SEARCH · Search NASA

Results for “large language models”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 523 records · Page 29

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Coupled Induction Machine and HVAC Models for Simulating HVAC Performance Considering Grid Dynamics in Buildings

This paper presents the development of novel models that integrate induction machines with HVAC equipment, such as pumps, heat pumps, and chillers, to analyze the impact of electrical parameters on the operational performance of thermo-fluid systems. The proposed model employs a coupling technique that captures the dynamic interactions between induction machines and HVAC systems. By integrating electrical, thermal, and mechanical dynamics, the models provide a comprehensive framework for simulating real-world scenarios, including interactions with the electrical grid. This achievement was made possible through the development of a Computationally Efficient and Accurate Induction Machine (CEAIM) model. Implemented using the equation-based Modelica language, the CEAIM model has been validated against experimental results, manufacturer data sheets, and various operating conditions. Its performance has been compared with existing induction machine models in the Modelica Standard Library (MSL), demonstrating superior accuracy and computational efficiency. The CEAIM model predicts torque, speed, and power consumption with a coefficient of determination (R 2 ) ranging from 0.98 to 1 and a coefficient of variation of root mean square error (CVRMSE) between 0.27% and 6.67%. Additionally, CEAIM scales more efficiently than conventional MSL models, with a slower computational growth rate in large-scale simulations. After thorough validation of the CEAIM model, it was coupled with HVAC equipment as this approach provides a detailed multi-dimensional view of capturing electrical transients and mechanical performance. To support this, a case study was conducted to showcase its capabilities.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS1993

An on-line expert system for diagnosing environmentally induced spacecraft anomalies using CLIPS

A new rule-based, expert system for diagnosing spacecraft anomalies is under development. The knowledge base consists of over two-hundred rules and provide links to historical and environmental databases. Environmental causes considered are bulk charging, single event upsets (SEU), surface charging, and total radiation dose. The system's driver translates forward chaining rules into a backward chaining sequence, prompting the user for information pertinent to the causes considered. The use of heuristics frees the user from searching through large amounts of irrelevant information (varying degrees of confidence in an answer) or 'unknown' to any question. The expert system not only provides scientists with needed risk analysis and confidence estimates not available in standard numerical models or databases, but it is also an effective learning tool. In addition, the architecture of the expert system allows easy additions to the knowledge base and the database. For example, new frames concerning orbital debris and ionospheric scintillation are being considered. The system currently runs on a MicroVAX and uses the C Language Integrated Production System (CLIPS).

Lauriente, Michael↗

NASA NTRS2000

Object-oriented Approach to High-level Network Monitoring and Management

An absolute prerequisite for the management of large investigating methods to build high-level monitoring computer networks is the ability to measure their systems that are built on top of existing monitoring performance. Unless we monitor a system, we cannot tools. Due to the heterogeneous nature of the hope to manage and control its performance. In this underlying systems at NASA Langley Research Center, paper, we describe a network monitoring system that we use an object-oriented approach for the design, we are currently designing and implementing. Keeping, first, we use UML (Unified Modeling Language) to in mind the complexity of the task and the required model users' requirements. Second, we identify the flexibility for future changes, we use an object-oriented existing capabilities of the underlying monitoring design methodology. The system is built using the system. Third, we try to map the former with the latter. APIs offered by the HP OpenView system.

Mukkamala, Ravi↗

NASA NTRS2014

Object-Oriented/Data-Oriented Design of a Direct Simulation Monte Carlo Algorithm

Over the past decade, there has been much progress towards improved phenomenological modeling and algorithmic updates for the direct simulation Monte Carlo (DSMC) method, which provides a probabilistic physical simulation of gas Rows. These improvements have largely been based on the work of the originator of the DSMC method, Graeme Bird. Of primary importance are improved chemistry, internal energy, and physics modeling and a reduction in time to solution. These allow for an expanded range of possible solutions In altitude and velocity space. NASA's current production code, the DSMC Analysis Code (DAC), is well-established and based on Bird's 1994 algorithms written in Fortran 77 and has proven difficult to upgrade. A new DSMC code is being developed in the C++ programming language using object-oriented and data-oriented design paradigms to facilitate the inclusion of the recent improvements and future development activities. The development efforts on the new code, the Multiphysics Algorithm with Particles (MAP), are described, and performance comparisons are made with DAC.

