Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Bayesian framework”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Operations for Learning with Graphical Models

This paper is a multidisciplinary review of empirical, statistical learning from a graphical model perspective. Well-known examples of graphical models include Bayesian net- works, directed graphs representing a Markov chain, and undirected networks representing a Markov field. These graphical models are extended to model data analysis and empirical learning using the notation of plates. Graphical operations for simplifying and manipulating a problem are provided including decomposition, differentiation, and the manipulation of probability models from the exponential family. These operations adapt existing techniques from statistics and automatic differentiation to graphs. Two standard algorithm schemes for learning are reviewed in a graphical framework: Gibbs sampling and the expectation maximization algorithm. Some algorithms are developed in this graphical framework including a generalized version of linear regression, techniques for feed-forward networks, and learning Gaussian and discrete Bayesian networks from data. The paper concludes by sketching some implications for data analysis and summarizing some popular algorithms that fall within the framework presented. The main original contributions here are the decomposition techniques and the demonstration that graphical models provide a framework for understanding and developing complex learning algorithms.

Buntine, Wray L.↗
NASA NTRS2016

Probabilistic Damage Characterization Using the Computationally-Efficient Bayesian Approach

This work presents a computationally-ecient approach for damage determination that quanti es uncertainty in the provided diagnosis. Given strain sensor data that are polluted with measurement errors, Bayesian inference is used to estimate the location, size, and orientation of damage. This approach uses Bayes' Theorem to combine any prior knowledge an analyst may have about the nature of the damage with information provided implicitly by the strain sensor data to form a posterior probability distribution over possible damage states. The unknown damage parameters are then estimated based on samples drawn numerically from this distribution using a Markov Chain Monte Carlo (MCMC) sampling algorithm. Several modi cations are made to the traditional Bayesian inference approach to provide signi cant computational speedup. First, an ecient surrogate model is constructed using sparse grid interpolation to replace a costly nite element model that must otherwise be evaluated for each sample drawn with MCMC. Next, the standard Bayesian posterior distribution is modi ed using a weighted likelihood formulation, which is shown to improve the convergence of the sampling process. Finally, a robust MCMC algorithm, Delayed Rejection Adaptive Metropolis (DRAM), is adopted to sample the probability distribution more eciently. Numerical examples demonstrate that the proposed framework e ectively provides damage estimates with uncertainty quanti cation and can yield orders of magnitude speedup over standard Bayesian approaches.

Warner, James E.↗
NASA NTRS1980

Failure detection system design methodology

The design of a failure detection and identification system consists of designing a robust residual generation process and a high performance decision making process. The design of these two processes are examined separately. Residual generation is based on analytical redundancy. Redundancy relations that are insensitive to modelling errors and noise effects are important for designing robust residual generation processes. The characterization of the concept of analytical redundancy in terms of a generalized parity space provides a framework in which a systematic approach to the determination of robust redundancy relations are developed. The Bayesian approach is adopted for the design of high performance decision processes. The FDI decision problem is formulated as a Bayes sequential decision problem. Since the optimal decision rule is incomputable, a methodology for designing suboptimal rules is proposed. A numerical algorithm is developed to facilitate the design and performance evaluation of suboptimal rules.

Chow, E. Y.↗
NASA NTRS2007

Uncertainty Management for Diagnostics and Prognostics of Batteries using Bayesian Techniques

Uncertainty management has always been the key hurdle faced by diagnostics and prognostics algorithms. A Bayesian treatment of this problem provides an elegant and theoretically sound approach to the modern Condition- Based Maintenance (CBM)/Prognostic Health Management (PHM) paradigm. The application of the Bayesian techniques to regression and classification in the form of Relevance Vector Machine (RVM), and to state estimation as in Particle Filters (PF), provides a powerful tool to integrate the diagnosis and prognosis of battery health. The RVM, which is a Bayesian treatment of the Support Vector Machine (SVM), is used for model identification, while the PF framework uses the learnt model, statistical estimates of noise and anticipated operational conditions to provide estimates of remaining useful life (RUL) in the form of a probability density function (PDF). This type of prognostics generates a significant value addition to the management of any operation involving electrical systems.

