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.
This is a Python code base that takes openly-available genetic information on known viruses and performs supervised machine learning and feature importance analysis on the relationship of the viral genomes to the competence to infect humans or bind to a specific host cell receptor.
NASA's Hubble Space Telescope contain large, diffraction limited optics with extraordinary resolution and performance for surpassing existing observatories. The need to reduce structural borne vibration and resultant optical jitter from critical Pointing Control System components, Reaction Wheels, prompted the feasibility investigation and eventual development of a passive isolation system. Alternative design concepts considered were required to meet a host of stringent specifications and pass rigid tests to be successfully verified and integrated into the already built flight vehicle. The final design employs multiple arrays of fluid damped springs that attenuate over a wide spectrum, while confining newly introduced resonances to benign regions of vehicle dynamic response. Overall jitter improvement of roughly a factor of 2 to 3 is attained with this system. The basis, evolution, and performance of the isolation system, specifically discussing design concepts considered, optimization studies, development lessons learned, innovative features, and analytical and ground test verified results are presented.
All the options in the NASA VEGetation Workbench (VEG) make use of a database of historical cover types. This database contains results from experiments by scientists on a wide variety of different cover types. The learning system uses the database to provide positive and negative training examples of classes that enable it to learn distinguishing features between classes of vegetation. All the other VEG options use the database to estimate the error bounds involved in the results obtained when various analysis techniques are applied to the sample of cover type data that is being studied. In the previous version of VEG, the historical cover type database was stored as part of the VEG knowledge base. This database was removed from the knowledge base. It is now stored as a series of flat files that are external to VEG. An interface between VEG and these files was provided. The interface allows the user to select which files of historical data to use. The files are then read, and the data are stored in Knowledge Engineering Environment (KEE) units using the same organization of units as in the previous version of VEG. The interface also allows the user to delete some or all of the historical database units from VEG and load new historical data from a file. This report summarizes the use of the historical cover type database in VEG. It then describes the new interface to the files containing the historical data. It describes minor changes that were made to VEG to enable the externally stored database to be used. Test runs to test the operation of the new interface and also to test the operation of VEG using historical data loaded from external files are described. Task F was completed. A Sun cartridge tape containing the KEE and Common Lisp code for the new interface and the modified version of the VEG knowledge base was delivered to the NASA GSFC technical representative.
Neural networks and fuzzy expert systems perform the same task of functional mapping using entirely different approaches. Each approach has certain unique features. The ability to learn specific input-output mappings from large input/output data possibly corrupted by noise and the ability to adapt or continue learning are some important features of neural networks. Fuzzy expert systems are known for their ability to deal with fuzzy information and incomplete/imprecise data in a structured, logical way. Since both of these techniques implement the same task (that of functional mapping--we regard 'inferencing' as one specific category under this class), a fusion of the two concepts that retains their unique features while overcoming their individual drawbacks will have excellent applications in the real world. In this paper, we arrive at a new architecture by fusing the two concepts. The architecture has the trainability/adaptibility (based on input/output observations) property of the neural networks and the architectural features that are unique to fuzzy expert systems. It also does not require specific information such as fuzzy rules, defuzzification procedure used, etc., though any such information can be integrated into the architecture. We show that this architecture can provide better performance than is possible from a single two or three layer feedforward neural network. Further, we show that this new architecture can be used as an efficient vehicle for hardware implementation of complex fuzzy expert systems for real-time applications. A numerical example is provided to show the potential of this approach.
This paper presents an artificial intelligence monitoring system developed by the NASA Glenn Principal Investigator Microgravity Services project to help the principal investigator teams identify the primary vibratory disturbance sources that are active, at any moment in time, on-board the International Space Station, which might impact the microgravity environment their experiments are exposed to. From the Principal Investigator Microgravity Services' web site, the principal investigator teams can monitor via a graphical display, in near real time, which event(s) is/are on, such as crew activities, pumps, fans, centrifuges, compressor, crew exercise, platform structural modes, etc., and decide whether or not to run their experiments based on the acceleration environment associated with a specific event. This monitoring system is focused primarily on detecting the vibratory disturbance sources, but could be used as well to detect some of the transient disturbance sources, depending on the events duration. The system has built-in capability to detect both known and unknown vibratory disturbance sources. Several soft computing techniques such as Kohonen's Self-Organizing Feature Map, Learning Vector Quantization, Back-Propagation Neural Networks, and Fuzzy Logic were used to design the system.