Liechty, Derek S.↗

NASA NTRS2017

QSPIN: A High Level Java API for Quantum Computing Experimentation

QSPIN is a high level Java language API for experimentation in QC models used in the calculation of Ising spin glass ground states and related quadratic unconstrained binary optimization (QUBO) problems. The Java API is intended to facilitate research in advanced QC algorithms such as hybrid quantum-classical solvers, automatic selection of constraint and optimization parameters, and techniques for the correction and mitigation of model and solution errors. QSPIN includes high level solver objects tailored to the D-Wave quantum annealing architecture that implement hybrid quantum-classical algorithms [Booth et al.] for solving large problems on small quantum devices, elimination of variables via roof duality, and classical computing optimization methods such as GPU accelerated simulated annealing and tabu search for comparison. A test suite of documented NP-complete applications ranging from graph coloring, covering, and partitioning to integer programming and scheduling are provided to demonstrate current capabilities.

Quantu↗

NASA NTRS1992

Artificial intelligence support for scientific model-building

Scientific model-building can be a time-intensive and painstaking process, often involving the development of large and complex computer programs. Despite the effort involved, scientific models cannot easily be distributed and shared with other scientists. In general, implemented scientific models are complex, idiosyncratic, and difficult for anyone but the original scientific development team to understand. We believe that artificial intelligence techniques can facilitate both the model-building and model-sharing process. In this paper, we overview our effort to build a scientific modeling software tool that aids the scientist in developing and using models. This tool includes an interactive intelligent graphical interface, a high-level domain specific modeling language, a library of physics equations and experimental datasets, and a suite of data display facilities.

Keller, Richard M.↗

NASA NTRS2006

X-Windows PVT Widget Class

The X-Windows Process Validation Table (PVT) Widget Class ( Class is used here in the object-oriented-programming sense of the word) was devised to simplify the task of implementing network registration services for Information Sharing Protocol (ISP) graphical-user-interface (GUI) computer programs. Heretofore, ISP PVT programming tasks have required many method calls to identify, query, and interpret the connections and messages exchanged between a client and a PVT server. Normally, programmers have utilized direct access to UNIX socket libraries to implement the PVT protocol queries, necessitating the use of many lines of source code to perform frequent tasks. Now, the X-Windows PVT Widget Class encapsulates ISP client server network registration management tasks within the framework of an X Windows widget. Use of the widget framework enables an X Windows GUI program to interact with PVT services in an abstract way and in the same manner as that of other graphical widgets, making it easier to program PVT clients. Wrapping the PVT services inside the widget framework enables a programmer to treat a PVT server interface as though it were a GUI. Moreover, an alternate subclass could implement another service in a widget of the same type. This program was written by Matthew R. Barry of United Space Alliance for Johnson Space Center. For further information, contact the Johnson Technology Transfer Office at (281) 483-3809. MSC-23582 Shuttle Data Center File- Processing Tool in Java A Java-language computer program has been written to facilitate mining of data in files in the Shuttle Data Center (SDC) archives. This program can be executed on a variety of workstations or via Web-browser programs. This program is partly similar to prior C-language programs used for the same purpose, while differing from those programs in that it exploits the platform-neutrality of Java in implementing several features that are important for analysis of large sets of time-series data. The program supports regular expression queries of SDC archive files, reads the files, interleaves the time-stamped samples according to a chosen output, then transforms the results into that format. A user can choose among a variety of output file formats that are useful for diverse purposes, including plotting, Markov modeling, multivariate density estimation, and wavelet multiresolution analysis, as well as for playback of data in support of simulation and testing.