Saha, Bhaskar↗
NASA NTRS2023

Modelling the Greenland Ice Sheet's Committed Contribution to Sea Level During the 21st Century

Mass loss from the Greenland Ice Sheet can be partitioned between surface mass balance and discharge due to ice dynamics through its marine-terminating outlet glaciers. A perturbation to a glacier terminus (e.g., a calving event) results in both an instantaneous response in velocity and mass loss and a diffusive response due to the evolution of ice thickness over time. This diffusive response means the total impact of a retreat event can take decades to be fully realized. Here we model the committed response of the Greenland Ice Sheet by applying perturbations to the marine-terminating glacier termini that represent recent observed changes, and simulating the response over the 21st century, while holding the climate forcing constant. The sensitivity of the ice sheet response to model parameter uncertainty is explored within an ensemble framework, and Gravity Recovery and Climate Experiment data is used to constrain the results using a Bayesian calibration approach. We find that the Greenland Ice Sheet's committed contribution to 21st century sea level rise is at least 33.5 [17.5 52.4] mm (25th and 75th percentiles in brackets), with at least 6 mm being attributable directly to terminus retreat that occurred between 2007 and 2015. The spread in our projections is driven by uncertainty in the basal friction coefficient. Our results complement the ISMIP6 Greenland projections, which report the ice sheet response to future forcing, excluding the background response. In this way, we can obtain estimates of Greenland's total contribution to sea level rise in 2100.

Isabel J. Nias↗
NASA NTRS1995

Computer-Simulation Surrogates for Optimization: Application to Trapezoidal Ducts and Axisymmetric Bodies

Engineering design and optimization efforts using computational systems rapidly become resource intensive. The goal of the surrogate-based approach is to perform a complete optimization with limited resources. In this paper we present a Bayesian-validated approach that informs the designer as to how well the surrogate performs; in particular, our surrogate framework provides precise (albeit probabilistic) bounds on the errors incurred in the surrogate-for-simulation substitution. The theory and algorithms of our computer{simulation surrogate framework are first described. The utility of the framework is then demonstrated through two illustrative examples: maximization of the flowrate of fully developed ow in trapezoidal ducts; and design of an axisymmetric body that achieves a target Stokes drag.

Otto, John C.↗
NASA NTRS1994

Operations on Graphical Models with Plates

This paper explains how graphical models, for instance Bayesian or Markov networks, can be extended to model problems in data analysis and learning. This provides a unified framework that combines lessons learned from the artificial intelligence, statistical and connectionist communities. This also offers a set of principles for developing a software generator for data analysis, whereby a learning or discovery system can be compiled from specifications. Many of the popular learning algorithms can be compiled in this way from graphical specifications. While in a sense this paper is a multidisciplinary review of learning, the main contribution here is the presentation of the material within the unifying framework of graphical models, and the observation that, as a result, the process of developing learning algorithms can be partly automated.

