Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model Inference”

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 1,747 records · Page 97
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Bayesian Poroelastic Aquifer Characterization From InSAR Surface Deformation Data. 2. Quantifying the Uncertainty

Uncertainty quantification of groundwater (GW) aquifer parameters is critical for efficient management and sustainable extraction of GW resources. These uncertainties are introduced by the data, model, and prior information on the parameters. We develop a Bayesian inversion framework that uses Interferometric Synthetic Aperture Radar (InSAR) surface deformation data to infer the laterally heterogeneous permeability of a transient linear poroelastic model of a confined GW aquifer. The Bayesian solution of this inverse problem takes the form of a posterior probability density of the permeability. Exploring this posterior using classical Markov chain Monte Carlo (MCMC) methods is computationally prohibitive due to the large dimension of the discretized permeability field and the expense of solving the poroelastic forward problem. However, in many partial differential equation (PDE)-based Bayesian inversion problems, the data are only informative in a few directions in parameter space. For the poroelasticity problem, we prove this property theoretically for a one-dimensional problem and demonstrate it numerically for a three-dimensional aquifer model. Here we design a generalized preconditioned Crank-Nicolson (gpCN) MCMC method that exploits this intrinsic low dimensionality by using a low-rank-based Laplace approximation of the posterior as a proposal, which we build scalably. The feasibility of our approach is demonstrated through a real GW aquifer test in Nevada. The inherently two-dimensional nature of InSAR surface deformation data informs a sufficient number of modes of the permeability field to allow detection of major structures within the aquifer, significantly reducing the uncertainty in the pressure and the displacement quantities of interest.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Solar Modeling and Opacities

In 2004, improved analyses of solar spectra resulted in a downward revision of the abundances of elements heavier than hydrogen and helium, in particular, the elements C, N, and O. Solar models evolved using these lower abundances showed discrepancies with inferences from solar oscillation observations (helioseismology). This problem has not been solved satisfactorily in the intervening 16 years. How serious/important is this problem? This talk will give an overview of how standard solar models are calculated and of the constraints from helioseismology. The talk will also present results of some attempts to change input physics or assumptions in the standard solar model, including opacity modifications, to try to resolve the discrepancies. I would like to have a discussion with the participants after the talk about which directions appear most promising to resolve the problem.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

The primordial matter power spectrum on sub-galactic scales

The primordial matter power spectrum quantifies fluctuations in the distribution of dark matter immediately following inflation. Over cosmic time, overdense regions of the primordial density field grow and collapse into dark matter haloes, whose abundance and density profiles retain memory of the initial conditions. By analysing the image magnifications in 11 strongly lensed and quadruply imaged quasars, we infer the abundance and concentrations of low-mass haloes, and cast the measurement in terms of the amplitude of the primordial matter power spectrum. We anchor the power spectrum on large scales, isolating the effect of small-scale deviations from the Lambda cold dark matter (ΛCDM) prediction. Assuming an analytic model for the power spectrum and accounting for several sources of potential systematic uncertainty, including three different models for the halo mass function, we obtain correlated inferences of $\log _{10}\left(P / P_{\Lambda \rm {CDM}}\right)$, the power spectrum amplitude relative to the predictions of the concordance cosmological model, of $0.0_{-0.4}^{+0.5}$, $0.1_{-0.6}^{+0.7}$, and $0.2_{-0.9}^{+1.0}$ at k = 10, 25, and 50 $\rm {Mpc^{-1}}$ at $68 {{\ \rm per\ cent}}$ confidence, consistent with CDM and single-field slow-roll inflation.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRSDate not supplied

Use of Design of Experiments and Rule-Based Inference in Determining Neural Network Architectures for Loss of Control Detection

In this work, we describe methods for selecting the neural network architectures and input spaces to implement belief state inference on generic commercial transport aircraft. First, we highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). We present a structured method that can be used in a number of aerospace applications, to optimize the structure and training parameters of the CVAE for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from a NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications. While theoretically, we could create a single CVAE with an input space the size of all measurable flight variables and environmental dynamics, it becomes intractable to use such a neural network in an in-situ intelligent multi-agent system. Using the recommendations from our case study, we introduce a technical approach for feasibly describing the belief space by (1) identifying significant statistical relationships among flight variables using rule induction, (2) using a set of rules that cover all features to define the input space of multiple CVAEs, and (3) forming a belief space based on the joint probability density of their collective latent spaces. This results in a series of relatively small matrix multiplications that can be performed in real time, as opposed to large matrix computations in a single CVAE. We demonstrate the application of this approach on the T-2 flight loss-of control experiments, using the architecture and hyperparameter recommendations from the case study. We compare the utilities of an individual CVAE trained on all flight variables and multiple CVAEs defined on subsets of flight variables for detecting qualitative changes in flight. We demonstrate that the use of multiple CVAEs with smaller input spaces permits the CVAE to capture more granular relationships in the latent space, permitting better state space characterization and loss-of-control detection.

