Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning systems”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Topological Machine Learning Methods for Power System Responses to Contingencies

While deep learning tools, coupled with the emerging machinery of topological data analysis, are proven to deliver various performance gains in a broad range of applications, from image classification to biosurveillance to blockchain fraud detection, their utility in areas of high societal importance such as power system modeling and, particularly, resilience quantification in the energy sector yet remains untapped. To provide fast acting synthetic regulation and contingency reserve services to the grid while having minimal disruptions on customer quality of service, we propose a new topology-based system that depends on a neural network architecture for impact metric classification and prediction in power systems. This novel topology-based system allows one to evaluate the impact of three power system contingency types, in conjunction with transmission lines, transformers, and transmission lines combined with transformers. We show that the proposed new neural network architecture equipped with local topological measures facilitates more accurate classification of unserved load as well as the amount of unserved load. In addition, we are able to learn more about the complex relationships between electrical properties and local topological measurements on their simulated response to contingencies for the NREL-SIIP power system.

contingency analysis↗
DOE OSTI2021

Machine-Learning-Assisted Hybrid Earth System Modelling

We propose a novel hybrid modeling approach that combines a physics-based, numerical model of the Earth system with a machine learning model. We also envision to integrate the hybrid model training with a data assimilation cycle, so that new observations update both the state estimate used as initial conditions and the machine learning model parameters.

58 GEOSCIENCES↗
DOE OSTI2024

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

Deep Reinforcement Learning (DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers (RBCs), but it still lacks scalability and generalisation due to the necessity of using tailored models for the training process. Transfer Learning (TL) is a potential solution to address this limitation. However, existing TL applications in building control have been mostly tested among buildings with similar features, not addressing the need to scale up advanced control in real-world scenarios with diverse energy systems. This paper assesses the performance of an online heterogeneous TL strategy, comparing it with RBC and offline and online DRL controllers in a simulation setup using EnergyPlus and Python. The study tests the transfer in both transductive and inductive settings of a DRL policy designed to manage a chiller coupled with a Thermal Energy Storage (TES). The control policy is pre-trained on a source building and transferred to various target buildings characterised by an integrated energy system including photovoltaic and battery energy storage systems, different building envelope features, occupancy schedule and boundary conditions (e.g., weather and price signal). The TL approach incorporates model slicing, imitation learning and fine-tuning to handle diverse state spaces and reward functions between source and target buildings. Results show that the proposed methodology leads to a reduction of 10% in electricity cost and between 10% and 40% in the mean value of the daily average temperature violation rate compared to RBC and online DRL controllers. Moreover, online TL maximises self-sufficiency and self-consumption by 9% and 11% with respect to RBC. Conversely, online TL achieves worse performance compared to offline DRL in either transductive or inductive settings. However, offline Deep Reinforcement Learning (DRL) agents should be trained at least for 15 episodes to reach the same level of performance as the online TL. Therefore, the proposed online TL methodology is effective, completely model-free and it can be directly implemented in real buildings with satisfying performance.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

High performance FPGA embedded system for machine learning based tracking and trigger in sPhenix and EIC

We present a comprehensive end-to-end pipeline to classify triggers versus background events in this paper. This pipeline makes online decisions to select signal data and enables the intelligent trigger system for efficient data collection in the Data Acquisition System (DAQ) of the upcoming sPHENIX and future EIC (Electron-Ion Collider) experiments. Starting from the coordinates of pixel hits that are lightened by passing particles in the detector, the pipeline applies three-stage of event processing (hits clustering, track reconstruction, and trigger detection) and labels all processed events with the binary tag of trigger versus background events. The pipeline consists of deterministic algorithms such as clustering pixels to reduce event size, tracking reconstruction to predict candidate edges, and advanced graph neural network-based models for recognizing the entire jet pattern. In particular, we apply the message-passing graph neural network to predict links between hits and reconstruct tracks and a hierarchical pooling algorithm (DiffPool) to make the graph-level trigger detection. We obtain an impressive performance (≥70% accuracy) for trigger detection with only 3200 neuron weights in the end-to-end pipeline. We deploy the end-to-end pipeline into a field-programmable gate array (FPGA) and accelerate the three stages with speedup factors of 1152, 280, and 21, respectively.

Instruments & Instrumentation↗
DOE OSTI2021

Automated control of microfluidic devices based on machine learning

A system is provided to automatically monitor and control the operation of a microfluidic device using machine learning technology. The system receives images of a channel of a microfluidic device collected by a camera during operation of the microfluidic device. Upon receiving an image, the system applies a classifier to the image to classify the operation of the microfluidic device as normal, in which no adjustment to the operation is needed, or as abnormal, in which an adjustment to the operation is needed. When an image is classified as normal, the system may make no adjustment to the microfluidic device. If, however, an image is classified as abnormal, the system may output an indication that the operation is abnormal, output an indication of a needed adjustment, or control the microfluidic device to make the needed adjustment.