Barry, Matthew R.↗

NASA NTRS2006

Shuttle Data Center File-Processing Tool in Java

A Java-language computer program has been written to facilitate mining of data in files in the Shuttle Data Center (SDC) archives. This program can be executed on a variety of workstations or via Web-browser programs. This program is partly similar to prior C-language programs used for the same purpose, while differing from those programs in that it exploits the platform-neutrality of Java in implementing several features that are important for analysis of large sets of time-series data. The program supports regular expression queries of SDC archive files, reads the files, interleaves the time-stamped samples according to a chosen output, then transforms the results into that format. A user can choose among a variety of output file formats that are useful for diverse purposes, including plotting, Markov modeling, multivariate density estimation, and wavelet multiresolution analysis, as well as for playback of data in support of simulation and testing.

Barry, Matthew R.↗

DOE OSTI2025

Molecular property prediction for very large databases with natural language processing: a case study in ionic liquid design

The prospect of using artificial intelligence (AI) to accurately screen very large databases of compounds for multiple properties has yet to be realized. Here, we explore this possibility using ionic liquids (ILs) which offer unique physicochemical properties and excellent tunability, making them highly versatile solvents for various research applications. Screening millions of potential ILs for the best perfomance for use in specific tasks with experimental methods alone however, is impractical. Further, traditional’ physics-based computational chemistry is hindered by high computational cost. To address this challenge, we leverage a natural language processing (NLP)-based molecular embedding technique with advanced machine learning (ML) models to predict seven key IL properties: viscosity, density, ionic conductivity, surface tension, melting temperature, toxicity, and water solubility. Comprehensive datasets for these properties are obtained, then NLP featurization with Mol2vec is compared with other featurization techniques such as 2D Morgan fingerprints, and 3D quantum chemistry-derived sigma profiles. NLP-based featurization exhibited the best predictive performance, achieving the highest R 2 and lowest RMSE values for all the studied IL properties. Further, we present case studies of how ILs might be screened using combined property criteria for practical cases – lignocellulosic biomass processing, CO 2 capture, and optimal electrolytes for batteries – screening a novel database of ∼10.6 million generated feasible ILs. The results introduce NLP as a powerful tool for engineering many designer solvents with desirable properties for task specific applications.

Mohan, Mood [Oak Ridge National Laboratory (ORNL),↗

NASA NTRS1990

Parallelism in backward-chained expert systems - Experimental results

There are many applications which may be done by an expert system in real time, if the system is capable of real-time response. The LISP and PROLOG-based expert systems have typically been too slow for real-time response. This has led to an effort to use other languages, the development of fast pattern matching techniques and other methods of improving the speed of expert systems. Another approach to developing faster expert systems is to make use of the emerging parallel processing computer technology. A further use for parallelism is to allow reasonable response time for large knowledge bases. The size of knowledge bases may become as large as 20,000 chunks of knowledge (and more) in the near future in medical and space applications. This paper describes the use of parallel processing in the EMYCIN backward chained rule-based model.

Hall, Lawrence O.↗

DOE OSTI2024

Performance on HPC Platforms Is Possible Without C++

Computing at large scales has become extremely challenging due to increasing heterogeneity in both hardware and software. More and more scientific workflows must tackle a range of scales and use machine learning and AI intertwined with more traditional numerical modeling methods, placing more demands on computational platforms. These constraints indicate a need to fundamentally rethink the way computational science is done and the tools that are needed to enable these complex workflows. The current set of C++-based solutions may not suffice, and relying exclusively upon C++ may not be the best option, especially because several newer languages and boutique solutions offer more robust design features to tackle the challenges of heterogeneity. In June 2023, we held a mini symposium that explored the use of newer languages and heterogeneity solutions that are not tied to C++ and that offer options beyond template metaprogramming and Parallel. For for performance and portability. In conclusion, we describe some of the presentations and discussion from the mini symposium in this article.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1996

