SEARCH · Search NASA
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.
An extension to NICBES (the nickel cadmium battery expert system), which is designed to make it more effective as a battery management tool, is described. The extension involves the incorporation of classifier system machine learning techniques into a subsystem of NICBES. The implementation of a user interface for this type of system is discussed.
An algorithm that performs sparse linear discriminant analysis (Sparse-LDA) finds near-optimal solutions in far less time than the prior art when specialized to binary classification (of 2 classes). Sparse-LDA is a type of feature- or variable- selection problem with numerous applications in statistics, machine learning, computer vision, computational finance, operations research, and bio-informatics. Because of its combinatorial nature, feature- or variable-selection problems are NP-hard or computationally intractable in cases involving more than 30 variables or features. Therefore, one typically seeks approximate solutions by means of greedy search algorithms. The prior Sparse-LDA algorithm was a greedy algorithm that considered the best variable or feature to add/ delete to/ from its subsets in order to maximally discriminate between multiple classes of data. The present algorithm is designed for the special but prevalent case of 2-class or binary classification (e.g. 1 vs. 0, functioning vs. malfunctioning, or change versus no change). The present algorithm provides near-optimal solutions on large real-world datasets having hundreds or even thousands of variables or features (e.g. selecting the fewest wavelength bands in a hyperspectral sensor to do terrain classification) and does so in typical computation times of minutes as compared to days or weeks as taken by the prior art. Sparse LDA requires solving generalized eigenvalue problems for a large number of variable subsets (represented by the submatrices of the input within-class and between-class covariance matrices). In the general (fullrank) case, the amount of computation scales at least cubically with the number of variables and thus the size of the problems that can be solved is limited accordingly. However, in binary classification, the principal eigenvalues can be found using a special analytic formula, without resorting to costly iterative techniques. The present algorithm exploits this analytic form along with the inherent sequential nature of greedy search itself. Together this enables the use of highly-efficient partitioned-matrix-inverse techniques that result in large speedups of computation in both the forward-selection and backward-elimination stages of greedy algorithms in general.
In this paper the classical "Westland" set of empirical accelerometer helicopter data is analyzed with the aim of condition monitoring for diagnostic purposes. The goal is to determine features for failure events from these data, via a proprietary signal processing toolbox, and to weigh these according to a variety of classification algorithms. As regards signal processing, it appears that the autoregressive (AR) coefficients from a simple linear model encapsulate a great deal of information in a relatively few measurements; it has also been found that augmentation of these by harmonic and other parameters can improve classification significantly. As regards classification, several techniques have been explored, among these restricted Coulomb energy (RCE) networks, learning vector quantization (LVQ), Gaussian mixture classifiers and decision trees. A problem with these approaches, and in common with many classification paradigms, is that augmentation of the feature dimension can degrade classification ability. Thus, we also introduce the Bayesian data reduction algorithm (BDRA), which imposes a Dirichlet prior on training data and is thus able to quantify probability of error in an exact manner, such that features may be discarded or coarsened appropriately.
This is a fully parallel analog backpropagation learning processor which comprises a plurality of programmable resistive memory elements serving as synapse connections whose values can be weighted during learning with buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in a plurality of neuron layers in accordance with delta-backpropagation algorithms modified so as to control weight changes due to circuit drift.
We developed techniques to predict application execution times for instance-based learning with an average error of 33% of average run time. We developed techniques to predict queue wait times that included a simulation of scheduling algorithms and execution time predictions. We implemented these techniques for the NAS Origin cluster.
In extensive form noncooperative game theory, at each instant t, each agent i sets its state x, independently of the other agents, by sampling an associated distribution, q(sub i)(x(sub i)). The coupling between the agents arises in the joint evolution of those distributions. Distributed control problems can be cast the same way. In those problems the system designer sets aspects of the joint evolution of the distributions to try to optimize the goal for the overall system. Now information theory tells us what the separate q(sub i) of the agents are most likely to be if the system were to have a particular expected value of the objective function G(x(sub 1),x(sub 2), ...). So one can view the job of the system designer as speeding an iterative process. Each step of that process starts with a specified value of E(G), and the convergence of the q(sub i) to the most likely set of distributions consistent with that value. After this the target value for E(sub q)(G) is lowered, and then the process repeats. Previous work has elaborated many schemes for implementing this process when the underlying variables x(sub i) all have a finite number of possible values and G does not extend to multiple instants in time. That work also is based on a fixed mapping from agents to control devices, so that the the statistical independence of the agents' moves means independence of the device states. This paper also extends that work to relax all of these restrictions. This extends the applicability of that work to include continuous spaces and Reinforcement Learning. This paper also elaborates how some of that earlier work can be viewed as a first-principles justification of evolution-based search algorithms.
A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.
