Deep Learning for Space Applications
Explore the source record for details and available documents.
Augmented Reality↗
SEARCH · Engineering Papers
Results for “machining processes”
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.
Autonomous Ocean World Exploration: Advancement of a Virtual Testbed
The search for life (extinct or extant) and potentially habitable bodies in our solar system and beyond is one of the 12 priority science questions outlined in the National Acadamies’ 2022 decadal survey [5]. Extraterrestrial destinations containing liquid water present an opportunity to search for life as we know it, and in recent years an increasing number of such locations have been discovered within our solar system. Several Jovian moons—Europa, Ganymede, and Callisto [10]—and the Saturnian moons Enceladus [8] and Titan [9] are known or suspected to harbor massive subsurface oceans. Of these "ocean worlds", Europa is the focus of at least one planned NASA orbiter mission, Europa Clipper [4], and an early lander mission concept, the Europa Lander [2, 3]. Whereas most robotic missions to the Moon and Mars (e.g. orbiters, rovers, landers) to date have had ground controllers on Earth tightly involved in mission operations, missions to more distant worlds will require a high degree of onboard autonomy due to long communication lags and blackouts, harsh environments (radiation, cold), and more limited battery and hardware life. The past decade has seen great advances in both AI technologies and computing scalability and performance that offer promising solutions for spacecraft autonomy and motivate the software system and research programs described in this paper. The Ocean Worlds Autonomy Testbed for Exploration, Research, and Simulation (OceanWATERS) [1], which has been in development at the NASA Ames Research Center since 2018, is a virtual environment for testing lander autonomy solutions. It is built on the Robot Operating System (ROS), runs on consumer-grade Linux workstations, and was released as open source in 2020. OceanWATERS provides a physical and visual simulation of a prototypical lander in a Europa-like environment (Figure 1). The lander was modeled after requirements and specifications made in JPL’s Europa Lander Study of 2016 [3]. Simulated lander systems include stereo cameras and spotlights mounted on an antenna mast that pans and tilts, a 6 degrees of freedom (DoF) robotic arm with a force-torque sensor and two interchangeable end effectors, and a battery pack power system. The environment consists of multiple terrain models including a highly detailed model sourced from the FROST dataset [11], simulation of surrounding planetary bodies based on an ephemeris model, and lighting from the sun with associated surface illumination, reflectance, and shadows. Operations supported by OceanWATERS include panoramic and directed imaging of the environment and lander workspace, Cartesian and joint-level arm commanding, grinding of the terrain surface (e.g. digging a trench), and scooping of ground material (Figure 2) which can be discarded or collected as science samples in a receptacle that can be emptied (science operations themselves are not simulated). These operations are realized as ROS Actions and are complimented by a wide selection of telemetry that is continually produced by each lander subsystem. The power system model is driven by the open-source Generic Software Architecture for Prognostics (GSAP) [11] that predicts the battery’s remaining useful life and other characteristics. As a testbed for high-level autonomy, OceanWATERS provides an execution framework based on PLEXIL [12], an open-source plan specification language and execution engine developed largely at Ames. NASA's initial development of OceanWATERS, as well the Ocean Worlds Lander Autonomy Testbed (OWLAT) [6], a complimentary physical testbed developed at JPL, was the first step in a plan for realizing candidate onboard autonomy solutions for such planetary landers. In 2020 NASA solicited applications for its Autonomous Robotics Research for Ocean Worlds (ARROW) program, and in 2021 the similar Concepts for Ocean worlds Life Detection Technology (COLDTech) program. Collectively six research teams, based in universities and companies across the United States, were awarded grants to develop and demonstrate autonomy solutions on OceanWATERS and OWLAT. These 1–2-year projects have now finished or are nearing completion, and a wide variety of autonomy challenges in ocean world surface missions were addressed. Prototyped and demonstrated solutions have included autonomous discovery, response and adaptation to system faults and unexpected environmental events, world model synthesis through perception, plan synthesis using learned models, methods to optimize sample target selection and prioritize science data transmission, extension