Geodata Modeling and Query in Geographic Information Systems

Geographic information systems (GIS) deal with collecting, modeling, man- aging, analyzing, and integrating spatial (locational) and non-spatial (attribute) data required for geographic applications. Examples of spatial data are digital maps, administrative boundaries, road networks, and those of non-spatial data are census counts, land elevations and soil characteristics. GIS shares common areas with a number of other disciplines such as computer- aided design, computer cartography, database management, and remote sensing. None of these disciplines however, can by themselves fully meet the requirements of a GIS application. Examples of such requirements include: the ability to use locational data to produce high quality plots, perform complex operations such as network analysis, enable spatial searching and overlay operations, support spatial analysis and modeling, and provide data management functions such as efficient storage, retrieval, and modification of large datasets; independence, integrity, and security of data; and concurrent access to multiple users. It is on the data management issues that we devote our discussions in this monograph. Traditionally, database management technology have been developed for business applications. Such applications require, among other things, capturing the data requirements of high-level business functions and developing machine- level implementations; supporting multiple views of data and yet providing integration that would minimize redundancy and maintain data integrity and security; providing a high-level language for data definition and manipulation; allowing concurrent access to multiple users; and processing user transactions in an efficient manner. The demands on database management systems have been for speed, reliability, efficiency, cost effectiveness, and user-friendliness. Significant progress have been made in all of these areas over the last two decades to the point that many generalized database platforms are now available for developing data intensive applications that run in real-time. While continuous improvement is still being made at a very fast-paced and competitive rate, new application areas such as computer aided design, image processing, VLSI design, and GIS have been identified by many as the next generation of database applications. These new application areas pose serious challenges to the currently available database technology. At the core of these challenges is the nature of data that is manipulated. In traditional database applications, the database objects do not have any spatial dimension, and as such, can be thought of as point data in a multi-dimensional space. For example, each instance of an entity EMPLOYEE will have a unique value corresponding to every attribute such as employee id, employee name, employee address and so on. Thus, every Employee instance can be thought of as a point in a multi-dimensional space where each dimension is represented by an attribute. Furthermore, all operations on such data are one-dimensional. Thus, users may retrieve all entities satisfying one or more constraints. Examples of such constraints include employees with addresses in a certain area code, or salaries within a certain range. Even though constraints can be specified on multiple attributes (dimensions), the search for such data is essentially orthogonal across these dimensions.

Adam, Nabil↗

NASA NTRSDate not supplied

Sheaf Theoretic Models for Routing in Delay Tolerant Networks

One key to communications scalability is routing; as such the goal of this paper is to build upon successful efforts towards general routing for space-based networks. With the ever-increasing accessibility of space, the number of assets is increasing, which becomes a critical communications burden in terms of scheduling, spectrum allocation, and resource allocation. In order to mitigate these concerns, a true networking approach is necessary; a standard approach for space systems is Delay Tolerant Networking (DTN). For DTN to be a meaningful answer to the Solar System Internet (SSI) question, DTN must offer meaningful routing solutions that span the heterogeneous collection of links and nodes. This, in turn, depends on the general structure of these disconnected networks -- a structure that remains largely unknown. In ground communications networks, routing decisions are made based on several pathfinding algorithms working in tandem. In previous work, we modeled Dijkstra's pathfinding algorithm using sheaves and provided a more general framework for determining paths using sheaves over graphs. Continuing our sheaf-theoretic approach, we introduce here an expansion of our pathfinding sheaf to handle more general information, and we expand on additional pathfinding algorithms that can be represented using sheaves. Moreover, we demonstrate means of combining multiple algorithms into a single sheaf structure so that changes of scale can be presented in the language of sheaves. In addition, space communications networks rely upon radio transmitter antennas which can establish broadcast and multicast communications options, rather than the primarily unicast options available to wired networks. Last year, we also introduced a multicast routing sheaf for presenting broadcast, unicast, and multicast communications over a graph. Extending that work, we also introduce queuing sheaves so that we can blend these communications options together to simulate a variety of routing options across space networks. In addition, we include examples to illustrate the applicability of this abstract theory to routing in disconnected networks.

