Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning based 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 1,189 records · Page 66
All sourcesNASA NTRSDOE OSTI
NASA NTRS2004

Development of a State Machine Sequencer for the Keck Interferometer: Evolution, Development and Lessons Learned using a CASE Tool Approach

This paper presents a discussion of the evolution of a sequencer from a simple EPICS (Experimental Physics and Industrial Control System) based sequencer into a complex implementation designed utilizing UML (Unified Modeling Language) methodologies and a CASE (Computer Aided Software Engineering) tool approach. The main purpose of the sequencer (called the IF Sequencer) is to provide overall control of the Keck Interferometer to enable science operations be carried out by a single operator (and/or observer). The interferometer links the two 10m telescopes of the W. M. Keck Observatory at Mauna Kea, Hawaii. The IF Sequencer is a high-level, multi-threaded, Hare1 finite state machine, software program designed to orchestrate several lower-level hardware and software hard real time subsystems that must perform their work in a specific and sequential order. The sequencing need not be done in hard real-time. Each state machine thread commands either a high-speed real-time multiple mode embedded controller via CORB A, or slower controllers via EPICS Channel Access interfaces. The overall operation of the system is simplified by the automation. The UML is discussed and our use of it to implement the sequencer is presented. The decision to use the Rhapsody product as our CASE tool is explained and reflected upon. Most importantly, a section on lessons learned is presented and the difficulty of integrating CASE tool automatically generated C++ code into a large control system consisting of multiple infrastructures is presented.

interferometer↗
DOE OSTI2022

On the specificity between mapping of initial and final states of the magneto Rayleigh-Taylor instability

In this LDRD we investigated the application of machine learning methods to understand dimensionality reduction and evolution of the Rayleigh-Taylor instability (RTI). As part of the project, we undertook a significant literature review to understand current analytical theory and machine learning based methods to treat evolution of this instability. We note that we chose to refocus on assessing the hydrodynamic RTI as opposed to the magneto-Rayleigh-Taylor instability originally proposed. This choice enabled utilizing a wealth of analytic test cases and working with relatively fast running open-source simulations of single-mode RTI. This greatly facilitated external collaboration with URA summer fellowship student, Theodore Broeren. In this project we studied the application of methods from dynamical systems learning and traditional regression methods to recover behavior of RTI ranging from the fully nonlinear to weakly nonlinear (wNL) regimes. Here we report on two of the tested methods SINDy and a more traditional regression-based approach inspired by analytic wNL theory with which we had the most success. We conclude with a discussion of potential future extensions to this work that may improve our understanding from both theoretical and phenomenological perspectives.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1985

Expert systems for Space Station automation

The expert systems required for automating key functions of the Manned Space Station (MSS) are explored. It is necessary that the expert systems developed be flexible, degrade gracefully in the case of a failure, and be able to work with incomplete data. The AI systems will have to perform interpretation and diagnosis, design, prediction and induction, and monitoring and control functions. Both quantitative and qualitative reasoning capabilities need improvements, as do automatic verification techniques, explanation and learning capabilities, and the use of metaknowledge, i. e., knowledge about the knowledge contained in the knowledge base. Information retrieval, fault isolation and manufacturing process control demonstrations are needed to validate expert systems for the MSS.

Georgeff, M. P.↗
DOE OSTI2022

Accurate and Rapid Forecasts for Geologic Carbon Storage via Learning-Based Inversion-Free Prediction

Carbon capture and storage (CCS) is one approach being studied by the U.S. Department of Energy to help mitigate global warming. The process involves capturing CO 2 emissions from industrial sources and permanently storing them in deep geologic formations (storage reservoirs). However, CCS projects generally target “green field sites,” where there is often little characterization data and therefore large uncertainty about the petrophysical properties and other geologic attributes of the storage reservoir. Consequently, ensemble-based approaches are often used to forecast multiple realizations prior to CO 2 injection to visualize a range of potential outcomes. In addition, monitoring data during injection operations are used to update the pre-injection forecasts and thereby improve agreement between forecasted and observed behavior. Thus, a system for generating accurate, timely forecasts of pressure buildup and CO 2 movement and distribution within the storage reservoir and for updating those forecasts via monitoring measurements becomes crucial. This study proposes a learning-based prediction method that can accurately and rapidly forecast spatial distribution of CO 2 concentration and pressure with uncertainty quantification without relying on traditional inverse modeling. The machine learning techniques include dimension reduction, multivariate data analysis, and Bayesian learning. The outcome is expected to provide CO 2 storage site operators with an effective tool for timely and informative decision making based on limited simulation and monitoring data.