Buntine, Wray L.↗
NASA NTRS2019

Health Management and Prognostics for Electric Aircraft Powertrain

W and c Any air borne vehicle needs incorporating safety as key parameter of measure, and inclusion of autonomy raises the critical need for safety under autonomous operations. Management of faults and component degradation is key as complexity in autonomous operations grow over the period of time. Therefore, in addition to basic operational requirements, an autonomous electric vehicle should be able to make accurate estimates of its current system health and take the correct decisions to complete its mission successfully. Real-time safety and state-awareness tools are therefore essential for the vehicle to be able to reach its destination in a safe and successful manner. The need for safety assurance and health management capabilities is particularly relevant for aircraft electric propulsion systems, which are relatively new and with limited historical to learn. They are critical systems requiring high power density along with reliability, resilience, efficient management of weight, and operational costs. A model- based fault diagnosis and prognostics approach of complex critical systems can successfully accomplish the safety and state awareness goal for such electric propulsion systems, enabling autonomous decision making capability for safe and efficient operation. To identify critical components in the system a Qualitative Bayesian approach using FMECA is implemented. This requires the assessment of some quantities representing the state of the electric unmanned aerial systems (e-UAS), as well as look-ahead forecasts of such states during the entire flight, presented in form of safety metrics (SM). In-service data and performance data gathered from degraded components sup- ports diagnostic and prognostic methods for these systems, but this data can be difficult to obtain as weight and packaging restrictions reduce redundancy and instrumentation on-board the vehicle. Therefore, an model-based framework should be capable or operating with limited data. In addition to data scarcity, the variability of such complex critical systems re- quires the model-based framework to reason in the presence of uncertainty, such as sensor noise, and modeling imperfections. Quantification of errors and uncertainties in the measured states and quantities is therefore a fundamental step for a precise estimation of such SMs; un-modeled uncertainty may result in erroneous state assessment and un- reliable predictions of future states of e-UAVs. Typical, centralized model-based schemes suffer from inherent disadvantages such as computational complexity, single point of failure, and scalability issues, and therefore may fail in such a complex scenario. This paper presents a methodology for developing a system level diagnostics and prognostics approach using a Qualitative Bayesian FMECA approach along with a formal uncertainty management framework for an e-UAS. In this work we demonstrate the efficacy of the framework to predict effects of sub-system level degradation on vehicle operation incorporating uncertainty management to predict future behavior under different operating conditions.

Kulkarni, Chetan↗
NASA NTRS2005

Intelligent Vehicle Health Management

As a part of the overall goal of developing Integrated Vehicle Health Management systems for aerospace vehicles, the NASA Faculty Fellowship Program (NFFP) at Marshall Space Flight Center has performed a pilot study on IVHM principals which integrates researched IVHM technologies in support of Integrated Intelligent Vehicle Management (IIVM). IVHM is the process of assessing, preserving, and restoring system functionality across flight and ground systems (NASA NGLT 2004). The framework presented in this paper integrates advanced computational techniques with sensor and communication technologies for spacecraft that can generate responses through detection, diagnosis, reasoning, and adapt to system faults in support of INM. These real-time responses allow the IIVM to modify the affected vehicle subsystem(s) prior to a catastrophic event. Furthermore, the objective of this pilot program is to develop and integrate technologies which can provide a continuous, intelligent, and adaptive health state of a vehicle and use this information to improve safety and reduce costs of operations. Recent investments in avionics, health management, and controls have been directed towards IIVM. As this concept has matured, it has become clear the INM requires the same sensors and processing capabilities as the real-time avionics functions to support diagnosis of subsystem problems. New sensors have been proposed, in addition, to augment the avionics sensors to support better system monitoring and diagnostics. As the designs have been considered, a synergy has been realized where the real-time avionics can utilize sensors proposed for diagnostics and prognostics to make better real-time decisions in response to detected failures. IIVM provides for a single system allowing modularity of functions and hardware across the vehicle. The framework that supports IIVM consists of 11 major on-board functions necessary to fully manage a space vehicle maintaining crew safety and mission objectives: Guidance and Navigation; Communications and Tracking; Vehicle Monitoring; Information Transport and Integration; Vehicle Diagnostics; Vehicle Prognostics; Vehicle mission Planning; Automated Repair and Replacement; Vehicle Control; Human Computer Interface; and Onboard Verification and Validation. Furthermore, the presented framework provides complete vehicle management which not only allows for increased crew safety and mission success through new intelligence capabilities, but also yields a mechanism for more efficient vehicle operations. The representative IVHM technologies for computer platform using heterogeneous communication, 3) coupled electromagnetic oscillators for enhanced communications, 4) Linux-based real-time systems, 5) genetic algorithms, 6) Bayesian Networks, 7) evolutionary algorithms, 8) dynamic systems control modeling, and 9) advanced sensing capabilities. This paper presents IVHM technologies developed under NASA's NFFP pilot project and the integration of these technologies forms the framework for IIVM.