of PLEXIL for stochastic decision-making, and an integration of a model of JPL’s mission-ready COLDArm [7]. Technologies used in these projects include many forms of machine learning, causal reasoning, automated planning, Markov decision processes, formal methods, and other advanced techniques. A more detailed summary of the ARROW and COLDTech projects is given herein. OceanWATERS has had significant enhancements since its open-source release in 2020. Many of its new features were driven or shaped by feedback from the ARROW and COLDTech teams and requirements of their projects. In support of enabling autonomous adaptation to spacecraft faults (a specific capability solicited by both programs), a fault injection and detection framework was developed that supports a wide and growing range of fault types such as locked joints, image loss, and battery failures. The power system model was completed and integrated into the simulator, starting as a single-cell battery model and later upgraded to a multi-cell model with associated faults such as cell disconnection. Arm/terrain interaction was improved by adding a force-torque sensor and associated faults, and an analytic dig force model based on the Balovnev bucket force equations. Environment fidelity was increased by modeling terrain deformation resulting from digging and scooping; visual improvements were made in textures, lighting, and shadows. To facilitate interoperation with OWLAT, a unified command and telemetry interface between the testbeds was developed at the ROS level, along with a PLEXIL interface. The number of lander operations was greatly expanded (e.g. with Cartesian-based arm and antenna movement), and a framework was designed for users to build their own lander actions. A GUI for PLEXIL plan selection was created (Figure 3), and an expansive set of plans were added, such as those that illustrate patterns for fault handling. This paper provides a self-contained high-level description of OceanWATERS, focusing on more detailed coverage of the aforementioned enhancements. It provides a high-level summary of the projects undertaken by participants in the ARROW and COLDTech programs and how these efforts have helped shape OceanWATERS. Finally, potential future work and directions for the testbed are listed, as likely informed by the recent planetary science decadal survey [5].
K Michael Dalal↗
GPU Implementation of the OVERFLOW CFD Code
The high-performance computing (HPC) landscape is quickly changing to systems where most of the performance comes from specialized chips, specifically graphics processing units (GPUs). Such GPU systems are throughput machines, where efficient use of the GPU often requires code refactoring to expose a few orders of magnitude more fine grain parallelism than was previously used on the CPU. Recent modifications to OVERFLOW, an overset, structured grid, computational fluid dynamics flow solver, written in Fortran will be presented. These modifications include both code modernization efforts and algorithmic changes to enable OVERFLOW to efficiently utilize GPUs. Many of these algorithmic changes would likely also be applicable for other structured grid, stencil-based codes wanting to utilize GPUs. The capabilities that have been ported to run on the GPUs are presented, along with the performance gains of the GPU version relative the CPU version of OVERFLOW.
GPU Programming↗
Aerospace Engineering Systems and the Advanced Design Technologies Testbed Experience
Continuous improvement of aerospace product development processes is a driving requirement across much of the aerospace community. As up to 90% of the cost of an aerospace product is committed during the first 10% of the development cycle, there is a strong emphasis on capturing, creating, and communicating better information (both requirements and performance) early in the product development process. The community has responded by pursuing the development of computer-based systems designed to enhance the decision-making capabilities of product development individuals and teams. Recently, the historical foci on sharing the geometrical representation and on configuration management are being augmented: 1) Physics-based analysis tools for filling the design space database; 2) Distributed computational resources to reduce response time and cost; 3) Web-based technologies to relieve machine-dependence; and 4) Artificial intelligence technologies to accelerate processes and reduce process variability. The Advanced Design Technologies Testbed (ADTT) activity at NASA Ames Research Center was initiated to study the strengths and weaknesses of the technologies supporting each of these trends, as well as the overall impact of the combination of these trends on a product development event. Lessons learned and recommendations for future activities are reported.
