Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine”

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 1,135 records · Page 63

DELTA: An Open-Source Framework to Simplify Machine Learning with Satellite Imagery

DELTA (Deep Earth Learning, Tools, and Analysis) is an open-source framework developed at NASA to simplify running and training machine learning (ML) models on satellite imagery. Users new to machine learning can run existing ML models on satellite imagery with minimal setup and configuration. For experienced ML users, DELTA helps simplify data engineering, preprocessing steps, and reduces the need for boilerplate code that needs written to make satellite imagery datasets palatable for machine learning. This lets data scientists focus on model development while DELTA handles the imagery manipulation. This presentation will demonstrate DELTA’s functionality and share some examples from an active project using it for flood mapping using imagery from multiple satellite sources

Michael von Pohle↗

GeoNEX-ML: A Machine Learning System for Geostationary Satellite Imagery

Improved capabilities of earth monitoring satellites are enabling a wide range of studies on the environmental effects of climate change, often leveraging the recent advancements in machine learning. At the same time, the new capabilities, including higher spatial resolution and temporal frequency, are expanding the amount of data generated at exponential rates. Further, a large majority of archived datasets generated by scientific processing is never used. This motivates the development of an efficient machine learning system for end-to-end processing of multi-level satellite datasets, from level 1 top of atmosphere observations to user friendly environmental variables of interest. Using current generation geostationary satellites GOES-16/17 (NOAA/NASA), Himawari-8/9 (JAXA), and GK-2A (Korea), we present an interchangeable set of machine models to perform spectral adjustment, physical model emulation, LEO-GEO emulation, and optical flow in a high performance computing environment. We use these tools to generate consistent virtual observations across sensors, perform atmospheric correction and cloud detection, and estimate land surface temperature and atmospheric winds. This approach aims to improve the robustness of remotely sensed data processing by learning from diverse sets of observations while enabling near real-time and on-demand capabilities.

Geostationary satellites↗

Exploring Applications of Machine Learning for Wildfire Monitoring and Detection using Unmanned Aerial Vehicles

Wildfires are increasing in frequency and severity around the world, including the United States. The losses caused by wildfires could be mitigated if high-risk areas, hotspots, and flare-ups could be monitored continuously, such as through the use of Unmanned Aerial Vehicles (UAVs). This paper documents exploratory efforts using machine learning to determine efficient flight paths for UAVs and to detect wildfires using image classification. On path planning, three machine learning techniques—Genetic Algorithm, Simulated Annealing, and Dynamic Programming—were explored. Genetic Algorithm was found to be an effective approach for path planning for wildfire monitoring and surveillance by UAVs. For a scenario of 25 locations in a circular arrangement, the algorithm was able to return the optimal path. The accuracy and execution time was found to be sensitive to the algorithm hyperparameters selected, which was especially evident in scenarios with hundreds or thousands of locations. Simulated Annealing was also found to be an effective approach for UAV path planning, with a major benefit of avoiding getting trapped in local minima and being straightforward to implement. Like Genetic Algorithm, the performance of Simulated Annealing was also found to be sensitive to the algorithm hyperparameters selected. By comparison, Dynamic Programming guarantees optimality for any number of locations, but it was found to be less practical in terms of execution time for scenarios with more than about a couple dozen locations. On wildfire detection, image classification using deep learning with a convolutional neural network was explored. Transfer learning was found to be a useful technique to efficiently train deep learning models. Also, it was determined that GPU processing can increase training speed by an order of magnitude, which enables significantly faster development. For a validation test set of 500 images, there were only two false negatives and zero false positives. These results demonstrate that detecting wildfires in static cameras using machine learning is feasible and establish a baseline for using images captured by UAVs in flight for wildfire detection.

