Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “AI system”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 721 records · Page 40
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

QoS-aware edge AI placement and scheduling with multiple implementations in FaaS-based edge computing

Resource constraints on the computing continuum require that we make smart decisions for serving AI-based services at the network edge. AI-based services typically have multiple implementations (e.g., image classification implementations include SqueezeNet, DenseNet, and others) with varying trade-offs (e.g., latency and accuracy). The question then is how should AI-based services be placed across Function-as-a-Service (FaaS) based edge computing systems in order to maximize total Quality-of-Service (QoS). To address this question, we propose a problem that jointly aims to solve (i) edge AI service placement and (ii) request scheduling. These are done across two time-scales (one for placement and one for scheduling). Here we first cast the problem as an integer linear program. We then decompose the problem into separate placement and scheduling subproblems and prove that both are NP-hard. We then propose a novel placement algorithm that places services while considering device-to-device communication across edge clouds to offload requests to one another. Our results show that the proposed placement algorithm is able to outperform a state-of-the-art placement algorithm for AI-based services, and other baseline heuristics, with regard to maximizing total QoS. Additionally, we present a federated learning-based framework, FLIES, to predict the future incoming service requests and their QoS requirements. Our results also show that our FLIES algorithm is able to outperform a standard decentralized learning baseline for predicting incoming requests and show comparable predictive performance when compared to centralized training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Toward a Holistic Performance Evaluation of Large Language Models Across Diverse AI Accelerators

Artificial intelligence (AI) methods have become critical in scientific applications to help accelerate scientific discovery. Large language models (LLMs) are being considered a promising approach to address some challenging problems because of their superior generalization capabilities across domains. The effectiveness of the models and the accuracy of the applications are contingent upon their efficient execution on the underlying hardware infrastructure. Specialized Al accelerator hardware systems have recently become available for accelerating Al applications. However, the comparative performance of these AI accelerators on large language models has not been previously studied. In this paper, we systematically study LLMs on multiple AI accelerators and GPUs and evaluate their performance characteristics for these models. We evaluate these systems with (i) a micro-benchmark using a core transformer block, (ii) a GPT-2 model, and (iii) an 1,I,M-driven science use case, GenSLM. We present our findings and analyses of the models' performance to better understand the intrinsic capabilities of AI accelerators. Furthermore, our analysis takes into account key factors such as sequence lengths, scaling behavior, and sensitivity to gradient accumulation steps.

Emani, Murali↗
NASA NTRS1990

The application of connectionism to query planning/scheduling in intelligent user interfaces

In the mid nineties, the Earth Observing System (EOS) will generate an estimated 10 terabytes of data per day. This enormous amount of data will require the use of sophisticated technologies from real time distributed Artificial Intelligence (AI) and data management. Without regard to the overall problems in distributed AI, efficient models were developed for doing query planning and/or scheduling in intelligent user interfaces that reside in a network environment. Before intelligent query/planning can be done, a model for real time AI planning and/or scheduling must be developed. As Connectionist Models (CM) have shown promise in increasing run times, a connectionist approach to AI planning and/or scheduling is proposed. The solution involves merging a CM rule based system to a general spreading activation model for the generation and selection of plans. The system was implemented in the Rochester Connectionist Simulator and runs on a Sun 3/260.

Short, Nicholas, Jr.↗
DOE OSTI2021

TCR Data Management Plan

The Oak Ridge National Laboratory (ORNL) Transformation Challenge Reactor (TCR) program is developing additive manufacturing and artificial intelligence (AI) to deliver enabling technologies for advanced reactors. Through the application of these advanced technologies, the program targets delivering solutions to the high costs and lengthy deployment timelines that threaten the future of nuclear energy—the country’s largest source of carbon-free energy. This document describes the plan for integrating and managing TCR data from multiple sources throughout ORNL and external sources, including novel data sources associated with advanced manufacturing, characterization systems, and the TCR Digital Platform that incorporates various levels of AI and data analytics.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRS2003

Application of Artificial Intelligence Techniques in Unmanned Aerial Vehicle Flight