Paris, Deidre E.↗
NASA NTRS2017

Real-Time Risk Assessment Framework for Unmanned Aircraft System (UAS) Traffic Management (UTM)

The new Federal Aviation Administration (FAA) Small Unmanned Aircraft rule (Part 107) marks the first national regulations for commercial operation of small unmanned aircraft systems (sUAS) under 55 pounds within the National Airspace System (NAS). Although sUAS flights may not be performed beyond visual line-of-sight or over non- participant structures and people, safety of sUAS operations must still be maintained and tracked at all times. Moreover, future safety-critical operation of sUAS (e.g., for package delivery) are already being conceived and tested. NASA's Unmanned Aircraft System Trac Management (UTM) concept aims to facilitate the safe use of low-altitude airspace for sUAS operations. This paper introduces the UTM Risk Assessment Framework (URAF) which was developed to provide real-time safety evaluation and tracking capability within the UTM concept. The URAF uses Bayesian Belief Networks (BBNs) to propagate off -nominal condition probabilities based on real-time component failure indicators. This information is then used to assess the risk to people on the ground by calculating the potential impact area and the effects of the impact. The visual representation of the expected area of impact and the nominal risk level can assist operators and controllers with dynamic trajectory planning and execution. The URAF was applied to a case study to illustrate the concept.

Ancel, Ersin↗
NASA NTRS2021

Systems Engineering and Assurance Modeling (SEAM): A Web-Based Solution for Integrated Mission Assurance

We present an overview of the Systems Engineering and Assurance Modeling (SEAM) platform, a web-browser-based tool which is designed to help engineers evaluate the radiation vulnerabilities and develop an assurance approach for electronic parts in space systems. The SEAM framework consists of three interconnected modeling tools, a SysML compatible system description tool, a Goal Structuring Notation (GSN) visual argument tool, and Bayesian Net and Fault Tree extraction and export tools. The SysML and GSN sections also have a coverage check application that ensures that every radiation fault identified on the SysML side is also addressed in the assurance case in GSN. The SEAM platform works on space systems of any degree of radiation hardness but is especially helpful for assessing radiation performance in systems with commercial-off-the-shelf (COTS) electronic components.

SEAM↗
NASA NTRS2008

Joint Bayesian Component Separation and CMB Power Spectrum Estimation

We describe and implement an exact, flexible, and computationally efficient algorithm for joint component separation and CMB power spectrum estimation, building on a Gibbs sampling framework. Two essential new features are (1) conditional sampling of foreground spectral parameters and (2) joint sampling of all amplitude-type degrees of freedom (e.g., CMB, foreground pixel amplitudes, and global template amplitudes) given spectral parameters. Given a parametric model of the foreground signals, we estimate efficiently and accurately the exact joint foreground- CMB posterior distribution and, therefore, all marginal distributions such as the CMB power spectrum or foreground spectral index posteriors. The main limitation of the current implementation is the requirement of identical beam responses at all frequencies, which restricts the analysis to the lowest resolution of a given experiment. We outline a future generalization to multiresolution observations. To verify the method, we analyze simple models and compare the results to analytical predictions. We then analyze a realistic simulation with properties similar to the 3 yr WMAP data, downgraded to a common resolution of 3 deg FWHM. The results from the actual 3 yr WMAP temperature analysis are presented in a companion Letter.

numerical↗
NASA NTRS2005

A Framework for Integration of IVHM Technologies for Intelligent Integration for Vehicle Management