VanDalsem, William R.↗
Thermal and Mechanical Property Characterization of the Advanced Disk Alloy LSHR
A low solvus, high refractory (LSHR) powder metallurgy disk alloy was recently designed using experimental screening and statistical modeling of composition and processing variables on sub-scale disks to have versatile processing-property capabilities for advanced disk applications. The objective of the present study was to produce a scaled-up disk and apply varied heat treat processes to enable full-scale demonstration of LSHR properties. Scaled-up disks were produced, heat treated, sectioned, and then machined into specimens for mechanical testing. Results indicate the LSHR alloy can be processed to produce fine and coarse grain microstructures with differing combinations of strength and time-dependent mechanical properties, for application at temperatures exceeding 1300 F.
Gabb, Timothy P.↗
Automated Recognition of 3D Features in GPIR Images
A method of automated recognition of three-dimensional (3D) features in images generated by ground-penetrating imaging radar (GPIR) is undergoing development. GPIR 3D images can be analyzed to detect and identify such subsurface features as pipes and other utility conduits. Until now, much of the analysis of GPIR images has been performed manually by expert operators who must visually identify and track each feature. The present method is intended to satisfy a need for more efficient and accurate analysis by means of algorithms that can automatically identify and track subsurface features, with minimal supervision by human operators. In this method, data from multiple sources (for example, data on different features extracted by different algorithms) are fused together for identifying subsurface objects. The algorithms of this method can be classified in several different ways. In one classification, the algorithms fall into three classes: (1) image-processing algorithms, (2) feature- extraction algorithms, and (3) a multiaxis data-fusion/pattern-recognition algorithm that includes a combination of machine-learning, pattern-recognition, and object-linking algorithms. The image-processing class includes preprocessing algorithms for reducing noise and enhancing target features for pattern recognition. The feature-extraction algorithms operate on preprocessed data to extract such specific features in images as two-dimensional (2D) slices of a pipe. Then the multiaxis data-fusion/ pattern-recognition algorithm identifies, classifies, and reconstructs 3D objects from the extracted features. In this process, multiple 2D features extracted by use of different algorithms and representing views along different directions are used to identify and reconstruct 3D objects. In object linking, which is an essential part of this process, features identified in successive 2D slices and located within a threshold radius of identical features in adjacent slices are linked in a directed-graph data structure. Relative to past approaches, this multiaxis approach offers the advantages of more reliable detections, better discrimination of objects, and provision of redundant information, which can be helpful in filling gaps in feature recognition by one of the component algorithms. The image-processing class also includes postprocessing algorithms that enhance identified features to prepare them for further scrutiny by human analysts (see figure). Enhancement of images as a postprocessing step is a significant departure from traditional practice, in which enhancement of images is a preprocessing step.
Park, Han↗
Granular Material Flows with Interstitial Fluid Effects
The research focused on experimental measurements of the rheological properties of liquid-solid and granular flows. In these flows, the viscous effects of the interstitial fluid, the inertia of the fluid and particles, and the collisional interactions of the particles may all contribute to the flow mechanics. These multiphase flows include industrial problems such as coal slurry pipelines, hydraulic fracturing processes, fluidized beds, mining and milling operation, abrasive water jet machining, and polishing and surface erosion technologies. In addition, there are a wide range of geophysical flows such as debris flows, landslides and sediment transport. In extraterrestrial applications, the study of transport of particulate materials is fundamental to the mining and processing of lunar and Martian soils and the transport of atmospheric dust (National Research Council 2000). The recent images from Mars Global Surveyor spacecraft dramatically depict the complex sand and dust flows on Mars, including dune formation and dust avalanches on the slip-face of dune surfaces. These Aeolian features involve a complex interaction of the prevailing winds and deposition or erosion of the sediment layer; these features make a good test bed for the verification of global circulation models of the Martian atmosphere.