Wildfire management↗

Design Implications of Rotordynamics and Mass Balancing on a 1.4 MW Partially Superconducting Machine

To ensure that rotating machines operate without excessive bearing loads, vibration, and dynamic stresses, their design must consider rotordynamic response and provisions for mass balancing of rotors, even when their rotational speeds are modest. This paper presents a rotordynamics design study for a 1.4 MW, partially superconducting electric machine proposed for electrified aircraft propulsion – NASA’s High Efficiency Megawatt Motor (HEMM). The study includes the selection of mass balancing grade and mount and bearing stiffnesses to yield satisfactory critical speeds, deflection, and unbalance force, and predictions of the expected mass unbalance caused by the superconducting rotor coils. The impact of the machine’s number of rotor poles on expected mass unbalance is also quantified. Design decisions and lessons learned are discussed.

hybrid electric aircraft↗

Design Implications of Rotordynamics and Mass Balancing on a 1.4 MW Partially Superconducting Machine

To ensure that rotating machines operate without excessive bearing loads, vibration, and dynamic stresses, their design must consider rotordynamic response and provisions for mass balancing of rotors, even when their rotational speeds are modest. This paper presents a rotordynamics design study for a 1.4 MW, partially superconducting electric machine proposed for electrified aircraft propulsion – NASA’s High Efficiency Megawatt Motor (HEMM). The study includes the selection of mass balancing grade and mount and bearing stiffnesses to yield satisfactory critical speeds, deflection, and unbalance force, and predictions of the expected mass unbalance caused by the superconducting rotor coils. The impact of the machine’s number of rotor poles on expected mass unbalance is also quantified. Design decisions and lessons learned are discussed.

hybrid electric aircraft↗

Muon Collider interaction region and machine-detector interface design

One of the key systems of a Muon Collider (MC) - seen as the most exciting option for the energy frontier machine in the post-LHC era - is its interaction region (IR). Designs of its optics, magnets and machine-detector interface are strongly interlaced and iterative. As a result of recent comprehensive studies, consistent solutions for the 1.5-TeV c.o.m. MC IR have been found and are described here. To provide the required momentum acceptance, dynamic aperture and chromaticity, an innovative approach was used for the IR optics. Conceptual designs of large-aperture high-field dipole and high-gradient quadrupole magnets based on Nb{sub 3}Sn superconductor were developed and analyzed in terms of the operating margin, field quality, mechanics, coil cooling and quench protection. Shadow masks in the interconnect regions and liners inside the magnets are used to mitigate the unprecedented dynamic heat deposition due to muon decays ({approx}0.5 kW/m). It is shown that an appropriately designed machine-detector interface (MDI) with sophisticated shielding in the detector has a potential to substantially suppress the background rates in the MC detector.

43 PARTICLE ACCELERATORS↗

Using support vector machines for anomalous change detonation

We cast anomalous change detection as a binary classification problem, and use a support vector machine (SVM) to build a detector that does not depend on assumptions about the underlying data distribution. To speed up the computation, our SVM is implemented, in part, on a graphical processing unit. Results on real and simulated anomalous changes are used to compare performance to algorithms which effectively assume a Gaussian distribution. In this paper, we investigate the use of support vector machines (SVMs) with radial basis kernels for finding anomalous changes. Compared to typical applications of SVMs, we are operating in a regime of very low false alarm rate. This means that even for relatively large training sets, the data are quite meager in the regime of operational interest. This drives us to use larger training sets, which in turn places more of a computational burden on the SVM. We initially considered three different approaches to to address the need to work in the very low false alarm rate regime. The first is a standard SVM which is trained at one threshold (where more reliable estimates of false alarm rates are possible) and then re-thresholded for the low false alarm rate regime. The second uses the same thresholding approach, but employs a so-called least squares SVM; here a quadratic (instead of a hinge-based) loss function is employed, and for this model, there are good theoretical arguments in favor of adjusting the threshold in a straightforward manner. The third approach employs a weighted support vector machine, where the weights for the two types of errors (false alarm and missed detection) are automatically adjusted to achieve the desired false alarm rate. We have found in previous experiments (not shown here) that the first two types can in some cases work well, while in other cases they do not. This renders both approaches unreliable for automated change detection. By contrast, the third approach reliably produces good results, but at the cost of larger computational requirements caused by the need to estimate very small false alarm rates. To address these computational requirements, we employ a recently developed in-house solver for SVMs that is significantly faster than freely available standard solvers. But these computational issues are secondary to the larger question: do kernelized solutions provide better performance, in terms of detection rates and false alarm rates, than more traditional methods for change detection that effectively assume Gaussian data distributions? To this end, we will compare ROC curves obtained from the SVM with those from chronochrome, covariance equalization, and hyperbolic anomalous change detection.