As a part of the overall goal of developing Integrated Vehicle Health Management (IVHM) systems for aerospace vehicles, the NASA Faculty Fellowship Program (NFFP) at Marshall Space Flight Center has performed a pilot study on IVHM principals which integrates researched IVHM technologies in support of Integrated Intelligent Vehicle Management (IIVM). IVHM is the process of assessing, preserving, and restoring system functionality across flight and ground systems (NASA NGLT 2004). The framework presented in this paper integrates advanced computational techniques with sensor and communication technologies for spacecraft that can generate responses through detection, diagnosis, reasoning, and adapt to system faults in support of IIVM. These real-time responses allow the IIVM to modify the effected vehicle subsystem(s) prior to a catastrophic event. Furthermore, the objective of this pilot program is to develop and integrate technologies which can provide a continuous, intelligent, and adaptive health state of a vehicle and use this information to improve safety and reduce costs of operations. Recent investments in avionics, health management, and controls have been directed towards IIVM. As this concept has matured, it has become clear the IIVM requires the same sensors and processing capabilities as the real-time avionics functions to support diagnosis of subsystem problems. New sensors have been proposed, in addition, to augment the avionics sensors to support better system monitoring and diagnostics. As the designs have been considered, a synergy has been realized where the real-time avionics can utilize sensors proposed for diagnostics and prognostics to make better real-time decisions in response to detected failures. IIVM provides for a single system allowing modularity of functions and hardware across the vehicle. The framework that supports IIVM consists of 11 major on-board functions necessary to fully manage a space vehicle maintaining crew safety and mission objectives: Guidance and Navigation; Communications and Tracking; Vehicle Monitoring; Information Transport and Integration; Vehicle Diagnostics; Vehicle Prognostics; Vehicle mission Planning; Automated Repair and Replacement; Vehicle Control; Human Computer Interface; and Onboard Verification and Validation. Furthermore, the presented framework provides complete vehicle management which not only allows for increased crew safety and mission success through new intelligence capabilities, but also yields a mechanism for more efficient vehicle operations. The representative IVHM technologies for IIVH includes: 1) robust controllers for use in re-usable launch vehicles, 2) scaleable/flexible computer platform using heterogeneous communication, 3) coupled electromagnetic oscillators for enhanced communications, 4) Linux-based real-time systems, 5) genetic algorithms, 6) Bayesian Networks, 7) evolutionary algorithms, 8) dynamic systems control modeling, and 9) advanced sensing capabilities. This paper presents IVHM technologies developed under NASA's NFFP pilot project. The integration of these IVHM technologies forms the framework for IIVM.

Paris, Deidre E.↗
NASA NTRS2018

A Singular Value Decomposition Framework for Retrievals with Vertical Distribution Information from Greenhouse Gas Column Absorption Spectroscopy Measurements

We review the singular value decomposition (SVD) framework and use it for quantifying and discerning vertical information in greenhouse gas retrievals from column integrated absorption measurements. While the commonly used traditional Bayesian optimal estimation (OE) assumes a prior distribution in order to regularize the inversion problem, the SVD approach identifies principal components that can be retrieved from the measurement without explicitly specifying a prior mean and prior covariance matrix. We review the SVD method, explicitly recognize the use of an uninformative prior and show it to incur no bias from the choice of the prior. We also make the connection between the SVD method and the pseudo-inverse, which makes it more intuitive and easy to understand. We illustrate the use of the SVD method on an integrated path differential absorption CO2 lidar measurement model and verify our derivations and bias-free properties versus optimal estimation using numerical simulations. In contrast, traditional OE retrievals exhibit bias when the prior mean used in the retrieval differs from the true mean. Hence, the SVD method is particularly useful for situations in which knowledge of the prior mean and prior covariance of the true state (e.g., greenhouse gas profiles) is inadequate.