Hunt, Melany L.↗
The Development and Deployment of Machine Learning Models for Aircraft Engine Concept Assessment
In today's competitive landscape, the effective development and utilization of machine-learning (ML) applications have become crucial across diverse economic sectors. This study presents an outline of the procedure involved in creating and implementing ML models for conceptualizing and evaluating aircraft engines. These models leverage supervised deep-learning algorithms to analyze patterns within an open-source repository containing data on both production and research conventional turbofan engines. The main areas of focus encompass crucial engine parameters like thrust-specific fuel consumption (TSFC), engine weight, engine diameter, and turbomachinery stage counts. While the creation of ML models is fundamental for their utilization, ensuring their seamless deployment holds equal significance. To address this aspect, a conversational AI chatbot that specifically focuses on propulsion has been developed. Leveraging natural language processing (NLP) techniques, this chatbot simplifies the deployment of machine learning (ML) models. The comprehensive workflow encompasses several key stages: gathering and enhancing engine data, training and cross validating the ML models, testing and evaluating their performance, and finally, deploying, monitoring, and updating the ML models. By following this systematic approach, the aim is to streamline the development and deployment process of ML models tailored for aircraft engine assessment.
AI Chatbot↗
System software for the finite element machine
The Finite Element Machine is an experimental parallel computer developed at Langley Research Center to investigate the application of concurrent processing to structural engineering analysis. This report describes system-level software which has been developed to facilitate use of the machine by applications researchers. The overall software design is outlined, and several important parallel processing issues are discussed in detail, including processor management, communication, synchronization, and input/output. Based on experience using the system, the hardware architecture and software design are critiqued, and areas for further work are suggested.
Crockett, T. W.↗
Assuring Safety-Critical Machine Learning Enabled Systems: Challenges and Promise
Machine learning is increasingly being used in safety-critical systems, where the public safety requires a rigorous assurance process. We shall outline how assurance processes work for conventional systems and identify the primary difficulty in applying them to machine learning enabled systems. We will then outline a path forward including identifying where considerable basic research remains
Safety-critical systems↗
Assuring Safety-Critical Machine Learning Enabled Systems: Challenges and Promise
Machine learning is increasingly being used in safety-critical systems, where the public safety requires a rigorous assurance process. We shall outline how assurance processes work for conventional systems and identify the primary difficulty in applying them to machine learning enabled systems. We will then outline a path forward including identifying where considerable basic research remains.
machine learning↗
Asynchronous and corrected-asynchronous numerical solutions of parabolic PDES on MIMD multiprocessors
A major problem in achieving significant speed-up on parallel machines is the overhead involved with synchronizing the concurrent process. Removing the synchronization constraint has the potential of speeding up the computation. The authors present asynchronous (AS) and corrected-asynchronous (CA) finite difference schemes for the multi-dimensional heat equation. Although the discussion concentrates on the Euler scheme for the solution of the heat equation, it has the potential for being extended to other schemes and other parabolic partial differential equations (PDEs). These schemes are analyzed and implemented on the shared memory multi-user Sequent Balance machine. Numerical results for one and two dimensional problems are presented. It is shown experimentally that the synchronization penalty can be about 50 percent of run time: in most cases, the asynchronous scheme runs twice as fast as the parallel synchronous scheme. In general, the efficiency of the parallel schemes increases with processor load, with the time level, and with the problem dimension. The efficiency of the AS may reach 90 percent and over, but it provides accurate results only for steady-state values. The CA, on the other hand, is less efficient, but provides more accurate results for intermediate (non steady-state) values.
Amitai, Dganit↗
Computational Modeling in Structural Materials Processing
High temperature materials such as silicon carbide, a variety of nitrides, and ceramic matrix composites find use in aerospace, automotive, machine tool industries and in high speed civil transport applications. Chemical vapor deposition (CVD) is widely used in processing such structural materials. Variations of CVD include deposition on substrates, coating of fibers, inside cavities and on complex objects, and infiltration within preforms called chemical vapor infiltration (CVI). Our current knowledge of the process mechanisms, ability to optimize processes, and scale-up for large scale manufacturing is limited. In this regard, computational modeling of the processes is valuable since a validated model can be used as a design tool. The effort is similar to traditional chemically reacting flow modeling with emphasis on multicomponent diffusion, thermal diffusion, large sets of homogeneous reactions, and surface chemistry. In the case of CVI, models for pore infiltration are needed. In the present talk, examples of SiC nitride, and Boron deposition from the author's past work will be used to illustrate the utility of computational process modeling.