58 GEOSCIENCES↗
NASA NTRS1990

Application of adjoint operators to neural learning

A technique for the efficient analytical computation of such parameters of the neural architecture as synaptic weights and neural gain is presented as a single solution of a set of adjoint equations. The learning model discussed concentrates on the adiabatic approximation only. A problem of interest is represented by a system of N coupled equations, and then adjoint operators are introduced. A neural network is formalized as an adaptive dynamical system whose temporal evolution is governed by a set of coupled nonlinear differential equations. An approach based on the minimization of a constrained neuromorphic energylike function is applied, and the complete learning dynamics are obtained as a result of the calculations.

Barhen, J.↗
DOE OSTI2022

Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithms

Machine learning methods have been extensively used to study the dynamics of complex fluid flows. One such algorithm, known as adaptive neural fuzzy inference system (ANFIS), can generate data-driven predictions for flow fields, but has not been applied to natural geophysical flows in large-scale rivers. Herein, we demonstrate the potential of ANFIS to produce three-dimensional (3D) realizations of the instantaneous flood flow field in several large-scale, virtual meandering rivers. The 3D dynamics of flood flow in large-scale rivers were obtained using large-eddy simulation (LES). The LES results, i.e., the 3D velocity components, were employed to train the learnable coefficients of an ANFIS. Further, the trained ANFIS, along with a few time-steps of LES results (precursor data) were then used to produce 3D realizations of flood flow fields in large-scale rivers with geometries other than the one the ANFIS was trained with. We also used the trained ANFIS to generate 3D realizations of river flow at a discharge other than that the ANFIS was trained with. The flow field results obtained from ANFIS were validated using separate LES runs to assess the accuracy of the 3D instantaneous realizations of the machine learning algorithm. An error analysis was conducted to quantify the discrepancies among the ANFIS and LES results for various flood flow predictions in large-scale rivers.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learningautonomous systems; flight simulat↗
NASA NTRSDate not supplied

Differential Equation Approximation Using Gradient-Boosted Quantile Regression

The operation of cyber-physical-human (CPH) systems is subject to various epistemic and aleatory uncertainties. Overall trustworthiness of CPH systems relies on the trustworthiness of its components and their interactions. It is important that computational models comprising the cyber component of CPH provide predictions accompanied by a measure of confidence in model outcomes. Uncertainty quantification (UQ) and propagation are especially important in safety critical CPH systems. Gradient-boosted trees is a modeling approach capable both of learning the dynamics of a system and performing UQ. In this paper, we devise a method for using gradient boosting to learn the dynamics of a second order differential equation and estimate uncertainty at the same time. We do this by creating a custom loss function that trains the model to approximate the second derivative of a noisy time series, and to penalize based on a parameter that corresponds to the desired quantile. The resulting gradient boosting model can simulate stochastic trajectories of the system given a single starting point, that is, it can estimate both the expected trajectory and its uncertainty. We show that the uncertainty estimation is well calibrated and that the model can learn the dynamics even in the presence of noise. We demonstrate the approach on a simple cartpole system.

Autonomous systems↗
DOE OSTI2025

SECURED: Simulator-Enhanced Control and Understanding of Reactor systems for cyber-Event Defense

The study discusses a learning approach for analyzing cyber-events in reactor systems using integrated hardware and personal computer simulator models. Key points include the rise in cyber-attacks and their sophistication in industrial control systems (ICS), the necessity for awareness, understanding, resource allocation, and preparation to combat these threats, and the digital transformation of old and new nuclear plants, increasing their exposure to cyber threats. It highlights the cyber vulnerabilities of advanced reactor systems, which rely on digital instrumentation and control for operations and safety functions, making them susceptible to cyber-attacks. The approach involves demonstrating reactor system plant ICS cyber-attacks under various operational conditions utilizing tools like simulator models and hardware-based kits. A strategic solution approach tailored to critical infrastructure is emphasized, along with community engagement for public and government support, adopting effective learning approaches, and the preparation for anticipated future challenges. The presentation concludes with a call to action to address challenges, leverage opportunities, and advance through lesson learning in cybersecurity for nuclear energy systems.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2024