An intelligent system for monitoring the microgravity environment quality on-board the International Space Station is presented. The monitoring system uses a new approach combining Kohonen's self-organizing feature map, learning vector quantization, and back propagation neural network to recognize and classify the known and unknown patterns. Finally, fuzzy logic is used to assess the level of confidence associated with each vibrating source activation detected by the system.
This paper presents the preliminary performance results of the artificial intelligence monitoring system in full operational mode using near real time acceleration data downlinked from the International Space Station. Preliminary microgravity environment characterization analysis result for the International Space Station (Increment-2), using the monitoring system is presented. Also, comparison between the system predicted performance based on ground test data for the US laboratory "Destiny" module and actual on-orbit performance, using measured acceleration data from the U.S. laboratory module of the International Space Station is presented. Finally, preliminary on-orbit disturbance magnitude levels are presented for the Experiment of Physics of Colloids in Space, which are compared with on ground test data. The ground test data for the Experiment of Physics of Colloids in Space were acquired from the Microgravity Emission Laboratory, located at the NASA Glenn Research Center, Cleveland, Ohio. The artificial intelligence was developed by the NASA Glenn Principal Investigator Microgravity Services Project to help the principal investigator teams identify the primary vibratory disturbance sources that are active, at any moment of time, on-board the International Space Station, which might impact the microgravity environment their experiments are exposed to. From the Principal Investigator Microgravity Services' web site, the principal investigator teams can monitor via a dynamic graphical display, implemented in Java, in near real time, which event(s) is/are on, such as crew activities, pumps, fans, centrifuges, compressor, crew exercise, structural modes, etc., and decide whether or not to run their experiments, whenever that is an option, based on the acceleration magnitude and frequency sensitivity associated with that experiment. This monitoring system detects primarily the vibratory disturbance sources. The system has built-in capability to detect both known and unknown vibratory disturbance sources. Several soft computing techniques such as Kohonen's Self-Organizing Feature Map, Learning Vector Quantization, Back-Propagation Neural Networks, and Fuzzy Logic were used to design the system.
Space Technology 5 (ST-5) is a three-satellite constellation, technology validation mission under the New Millennium Program at NASA to be launched in March 2006. One of the key technologies to be validated is a lights-out, model-based operations approach to be used for one week to control the ST-5 constellation with no manual intervention. The ground architecture features the GSFC Mission Services Evolution Center (GMSEC) middleware, which allows easy plugging in of software components and a standardized messaging protocol over a software bus. A predictive modeling tool built on MatLab's Simulink software package makes use of the GMSEC standard messaging protocol to interface to the Advanced Mission Planning System (AMPS) Scenario Scheduler which controls all activities, resource allocation and real-time re-profiling of constellation resources when non-nominal events occur. The key features of this system, which we refer to as the ST-5 Simulink system, are as follows: Original daily plan is checked to make sure that predicted resources needed are available by comparing the plan against the model. As the plan is run in real-time, the system re-profiles future activities in real-time if planned activities do not occur in the predicted timeframe or fashion. Alert messages are sent out on the GMSEC bus by the system if future predicted problems are detected. This will allow the Scenario Scheduler to correct the situation before the problem happens. The predictive model is evolved automatically over time via telemetry updates thus reducing the cost of implementing and maintaining the models by an order of magnitude from previous efforts at GSFC such as the model-based system built for MAP in the mid-1990's. This paper will describe the key features, lessons learned and implications for future missions once this system is successfully validated on-orbit in 2006.
We are developing a pixel-level cloud-type classifier for the Multi-angle Imaging SpectroRadiometer (MISR), an instrument used to study clouds and aerosols from NASA's Terra satellite.