Design of experiments↗
NASA NTRSDate not supplied

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

Loss of Control↗
NASA NTRSDate not supplied

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T 2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

Loss of Control↗
NASA NTRSDate not supplied

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

Abstract—We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

neural networks↗
NASA NTRSDate not supplied

Sensitivity of Simulated Radiative Emission from Nitrogen Flows to Chemical Parameters

Numerical models of hypersonic flows rely on chemistry data inferred from experiments and quantum calculations. Experiments from NASA's Electric Arc Shock Tube (EAST) measure the spectral emission of strong shocks in pure nitrogen flows. These spectral profiles are only approximately captured by numerical simulations. To address these discrepancies, one wishes to calibrate some of the chemical parameters to better match experiment. Because there are hundreds of parameters in the numerical model, a sensitivity analysis was carried out on the entire chemistry database to determine which parameters are most important to analyze in the future. In order to perform this work it was necessary to generate a consistent chemical database that interfaced with both the CFD and line-by-line radiation solver. Using Monte Carlo methods, the total Sobol index was calculated for important parameters. Twenty parameters were identified as important across the nitrogen system. However, it was noted that in some spectral regions, the parametric uncertainty was unable to bound EAST measurements. Further improvements could be made by increasing the parameter uncertainties or addressing other sources of modeling error.

Kaelan B Hansson↗
NASA NTRSDate not supplied

Sensitivity of Simulated Radiative Emission from Nitrogen Flows to Chemical Parameters

Numerical models of hypersonic flows rely on chemistry data inferred from experiments and quantum calculations. Experiments from NASA's Electric Arc Shock Tube (EAST) measure the spectral emission of strong shocks in pure nitrogen flows. These spectral profiles are only approximately captured by numerical simulations. To address these discrepancies, one wishes to calibrate some of the chemical parameters to better match experiment. Because there are hundreds of parameters in the numerical model, a sensitivity analysis was carried out on the entire chemistry database to determine which parameters are most important to analyze in the future. In order to perform this work it was necessary to generate a consistent chemical database that interfaced with both the CFD and line-by-line radiation solver. Using Monte Carlo methods, the total Sobol index was calculated for important parameters. Twenty parameters were identified as important across the nitrogen system. However, it was noted that in some spectral regions, the parametric uncertainty was unable to bound EAST measurements. Further improvements could be made by increasing the parameter uncertainties or addressing other sources of modeling error.

Kaelan Hansson↗
DOE OSTI2021

DETECTING FIRE WITH MACHINE LEARNING-ENABLED VISUAL MONITORING FOR NUCLEAR POWER PLANT ENVIRONMENTS

Nuclear power plants are experiencing significant cost challenges to remain competitive with other energy-generation utilities. Unlike other industries, the cost of operation and maintenance activities is mostly attributed to workforce costs. To mitigate this, nuclear power plant stakeholders are increasingly interested in the development and deployment of machine learning methods to potentially automate or augment manually intensive tasks to reduce costs, especially for monitoring activities. One monitoring function that is visually demanding and that can occur frequently to meet the requirements of a fire protection program is visually monitoring an area for fire occurrence. Currently, fire watch activities consist of a worker physically stationed at a given location with the sole responsibility of observing a given area to ensure a fire is detected and mitigated promptly. This effort focused on the development and evaluation of a suitable deep convolutional neural network to classify individual video frames at a sub-second frequency for the occurrence of “fire” and “no fire” in varying industrial environments similar to nuclear power plants. It is believed that a trained neural network model could be integrated with existing facility video surveillance camera feeds to generate alerts when fire inferences occur in individual frames captured at sub-second temporal resolutions. Extensive effort was dedicated to identifying and curating suitable imagery training data representing varying environments and scene settings with and without flame features to maximize generalization in nuclear power plant environments. The data collection effort resulted in the aggregation of a large, labeled image library exceeding 12,000 images to support model training for diverse industrial environments. A deep neural network model incorporating parallel multi-scale capabilities was developed and trained to support accurate image-based detection of flame incidents of varying sizes and spectral feature properties within heterogeneous scenes. Analysis results show that the trained model can achieve high inference accuracy despite heterogeneous scene environments and components. Testing accuracy exceeded 95.0 percent with very low false positive and false negative inferences.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1974