A fast, reliable way of predicting aerodynamic coefficients is produced using a neural network optimized by a genetic algorithm. Basic aerodynamic coefficients (e.g. lift, drag, pitching moment) are modelled as functions of angle of attack and Mach number. The neural network is first trained on a relatively rich set of data from wind tunnel tests of numerical simulations to learn an overall model. Most of the aerodynamic parameters can be well-fitted using polynomial functions. A new set of data, which can be relatively sparse, is then supplied to the network to produce a new model consistent with the previous model and the new data. Because the new model interpolates realistically between the sparse test data points, it is suitable for use in piloted simulations. The genetic algorithm is used to choose a neural network architecture to give best results, avoiding over-and under-fitting of the test data.
The Data Systems Dynamic Simulator (DSDS+) is a software tool being developed by the authors to evaluate candidate architectures for NASA's end-to-end data systems. Via modeling and simulation, we are able to quickly predict the performance characteristics of each architecture, to evaluate 'what-if' scenarios, and to perform sensitivity analyses. As such, we are using modeling and simulation to help NASA select the optimal system configuration, and to quantify the performance characteristics of this system prior to its delivery. This paper is divided into the following six sections: (1) The role of modeling and simulation in the systems engineering process. In this section, we briefly describe the different types of results obtained by modeling each phase of the systems engineering life cycle, from concept definition through operations and maintenance; (2) Recent applications of DSDS+. In this section, we describe ongoing applications of DSDS+ in support of the Earth Observing System (EOS), and we present some of the simulation results generated of candidate system designs. So far, we have modeled individual EOS subsystems (e.g. the Solid State Recorders used onboard the spacecraft), and we have also developed an integrated model of the EOS end-to-end data processing and data communications systems (from the payloads onboard to the principle investigator facilities on the ground); (3) Overview of DSDS+. In this section we define what a discrete-event model is, and how it works. The discussion is presented relative to the DSDS+ simulation tool that we have developed, including it's run-time optimization algorithms that enables DSDS+ to execute substantially faster than comparable discrete-event simulation tools; (4) Summary. In this section, we summarize our findings and 'lessons learned' during the development and application of DSDS+ to model NASA's data systems; (5) Further Information; and (6) Acknowledgements.
The Tropical Rainfall Measuring Mission (TRMM) spacecraft is a nadir pointing spacecraft that nominally controls the roll and pitch attitude based on the Earth Sensor Assembly (ESA) output. TRMM's nominal orbit altitude was 350 km, until raised to 402 km to prolong mission life. During the boost, the ESA experienced a decreasing signal to noise ratio, until sun interference at 393 km altitude made the ESA data unreliable for attitude determination. At that point, the backup attitude determination algorithm, an extended Kalman filter, was enabled. After the boost finished, TRMM reacquired its nadir-pointing attitude, and continued its mission. This paper will briefly discuss the boost and the decision to turn on the backup attitude determination algorithm. A description of the extended Kalman filter algorithm will be given. In addition, flight results from analyzing attitude data and the results of software changes made onboard TRMM will be discussed. Some lessons learned are presented.
Tracked mobile robots in the 20 kg size class are under development for applications in urban reconnaissance. For efficient deployment, it is desirable for teams of robots to be able to automatically execute path following behaviors, with one or more followers tracking the path taken by a leader. The key challenges to enabling such a capability are (l) to develop sensor packages for such small robots that can accurately determine the path of the leader and (2) to develop path following algorithms for the subsequent robots. To date, we have integrated gyros, accelerometers, compass/inclinometers, odometry, and differential GPS into an effective sensing package. This paper describes the sensor package, sensor processing algorithm, and path tracking algorithm we have developed for the leader/follower problem in small robots and shows the result of performance characterization of the system. We also document pragmatic lessons learned about design, construction, and electromagnetic interference issues particular to the performance of state sensors on small robots.
Traditional methods of control allocation optimization have shown difficulties in exploiting the full potential of controlling large arrays of control devices on innovative air vehicles. Artificial neutral networks are inspired by biological nervous systems and neurocomputing has successfully been applied to a variety of complex optimization problems. This project investigates the potential of applying neurocomputing to the control allocation optimization problem of Hybrid Wing Body (HWB) aircraft concepts to minimize control power, hinge moments, and actuator forces, while keeping system weights within acceptable limits. The main objective of this project is to develop a proof-of-concept process suitable to demonstrate the potential of using neurocomputing for optimizing actuation power for aircraft featuring multiple independently actuated control surfaces. A Nastran aeroservoelastic finite element model is used to generate a learning database of hinge moment and actuation power characteristics for an array of flight conditions and control surface deflections. An artificial neural network incorporating a genetic algorithm then uses this training data to perform control allocation optimization for the investigated aircraft configuration. The phase I project showed that optimization results for the sum of required hinge moments are improved by more than 12% over the best Nastran solution by using the neural network optimization process.
This report describes a formal verification of a concise algorithm that computes a solution to the n-Queens problem for all natural numbers n, such that n > 3. The formal proof of the algorithm is completed in the Prototype Verification System (PVS) theorem prover. This verification effort serves two purposes. First, it is presented as a pedagogical example for learning a theorem prover, such as PVS, and second, as a candidate benchmark for comparing other formal methods tools to PVS.