97 MATHEMATICS AND COMPUTING↗

Dovetail spoke internal permanent magnet machine

An internal permanent magnet (IPM) machine is provided. The IPM machine includes a stator assembly and a stator core. The stator core also includes multiple stator teeth. The stator assembly is further configured with stator windings to generate a stator magnetic field when excited with alternating currents and extends along a longitudinal axis with an inner surface defining a cavity. The IPM machine also includes a rotor assembly and a rotor core. The rotor core is disposed inside the cavity and configured to rotate about the longitudinal axis. The rotor assembly further includes a shaft. The shaft further includes multiple protrusions alternately arranged relative to multiple bottom structures provided on the shaft. The rotor assembly also includes multiple stacks of laminations disposed on the protrusions and dovetailed circumferentially around the shaft. The rotor assembly further includes multiple pair of permanent magnets for generating a magnetic field, which magnetic field interacts with the stator magnetic field to produce a torque. The multiple pair of permanent magnets are disposed between the stacks. The rotor assembly also includes multiple middle wedges mounted between each pair of the multiple permanent magnets.

47 OTHER INSTRUMENTATION↗

System and method for cooling a superconducting rotary machine

A system for cooling a superconducting rotary machine includes a plurality of sealed siphon tubes disposed in balanced locations around a rotor adjacent to a superconducting coil. Each of the sealed siphon tubes includes a tubular body and a heat transfer medium disposed in the tubular body that undergoes a phase change during operation of the machine to extract heat from the superconducting coil. A siphon heat exchanger is thermally coupled to the siphon tubes for extracting heat from the siphon tubes during operation of the machine.

42 ENGINEERING↗

High speed internal permanent magnet machine and method of manufacturing the same

An internal permanent magnet (IPM) machine is provided. The IPM machine includes a stator assembly and a stator core. The stator core also includes multiple stator teeth. The stator assembly is further configured with stator windings to generate a magnetic field when excited with alternating currents and extends along a longitudinal axis with an inner surface defining a cavity. The IPM machine also includes a rotor assembly and a rotor core. The rotor core is disposed inside the cavity and configured to rotate about the longitudinal axis. The rotor assembly further includes a shaft. The shaft further includes multiple protrusions alternately arranged relative to multiple bottom structures provided on the shaft. The rotor assembly also includes multiple stacks of laminations disposed on the protrusions and dovetailed circumferentially around the shaft. The rotor assembly further includes multiple permanent magnets for generating a magnetic field, which interacts with the stator magnetic field to produce torque. The permanent magnets are disposed between the stacks. The rotor assembly also includes multiple bottom wedges disposed on the bottom structures of the shaft and configured to hold the multiple stacks and the multiple permanent magnets.

47 OTHER INSTRUMENTATION↗

NVMalloc: Exposing an Aggregate SSD Store as a Memory Partition in Extreme-Scale Machines

DRAM is a precious resource in extreme-scale machines and is increasingly becoming scarce, mainly due to the growing number of cores per node. On future multi-petaflop and exaflop machines, the memory pressure is likely to be so severe that we need to rethink our memory usage models. Fortunately, the advent of non-volatile memory (NVM) offers a unique opportunity in this space. Current NVM offerings possess several desirable properties, such as low cost and power efficiency, but suffer from high latency and lifetime issues. We need rich techniques to be able to use them alongside DRAM. In this talk, we present a novel approach for exploiting NVM as a secondary memory partition so that applications can explicitly allocate and manipulate memory regions therein. More specifically, we propose an NVMalloc library with a suite of services that enables applications to access a distributed NVM storage system. We have devised ways within NVMalloc so that the storage system, built from compute node-local NVM devices, can be accessed in a byte-addressable fashion using the memory mapped I/O interface. Our approach has the potential to re-energize out-of-core computations on largescale machines by having applications allocate certain variables through NVMalloc, thereby increasing the overall memory capacity available. Our evaluation on a 128-core cluster shows that NVMalloc enables applications to compute problem sizes larger than the physical memory in a cost-effective manner. It can bring more performance/efficiency gain with increased computation time between NVM memory accesses or increased data access locality. In addition, our results suggest that while NVMalloc enables transparent access to NVM-resident variables, the explicit control it provides is crucial to optimize application performance.