This paper describes the development of an application of Artificial Intelligence for Unmanned Aerial Vehicle (UAV) control. The project was done as part of the requirements for a class in Artificial Intelligence (AI) at Nova southeastern University and as an adjunct to a project at NASA Goddard Space Flight Center's Wallops Flight Facility for a resilient, robust, and intelligent UAV flight control system. A method is outlined which allows a base level application for applying an AI method, Fuzzy Logic, to aspects of Control Logic for UAV flight. One element of UAV flight, automated altitude hold, has been implemented and preliminary results displayed. A low cost approach was taken using freeware, gnu, software, and demo programs. The focus of this research has been to outline some of the AI techniques used for UAV flight control and discuss some of the tools used to apply AI techniques. The intent is to succeed with the implementation of applying AI techniques to actually control different aspects of the flight of an UAV.

Bauer, Frank H.↗
NASA NTRS1985

Development of an Expert System for Representing Procedural Knowledge

A high level of automation is of paramount importance in most space operations. It is critical for unmanned missions and greatly increases the effectiveness of manned missions. However, although many functions can be automated by using advanced engineering techniques, others require complex reasoning, sensing, and manipulatory capabilities that go beyond this technology. Automation of fault diagnosis and malfunction handling is a case in point. The military have long been interested in this problem, and have developed automatic test equipment to aid in the maintenance of complex military hardware. These systems are all based on conventional software and engineering techniques. However, the effectiveness of such test equipment is severely limited. The equipment is inflexible and unresponsive to the skill level of the technicians using it. The diagnostic procedures cannot be matched to the exigencies of the current situation nor can they cope with reconfiguration or modification of the items under test. The diagnosis cannot be guided by useful advice from technicians and, when a fault cannot be isolated, no explanation is given as to the cause of failure. Because these systems perform a prescribed sequence of tests, they cannot utilize knowledge of a particular situation to focus attention on more likely trouble spots. Consequently, real-time performance is highly unsatisfactory. Furthermore, the cost of developing test software is substantial and time to maturation is excessive. Significant advances in artificial intelligence (AI) have recently led to the development of powerful and flexible reasoning systems, known as expert or knowledge-based systems. We have devised a powerful and theoretically sound scheme for representing and reasoning about procedural knowledge.

Georgeff, Michael P.↗
DOE OSTI2026

Storing Affordability: Battery Storage as an Asset to Reduce Data Center Cost Shifts

This report examines how battery energy storage systems (BESS) can help utilities accommodate large load growth while protecting affordability for existing ratepayers. Rapid growth in electricity demand from artificial intelligence (AI) data centers is straining the U.S. grid. Furthermore, many new data centers are entering rural markets, which could offer economic benefits but may also pose implementation challenges for smaller utilities. At the same time, retail electricity prices are increasing faster than inflation, elevating customer affordability as a key challenge. While data centers have not been the primary driver of increases in residential prices to date, they have pushed wholesale energy and capacity prices higher in several markets. Fundamental utility cost-allocation principles show that data center growth can be rate-positive for existing customers only if new peak demand grows faster than the costs a utility must incur to serve it. Several factors, including a utility’s degree of wholesale market exposure, forecast uncertainty and stranded-asset risk, and tariff design can determine the outcome of load growth on retail rates. Energy storage can make several affordability contributions in the face of this landscape of uncertainty and market volatility, including deferral of higher-cost grid investments through improved utilization of existing assets and flexibility of new large loads, insulation from volatile wholesale prices through peak shaving, and reliability support to address grid risks stemming from the behavior of AI data center loads. Different potential BESS deployment pathways—utility-scale front-of-the-meter systems, aggregated small-scale storage installations, and data center-sited behind-the-meter storage—are compared against each other and against conventional capacity alternatives. This framework is intended as a conceptual resource to utilities, particularly smaller public utilities with rural service territories, who may be considering the role that energy storage can play in insulating existing ratepayers from data center cost shifts.