Robert Short↗

DOE OSTI2025

System Engineers and Decisions: It?s All about Knowledge

In order to guarantee that a system meets adequate levels of reliability and availability, system performances are continuously monitored and analyzed thanks to the technological advancements driving the Industry 4.0 revolution. An Industry 4.0 approach is typically based on advanced statistical, big data mining, machine learning, and internet-of-things methods designed to detect anomalies in the behavior of system, detect the most likely failure modes, and provide indications to system engineers on when maintenance activities should be performed before system performance are deemed unacceptable (which can be generated by diagnostic and prognostic methods). However, these analyses, which are designed to automatize and increase the efficacy of the system maintenance program, require large amount of data which can come in various forms: numeric, textual, images, sounds etc. Such data constitutes the historic knowledge benchmark to track system performances and support system engineer decisions. Here we claim that data is not sufficient to support this kind of analyses when applied to systems characterized by complex architectures and behaviors. Robust system engineer decisions require the ability to understand the system operational context that lies behind the observed data elements. In this respect, system models are in fact necessary to “put data in context” and capture relationships between data elements. Industry 4.0 methods require in fact contextual knowledge as a basis upon which hypotheses can be generated and assumptions tested. In our view, for complex systems, model-based system engineering (MBSE) models can afford this contextual knowledge, as they are typically used to describe systems architecture and dynamic behaviors. System knowledge is here intended as the blending of collected data and system architecture which takes the form of a “knowledge graph”. A knowledge graph is a database which consists of a large set of nodes (in our case an entity can be either a data or an MBSE element) which are linked to each other. The types of nodes and links follow a pre-defined topology, sometimes also refers as an ontology, that is designed to fit the actual decisions that needs to be performed. We show here how a knowledge graph can be defined to support system engineer maintenance decisions and how the same graph can be built based on system MBSE models and pre-processed data from numeric (through anomaly detections and diagnostic methods) and textual elements (through technical language processing TLP).

97 - MATHEMATICS AND COMPUTING↗

NASA NTRS1988

A new algorithm for modeling friction in dynamic mechanical systems

A method of modeling friction forces that impede the motion of parts of dynamic mechanical systems is described. Conventional methods in which the friction effect is assumed a constant force, or torque, in a direction opposite to the relative motion, are applicable only to those cases where applied forces are large in comparison to the friction, and where there is little interest in system behavior close to the times of transitions through zero velocity. An algorithm is described that provides accurate determination of friction forces over a wide range of applied force and velocity conditions. The method avoids the simulation errors resulting from a finite integration interval used in connection with a conventional friction model, as is the case in many digital computer-based simulations. The algorithm incorporates a predictive calculation based on initial conditions of motion, externally applied forces, inertia, and integration step size. The predictive calculation in connection with an external integration process provides an accurate determination of both static and Coulomb friction forces and resulting motions in dynamic simulations. Accuracy of the results is improved over that obtained with conventional methods and a relatively large integration step size is permitted. A function block for incorporation in a specific simulation program is described. The general form of the algorithm facilitates implementation with various programming languages such as FORTRAN or C, as well as with other simulation programs.

Hill, R. E.↗

NASA NTRS1994

Understanding software faults and their role in software reliability modeling

This study is a direct result of an on-going project to model the reliability of a large real-time control avionics system. In previous modeling efforts with this system, hardware reliability models were applied in modeling the reliability behavior of this system. In an attempt to enhance the performance of the adapted reliability models, certain software attributes were introduced in these models to control for differences between programs and also sequential executions of the same program. As the basic nature of the software attributes that affect software reliability become better understood in the modeling process, this information begins to have important implications on the software development process. A significant problem arises when raw attribute measures are to be used in statistical models as predictors, for example, of measures of software quality. This is because many of the metrics are highly correlated. Consider the two attributes: lines of code, LOC, and number of program statements, Stmts. In this case, it is quite obvious that a program with a high value of LOC probably will also have a relatively high value of Stmts. In the case of low level languages, such as assembly language programs, there might be a one-to-one relationship between the statement count and the lines of code. When there is a complete absence of linear relationship among the metrics, they are said to be orthogonal or uncorrelated. Usually the lack of orthogonality is not serious enough to affect a statistical analysis. However, for the purposes of some statistical analysis such as multiple regression, the software metrics are so strongly interrelated that the regression results may be ambiguous and possibly even misleading. Typically, it is difficult to estimate the unique effects of individual software metrics in the regression equation. The estimated values of the coefficients are very sensitive to slight changes in the data and to the addition or deletion of variables in the regression equation. Since most of the existing metrics have common elements and are linear combinations of these common elements, it seems reasonable to investigate the structure of the underlying common factors or components that make up the raw metrics. The technique we have chosen to use to explore this structure is a procedure called principal components analysis. Principal components analysis is a decomposition technique that may be used to detect and analyze collinearity in software metrics. When confronted with a large number of metrics measuring a single construct, it may be desirable to represent the set by some smaller number of variables that convey all, or most, of the information in the original set. Principal components are linear transformations of a set of random variables that summarize the information contained in the variables. The transformations are chosen so that the first component accounts for the maximal amount of variation of the measures of any possible linear transform; the second component accounts for the maximal amount of residual variation; and so on. The principal components are constructed so that they represent transformed scores on dimensions that are orthogonal. Through the use of principal components analysis, it is possible to have a set of highly related software attributes mapped into a small number of uncorrelated attribute domains. This definitively solves the problem of multi-collinearity in subsequent regression analysis. There are many software metrics in the literature, but principal component analysis reveals that there are few distinct sources of variation, i.e. dimensions, in this set of metrics. It would appear perfectly reasonable to characterize the measurable attributes of a program with a simple function of a small number of orthogonal metrics each of which represents a distinct software attribute domain.