99 GENERAL AND MISCELLANEOUS↗

Multi-winding homopolar electric machine

A multi-winding homopolar electric machine and method for converting between mechanical energy and electrical energy. The electric machine includes a shaft defining an axis of rotation, first and second magnets, a shielding portion, and a conductor. First and second magnets are coaxial with the shaft and include a charged pole surface and an oppositely charged pole surface, the charged pole surfaces facing one another to form a repulsive field therebetween. The shield portion extends between the magnets to confine at least a portion of the repulsive field to between the first and second magnets. The conductor extends between first and second end contacts and is toroidally coiled about the first and second magnets and the shield portion to develop a voltage across the first and second end contacts in response to rotation of the electric machine about the axis of rotation.

30 DIRECT ENERGY CONVERSION↗

Methods, systems and apparatus for optimization of third harmonic current injection in a multi-phase machine

Methods, system and apparatus are provided for increasing voltage utilization in a five-phase vector controlled machine drive system that employs third harmonic current injection to increase torque and power output by a five-phase machine. To do so, a fundamental current angle of a fundamental current vector is optimized for each particular torque-speed of operating point of the five-phase machine.

42 ENGINEERING↗

Methods, systems and apparatus for synchronous current regulation of a five-phase machine

Methods, systems and apparatus are provided for controlling operation of and regulating current provided to a five-phase machine when one or more phases has experienced a fault or has failed. In one implementation, the disclosed embodiments can be used to synchronously regulate current in a vector controlled motor drive system that includes a five-phase AC machine, a five-phase inverter module coupled to the five-phase AC machine, and a synchronous current regulator.

47 OTHER INSTRUMENTATION↗

Analyzing reliability of virtual machine instances with dynamic pricing in the public cloud

This study presents reliability analysis of virtual machine instances in public cloud environments in the face of dynamic pricing. Different from traditional fixed pricing, dynamic pricing allows price to dynamically fluctuate over arbitrary period of time according to external factors such as supply and demand, excess capacity, etc. This pricing option introduces a new type of fault: virtual machine instances may be unexpectedly terminated due to conflicts in the original bid price and the current offered price. This new class of fault under dynamic pricing may be more dominant than traditional faults in cloud computing environments, where resource availability associated with traditional faults is often above 99.9%. To address and understand this new type of fault, we translated two classic reliability metrics, mean time between failures and availability, to the Amazon Web Services spot market using historical price data. We also validated our findings by submitting actual bids in the spot market. We found that overall, our historical analysis and experimental validation lined up well. Based upon these experimental results, we also provided suggestions and techniques to maximize overall reliability of virtual machine instances under dynamic pricing.

Cloud computing↗

Novel Transverse Flux Machine for Vehicle Traction Applications: Preprint

A novel transverse flux machine topology for electric vehicle traction applications using ferrite magnets is presented in this paper. The proposed transverse flux topology utilizes novel magnet arrangements in the rotor that are similar to the Halbach array to boost flux linkage; on the stator side, cores are alternately arranged around a pair of ring windings in each phase to make use of the entire rotor flux that eliminates end windings. Analytical design considerations and finite-element methods are used for an optimized design of a scooter in-wheel motor. Simulation results from finite element analysis (FEA) show that the motor achieved comparable torque density to conventional rare-earth permanent magnet (PM) machines. This machine is a viable candidate for direct-drive applications with low cost and high torque density.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Machine Learning Toolkit for Extreme Scale

Support Vector Machines (SVM) is a popular machine learning technique, which has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. MaTEx undertakes the challenge of designing a scalable parallel SVM training algorithm for large scale systems, which includes commodity multi-core machines, tightly connected supercomputers and cloud computing systems. Several techniques are proposed for improved speed and memory space usage including adaptive and aggressive elimination of samples for faster convergence , and sparse format representation of data samples. Several heuristics for earliest possible to lazy elimination of non-contributing samples are considered in MaTEx. In many cases, where an early sample elimination might result in a false positive, low overhead mechanisms for reconstruction of key data structures are proposed. The proposed algorithm and heuristics are implemented and evaluated on various publicly available datasets

Source record↗

Virtual Machine Builder

Virtual Machine Builder is a graphical user interface for use and modification of virtual machine templates using Hashi Corp packer to perform virtual machine creation.

Nielsen, Roy↗