25 ENERGY STORAGE↗
DOE OSTI2023

Developing an AI-Powered Zero-Trust Cybersecurity Framework for Malware Prevention in Nuclear Power Plants

This study presents the development of an AI-powered Zero-Trust cybersecurity framework for malware prevention in nuclear power plants. The framework aims to enhance the security of critical systems within nuclear power plants by adopting the principles of Zero-Trust and leveraging artificial intelligence (AI) technologies. By assuming no implicit trust in any user or device and continuously authenticating and authorizing access, the framework ensures a robust defense against malware attacks. The integration of AI allows for the detection and prevention of malware through behavioral analytics, endpoint protection, network segmentation, and continuous monitoring. The paper discusses the key considerations, steps, and technologies involved in developing this framework, emphasizing the importance of regular updates, training, compliance, and auditing. The proposed framework serves as a comprehensive approach to safeguarding nuclear power plants from sophisticated malware threats and protecting the integrity and safety of critical infrastructure.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRS1991

Using C to build a satellite scheduling expert system: Examples from the Explorer platform planning system

Recently, many expert systems were developed in a LISP environment and then ported to the real world C environment before the final system is delivered. This situation may require that the entire system be completely rewritten in C and may actually result in a system which is put together as quickly as possible with little regard for maintainability and further evolution. With the introduction of high performance UNIX and X-windows based workstations, a great deal of the advantages of developing a first system in the LISP environment have become questionable. A C-based AI development effort is described which is based on a software tools approach with emphasis on reusability and maintainability of code. The discussion starts with simple examples of how list processing can easily be implemented in C and then proceeds to the implementations of frames and objects which use dynamic memory allocation. The implementation of procedures which use depth first search, constraint propagation, context switching and a blackboard-like simulation environment are described. Techniques for managing the complexity of C-based AI software are noted, especially the object-oriented techniques of data encapsulation and incremental development. Finally, all these concepts are put together by describing the components of planning software called the Planning And Resource Reasoning (PARR) shell. This shell was successfully utilized for scheduling services of the Tracking and Data Relay Satellite System for the Earth Radiation Budget Satellite since May 1987 and will be used for operations scheduling of the Explorer Platform in November 1991.

Mclean, David R.↗
DOE OSTI2021

In Situ Inference for Earth System Predictability

Focal Area: Focal Area 3: Insight gleaned from complex simulated data using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge-guided AI. Science Challenge: An understanding of future evolution in precipitation extremes is critical to numerous DOE mission questions. Extreme events are by nature short time-scale events that are difficult to diagnose in available model data. Accurate modeling of extreme events necessarily requires high spatial resolution at the storm scale locally. However, the environment in which storms grow is dependent on global, remote, processes. These complex spatiotemporal relationships are impossible to diagnose at resolutions required to accurately model storms responsible for extreme precipitation. At exascale, climate simulations will produce results at fine enough resolution to investigate these relationships. However, the resulting data from these simulations will be far too large to save for post-simulation analysis. We advocate for fitting statistical models inside the simulations as they run, a context known as in situ, which will facilitate scientific investigations using the full fine-scale data stream. Figure 1 shows an example of the type of model we could consider, a Bayesian hierarchical spatial regression model. Precipitation extremes at each grid cell are modeled using extreme value distributions. Since extremes are rare, fitting models to individual grid cells can result in high variance and poor estimates. Instead, the model can be made more robust by smoothing the parameters of the extreme value model across space. Additionally, the parameters themselves can be functionally linked to other variables elsewhere in the simulation. Thus, we can use the fine-scale data to build more robust models for extremes that link extreme behavior to other climate patterns.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1993

The computer integrated documentation project: A merge of hypermedia and AI techniques

To generate intelligent indexing that allows context-sensitive information retrieval, a system must be able to acquire knowledge directly through interaction with users. In this paper, we present the architecture for CID (Computer Integrated Documentation). CID is a system that enables integration of various technical documents in a hypertext framework and includes an intelligent browsing system that incorporates indexing in context. CID's knowledge-based indexing mechanism allows case based knowledge acquisition by experimentation. It utilizes on-line user information requirements and suggestions either to reinforce current indexing in case of success or to generate new knowledge in case of failure. This allows CID's intelligent interface system to provide helpful responses, based on previous experience (user feedback). We describe CID's current capabilities and provide an overview of our plans for extending the system.