This work explores on-board planning for the single spacecraft, multiple ground station Earth-observing satellite scheduling problem through artificial neural network function approximation of state–action value estimates generated by Monte Carlo tree search (MCTS). An extensive hyperparameter search is conducted for MCTS on the basis of performance, safety, and downlink opportunity utilization to determine the best hyperparameter combination for data generation. A hyperparameter search is also conducted on neural network architectures. The learned behavior of each network is explored, and each network architecture’s robustness to orbits and epochs outside of the training distributions is investigated. Furthermore, each algorithm is compared with a genetic algorithm, which serves to provide a baseline for optimality. MCTS is shown to compute near-optimal solutions in comparison to the genetic algorithm. The state–action value networks are shown to match or exceed the performance of MCTS in six orders of magnitude less execution time, showing promise for execution on board spacecraft.
Access to high-quality, high-resolution, near-real-time precipitation data is essential for hydrological and meteorological research and disaster mitigation. Traditional tools such as rain gauges and radar networks, though effective, have limitations, including sparse coverage in remote areas and high operational costs. Satellite data, with its global coverage and high spatial and temporal resolutions, mitigates limitations in coverage. Satellite precipitation products like Hydro Estimator (HE), Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (IMERG), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) utilize both geosynchronous thermal infrared (IR) and passive microwave (PMW) data in their operation. PMW sensors offer detailed atmospheric profiles but suffer from higher latency, whereas IR sensors provide lower latency but only capture cloud-top information. Despite this constraint, IR data remains attractive for low-latency precipitation estimation. Recent advances in deep learning, particularly convolutional neural networks (CNNs), have further improved satellite precipitation retrievals. This study introduces PERSIANN-Unet (PUnet or PERSIANN V3), a quasi-global algorithm covering 60°N–60°S that combines IR data, monthly climatology, and the UNet architecture to produce half-hourly precipitation estimates at 0.04° resolution. The product is evaluated against HE, IMERG, and PDIR-Now for 2022–2023. Results show that PUnet closely matches its training target, IMERG V07 Final, at the global scale, and performance is further evaluated against Stage IV as a reference over CONUS. Training PUnet on IMERG (2016–2021) leverages a high-quality, integrated PMW IR-gauge precipitation product while developing an IR-based framework not reliant on PMW availability. By operating on a single global image, PUnet avoids tile partitioning and blending steps, reducing edge discontinuities, and produces more spatially consistent precipitation fields across hemispheres.
The Wind spacecraft has yielded several decades of high-resolution magnetic field data, a large fraction of which displays small-scale structures. In particular, the solar wind is full of wavelike fluctuations that appear in both the field magnitude and its components. The nature of these fluctuations can be tied to the properties of other structures in the solar wind, such as shocks, that have implications for the time evolution of the solar wind. As such, having a large collection of wave events would facilitate further study of the effects that these fluctuations have on solar wind evolution. Given the large volume of magnetic field data available, machine learning is the most practical approach to classifying the myriad small-scale structures observed. To this end, a subset of Wind data is labeled and used as a training set for a multi-branch 1D convolutional neural network aimed at classifying circularly polarized wave modes. Using this algorithm, a preliminary statistical study of one year of data is performed, yielding about 300,000 wave intervals out of about 5,000,000 solar wind intervals. The wave intervals come about more often in the fast solar wind and at higher temperatures, and the number of waves per day is highly periodic. This machine learning-based approach to wave detection has the potential to be a powerful, inexpensive way to catalog waves throughout decades of spacecraft data.
Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.
This research uses machine-learned computational analyses to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is from a rodent model exposed to ≤ 15 cGy of individual Galactic Cosmic Radiation (GCR) ions: 4He, 16O, 28Si, 48Ti, or 56Fe, expected for a Lunar or Mars mission. This work investigates rats at a subject-based level and uses performance scores taken before irradiation to predict impairment in Attentional Set-shifting (ATSET) data post-irradiation. Here, the worst performing rats of the control group define the impairment thresholds based on population analyses via cumulative distribution functions, leading to the labeling of impairment for each subject. A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the Simple Discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the Compound Discrimination (CD) stage. On a subject-based level, implementing Machine Learning (ML) classifiers such as the Gaussian Naïve Bayes, Support Vector Machine, and Artificial Neural Networks identifies rats that have a higher tendency for impairment after GCR exposure. The algorithms employ the experimental prescreenperformance scores as multidimensional input features to predict each rodent’s susceptibility to cognitive impairment due to space radiation exposure. The receiver operating characteristic and the precision-recall curves of the ML models show a better prediction of impairment when 56Feis the ion in question in both SD and CD stages. They, however, do not depict impairment due to 4Hein SD and 28Siin CD, suggesting no dose-dependent impairment response in these cases. One key finding of our study is that prescreen performance scores can be used to predict the ATSET performance impairments. This result is significant to crewed space missions as it supports the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. Future research can focus on constructing ML ensemble methods to integrate the findings from the methodologies implemented in this study for morerobust predictionsof cognitive decrements due to space radiation exposure.