Meyyappan, Meyya↗
Study of the modifications needed for efficient operation of NASTRAN on the Control Data Corporation STAR-100 computer
NASA structural analysis (NASTRAN) computer program is operational on three series of third generation computers. The problem and difficulties involved in adapting NASTRAN to a fourth generation computer, namely, the Control Data STAR-100, are discussed. The salient features which distinguish Control Data STAR-100 from third generation computers are hardware vector processing capability and virtual memory. A feasible method is presented for transferring NASTRAN to Control Data STAR-100 system while retaining much of the machine-independent code. Basic matrix operations are noted for optimization for vector processing.
Source record↗
NASA Tech Briefs, June 2014
Topics include: Real-Time Minimization of Tracking Error for Aircraft Systems; Detecting an Extreme Minority Class in Hyperspectral Data Using Machine Learning; KSC Spaceport Weather Data Archive; Visualizing Acquisition, Processing, and Network Statistics Through Database Queries; Simulating Data Flow via Multiple Secure Connections; Systems and Services for Near-Real-Time Web Access to NPP Data; CCSDS Telemetry Decoder VHDL Core; Thermal Response of a High-Power Switch to Short Pulses; Solar Panel and System Design to Reduce Heating and Optimize Corridors for Lower-Risk Planetary Aerobraking; Low-Cost, Very Large Diamond-Turned Metal Mirror; Very-High-Load-Capacity Air Bearing Spindle for Large Diamond Turning Machines; Elevated-Temperature, Highly Emissive Coating for Energy Dissipation of Large Surfaces; Catalyst for Treatment and Control of Post-Combustion Emissions; Thermally Activated Crack Healing Mechanism for Metallic Materials; Subsurface Imaging of Nanocomposites; Self-Healing Glass Sealants for Solid Oxide Fuel Cells and Electrolyzer Cells; Micromachined Thermopile Arrays with Novel Thermo - electric Materials; Low-Cost, High-Performance MMOD Shielding; Head-Mounted Display Latency Measurement Rig; Workspace-Safe Operation of a Force- or Impedance-Controlled Robot; Cryogenic Mixing Pump with No Moving Parts; Seal Design Feature for Redundancy Verification; Dexterous Humanoid Robot; Tethered Vehicle Control and Tracking System; Lunar Organic Waste Reformer; Digital Laser Frequency Stabilization via Cavity Locking Employing Low-Frequency Direct Modulation; Deep UV Discharge Lamps in Capillary Quartz Tubes with Light Output Coupled to an Optical Fiber; Speech Acquisition and Automatic Speech Recognition for Integrated Spacesuit Audio Systems, Version II; Advanced Sensor Technology for Algal Biotechnology; High-Speed Spectral Mapper; "Ascent - Commemorating Shuttle" - A NASA Film and Multimedia Project DVD; High-Pressure, Reduced-Kinetics Mechanism for N-Hexadecane Oxidation; Method of Error Floor Mitigation in Low-Density Parity-Check Codes; X-Ray Flaw Size Parameter for POD Studies; Large Eddy Simulation Composition Equations for Two-Phase Fully Multicomponent Turbulent Flows; Scheduling Targeted and Mapping Observations with State, Resource, and Timing Constraints;
Source record↗
Ramp Technology and Intelligent Processing in Small Manufacturing
To address the issues of excessive inventories and increasing procurement lead times, the Navy is actively pursuing flexible computer integrated manufacturing (FCIM) technologies, integrated by communication networks to respond rapidly to its requirements for parts. The Rapid Acquisition of Manufactured Parts (RAMP) program, initiated in 1986, is an integral part of this effort. The RAMP program's goal is to reduce the current average production lead times experienced by the Navy's inventory control points by a factor of 90 percent. The manufacturing engineering component of the RAMP architecture utilizes an intelligent processing technology built around a knowledge-based shell provided by ICAD, Inc. Rules and data bases in the software simulate an expert manufacturing planner's knowledge of shop processes and equipment. This expert system can use Product Data Exchange using STEP (PDES) data to determine what features the required part has, what material is required to manufacture it, what machines and tools are needed, and how the part should be held (fixtured) for machining, among other factors. The program's rule base then indicates, for example, how to make each feature, in what order to make it, and to which machines on the shop floor the part should be routed for processing. This information becomes part of the shop work order. The process planning function under RAMP greatly reduces the time and effort required to complete a process plan. Since the PDES file that drives the intelligent processing is 100 percent complete and accurate to start with, the potential for costly errors is greatly diminished.
