Reliability Prediction Using Bayesian Updating of On-Orbit Performance
No abstract available
Lindsey, nancy J.↗
SEARCH · Search NASA
Results for “Bayesian prediction”
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.
On Bayesian Inductive Inference & Predictive Estimation
We investigate Bayesian inference and the Principle of Maximum Entropy (PME) as methods for doing inference under uncertainty. This investigation is primarily through concrete examples that have been previously investigated in the literature. We find that it is possible to do Bayesian inference and PME inference using the same information, despite claims to the contrary, but that the results are not directly comparable. This is because Bayesian inference yields a probability density function (pdf) over the unknown model parameters, whereas PME yields point estimates. If mean estimates are extracted from the Bayesian pdfs, the resulting parameter estimates can differ radically from the PME values and also from the Maximum Likelihood values. We conclude that these differences are due to the Bayesian inference not assuming anything beyond the given prior probabilities and the data, whereas PME implicitly assumes that the given constraints are the only constraints that are operating. Since this assumption can be wrong, PME values may have to be revised when subsequent data shows evidence for more constraints. The entropy concentration previously "proved" by E. T. Jaynes is shown to be in error. Further, we show that PME is a generalized form of independence assumption, and so can be a very powerful method of inference when the variables being investigated are largely independent of each other.
Cheeseman, Peter↗
Methods for Probabilistic Uncertainty Analysis and Bayesian Analysis with Examples of Statistically Analyzing Data to Revise MMOD Risk Estimates and Compare Models
Probabilistic methods are presented for characterizing and quantifying uncertainties in models and model predictions. Techniques are given for constructing specific uncertainty distributions based on available information. Alternative techniques are given for propagating uncertainties in model inputs to obtain the uncertainty in the model result or prediction. Bayesian techniques are also described for utilizing data and information to update and revise model results and predictions. The focus is on applications with numerous specific examples given. The use of data to revise Micrometeoroid and Orbital Debris (MMOD) risk prediction models are among the examples given.
Risk↗
Bayesian Approach for Reliability Assessment of Sunshield Deployment on JWST
Deployable subsystems are essential to mission success of most spacecraft. These subsystems enable critical functions including power, communications and thermal control. The loss of any of these functions will generally result in loss of the mission. These subsystems and their components often consist of unique designs and applications, for which various standardized data sources are not applicable for estimating reliability and for assessing risks. In this study, a Bayesian approach for reliability estimation of spacecraft deployment was developed for this purpose. This approach was then applied to the James Webb Space Telescope (JWST) Sunshield subsystem, a unique design intended for thermal control of the observatory's telescope and science instruments. In order to collect the prior information on deployable systems, detailed studies of "heritage information", were conducted extending over 45 years of spacecraft launches. The NASA Goddard Space Flight Center (GSFC) Spacecraft Operational Anomaly and Reporting System (SOARS) data were then used to estimate the parameters of the conjugative beta prior distribution for anomaly and failure occurrence, as the most consistent set of available data and that could be matched to launch histories. This allows for an emperical Bayesian prediction for the risk of an anomaly occurrence of the complex Sunshield deployment, with credibility limits, using prior deployment data and test information.
Kaminskiy, Mark P.↗
Preliminary Design of an 'Autonomous Medical Response Agent' Interface Prototype for Long Duration Spaceflight
Major challenges for astronauts in future long-duration exploration missions (LDEMs) will be that crewmembers are not expected to be medical professionals, may be under high workload and stress, are facing physiological challenges caused by spaceflight, and will have limited, delayed voice communications with medical support from Earth. An autonomous medical response agent (AMRA) is envisioned to help astronauts address medical complaints, develop a differential diagnosis, and guide self-treatment until a healthy state is restored. AMRA develops a process of personalized diagnosis and treatment through a Bayesian predictive control system that recommends therapeutic control actions including diagnostic tests and treatments to crewmembers (Menon, 2020). The Human Computer Interaction (HCI) lab from NASA Ames Research Center’s Human Systems Integration Division (Code TH) has collaborated with Nahlia Inc in human-centered design augmentation research for AMRA. The project, titled Design of ‘Autonomous Medical Response Agent Interface Prototype for Long Duration Spaceflight, has been funded by the Translational Research Institute for Space Health (TRISH) and introduces an interactive user-interface prototype that guides astronauts through self-diagnosis, treatment, and rehabilitation while communicating with remote specialists in ground support (most notably a patient’s flight surgeon). Our project develops the interaction design for the crewmember using AMRA through user research, iterative design, and usability testing to evaluate the user interface and workflow designed. The interface design deliverable for this project, titled AMRA Aggregate Information Display (AMRA AID) is an integrated information display system for comprehensive autonomous medical guidance, diagnosis, and treatment