Mathe, Nathalie↗
NASA NTRS1996

Immobile Robots: AI in the New Millennium

A new generation of sensor rich, massively distributed, autonomous systems are being developed that have the potential for profound social, environmental, and economic change. These include networked building energy systems, autonomous space probes, chemical plant control systems, satellite constellations for remote ecosystem monitoring, power grids, biosphere-like life support systems, and reconfigurable traffic systems, to highlight but a few. To achieve high performance, these immobile robots (or immobots) will need to develop sophisticated regulatory and immune systems that accurately and robustly control their complex internal functions. To accomplish this, immobots will exploit a vast nervous system of sensors to model themselves and their environment on a grand scale. They will use these models to dramatically reconfigure themselves in order to survive decades of autonomous operations. Achieving these large scale modeling and configuration tasks will require a tight coupling between the higher level coordination function provided by symbolic reasoning, and the lower level autonomic processes of adaptive estimation and control. To be economically viable they will need to be programmable purely through high level compositional models. Self modeling and self configuration, coordinating autonomic functions through symbolic reasoning, and compositional, model-based programming are the three key elements of a model-based autonomous systems architecture that is taking us into the New Millennium.

Williams, Brian C.↗
DOE OSTI2021

Learning from learning machines: improving the predictive power of energy-water-land nexus models with insights from complex measured and simulated data

Focal Area(s): Insights gleaned from complex data (observed and simulated) using AI; Predictive modeling through the use of AI techniques and AI-derived model components, including physics- and knowledge-informed models; Energy-water-land nexus and integrated energy systems – models of MultiSector dynamics. Science Challenge: Scientific communities are in need of tools for the computational integration of physics-based models, experimental data, and empirical/observational studies across a broad range of temporal and spatial scales to explore and meet EESSD grand challenges. We require AI algorithms for the discovery of process-drivers in the Earth-energy-human system and to link them with complex measured and simulated data. We aim to understand the energy-water-land nexus, particularly under extreme forcing scenarios and rare events, leveraging scale-aware AI process models, including probabilistic uncertainties, and benefiting from the emerging 5G-enabled landscape-scale sensing and edge computing capabilities. These models are needed to identify instabilities and tipping points that manifest extreme system behaviors with consequences for integrated energy systems and the environment. This work requires fundamental advances in uncertainty quantification, in particular, to identify and model unlikely but catastrophic outliers. Specifically, we need models that are interpretable to domain scientists and, essentially, explainable to public and private stake holders.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1985

STAR (Simple Tool for Automated Reasoning): Tutorial guide and reference manual

STAR is an interactive, interpreted programming language for the development and operation of Artificial Intelligence application systems. The language is intended for use primarily in the development of software application systems which rely on a combination of symbolic processing, central to the vast majority of AI algorithms, with routines and data structures defined in compiled languages such as C, FORTRAN and PASCAL. References to routines and data structures defined in compiled languages are intermixed with symbolic structures in STAR, resulting in a hybrid operating environment in which symbolic and non-symbolic processing and organization of data may interact to a high degree within the execution of particular application systems. The STAR language was developed in the course of a project involving AI techniques in the interpretation of imaging spectrometer data and is derived in part from a previous language called CLIP. The interpreter for STAR is implemented as a program defined in the language C and has been made available for distribution in source code form through NASA's Computer Software Management and Information Center (COSMIC). Contained within this report are the STAR Tutorial Guide, which introduces the language in a step-by-step manner, and the STAR Reference Manual, which provides a detailed summary of the features of STAR.

Borchardt, G. C.↗
DOE OSTI2024

AI-assisted detector design for the EIC (AID(2)E)

