods, the latter addresses real-time control tasks and monitors the response of constrained variables at a much finer time resolution. A tentative procedure for training the embedded Digital Twins with the experimental data is also proposed. Finally, the capabilities of the designed architecture and the impact of the added Supervisory Control layer are demonstrated by simulating a representative power dispatch scenario.

25 ENERGY STORAGE↗