of in-flight medical conditions experienced by crewmembers. AMRA AID demonstrates how we might ensure crew autonomy, increase the crew’s medical capabilities, and decrease cognitive burden within a front-end user interface. AMRA AID refrains from relying on input from ground or mission control for self-treatment of medical issues—though ground awareness and communication with ground is maintained as a means of ensuring trust between mission control and crew. AMRA AID demonstrates how the crew’s on-board medical system might integrate with information from vehicle monitoring and crew schedule, without assuming causal relationships. AMRA AID’s comprehensive view enables efficient information access for both crew and ground support, reducing cognitive burden in the event of an unplanned or emergency medical incident and enabling informed analytical decisions to be made based on both crew and vehicle health. Human-centered design augmentation advanced within the prototype included: enhanced workflow and treatment guidance for two medical scenarios for a non-specialist user base with various levels of medical training, interaction design which considered speech (conversational user interface) elements and on-screen interactions to be developed in future iterations of the project, communication design and functional requirements relevant to self-care versus caring for another astronaut, as well as user testing of the prototype with an international space medical community. This project arrives at critical findings regarding usability needs, communication requirements, and integrated information requirements for a future technology interface functioning to increase confidence between ground support and LDEM crewmembers.
TRISH↗
Continuous Habitable Zones: Pairing a GCM and Bayesian Framework to Predict Habitable Zone Evolution
In the near-future, new space telescopes like JWST, LUVOIR, and HabEx will begin attempting to explore the properties of atmospheres of potentially habitable planets. This will require a significant amount of time and resources for even a single planet, which makes it essential to prioritize observations by those most-likely to have detectable life. Here we present a statistical method to estimate the probabilities that specific exoplanets have been continuously in the habitable zone of their host stars for more than 2 billion years, the approximate time it took life on Earth to significantly increase the oxygen content of the atmosphere. We introduce the use of statistics of an ensemble of 3D planetary general circulation models to estimate these probabilities, replacing prior 1D model estimates.
habitable planets↗
Pairing a GCM and Bayesian Framework to Predict Habitable Zone Evolution
In the near-future, new space telescopes like JWST, LUVOIR, and HabEx will begin attempting to explore the properties of atmospheres of potentially habitable planets. This will require a significant amount of time and resources for even a single planet, which makes it essential to prioritize observations by those most-likely to have detectable life. Here we present a statistical method to estimate the probabilities that specific exoplanets have been continuously in the habitable zone of their host stars for more than 2 billion years, the approximate time it took life on Earth to significantly increase the oxygen content of the atmosphere. We introduce the use of statistics of an ensemble of 3D planetary general circulation models to estimate these probabilities, replacing prior 1D model estimates.
habitable planets↗
Predicting Software Suitability Using a Bayesian Belief Network
The ability to reliably predict the end quality of software under development presents a significant advantage for a development team. It provides an opportunity to address high risk components earlier in the development life cycle, when their impact is minimized. This research proposes a model that captures the evolution of the quality of a software product, and provides reliable forecasts of the end quality of the software being developed in terms of product suitability. Development team skill, software process maturity, and software problem complexity are hypothesized as driving factors of software product quality. The cause-effect relationships between these factors and the elements of software suitability are modeled using Bayesian Belief Networks, a machine learning method. This research presents a Bayesian Network for software quality, and the techniques used to quantify the factors that influence and represent software quality. The developed model is found to be effective in predicting the end product quality of small-scale software development efforts.
Beaver, Justin M.↗
Predicting extragalactic distance errors using Bayesian inference in multimeasurement catalogues
Explore the source record for details and available documents.
Germán Chaparro-Molano↗
The Extrapolation of Elementary Sequences
We study sequence extrapolation as a stream-learning problem. Input examples are a stream of data elements of the same type (integers, strings, etc.), and the problem is to construct a hypothesis that both explains the observed sequence of examples and extrapolates the rest of the stream. A primary objective -- and one that distinguishes this work from previous extrapolation algorithms -- is that the same algorithm be able to extrapolate sequences over a variety of different types, including integers, strings, and trees. We define a generous family of constructive data types, and define as our learning bias a stream language called elementary stream descriptions. We then give an algorithm that extrapolates elementary descriptions over constructive datatypes and prove that it learns correctly. For freely-generated types, we prove a polynomial time bound on descriptions of bounded complexity. An especially interesting feature of this work is the ability to provide quantitative measures of confidence in competing hypotheses, using a Bayesian model of prediction.