Reflection of a thick planar shock wave from a coplanar surface

The reflection of a thick shock wave from an adsorbing surface has been studied for argon and neon test gases using the direct simulation Monte Carlo method and laboratory shock-tube experiments. In the simulation, collisions between gas atoms were calculated with a point-center repulsive intermolecular potential, and collisions between gas atoms and the surface were described by a simple two-parameter model which includes the effects of adsorption and thermal accommodation. Experimental data included normal stress and temperature time histories on the surface of a shock-tube and wall. These data and published data of density variations near the end wall were compared with simulation results to assess the influence of adsorption and accommodation on the flowfield and the surface and also to infer optimum values for the surface-interaction model parameters. Good quantitative agreement between simulation and laboratory data was found with this simple surface-interaction model.

Deiwert, G. S.↗
NASA NTRS2010

Physics-Based Methods of Failure Analysis and Diagnostics in Human Space Flight

The Integrated Health Management (IHM) for the future aerospace systems requires to interface models of multiple subsystems in an efficient and accurate information environment at the earlier stages of system design. The complexity of modern aeronautic and aircraft systems (including e.g. the power distribution, flight control, solid and liquid motors) dictates employment of hybrid models and high-level reasoners for analysing mixed continuous and discrete information flow involving multiple modes of operation in uncertain environments, unknown state variables, heterogeneous software and hardware components. To provide the information link between key design/performance parameters and high-level reasoners we rely on development of multi-physics performance models, distributed sensors networks, and fault diagnostic and prognostic (FD&P) technologies in close collaboration with system designers. The main challenges of our research are related to the in-flight assessment of the structural stability, engine performance, and trajectory control. The main goal is to develop an intelligent IHM that not only enhances components and system reliability, but also provides a post-flight feedback helping to optimize design of the next generation of aerospace systems. Our efforts are concentrated on several directions of the research. One of the key components of our strategy is an innovative approach to the diagnostics/prognostics based on the real time dynamical inference (DI) technologies extended to encompass hybrid systems with hidden state trajectories. The major investments are into the multiphysics performance modelling that provides an access of the FD&P technologies to the main performance parameters of e.g. solid and liquid rocket motors and composite materials of the nozzle and case. Some of the recent results of our research are discussed in this chapter. We begin by introducing the problem of dynamical inference of stochastic nonlinear models and reviewing earlier results. Next, we present our analytical approach to the solution of this problem based on the path integral formulation. The resulting algorithm does not require an extensive global search for the model parameters, provides optimal compensation for the effects of dynamical noise, and is robust for a broad range of dynamical models. In the following Section the strengths of the algorithm are illustrated illustrated by inferring the parameters of the stochastic Lorenz system and comparing the results with those of earlier research. Next, we discuss a number of recent results in application to the development of the IHM for aerospace system. Firstly, we apply dynamical inference approach to a solution of classical three tank problems with mixed unknown continuous and binary parameters. The problem is considered in the context of ground support system for filling fuel tanks of liquid rocket motors. It is shown that the DI algorithm is well suited for successful solution of a hybrid version of this benchmark problem even in the presence of additional periodic and stochastic perturbation of unknown strength. Secondly, we illustrate our approach by its application to an analysis of the nozzle fault in a solid rocket motor (SRM). The internal ballistics of the SRM is modelled as a set of one-dimensional partial differential equations coupled to the dynamics of the propellant regression. In this example we are specifically focussed on the inference of discrete and continuous parameters of the nozzle blocking fault and on the possibility of an application of the DI algorithm to reducing the probability of "misses" of an on-board FD&P for SRM. In the next section re-contact problem caused by first stage/upper stage separation failure is discussed. The reaction forces imposed on the nozzle of the upper stage during the re-contact and their connection to the nozzle damage and to the thrust vector control (TVC) signal are obtained. It is shown that transient impact induced torquean be modelled as a response of an effective damped oscillator. A possible application of the DI algorithm to the inference of damage parameters and predicting fault dynamics ahead of time using the actuator signal is discussed. Finally, we formulate Bayesian inferential framework for development of the IHM system for in-flight structural health monitoring (SHM) of composite materials. We consider the signal generated by piezoelectric actuator mounted on composite structure generating elastic waves in it. The signal received by the sensor is than compared with the baseline signal. The possibility of damage inference is discussed in the context of development of the SHM.