One of the responsibilities of the NASA Glenn Principal Investigator Microgravity Services is to support NASA sponsored investigators in the area of reduced-gravity acceleration data analysis, interpretation and the monitoring of the reduced-gravity environment on-board various carriers. With the International Space Station currently operational, a significant amount of acceleration data is being down-linked and processed on ground for both the space station onboard environment characterization (and verification) and scientific experiments. Therefore, to help principal investigator teams monitor the acceleration level on-board the International Space Station to avoid undesirable impact on their experiment, when possible, the NASA Glenn Principal Investigator Microgravity Services developed an artificial intelligence monitoring system, which detects in near real time any change in the environment susceptible to affect onboard experiments. The main objective of the monitoring system is to help research teams identify the vibratory disturbances that are active at any instant of time onboard the International Space Station that might impact the environment in which their experiment is being conducted. The monitoring system allows any space research scientist, at any location and at any time, to see the current acceleration level on-board the Space Station via the World Wide Web. From the NASA Glenn s Exploration Systems Division web site, research scientists can see in near real time the active disturbances, such as pumps, fans, compressor, crew exercise, re-boost, extra-vehicular activity, etc., and decide whether or not to continue operating or stopping (or making note of such activity for later correlation with science results) their experiments based on the g-level associated with that specific event. A dynamic graphical display accessible via the World Wide Web shows the status of all the vibratory disturbance activities with their degree of confidence as well as their g-level contribution to the environment. The system can detect both known and unknown vibratory disturbance activities. It can also perform trend analysis and prediction by analyzing past data over many Increments of the space station for selected disturbance activities. This feature can be used to monitor the health of onboard mechanical systems to detect and prevent potential system failure as well as for use by research scientists during their science results analysis. Examples of both real time on-line vibratory disturbance detection and off-line trend analysis are presented in this paper. Several soft computing techniques such as Kohonen s Self-Organizing Feature Map, Learning Vector Quantization, Back-Propagation Neural Networks, and Fuzzy Logic were used to design the system.
Abstract Obtaining microscopic structure-property relationships for grain boundaries is challenging due to their complex atomic structures. Recent efforts use machine learning to derive these relationships, but the way the atomic grain boundary structure is represented can have a significant impact on the predictions. Key steps for property prediction common to grain boundaries and other variable-sized atom clustered structures include: (1) describing the atomic structure as a feature matrix, (2) transforming the variable-sized feature matrix to a fixed length common to all structures, and (3) applying a machine learning algorithm to predict properties from the transformed matrices. We examine how these steps and different combinations of engineered features impact the accuracy of grain boundary energy predictions using a database of over 7000 grain boundaries. Additionally, we assess how different engineered features support interpretability, offering insights into the physics of the structure-property relationships.
Physics-aware deep learning (PADL) has gained popularity for use in spatiotemporal dynamics simulations, such as those in computational modeling of energetic materials (EM). We show that the challenge PADL methods face while learning complex field evolution problems can be simplified and accelerated by decoupling it into two tasks: learning complex geometric features in evolving fields and modeling dynamics over these features in a lower-dimensional feature space. We build upon our previous work on physics-aware recurrent convolutional neural networks (PARC). PARC embeds knowledge of underlying physics into its neural network architecture for more robust and accurate prediction of evolving physical fields. PARC was shown to effectively learn complex nonlinear features such as the formation of hotspots and coupled shock fronts in various initiation scenarios of EMs, as a function of microstructures, serving effectively as a microstructure-aware burn model. Here, we further accelerate PARC and reduce its computational cost by projecting the original dynamics onto a lower-dimensional invariant manifold, or “latent space.” The projected latent representation encodes the complex geometry of evolving fields (e.g., temperature and pressure) in a set of data-driven features. The reduced dimension of this latent space allows us to learn the dynamics during the initiation of EM with a lighter and more efficient model. We observe a significant decrease in training and inference time while maintaining results comparable to PARC at inference. This work takes steps towards enabling rapid prediction of EM thermomechanics at larger scales and characterization of EM structure–property–performance linkages at a full application scale.
The present paper examines the role of neural computing strategies in structural analysis and design. A principal focus of the work resides in the use of neural networks to represent the force-displacement relationship in static structural analysis. Such models provide computationally efficient capabilities for reanalysis, and appear to be well suited for application in numerical optimum design. The paper presents an overview of the neural computing approach, with special emphasis on supervised learning techniques adopted in the present work. Special features of such learning strategies which have a direct bearing on numerical accuracy and efficiency, are examined in the context of representative structural optimization problems.
This paper examines the role of neural computing strategies in structural analysis and design. A principal focus of the work resides in the use of neural networks to represent the force-displacement relationship in static structural analysis. Such models provide computationally efficient capabilities for reanalysis, and appear to be well suited for application in numerical optimum design. The paper presents an overview of the neutral computing approach, with special emphasis on supervised learning techniques adopted in the present work. Special features of such learning strategies which have a direct bearing on numerically accuracy and efficiency, are examined in the context of representative structural optimization problems.