Laird, Philip↗
MOA-2007-BLG-400 A Super-Jupiter-mass Planet Orbiting a Galactic Bulge K-dwarf Revealed by Keck Adaptive Optics Imaging
We present Keck/NIRC2 adaptive optics imaging of planetary microlensing event MOA-2007-BLG-400 that resolves the lens star system from the source. We find that the MOA-2007-BLG-400L planetary system consists of a 1.71 ± 0.27M(sub Jup) planet orbiting a 0.69 ± 0.04M⨀ K-dwarf host star at a distance of 6.89 ± 0.77 kpc from the Sun. So, this planetary system probably resides in the Galactic bulge. The planet–host star projected separation is only weakly constrained due to the close-wide light-curve degeneracy; the 2σ projected separation ranges are 0.6–1.0 au and 4.7–7.7 au for close and wide solutions, respectively. This host mass is at the top end of the range of masses predicted by a standard Bayesian analysis. Our Keck follow-up program has now measured lens-source separations for six planetary microlensing events, and five of these six events have host star masses above the median prediction under the assumption that assumes that all stars have an equal chance of hosting planets detectable by microlensing. This suggests that more massive stars may be more likely to host planets of a fixed mass ratio that orbit near or beyond the snow line. These results also indicate the importance of host star mass measurements for exoplanets found by microlensing. The microlensing survey imaging data from NASA’s Nancy Grace Roman Space Telescope (formerly WFIRST) mission will be doing mass measurements like this for a huge number of planetary events.
Exoplanets↗
Advanced Statistical Methods in Spacecraft Flight Software Cost Estimation: Bayesian Regression and Nonlinear Principal Components Analysis to Support System Engineering in the Early Project Lifecycle
This paper provides an overview of the new features and model updates in the upcoming release of the NASA Analogy Software Cost Tool (ASCoT). ASCoT, hosted within the Online NASA Space Estimation Tools (ONSET) on the One NASA Cost Engineering (ONCE) Database, is a web-based tool that provides a suite of estimation tools to support early lifecycle NASA flight software cost analysis. In addition to the traditional parametric flight software costing method COCOMO II, ASCoT contains a Bayesian linear regression to predict total flight software development cost as a function of total spacecraft cost, as well as four analogic methods: k-Nearest Neighbors (kNN) and Clustering models to predict Effort (in work-months) and total source lines of code (SLOC). These methods are designed to work primarily with system-level inputs such as mission type (orbiter, lander, etc.), mission destination (Earth, Inner Planetary, etc.), and the number of instruments and deployables. Nonlinear principal components analysis (NLPCA) is performed to find the principal features of the data composed of both categorical and numerical variables and is necessary prior to defining our analogic methods. Sensitivity analyses and in- and out-of-sample model performance results are presented for the Bayesian CER and the analogic models.
Johnson, James K.↗
Generating Exploration Mission-3 Trajectories to a 9:2 NRHO using Machine Learning
The purpose of this thesis is to design a machine learning algorithm platform that provides expanded knowledge of mission availability through a launch season by improving trajectory resolution and introducing launch mission forecasting. The specific scenario addressed in this paper is one in which data is provided for four deterministic translational maneuvers through a mission to a Near Rectilinear Halo Orbit (NRHO) with a 9:2 synodic frequency. Current launch availability knowledge under NASA's Orion Orbit Performance Team is established by altering optimization variables associated to given reference launch epochs. This current method can bean abstract task and relies on an orbit analyst to structure a mission based on an established mission design methodology associated to the performance of Orion and NASA's Space Launch System. Introducing a machine learning algorithm trained to construct mission scenarios within the feasible range of known trajectories reduces the required interaction of the orbit analyst by removing the needed step of optimizing the orbit to fit an expected translational response required of the spacecraft. In this study, k-Nearest Neighbor and Bayesian Linear Regression successfully predicted classical orbital elements for the launch windows observed. However both algorithms had limitations due to their approaches to model fitting. Training machine learning algorithms off of classical orbital elements introduced a repetitive approach to reconstructing mission segments for different arrival opportunities through the launch window and can prove to be a viable method of launch window scan generation for future missions.