Anomaly detection for cyber-physical systems

An anomaly detector is configured to construct cyber and/or physical features comprising information configured to characterize the cyber and/or physical state of a cyber-physical system. The physical features may be based on physical and/or physics-based relationships between a plurality of physical state attributes. A health of the cyber-physical system may be based on an error between estimates of one or more of the physical state attributes and measurements of the one or more physical state attributes. The relationships may be incorporated into machine learning membership functions used to classify cyber and/or physical behavior of the system.

Rieger, Craig G.↗
NASA NTRS1988

The organization of an autonomous learning system

The organization of systems that learn from experience is examined, human beings and animals being prime examples of such systems. How is their information processing organized. They build an internal model of the world and base their actions on the model. The model is dynamic and predictive, and it includes the systems' own actions and their effects. In modeling such systems, a large pattern of features represents a moment of the system's experience. Some of the features are provided by the system's senses, some control the system's motors, and the rest have no immediate external significance. A sequence of such patterns then represents the system's experience over time. By storing such sequences appropriately in memory, the system builds a world model based on experience. In addition to the essential function of memory, fundamental roles are played by a sensory system that makes raw information about the world suitable for memory storage and by a motor system that affects the world. The relation of sensory and motor systems to the memory is discussed, together with how favorable actions can be learned and unfavorable actions can be avoided. Results in classical learning theory are explained in terms of the model, more advanced forms of learning are discussed, and the relevance of the model to the frame problem of robotics is examined.

Kanerva, Pentti↗
NASA NTRS2017

Training Early Career Scientists in Flight Instrument Design Through Experiential Learning: NASA Goddard's Planetary Science Winter School.

The NASA Goddard Planetary Science Winter School (PSWS) is a Goddard Space Flight Center-sponsored training program, managed by Goddard's Solar System Exploration Division (SSED), for Goddard-based postdoctoral fellows and early career planetary scientists. Currently in its third year, the PSWS is an experiential training program for scientists interested in participating on future planetary science instrument teams. Inspired by the NASA Planetary Science Summer School, Goddard's PSWS is unique in that participants learn the flight instrument lifecycle by designing a planetary flight instrument under actual consideration by Goddard for proposal and development. They work alongside the instrument Principal Investigator (PI) and engineers in Goddard's Instrument Design Laboratory (IDL; idc.nasa.gov), to develop a science traceability matrix and design the instrument, culminating in a conceptual design and presentation to the PI, the IDL team and Goddard management. By shadowing and working alongside IDL discipline engineers, participants experience firsthand the science and cost constraints, trade-offs, and teamwork that are required for optimal instrument design. Each PSWS is collaboratively designed with representatives from SSED, IDL, and the instrument PI, to ensure value added for all stakeholders. The pilot PSWS was held in early 2015, with a second implementation in early 2016. Feedback from past participants was used to design the 2017 PSWS, which is underway as of the writing of this abstract.

Flight↗
NASA NTRS1988

Knowledge-based assistance in costing the space station DMS

The Software Cost Engineering (SCE) methodology developed over the last two decades at IBM Systems Integration Division (SID) in Houston is utilized to cost the NASA Space Station Data Management System (DMS). An ongoing project to capture this methodology, which is built on a foundation of experiences and lessons learned, has resulted in the development of an internal-use-only, PC-based prototype that integrates algorithmic tools with knowledge-based decision support assistants. This prototype Software Cost Engineering Automation Tool (SCEAT) is being employed to assist in the DMS costing exercises. At the same time, DMS costing serves as a forcing function and provides a platform for the continuing, iterative development, calibration, and validation and verification of SCEAT. The data that forms the cost engineering database is derived from more than 15 years of development of NASA Space Shuttle software, ranging from low criticality, low complexity support tools to highly complex and highly critical onboard software.

Henson, Troy↗
DOE OSTI2021

pnnl/neuromancer

Dynamics-based deep learning methods to modernize current scientific computing methods. Neuromancer is currently capable of solving inverse problems for a system of ordinary differential equations. The functionality includes system identification and constrained optimal control of unknown or partially known ODEs.