Rentz, Richard E.↗
X-Ray Backscatter Machine Support Frame
This summer at Kennedy Space Center, I spent 10 weeks as an intern working at the Prototype Development Lab. During this time I learned about the design and machining done here at NASA. I became familiar with the process from where a design begins in Pro/Engineer and finishes at the hands of the machinists. As an intern I was given various small jobs to do and then one project of my own. My personal project was a job for the Applied Physics Lab; in their work they use an X-Ray Backscatter machine. Previously it was resting atop a temporary frame that limited the use of the machine. My job was to design a frame for the machine to rest upon that would allow a full range of sample sizes. The frame was required to support the machine and provide a strain relief for the cords attached to the machine as it moved in the x and y directions. Calculations also had to be done to be sure the design would be able to withstand any loads or outside sources of stress. After the calculations proved the design to be ready to withstand the requirements, the parts were ordered or fabricated, as required. This helped me understand the full process of jobs sent to the Prototype Development Lab.
Cannon, Brooke↗
TPSAS-NF1676L-32493-DND
The Committee on Earth Observation Satellites (CEOS) System Engineering Office (SEO) has supported the Open Data Cube (ODC) initiative to provide a data architecture solution that has value to its global users and increases the impact of EO satellite data. ODC is an open-source platform for processing satellite data. We have developed software products and tools around the core ODC that would help users perform machine learning on EO satellite data. The recent United Nations (UN) Sustainable Development Agenda provides a shared blueprint for peace and prosperity for people and for the planet, considering our current situation and helping to create a plan. The core of this agenda is a set of seventeen Sustainable Development Goals (SDGs), which represent an urgent call for action by all countries - both developed and developing - in a global partnership. The CEOS SEO team has recently developed and released a set of innovative Jupyter notebooks addressing UN SDGs 6.6.1 (spatial extents of water-related ecosystems), 11.3.1 (ratio of land consumption rate to population growth rate), and 15.3.1 (proportion of land that is degraded over total land area). These notebooks empower users by providing features that will assist with streamlining analysis ready data retrieval, processing, and visualization. We have recently incorporated several machine learning techniques in these notebooks. In this paper, we present the lessons learned from our experience on classifying land using supervised and unsupervised machine learning techniques using ODC framework for UN SDGs. We identify the current limitations of ODC to seamlessly support machine learning techniques. We propose features that would help machine learning, specifically within the ODC framework. We propose a thematic indexing/loading of data for both unsupervised learning as well as data annotation/labeling pipeline. Currently, ODC supports machine learning by separating data-management from the analysis process. It works as a mechanism to load cubes of data. ODC does not natively support features that are vital in machine learning such as validation splits, fair/balanced sampling, establishing load size constraints, etc. We believe that our proposed features will empower users by providing features that bring machine learning techniques closed to ODC. Enhancements to ODC to better accommodate machine learning techniques can assist in fulfilling UN SDGs such as 6.3.2, 6.4.2, 6.6.1, 11.3.1, 14.1.1, 15.1.1, 15.3.1, and 15.4.2.
Syed R Rizvi↗