Giera, Brian↗
NASA NTRS1987

Learning in Artificial Neural Systems

This paper presents an overview and analysis of learning in Artificial Neural Systems (ANS's). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANS's is then described, and compared with classical Machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized, and where possible, the limitations inherent to specific classes of rules are outlined.

Matheus, Christopher J.↗
DOE OSTI2020

Using Machine Learning to Predict Future Temperature Outputs in Geothermal Systems

Optimizing the power output, and economic value, of geothermal power plants over decades of operation is a major challenge in renewable energy. Optimizing the output requires the ability to predict the mass flow rates and the output temperatures of production wells based on the inputs of injection wells, as well as the time history of the system. Machine Learning (ML) that incorporates the known physics of geothermal systems is one possible solution to this challenge. In this work, we explore the ability of ML algorithms to predict future temperature outputs based on historical data. Considering the challenges with obtaining an empirical dataset from field data that is large enough to enable reliable ML, we propose an alternate approach: developing a high-fidelity reservoir model and using computational resources to build a dataset that enables ML. As a first step towards achieving this goal, we present preliminary results from applying ML to predict the temperature timeseries of simple modeled geothermal systems. We describe the application of relevant state-of-the-art ML approaches, such as the Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNN), to extract temporal structures in the model data. We assess the accuracy of the forecasts we obtain, compare the selected approaches, and share the lessons learned that would inform the process of training and utilizing ML algorithms for larger and more complex geothermal systems.

GEOTHERMAL ENERGY↗
DOE OSTI2021

Topological Machine Learning Methods for Power System Responses to Contingencies: Preprint

While deep learning tools, coupled with the emerging machinery of topological data analysis, are proven to deliver various performance gains in a broad range of applications, from image classification to biosurveillance to blockchain fraud detection, their utility in areas of high societal importance such as power system modeling and, particularly, resilience quantification in the energy sector yet remain untapped. To provide fast acting synthetic regulation and contingency reserve services to the grid while having minimal disruptions on customer quality of service, we propose a new topologybased system that depends on neural network architecture for impact metrics classification and prediction in power systems. This novel topology-based system allows one to evaluate the impact of three power system contingency types, namely, in conjunction with transmission lines, transformers, and transmission lines combined with transformers. We show that the proposed new neural network architecture equipped with local topological measures facilitates both more accurate classification of unserved load as well as the amount of unserved load. In addition, we are able to learn complex relationships between electrical properties and local topological measurements on the simulated response to contingencies for NREL-SIIP power system.

graph theory↗
NASA NTRS1993

Knowledge acquisition and interface design for learning on demand systems

The rapid changes in our world precipitated by technology have created new problems and new challenges for education and training. A knowledge 'explosion' is occurring as our society moves toward a service oriented economy that relies on information as the major resource. Complex computer systems are beginning to dominate the workplace, causing alarming growth and change in many fields. The rapidly changing nature of the workplace, especially in fields related to information technology, requires that our knowledge be updated constantly. This characteristic of modern society poses seemingly unsolvable instructional problems involving coverage and obsolescence. The sheer amount of information to be learned is rapidly increasing, while at the same time some information becomes obsolete in light of new information. Education, therefore, must become a lifelong process that features learning of new material and skills as needed in relation to the job to be done. Because of the problems cited above, the current model of learning in advance may no longer be feasible in our high-technology world. In many cases, learning in advance is impossible because there are simply too many things to learn. In addition, learning in advance can be time consuming, and often results in decontextualized knowledge that does not readily transfer to the work environment. The large and growing discrepancy between the amount of potentially relevant knowledge available and the amount a person can know and remember makes learning on demand an important alternative to current instructional practices. Learning on demand takes place whenever an individual must learn something new in order to perform a task or make a decision. Learning on demand is a promising approach for addressing the problems of coverage and obsolescence because learning is contextualized and integrated into the task environment rather than being relegated to a separate phase that precedes work. Learning on demand allows learners to see for themselves the usefulness of new knowledge for actual problem situations, thereby increasing the motivation for learning new information. Finally, learning on demand makes new information relevant to the task at hand, leading to more informed decision making, better quality products, and improved performance.