Artificial Intelligence is poised to transform the design of complex, large-scale detectors like ePIC at the future Electron Ion Collider. Featuring a central detector with additional detecting systems in the far forward and far backward regions, the ePIC experiment incorporates numerous design parameters and objectives, including performance, physics reach, and cost, constrained by mechanical and geometric limits. This project aims to develop a scalable, distributed AI-assisted detector design for the EIC (AID(2)E), employing state-of-the-art multiobjective optimization to tackle complex designs. Supported by the ePIC software stack and using G EANT 4 simulations, our approach benefits from transparent parameterization and advanced AI features. The workflow leverages the PanDA and iDDS systems, used in major experiments such as ATLAS at CERN LHC, the Rubin Observatory, and sPHENIX at RHIC, to manage the compute intensive demands of ePIC detector simulations. Tailored enhancements to the PanDA system focus on usability, scalability, automation, and monitoring. Ultimately, this project aims to establish a robust design capability, apply a distributed AI-assisted workflow to the ePIC detector, and extend its applications to the design of the second detector (Detector-2) in the EIC, as well as to calibration and alignment tasks. Additionally, we are developing advanced data science tools to efficiently navigate the complex, multidimensional trade-offs identified through this optimization process.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Learning dynamical systems from data: An introduction to physics-guided deep learning

Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expensive numerical integration, requiring significant computational resources and domain expertise. While deep learning (DL) provides efficient alternatives for modeling complex dynamics, they require a large amount of labeled training data. Furthermore, its predictions may disobey the governing physical laws and are difficult to interpret. Physics-guided DL aims to integrate first-principled physical knowledge into data-driven methods. It has the best of both worlds and is well equipped to better solve scientific problems. Recently, this field has gained great progress and has drawn considerable interest across discipline Here, we introduce the framework of physics-guided DL with a special emphasis on learning dynamical systems. We describe the learning pipeline and categorize state-of-the-art methods under this framework. We also offer our perspectives on the open challenges and emerging opportunities.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1988

Expert system validation in prolog

An overview of the Expert System Validation Assistant (EVA) is being implemented in Prolog at the Lockheed AI Center. Prolog was chosen to facilitate rapid prototyping of the structure and logic checkers and since February 1987, we have implemented code to check for irrelevance, subsumption, duplication, deadends, unreachability, and cycles. The architecture chosen is extremely flexible and expansible, yet concise and complementary with the normal interactive style of Prolog. The foundation of the system is in the connection graph representation. Rules and facts are modeled as nodes in the graph and arcs indicate common patterns between rules. The basic activity of the validation system is then a traversal of the connection graph, searching for various patterns the system recognizes as erroneous. To aid in specifying these patterns, a metalanguage is developed, providing the user with the basic facilities required to reason about the expert system. Using the metalanguage, the user can, for example, give the Prolog inference engine the goal of finding inconsistent conclusions among the rules, and Prolog will search the graph intantiations which can match the definition of inconsistency. Examples of code for some of the checkers are provided and the algorithms explained. Technical highlights include automatic construction of a connection graph, demonstration of the use of metalanguage, the A* algorithm modified to detect all unique cycles, general-purpose stacks in Prolog, and a general-purpose database browser with pattern completion.

Stock, Todd↗
DOE OSTI2025

Informing Plant Asset Reliability and Availability Through AI-Driven Analysis of Operator Logs

The availability and reliability of nuclear power plant (NPP) structures, systems, and components (SSCs) are critical parameters for NPP safety. Tracking these parameters is necessary but costly and labor-intensive, requiring the collection and evaluation of SSC event data such as shutdowns, startups, and failures. To show how these events are needed for the parameters an example is given: one measure of reliability is based on the number of equipment failure events and the number of run hours (i.e., the time from a startup event to a shutdown event). Here, this work investigates using artificial intelligence (AI) to mine NPP operator log entry texts for SSC event data. Four AI approaches were explored for identifying these events, including natural language processing (NLP) methods, generative AI, generative AI combined with NLP, and topic modeling. A key challenge addressed with all four approaches is the brevity of operator log entries. Among these four a neural network–based NLP method was shown to be the most promising for this application, achieving F1 scores of 86.0% for shutdowns, 92.2% for startups, and 80.4% for failures on a subject-matter-expert-curated dataset from NPP operator logs, compared to a baseline of 66.6% for a random classifier. This shows that NLP methods can perform better than generative AI. Additionally, the NLP methods combined with generative AI were shown to perform better than generative AI alone. Generative AI was most successful at providing the background information for the NLP methods to use. This work demonstrates the potential to use AI to automate parameter collection from NPP operator log entries and other records.

97 - MATHEMATICS AND COMPUTING↗