SEARCH · Engineering Papers
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.
Integration and commissioning of ARIES MW Electrolyzer system is complete, and several integration and operation lessons have been learned. An outline of the ARIES MW Electrolyzer system is presented. Lessons learned in both integration of the units and operations of the electrolyzer are also covered.
The increasing availability of precipitation observations from space, e.g., from the Tropical Rainfall Measuring Mission (TRMM) and the forthcoming Global Precipitation Measuring (GPM) Mission, has fueled renewed interest in developing frameworks for downscaling and multi-sensor data fusion that can handle large data sets in computationally efficient ways while optimally reproducing desired properties of the underlying rainfall fields. Of special interest is the reproduction of extreme precipitation intensities and gradients, as these are directly relevant to hazard prediction. In this paper, we present a new formalism for downscaling satellite precipitation observations, which explicitly allows for the preservation of some key geometrical and statistical properties of spatial precipitation. These include sharp intensity gradients (due to high-intensity regions embedded within lower-intensity areas), coherent spatial structures (due to regions of slowly varying rainfall),and thicker-than-Gaussian tails of precipitation gradients and intensities. Specifically, we pose the downscaling problem as a discrete inverse problem and solve it via a regularized variational approach (variational downscaling) where the regularization term is selected to impose the desired smoothness in the solution while allowing for some steep gradients(called 1-norm or total variation regularization). We demonstrate the duality between this geometrically inspired solution and its Bayesian statistical interpretation, which is equivalent to assuming a Laplace prior distribution for the precipitation intensities in the derivative (wavelet) space. When the observation operator is not known, we discuss the effect of its misspecification and explore a previously proposed dictionary-based sparse inverse downscaling methodology to indirectly learn the observation operator from a database of coincidental high- and low-resolution observations. The proposed method and ideas are illustrated in case studies featuring the downscaling of a hurricane precipitation field.
Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.
Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a nonparametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications.
Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a nonparametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications
Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a non-parametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications
A self-learning, sensor fail-operational, control system for the TF30-P-3 afterburning turbofan engine was designed and evaluated. The sensor fail-operational control system includes a digital computer program designed to operate in conjunction with the standard TF30-P-3 bill-of-materials control. Four engine measurements and two compressor face measurements are tested. If any engine measurements are found to have failed, they are replaced by values synthesized from computer-stored information. The control system was evaluated by using a realtime, nonlinear, hybrid computer engine simulation at sea level static condition, at a typical cruise condition, and at several extreme flight conditions. Results indicate that the addition of such a system can improve the reliability of an engine digital control system.
The goals and data collection requirements to be used for the economic and performance evaluation indexes and life cycle cost parameters for the upcoming operations demonstration of an automated Deep Space Station (DSS) run unattended and controlled remotely from JPL are presented. These evaluation indexes compare the remote operation of telemetry at DSS 13 with the cost and performance of a comparable manned operation at DSS 11. A description is presented of the data that needs to be collected, how the data will be analyzed, and what can and cannot be learned from this operations demonstration.
The operation parameter optimization in 2020 RHIC low energy run is difficult. First, the RHIC luminosity is affected by many RHIC operation parameters, as well as affected by many Low Energy RHIC electron Cooling (LEReC) operation parameters. Second, the luminosity signal in this run is noisy and not sensitive to these parameter changes, especially when these parameters are very close to their optimized values. It is not easy to distinguish the effects of one parameter from all other operation parameters separately. Therefore, it is difficult to optimize the luminosity by varying these parameters one by one. To find a way for luminosity optimization, we analyze some operation parameters via a machine learning algorithm - XGBoost. After constructing a black-box surrogate model from XGBoost and plotting their partial dependency plots (PDF) and SHAP value plots for different operation parameters, we can find the effects of an individual parameter on the RHIC luminosity and optimize it accordingly.
The dynamics-aware economic dispatch (DED) problem embeds low-level generator dynamics and operational constraints to enable near real-time scheduling of generation units in a power network. DED produces a more dynamic supervisory control policy than traditional economic dispatch (T-ED) that reduces overall generation costs. However, in contrast to T-ED, DED is a nonlinear, non-convex optimization problem that is computationally prohibitive to solve. We introduce a machine learning-based operator-theoretic approach for solving the DED problem efficiently. Specifically, we develop a novel discrete-time Koopman Operator (KO) formulation that embeds domain information into the structure of the KO to learn high-fidelity approximations of the generator dynamics. Using the KO approximation, the DED problem can be reformulated as a computationally tractable linear program (abbreviated DED-KO). We demonstrate the high solution quality and computational-time savings of the DED-KO model over the original DED formulation on a 9-bus test system.