Nelson, Wayne A.↗
DOE OSTI2024

Convolutional Variational Autoencoder-based Unsupervised Learning for Power Systems Faults

Classification of power system event data is a growing need, particularly where non-protective relaying-based sensors are used to monitor grid performance. Given the high burden of obtaining event data with appropriate labeling, an unsupervised approach is highly valuable. This approach enables using event data without labeling, which is far easier to obtain. This paper presents an unsupervised learning method to classify and label transients observed in the distribution grid. A Convolutional Variational Autoencoder (CVAE) was developed for this purpose. We demonstrate the efficacy of our approach using the transient data generated from the simulations. The simulation data is used to train the CVAE that identifies different faults as different clusters in the latent space. The clusters are then used as the foundation model to categorize the real-world data.

Alam, Maksudul↗
NASA NTRS2010

Heritage and Advanced Technology Systems Engineering Lessons Learned from NASA Space Missions

Use of heritage and new technology is necessary/enabling to implementing small, low cost missions, yet overruns decrease the ability to sustain future mission flight rates The majority of the cost growth drivers seen in the D&NF study were embedded early during formulation phase and later realized during the development and I&T phases Cost drivers can be avoided or significantly decreased by project management and SE emphasis on early identification of risks and realistic analyses SE processes that emphasize an assessment of technology within the mission system to identify technical issues in the design or operational use of the technology. Realistic assessment of new and heritage spacecraft technology assumptions , identification of risks and mitigation strategies. Realistic estimates of effort required to inherit existing or qualify new technology, identification of risks to estimates and develop mitigation strategies. Allocation of project reserves for risk-based mitigation strategies of each individual area of heritage or new technology. Careful tailoring of inheritance processes to ensure due diligence.

Barley, Bryan↗
NASA NTRSDate not supplied

X-57 Systems Engineering Lessons Learned

The X-57 Maxwell is an electric aircraft based on a 4-passenger, twin engine Tecnam P2006T General Aviation aircraft. The X-57 project originally envisioned a straightforward integration of commercial-off-the-shelf hardware components and software into a novel configuration to demonstrate the aerodynamic and performance benefits of Distributed Electric Propulsion (DEP). The project was initially started with a high-risk venture capitalist approach under NASA’s Convergent Aeronautics Solutions (CAS) project, which led to an initial philosophy of Project Management “light” (which was then interpreted as Systems Engineering (SE) “light”). As the project matured, it was forced to transition to one with increasing SE-rigor as the project scope changed, hardware and software deficiencies were found, and the team realized the magnitude of the technical and integration challenges. In hindsight, these technical challenges came in part from an overly optimistic technology readiness assessment (TRA) at the beginning of the project, which resulted in the project assuming that little to no subsystem development would be required. The project’s approach to systems engineering evolved throughout three separate informal phases of the project as it underwent two key transitions as a result of the team wrestling with the technical challenges and resultant changing project scope. This paper discusses the assumptions, approaches, and challenges encountered from a Systems Engineering standpoint in each of the three informal phases of the X-57 project. This paper also provides recommendations on how future projects can apply Systems Engineering best practices upfront along with a realistic TRA to aid projects that find themselves with similar challenges.

Systems Engineering↗
DOE OSTI2025

Machine Learning-Assisted Distribution System Network Reconfiguration Problem

High penetration from volatile renewable energy resources in the grid and the varying nature of loads raise the need for frequent line switching to ensure the efficient operation of electrical distribution networks. Operators must ensure maximum load delivery, reduced losses, and the operation between voltage limits. However, computations to decide the optimal feeder configuration are often computationally expensive and intractable, making it unfavorable for real-time operations. This is mainly due to the existence of binary variables in the network reconfiguration optimization problem. To tackle this issue, we have devised an approach that leverages machine learning techniques to reshape distribution networks featuring multiple substations. This involves predicting the substation responsible for serving each part of the network. Hence, it leaves simple and more tractable Optimal Power Flow problems to be solved. This method can produce accurate results in a significantly faster time, as demonstrated using the IEEE 37-bus distribution feeder. Compared to the traditional optimization-based approaches, a feasible solution is achieved approximately ten times faster for all the tested scenarios.

deep neural networks↗
NASA NTRSDate not supplied

Lessons Learned from Medical System Foundation Development for Long-Duration Lunar Orbit and Lunar Surface Missions