Guzman, Esteban↗
OGLE-2014-BLG-0962 and a Comparison of Galactic Model Priors to Microlensing Data
OGLE-2014-BLG-0962 (OB140962) is a stellar binary microlensing event that was well covered by observations from the Spitzer satellite as well as ground-based surveys. Modeling yields a unique physical solution: a mid-M+M-dwarf binary with M(prim) = 0.20 ± 0.01 M(☉) and M(sec) = 0.16 ± 0.01 M(☉), with projected separation of 2.0 ± 0.3 au. The lens is only D(LS) = 0.41 ± 0.06 kpc in front of the source, making OB140962 a bulge lens and the most distant Spitzer binary lens to date. In contrast, because the Einstein radius (θ(E) = 0.143 ± 0.007 mas) is unusually small, a standard Bayesian analysis, conducted in the absence of parallax information, would predict a brown dwarf binary. We compare the results of Bayesian analysis using two commonly used Galactic model priors to the measured values for a set of Spitzer lenses. We find all models tested predict lens properties consistent with the Spitzer data. Furthermore, we illustrate the methodology for probing the Galactic distribution of planets by comparing the cumulative distance distribution of the Spitzer two-body lenses to that of the Spitzer single lenses.
Yutong Shan↗
Predicting Time Series Outputs and Time-to-Failure for an Aircraft Controller Using Bayesian Modeling
Safety of unmanned aerial systems (UAS) is paramount, but the large number of dynamically changing controller parameters makes it hard to determine if the system is currently stable, and the time before loss of control if not. We propose a hierarchical statistical model using Treed Gaussian Processes to predict (i) whether a flight will be stable (success) or become unstable (failure), (ii) the time-to-failure if unstable, and (iii) time series outputs for flight variables. We first classify the current flight input into success or failure types, and then use separate models for each class to predict the time-to-failure and time series outputs. As different inputs may cause failures at different times, we have to model variable length output curves. We use a basis representation for curves and learn the mappings from input to basis coefficients. We demonstrate the effectiveness of our prediction methods on a NASA neuro-adaptive flight control system.
Statistics↗
Bayesian Deep Learning for Segmentation for Autonomous Safe Planetary Landing
Hazard detection is critical for enabling autonomous landing on planetary surfaces. Current state-of-the-art methods leverage traditional computer vision approaches to automate the identification of safe terrain from input digital elevation models (DEMs). However, performance for these methods can degrade for input DEMs with increased sensor noise. In the last decade, deep learning techniques have been developed for various applications. Nevertheless, their applicability to safety-critical space missions has often been limited due to concerns regarding their outputs’ reliability. In response to these limitations, this paper proposes an application of the Bayesian deep learning segmentation method for hazard detection. The developed approach enables reliable, safe landing site detection by i) generating simultaneously a safety prediction map and its uncertainty map via Bayesian deep learning and semantic segmentation, and ii) using the uncertainty map to filter out the uncertain pixels in the prediction map so that the safe site identification is performed only based on the certain pixels (i.e., pixels for which the model is certain about its safety prediction). Experiments are presented with simulated data based on a Mars HiRISE digital terrain model by varying uncertainty threshold and noise levels to demonstrate the performance of the proposed approach.
Kento Tomita↗
Using Bayesian Networks for Candidate Generation in Consistency-based Diagnosis
Consistency-based diagnosis relies heavily on the assumption that discrepancies between model predictions and sensor observations can be detected accurately. When sources of uncertainty like sensor noise and model abstraction exist robust schemes have to be designed to make a binary decision on whether predictions are consistent with observations. This risks the occurrence of false alarms and missed alarms when an erroneous decision is made. Moreover when multiple sensors (with differing sensing properties) are available the degree of match between predictions and observations can be used to guide the search for fault candidates. In this paper we propose a novel approach to handle this problem using Bayesian networks. In the consistency- based diagnosis formulation, automatically generated Bayesian networks are used to encode a probabilistic measure of fit between predictions and observations. A Bayesian network inference algorithm is used to compute most probable fault candidates.
Narasimhan, Sriram↗
Trending in Pc Measurements via a Bayesian Zero-Inflated Mixed Model
Two satellites predicted to come within close proximity of one another, usually a high-value satellite and a piece of space debris moving the active satellite is a means of reducing collision risk but reduces satellite lifetime, perturbs satellite mission, and introduces its own risks. So important to get a good statement of the risk of collision in order to determine whether a maneuver is truly necessary. Two aspects of this Calculation of the Probability of Collision (Pc) based on the most recent set of position velocity and uncertainty data for both satellites. Examination of the changes in the Pc value as the event develops. Events should follow a canonical development (Pc vs time to closest approach (TCA)). Helpful to be able to guess where the present data point fits in the canonical development in order to guide operational response.
Conjuction Assessment↗