The conclusions and recommendations that resulted from NASA's Hunting Sacred Cows Workshop are summarized, where a sacred cow is a belief or assumption that is so well established that it appears to be unreasonably immune to criticism. A link was identified between increased complexity and increased costs, especially in relation to automation and autonomy. An identical link was identified for outsourcing and commercialization. The work of NASA's Cost Less team is reviewed. The following conclusions were stated by the Cost Less team and considered at the workshop: the way Nasa conducts business must change; NASA makes its best contributions to the public areas not addressed by other government organizations; the management tool used for the last 30 years is no longer suitable; the most important work on any program or project is carried out before the development or operations stages; automation should only be used to achieve autonomy if the reasons for automation are well understood, and NASA's most critical resources are its personnel.
This paper discusses MECS' architecture for distributed operations and lessons learned from a field test in May 2001.
After four years on the International Space Station (ISS), the Astrobee Research Facility, has completed over 130 Test Sessions logging over 1000 hours of operations. Managed by the NASA ISS Program OZ office and supported by NASA Ames Research Center (ARC) in California, the Astrobee Team maintains three identical free-flying Astrobee robots for research on the ISS. As a technology demonstration platform, the Astrobee Robots are available for Guest Scientists to use for a spectrum of research capabilities. Astrobee, propelled by battery-operated fans, is designed to autonomously operate throughout most of the USOS (US Orbital Segment), with the objective of minimizing astronaut support. Astrobee carries a suite of six cameras, a two degree-of-freedom (DOF) arm with a gripper that can grasp ISS handrails and other objects, and three payload bays that provide power and data for guest science hardware. Astrobee can autonomously execute hours-long flight plans or be teleoperated from the ground or by astronauts. While the Astrobee Team continues to improve mapping and autonomous flight capabilities, one of the main goals of Astrobee Robots is to provide research opportunities for Guest Scientists. The Astrobee Robot Software (ARS) makes extensive use of the open-source Robot Operating System (ROS). The ARS can be used interchangeably with an Astrobee Simulator or as Astrobee’s onboard software. ARS features include autonomous docking and perching, real-time teleoperations from the ground, plan based autonomous tasks, multi Astrobee communication, among other capabilities. Through simulation software and ground testing laboratories, the Astrobee Team is available to support Guest Scientists during development and testing and lead real-time ISS operations. Guest Scientists can participate in this research opportunity following the Guest Science Lifecycle (GSL) shown in Figure 1: Guest Science Lifecycle below. The Astrobee Team and Guest Scientists have complete research including Gecko materials studies, RFID and sound sensing capabilities, student Robotics Programming Challenges, and Free Flyer formation flight investigations. Current science with the Astrobee Robots includes Free Flyer self-toss studies, new docking capabilities, advanced mapping resolution capabilities, and high resolution panoramic imagery. Future Guest scientists and Astrobee Team research will focus on robotics applications for future NASA missions such as Gateway and Artemis and potential experiments involving human-robot interactions. This presentation will focus on four main subjects, 1) completed, current, and future planned research using the Astrobee robots, 2) how Guest Scientist get from conception to the ISS, 3) Astrobee Facility resources available for Guest Science ground testing and real-time ISS operations support, and 4) lessons learned from four years of ISS operations.
This semester I worked with the Flight Planning Branch at the NASA Johnson Space Center. I learned about the different aspects of flight planning for the International Space Station as well as the software that is used internally and ISSLive! which is used to help educate the public on the space program. I had the opportunity to do on the job training in the Mission Control Center with the planning team. I transferred old timeline records from the planning team's old software to the new software in order to preserve the data for the future when the software is retired. I learned about the operations of the International Space Station, the importance of good communication between the different parts of the planning team, and enrolled in professional development classes as well as technical classes to learn about the space station.
The Cassini Attitude and Articulation Control Subsystem (AACS) Flight Software (FSW) has achieved its intended design goals by successfully guiding and controlling the Cassini-Huygens planetary mission to Saturn and its moons. This paper describes an overview of AACS FSW details from early design, development, implementation, and test to its fruition of operating and maintaining spacecraft control over an eleven year prime mission. Starting from phases of FSW development, topics expand to FSW development methodology, achievements utilizing in-flight autonomy, and summarize lessons learned during flight operations which can be useful to FSW in current and future spacecraft missions.