Smelyanskiy, Vadim N.↗
DOE OSTI2017

Masses and Ages for 230,000 LAMOST Giants, via Their Carbon and Nitrogen Abundances

We measure carbon and nitrogen abundances to a precision of ≲0.1 dex for 450,000 giant stars from their low-resolution (R∼1800) LAMOST DR2 survey spectra. We use these [C/M] and [N/M] measurements, together with empirical relations based on the APOKASC sample, to infer stellar masses and implied ages for 230,000 of these objects to 0.08 dex and 0.2 dex respectively. We use The Cannon, a data-driven approach to spectral modeling, to construct a predictive model for LAMOST spectra. Our reference set comprises 8125 stars observed in common between the APOGEE and LAMOST surveys, taking seven APOGEE DR12 labels (parameters) as ground truth: T{sub eff}, log g, [M/H], [α/M], [C/M], [N/M], and A{sub k}. We add seven colors to the Cannon model, based on the g, r, i, J, H, K, W1, W2 magnitudes from APASS, 2MASS, and WISE, which improves our constraints on T{sub eff} and log g by up to 20% and on A{sub k} by up to 70%. Cross-validation of the model demonstrates that, for high-S/N objects, our inferred labels agree with the APOGEE values to within 50 K in temperature, 0.04 mag in A{sub k}, and <0.1 dex in log g, [M/H], [C/M], [N/M], and [α/M]. We apply the model to 450,000 giants in LAMOST DR2 that have not been observed by APOGEE. This demonstrates that precise individual abundances can be measured from low-resolution spectra and represents the largest catalog to date of homogeneous stellar [C/M], [N/M], masses, and ages. As a result, we greatly increase the number and sky coverage of stars with mass and age estimates.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1983

The structure and emission spectrum of a nonradiative shock wave in the Cygnus Loop

The ultraviolet spectrum of a Balmer-line filament located just outside the main body of optical filaments in the Cygnus Loop confirms the nonradiative shock wave theory for its origin. This theory is extended to include the hydrogen two-photon continuum, and the possibility of slow electron-ion equilibration in the postshock gas is considered. The shock velocity is inferred from the H-alpha profile. Comparison of model calculations with optical and ultraviolet spectra favors Coulomb equilibration behind a 170 km/s shock over models with rapid equilibration due to plasma turbulence. Elemental abundances in the preshock gas are found to be typical of diffuse interstellar clouds. The ram pressure behind the shock is higher than the pressures inferred for bright optical filaments. It is suggested that the bright optical filaments are regions of thermally unstable cooling behind shocks faster than the shock velocities inferred from their optical and ultraviolet spectra.

Raymond, J. C.↗
NASA NTRS1980

Research in interactive scene analysis

The recovery of information about the three dimensional structure and physical characteristics of surfaces depicted in an image was studied focusing on two complementary problems: (1) basic techniques for inferring three dimensional surface shape from two dimensional images and (2) means for integrating the results of different techniques to obtain a globally consistent surface description. A technique was developed for constraining surface orientation along image contours that correspond to surface boundaries. A means for interpolating surface orientation estimates from a variety of sources into smooth surfaces--a major integration problem--was also developed. A computational model, based on these techniques, was proposed for inferring the three dimensional surface structure depicted in a line drawing.

Tenenbaum, J. M.↗
DOE OSTI2014

THE BINARITY OF MILKY WAY F,G,K STARS AS A FUNCTION OF EFFECTIVE TEMPERATURE AND METALLICITY

We estimate the fraction of F,G,K stars with close binary companions by analysing multi-epoch stellar spectra from the Sloan Digital Sky Survey (SDSS) and LAMOST for radial velocity variations. We employ a Bayesian method to infer the maximum likelihood of the fraction of binary stars with orbital periods of 1000 days or shorter, assuming a simple model distribution for a binary population with circular orbits. The overall inferred fraction of stars with such a close binary companion is 43.0% ± 2.0% for a sample of F,G,K stars from SDSS SEGUE, and 30% ± 8.0% in a similar sample from LAMOST. The apparent close binary fraction decreases with the stellar effective temperature. We divide the SEGUE and LEGUE data into three subsamples with different metallicity ([Fe/H] < –1.1; –1.1 < [Fe/H] < –0.6; –0.6 < [Fe/H]), for which the inferred close binary fractions are 56 ± 5.0%, 56.0 ± 3%, and 30 ± 5.7%. The metal-rich stars from our sample are therefore substantially less likely to possess a close binary companion than otherwise similar stars drawn from metal-poor populations. The different ages and formation environments of the Milky Way's thin disk, thick disk, and halo may contribute to explaining these observations. Alternatively, metallicity may have a significant effect on the formation and/or evolution of binary stars.

79 ASTRONOMY AND ASTROPHYSICS↗