Ramanathan, Anand K.↗
NASA NTRSDate not supplied

Setting the Bar for the Replacement of the Probability of Collision Metric

To date, satellite conjunction assessment (CA) risk analysis has largely embraced the probability of collision (Pc) as the omnibus metric to evaluate collision likelihood, and its use in such assessments has mostly been straightforward: at the point at which a conjunction mitigation decision is required, the calculated Pc is compared to a threshold; and if the calculated Pc exceeds that threshold, then a mitigation action is warranted. With only minor variation, this approach is employed by major CA risk assessment centers (e.g., NASA, EUSST, CNES, JAXA) and is advanced as the preferred method in the published CA best practices handbooks. Despite this near unanimity of operational practice, there is a major strain of secondary literature critical of the Pc and willing to propose alternatives. Alfano (2005) pointed out the ability of the Pc to underrepresent the risk in certain situations and counselled a maximum Pc construct. Carpenter (2017, 2019) reiterated this criticism and proposed using instead a confidence interval on the miss distance. Balch et al. (2019) identified what they argued was a defect in the entire Bayesian Pc construct and believed that the use of a more conservative methodology based on covariance ellipsoid overlap was necessary. Delande (2022) introduced the framework of collision “plausibility” to the risk assessment process and sketched out how this might be used operationally. Elkantassi (2022) published a full development of the miss distance confidence interval approach and applied it to several worked examples. While these different approaches to collision risk assessment do differ in their details, they all converge on two central points: first, the Pc’s failure to give an adequate expression of the risk in dilution region situations is a fatal flaw; and second, a conjunction should be presumed risky and in need of mitigation until the evidence of the situation can establish otherwise. These criticisms, if correct, would counsel a number of modifications to current CA operational practice; as such, they force a re-examination of fundamental aspects of the CA problem, including the following: 1. Is the CA risk assessment a probability problem, a statistics problem, or something else? 2. If it is a statistics problem, does it lend itself naturally to a hypothesis test construction? 3. If it can be construed as a hypothesis test, what form should the null hypothesis take, to wit: what constraints exist on the choice of the null hypothesis, what selections are in best alignment with all of the attendant parameters of the problem, and what is implied philosophically by different choices? 4. What are the implications of using the different proposed risk assessment parameters for CA? This question should be answered both in determining how frequently the dilution region situation cited by the critics of the Pc actually appears in an operationally significant manner and the missed detection and false alarm rates of all of the proposed risk assessment metrics, compared both to the Pc and to each other. This paper explores and offers preliminary answers to the above questions, presenting a researched treatment of the philosophical nature of the CA problem and the null hypothesis choice that achieves the greatest consistency with all of the different aspects of operational CA conduct. It then profiles all of the different proposed risk assessment metrics enumerated in the earlier paragraph against an extremely large database of conjunction events at both the 550km and 700km altitudes. The combination of the philosophical exploration of the CA problem and the results of the profiling activity articulates what a risk assessment metric will need to demonstrate, in terms of both innate construction and performance, in order to be a true competitor to the Pc.

conjunction assessment↗
NASA NTRS1994

Learning time series for intelligent monitoring

We address the problem of classifying time series according to their morphological features in the time domain. In a supervised machine-learning framework, we induce a classification procedure from a set of preclassified examples. For each class, we infer a model that captures its morphological features using Bayesian model induction and the minimum message length approach to assign priors. In the performance task, we classify a time series in one of the learned classes when there is enough evidence to support that decision. Time series with sufficiently novel features, belonging to classes not present in the training set, are recognized as such. We report results from experiments in a monitoring domain of interest to NASA.

Manganaris, Stefanos↗
NASA NTRS2010

A Model-Based Probabilistic Inversion Framework for Wire Fault Detection Using TDR

Time-domain reflectometry (TDR) is one of the standard methods for diagnosing faults in electrical wiring and interconnect systems, with a long-standing history focused mainly on hardware development of both high-fidelity systems for laboratory use and portable hand-held devices for field deployment. While these devices can easily assess distance to hard faults such as sustained opens or shorts, their ability to assess subtle but important degradation such as chafing remains an open question. This paper presents a unified framework for TDR-based chafing fault detection in lossy coaxial cables by combining an S-parameter based forward modeling approach with a probabilistic (Bayesian) inference algorithm. Results are presented for the estimation of nominal and faulty cable parameters from laboratory data.

Schuet, Stefan R.↗
NASA NTRS1996

A Surrogate Approach to the Experimental Optimization of Multielement Airfoils

The incorporation of experimental test data into the optimization process is accomplished through the use of Bayesian-validated surrogates. In the surrogate approach, a surrogate for the experiment (e.g., a response surface) serves in the optimization process. The validation step of the framework provides a qualitative assessment of the surrogate quality, and bounds the surrogate-for-experiment error on designs "near" surrogate-predicted optimal designs. The utility of the framework is demonstrated through its application to the experimental selection of the trailing edge ap position to achieve a design lift coefficient for a three-element airfoil.

Otto, John C.↗