The Human Research Program (HRP) Exploration Medical Capability (ExMC) Element has been tasked with the development of Medical System Foundations for Level of Care IV for both short-duration lunar orbital missions and, subsequently, long-duration lunar orbital and surface operations missions. These Medical System Foundations serve as a framework to aid in early medical system design and mission planning. The content of both Foundation models is similar, consisting of a concept of operations, functional decomposition, clinical content (medical conditions, capabilities, and resources), technical requirements (interface, non-functional, and functional), and traces between these components and to the NASA standards documents and parent-level (Program- and Vehicle habitat system-level) requirements. Additionally, the development of both Foundations employed systems engineering principles and a model-based systems engineering (MBSE) approach. Throughout the development of these Foundations, ExMC has strived to improve the efficiency and robustness of its processes and to be more responsive to change (i.e., in design reference mission parameters and assumptions) and to stakeholders’ feedback. The most significant improvements made between the short- and long-duration Foundation models during this transformation process are the following: • Replacement of the traditional document-based ConOps with a model-based ConOps according to MBSE principles, which facilitated more efficient understanding of the material and the consolidation of all relevant information into a centralized location. • Utilization of an agile approach with tasks organized into sprints. This approach enabled solicitation of more frequent usability feedback from stakeholders, incorporation of more human factors reviews into the sprints, and more efficient tasking of team members. This presentation will discuss the journey of developing both Foundation models, as well as the lessons learned and resulting improvements made between the Short- and Long-Duration models.

M Kaetzer↗
NASA NTRS2015

Systems Engineering Lessons Learned for Class D Missions

One of NASA's goals within human exploration is to determine how to get humans to Mars safely and to live and work on the Martian surface. To accomplish this goal, several smaller missions act as stepping-stones to the larger end goal. NASA uses these smaller missions to develop new technologies and learn about how to survive outside of Low Earth Orbit for long periods. Additionally, keeping a cadence of these missions allows the team to maintain proficiency in the complex art of bringing spacecraft to fruition. Many of these smaller missions are robotic in nature and have smaller timescales, whereas there are others that involve crew and have longer mission timelines. Given the timelines associated with these various missions, different levels of risk and rigor need to be implemented to be more in line with what is appropriate for the mission. Thus, NASA has four different classifications that range from Class A to Class D based on the mission details. One of these projects is the Resource Prospector (RP) Mission, which is a multi-center and multi-institution collaborative project to search for volatiles in the polar regions of the Moon. The RP mission is classified as a Class D mission and as such, has the opportunity to more tightly manage, and therefore accept, greater levels of risk. The requirements for Class D missions were at the forefront of the design and thus presented unique challenges in vehicle development and systems engineering processes. This paper will discuss the systems engineering process at NASA and how that process is tailored for Class D missions, specifically the RP mission.

Rojdev, Kristina↗
NASA NTRS2018

The Disruptive Technology That is Additive Construction: System Development Lessons Learned for Terrestrial and Planetary Applications

Disruptive technologies are unique in that they spawn other new technologies and applications as they grow. These activities are usually preceded by the question, "What If?" For example, "What if we could use an emerging technology and in-situ materials to promote exploration on the Moon or Mars, and then use that same technology to keep our troops out of harm's way and/or help the worlds' homeless?" This question allows us to flip the mindset of "how can people create more valuable innovation?" to "how can innovation create more valuable people?." This approach allows us to view augmented human labor as an inclusive opportunity, not a threat. The discipline of Additive Construction is growing rapidly due to the flexibility, speed, safety and logistics benefits offered as compared to standard construction techniques. Additive construction is a disruptive technology in that it employs the principles of additive manufacturing on a human habitat structure scale. Developed initially for emergency management and disaster relief applications, additive construction has now grown into military infrastructure and planetary (Moon and Mars) surface infrastructure applications as well. Additive Construction with Mobile Emplacement (ACME) is a NASA technology development project that seeks to demonstrate the feasibility of constructing shelters for human crews, and other surface infrastructure, on the Moon or Mars for a future human presence. The ACME project will allow, for the first time, the 3-dimensional printing of surface structures on planetary bodies using local materials for construction, thereby tremendously reducing launch and transportation mass and logistics. Some examples of infrastructure that could be constructed using robotic additive construction methods are landing pads, rocket engine blast protection berms, roads, dust free zones, equipment shelters, habitats and radiation shelters. Terrestrial applications include the development of surface structures using Earth-based materials for emergency response, disaster relief, general construction, and housing at all economic levels. This paper will describe the progress made by the NASA ACME project with a focus on prototypes and full scale additive construction demonstrations using both Portland cement concrete and other indigenous material mixtures. Rationale for the use of additive construction for both terrestrial and planetary applications will be explored and a thorough state-of-the-art of additive construction techniques will be presented. An evolutionary history of NASA's additive construction development efforts, dating back to 2004, will be included. The paper will then step through a series of trade studies performed to inform key processing and design decisions in the development of the full-scale ACES-3 system developed by NASA and the Jacobs Space Exploration Group for the U.S. Army Corps of Engineers (USACE) Construction Engineers Research Laboratory (CERL) in Champaign, IL. The selection of aggregate and binders, based on in-situ materials, will also be presented and discussed

Space Processing↗