Proprietary or unique designs and operations are expected early in any industry's development, and often provide a competitive early market advantage. However, there comes a time when a product or industry requires standardization for the whole industry to advance...or survive. For the space industry, that time has come. Here, we will focus on standardization of ground processing for space vehicles and their ground systems. With the retirement of the Space Shuttle, and emergence of a new global space race, affordability and sustainability are more important now than ever. The growing commercialization of the space industry and current global economic environment are driving greater need for efficiencies to save time and money. More RLV's (Reusable Launch Vehicles) are being developed for the gains of reusability not achievable with traditional ELV's (Expendable Launch Vehicles). More crew/passenger vehicles are also being developed. All of this calls for more attention needed for ground processing-repeatedly before launch and after landing/recovery. RLV's should provide more efficiencies than ELV's, as long as MRO (Maintenance, Repair, and Overhaul) is well-planned-even for the unplanned problems. NASA's Space Shuttle is a primary example of an RLV which was supposed to thrive on reusability savings with efficient ground operations, but lessons learned show that costs were (and still are) much greater than expected. International standards and specifications can provide the commonality needed to simplify design and manufacturing as well as to improve safety, quality, maintenance, and operability. There are standards organizations engaged in the space industry, but ground processing is one of the areas least addressed. Challenges are encountered due to various factors often not considered during development. Multiple vehicle elements, sites, customers, and contractors pose various functional and integration difficulties. Resulting technical publication structures and methods are incongruent. Some processing products are still done on paper, some electronic, and many being converted in between. Business systems then are not fully compatible, and paper as well as electronic conversions are time-consuming and costly. NASA and its Shuttle contractors setup rules and systems to handle what has produced over 130 RLV launches, but they have had many challenges. Attempts have been made to apply aviation industry specifications to make the Shuttle more efficient with its ground processing. One efficiency project example was to make a Shuttle Maintenance Manual (SMM) based on the commercial ATA (Air Transport Association of America) Spec 100 for technical publications. This industry standard, along with others, has been a foundation for efficient global MRO of commercial airlines for years. A modified version was also made for some military aircraft. The SMM project found many similarities in Spec 100 which apply to the Shuttle, and room for expansion for space systems/structures not in aircraft. The SMM project team met with the ATA and representatives from NASA's X-33 and X-34 programs to discuss collaboration on a national space standard based on Spec 100. A pilot project was enabled for a subset of Shuttle systems. Full implementation was not yet achieved, X-33 and X-34 were cancelled, and the Shuttles were then designated for retirement. Nonetheless, we can learn from this project how to expand this concept to all space vehicle products. Since then, ATA has joined with ASD (AeroSpace and Defence Industries Association of Europe) and AIA (Aerospace Industries Association) to form a much-enhanced and expanded international specification: Sl000D, International Specification for Technical Publications. It includes air, land, and sea vehicles, missiles, support equipment, ordnance, and communications. It is used by a growing number of countries for commercial and government products. Its modular design is supported by a Common Source Dabase (CSDB), and COTS (commercial off-the-shelf) software is available for production of IETP's (Interactive Electronic Technical Publications). A few space industry products in Europe have begun to apply Sl000D already. Also, there are other related standards/specifications which have global implications. We have an opportunity to adapt Sl000D and possibly other standards for use with space vehicles and ground systems. Sl000D has plenty of flexibility to apply to any product needed. To successfully grow the viability of the space industry, all members, commercial and government, will need to engage cooperatively in developing and applying standards to move toward interoperability. If we leverage and combine the best existing space standards and specifications, develop new ones to address known gaps, and adapt the best applicable features from other industries, we can establish an infrastructure to not only accelerate current development, but also build longevity for a more cohesive international space community.
Programmatic, applicatory, developmental, and operational aspects of sounding rocket utilization for materials processing studies are discussed. Lessons learned through the experience of 10 sounding rocket missions are described. Particular attention is given to missions from the SPAR, Consort, and Joust programs. Successful experiments on Consort include the study of polymer membranes and resins, biological processes, demixing of immiscible liquids, and electrodeposition.
National Aeronautics and Space Administration (NASA) Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers (SE) together across organizational boundaries. The overarching vision for the KbDP Concept for AAM R&D is a substantial undertaking. The initial concept and implementation will focus on UAM operations to tractably learn and adjust the concept with a manageable database. Lessons learned and best practices with a smaller scope will enable successful scalability to AAM R&D or even to the entire modes of transportation and logistics. The UAM vision is one in which advanced technologies and new operational procedures enable practical and cost-effective air transport as an integrated mode of movement of people and goods throughout metropolitan areas. Initial implementation of three KbDP concepts of use shows promising benefits to NASA’s Air Traffic Management-Exploration (ATM-X) UAM Airspace Subproject. It is envisioned that the KbDP will manage an information database defined by mathematical, data science, and system engineering principles. AIML algorithms play a vital role in this KbDP concept by extracting meaningful knowledge from the information database, which the human user leverages to improve the efficiency and effectiveness of their research greatly.