The research initiatives supported by the U.S. Department of Energy (DOE) Grant DE-SC0022265 are fundamentally aimed at pioneering advanced machine learning (ML) techniques for scientific data compression within high-performance computing (HPC) environments. This comprehensive body of work addresses the critical challenge posed by the exponential growth of data generated by scientific simulations in domains such as fusion energy, climate modeling, and computational fluid dynamics (CFD). A core objective is to develop compression algorithms that achieve substantial data reduction—often by orders of magnitude—while rigorously ensuring the fidelity of both the primary data (PD) and scientifically crucial derived quantities of interest (QoI). The methodologies deployed under this grant integrate sophisticated deep learning architectures, prominently featuring autoencoders, advanced generative models like conditional diffusion, and hybrid learning techniques. Key innovations include the development of Guaranteed Autoencoders (GAE) and the Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) framework, which provide explicit, instance-level error bounds on reconstructed data. Furthermore, specialized strategies such as nonlinear constraint satisfaction are employed to preserve the integrity of QoI, a vital requirement for the trustworthiness of downstream scientific analyses. This research also focuses on the design and implementation of scalable, GPU-accelerated software pipelines that seamlessly integrate into existing HPC workflows, ensuring both computational efficiency and practical applicability. The CAESAR framework, for example, unifies foundation and generative models to create an adaptive and efficient compression solution for spatio-temporal scientific data. Collectively, these efforts represent a significant advancement in mitigating the scientific data deluge, enabling more effective data management, accelerated scientific discovery, and optimized utilization of HPC resources.
The research initiatives supported by the U.S. Department of Energy (DOE) Grant DE-SC0022265 are fundamentally aimed at pioneering advanced machine learning (ML) techniques for scientific data compression within high-performance computing (HPC) environments. This comprehensive body of work addresses the critical challenge posed by the exponential growth of data generated by scientific simulations in domains such as fusion energy, climate modeling, and computational fluid dynamics (CFD). A core objective is to develop compression algorithms that achieve substantial data reduction—often by orders of magnitude—while rigorously ensuring the fidelity of both the primary data (PD) and scientifically crucial derived quantities of interest (QoI). The methodologies deployed under this grant integrate sophisticated deep learning architectures, prominently featuring autoencoders, advanced generative models like conditional diffusion, and hybrid learning techniques. Key innovations include the development of Guaranteed Autoencoders (GAE) and the Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) framework, which provide explicit, instance-level error bounds on reconstructed data. Furthermore, specialized strategies such as nonlinear constraint satisfaction are employed to preserve the integrity of QoI, a vital requirement for the trustworthiness of downstream scientific analyses. This research also focuses on the design and implementation of scalable, GPU-accelerated software pipelines that seamlessly integrate into existing HPC workflows, ensuring both computational efficiency and practical applicability. The CAESAR framework, for example, unifies foundation and generative models to create an adaptive and efficient compression solution for spatio-temporal scientific data. Collectively, these efforts represent a significant advancement in mitigating the scientific data deluge, enabling more effective data management, accelerated scientific discovery, and optimized utilization of HPC resources.
Context: This panel featured three presentations centered on the common theme of applying LLMs and inverse reinforcement learning (IRL) to capture the complex human-environment interactions that are central to the operation of reservoir systems. Dr. Wyatt Arnold will kick off the webinar with a talk on how analyzing LLM chain-of-thought reasoning reveals sophisticated quantitative justification and risk awareness, showing promise as a bridge between quantitative models and value-driven water management decisions. Next, Dr. Matteo Giuliani will build on this with a discussion demonstrating that AI- and IRL-driven approaches can infer the trade-offs between flood control and water supply using historical observations. Finally, Dr. Rohan Singh Wilkho will close the webinar with a talk establishing IRL as a generalizable diagnostic tool for decoding decision-making in managed hydrologic and human-infrastructure systems. Across the three presentations, the application of LLMs and IRL opens new possibilities for the development of adaptive, transparent, and human-aware models supporting water management in an increasingly uncertain future. Presenters: Wyatt Arnold (Politecnico di Milano); Matteo Giuliani (Politecnico di Milano); Rohan Singh Wilkho (Cornell University) Moderator: Patrick M. Reed (MSD CoP Facilitation Team); Stefano Galelli (MSD CoP AI Working Group Co-Chair); David Gold (MSD CoP AI Working Group Co-Chair) This webinar was held on: June 23rd, 2026 from 12-1 PM EST.
Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.