Skomski, Elliott↗
DOE OSTI2021

Gaussian Process Regression for Aggregate Baseline Load Forecasting

Demand response (DR) is one of the most effective ways to maintain the reliability and improve the flexibility of power systems. Accurate forecasts of baseline loads are essential for DR programs. In the era of big data, machine learning-based approaches present a unique opportunity for baseline load forecasting. Thus, this paper presents a machine learning-based approach using a relatively less explored algorithm, Gaussian process regression (GPR), to forecast aggregate baseline loads. As such, a dataset was generated using a set of EnergyPlus simulations. Using the generated dataset, a GPR-based forecasting model was developed. In addition, support vector regression (SVR)-, artificial neural network (ANN)-, and averaging-based models were developed as baseline models for comparison. These models were compared in terms of accuracy, simplicity, and integrity. The prediction performance of the models showed that the GPR-based model is more accurate and reliable than the others. Such high performance shows the potential of the GPR in baseline load forecasting. GPR, therefore, can be used for DR applications.

Amasyali, Kadir↗
NASA NTRS1994

Finding accurate frontiers: A knowledge-intensive approach to relational learning

An approach to analytic learning is described that searches for accurate entailments of a Horn Clause domain theory. A hill-climbing search, guided by an information based evaluation function, is performed by applying a set of operators that derive frontiers from domain theories. The analytic learning system is one component of a multi-strategy relational learning system. We compare the accuracy of concepts learned with this analytic strategy to concepts learned with an analytic strategy that operationalizes the domain theory.

Pazzani, Michael↗
NASA NTRS1998

NASA/DOD Aerospace Knowledge Diffusion Research Project. Paper 67: Maximizing the Results of Federally-Funded Research and Development Through Knowledge Management: A Strategic Imperative for Improving US Competitiveness

Federally-funded research and development (R&D) represents a significant annual investment (approximately $79 billion in fiscal year 1996) on the part of U.S. taxpayers. Based on the results of a 10-year study of knowledge diffusion in U.S. aerospace industry, the authors take the position that U.S. competitiveness will be enhanced if knowledge management strategies, employed within a capability-enhancing U.S. technology policy framework, are applied to diffusing the results of federally-funded R&D. In making their case, the authors stress the importance of knowledge as the source of competitive advantage in today's global economy. Next, they offer a practice-based definition of knowledge management and discuss three current approaches to knowledge management implementation-mechanistic, "the learning organization," and systemic. The authors then examine three weaknesses in existing U.S. public policy and policy implementation-the dominance of knowledge creation, the need for diffusion-oriented technology policy, and the prevalence of a dissemination model- that affect diffusion of the results of federally-funded R&D. To address these shortcomings, they propose the development of a knowledge management framework for diffusing the results of federally-funded R&D. The article closes with a discussion of some issues and challenges associated with implementing a knowledge management framework for diffusing the results of federally-funded R&D.

Pinelli, Thomas E.↗
NASA NTRS2011

Achieving Maximum Integration Utilizing Requirements Flow Down

A robust and experienced systems engineering team is essential for a successful program. It is often a challenge to build a core systems engineering team early enough in a program to maximize integration and assure a common path for all supporting teams in a project. Ares I was no exception. During the planning of IVGVT, the team had many challenges including lack of: early identification of stakeholders, team training in NASA s system engineering practices, solid requirements flow down and a top down documentation strategy. The IVGVT team started test planning early in the program before the systems engineering framework had been matured due to an aggressive schedule. Therefore the IVGVT team increased their involvement in the Constellation systems engineering effort. Program level requirements were established that flowed down to IVGVT aligning all stakeholders to a common set of goals. The IVGVT team utilized the APPEL REQ Development Management course providing the team a NASA focused model to follow. The IVGVT team engaged directly with the model verification and validation process to assure that a solid set of requirements drove the need for the test event. The IVGVT team looked at the initial planning state, analyzed the current state and then produced recommendations for the ideal future state of a wide range of systems engineering functions and processes. Based on this analysis, the IVGVT team was able to produce a set of lessons learned and to provide suggestions for future programs or tests to use in their initial planning phase.

Archiable, Wes↗