Munson, John C.↗

DOE OSTI2024

Unsupervised multimodal fusion of in-process sensor data for advanced manufacturing process monitoring

Effective monitoring of manufacturing processes is crucial for maintaining product quality and operational efficiency. Modern manufacturing environments often generate vast amounts of complementary multimodal data, including visual imagery from various perspectives and resolutions, hyperspectral data, and machine health monitoring information such as actuator positions, accelerometer readings, and temperature measurements. However, fusing and interpreting this complex, high-dimensional data presents significant challenges, particularly when labeled datasets are unavailable or impractical to obtain. This paper presents a novel approach to multimodal sensor data fusion in manufacturing processes, inspired by the Contrastive Language-Image Pre-training (CLIP) model. We leverage contrastive learning techniques to correlate different data modalities without the need for labeled data, overcoming limitations of traditional supervised machine learning methods in manufacturing contexts. Our proposed method demonstrates the ability to handle and learn encoders for five distinct modalities: visual imagery, audio signals, laser position (x and y coordinates), and laser power measurements. By compressing these high-dimensional datasets into low-dimensional representational spaces, our approach facilitates downstream tasks such as process control, anomaly detection, and quality assurance. The unsupervised nature of our method makes it broadly applicable across various manufacturing domains, where large volumes of unlabeled sensor data are common. We evaluate the effectiveness of our approach through a series of experiments, demonstrating its potential to enhance process monitoring capabilities in advanced manufacturing systems. This research contributes to the field of smart manufacturing by providing a flexible, scalable framework for multimodal data fusion that can adapt to diverse manufacturing environments and sensor configurations. The proposed method paves the way for more robust, data-driven decision-making in complex manufacturing processes.

Contrastive Learning↗

NASA NTRS1992

Reuse: A knowledge-based approach

This paper describes our research in automating the reuse process through the use of application domain models. Application domain models are explicit formal representations of the application knowledge necessary to understand, specify, and generate application programs. Furthermore, they provide a unified repository for the operational structure, rules, policies, and constraints of a specific application area. In our approach, domain models are expressed in terms of a transaction-based meta-modeling language. This paper has described in detail the creation and maintenance of hierarchical structures. These structures are created through a process that includes reverse engineering of data models with supplementary enhancement from application experts. Source code is also reverse engineered but is not a major source of domain model instantiation at this time. In the second phase of the software synthesis process, program specifications are interactively synthesized from an instantiated domain model. These specifications are currently integrated into a manual programming process but will eventually be used to derive executable code with mechanically assisted transformations. This research is performed within the context of programming-in-the-large types of systems. Although our goals are ambitious, we are implementing the synthesis system in an incremental manner through which we can realize tangible results. The client/server architecture is capable of supporting 16 simultaneous X/Motif users and tens of thousands of attributes and classes. Domain models have been partially synthesized from five different application areas. As additional domain models are synthesized and additional knowledge is gathered, we will inevitably add to and modify our representation. However, our current experience indicates that it will scale and expand to meet our modeling needs.

Iscoe, Neil↗