Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “AI hardware”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities

Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an x-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instruments and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex—a synthetic extension to the cognition of scientists—may radically transform scientific practice and discovery.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Hardware-in-the-Loop Evaluation for Potential High Limit Estimation-Based PV Plant Active Control: Preprint

This paper validates the effectiveness of an Artificial Intelligence (AI)-driven PV plant control and optimization approach, namely, the Automated Learner for Intermittency Control by Extrapolation (ALICE), in empowering PV plant as a dependable grid reliability service provider. The validation is performed in a realistic laboratory controller-hardware-in-the-loop (CHIL) environment, leveraging accurate PV plant modeling and standard industrial communication protocol. Simulation results, considering both varying weather conditions and active control scenarios, demonstrate the superior performance of ALICE in improving the grid service delivery precision and reducing the over-curtailment compared to a state-of-the-art approach, i.e., reference-control grouping based approach. Such a work could help mitigate risks and provide practical guidance during the field deployment of ALICE, while establishing a standardized testing framework for evaluating various PV active control strategies.

hardware-in-the-loop↗
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↗
DOE OSTI2021

Considerations regarding the Use of Computer Vision Machine Learning in Safety-Related or Risk-Significant Applications in Nuclear Power Plants

With the advancements made to date in the field of artificial intelligence (AI), significant potential exists to utilize AI capabilities for nuclear power plant (NPP) applications. AI can replicate human decision making and it is usually faster and more accurate than humans. For implementations that impact critical NPP applications (e.g., safety-related or non-safety systems that potentially affect overall plant risk), a deeper safety analysis of the AI methods is necessary. AI applied to NPP operations could resemble the use of digital I&C (DI&C) because such applications involve digital computer hardware and custom-designed software that input plant data, execute complex software algorithms, and output the results to a system or licensed human operator to potentially provoke an action. For AI methods to be compliant with current safety requirements for DI&C, AI compatibility must be evaluated, and AI-related gaps may exist that prevent the prompt deployment of AI in NPPs. This effort aims to evaluate how example AI technologies align with the DI&C safety framework, and discusses how they could be analyzed, modeled, tested, and validated in a manner similar to typical DI&C technologies. Because AI is a broad field that encompasses areas such as machine learning (ML), natural language processing, and computer vision, this research focused on a subset of methods categorized as the computer vision ML (CVML) methods. This report explores two CVML use cases, gauge reading and fire watch, considered relevant to the DI&C standards, as they could play a safety-critical role. For the gauge reading use case, a CVML-enabled technology that can read gauges at oblique angles is utilized. For the fire watch use case, a CVML-enabled technology is utilized that migrates fire watch from a manual (human) approach to automated fire detection. These use cases are mainly intended to give context to the CVML system discussion. This effort assumes the worst-case scenario, with the CVML system being used to replace a safety-related or risk-significant system, thus requiring evaluation. Evaluating CVML against most of the relevant safety requirements for DI&C yielded several CVML-specific considerations due to the uniqueness of its characteristics in comparison with typical DI&C systems. For example, CVML models often employ commonly used (open-source) datasets, and it is not always possible to determine the level of overlap among open-source datasets. Therefore, the independence of the developed CVML models when demonstrating diversity is questionable, therefore creating vulnerability to common cause failure (CCF). The design verification process is also impacted since the data overlap could result in overestimation of the software validation and verification (V&V) performance results. Section 2 of this report evaluates a list of the identified CVML-specific characteristics and discusses the resulting considerations and potential solutions in the context of each referenced requirement. A summation is provided in Section 3. This report is not to be used as a guideline. It was developed to identify and consider issues in the implementation of ML technologies used to augment activities that may have a bearing on plant operation. The report draws parallels to the use of DI&C technologies, for which many standards are available to guide their use in nuclear plant operation. It considers the technologies and some of the potential implications of their use in safety-related applications but is not intended to address regulatory or licensing related issues.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

A Self-Evolution Data Fusion Platform for Large-Scale Water Models

Focal Area: Data acquisition and assimilation enabled by machine learning (ML), artificial intelligence (AI), and advanced methods including experimental/network design/optimization, unsupervised learning (deep learning), leveraging advanced hardware (e.g., edge computing). This development is to enable solving the science questions regarding the human and climatic factors that interact with and drive global water scarcity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Artificial Intelligence for Autonomous Molecular Design: A Perspective

Domain-aware artificial intelligence has been increasingly adopted in recent years to expedite molecular design in various applications, including drug design and discovery. Recent advances in areas such as physics-informed machine learning and reasoning, software engineering, high-end hardware development, and computing infrastructures are providing opportunities to build scalable and explainable AI molecular discovery systems. This could improve a design hypothesis through feedback analysis, data integration that can provide a basis for the introduction of end-to-end automation for compound discovery and optimization, and enable more intelligent searches of chemical space. Several state-of-the-art ML architectures are predominantly and independently used for predicting the properties of small molecules, their high throughput synthesis, and screening, iteratively identifying and optimizing lead therapeutic candidates. However, such deep learning and ML approaches also raise considerable conceptual, technical, scalability, and end-to-end error quantification challenges, as well as skepticism about the current AI hype to build automated tools. To this end, synergistically and intelligently using these individual components along with robust quantum physics-based molecular representation and data generation tools in a closed-loop holds enormous promise for accelerated therapeutic design to critically analyze the opportunities and challenges for their more widespread application. This article aims to identify the most recent technology and breakthrough achieved by each of the components and discusses how such autonomous AI and ML workflows can be integrated to radically accelerate the protein target or disease model-based probe design that can be iteratively validated experimentally. Taken together, this could significantly reduce the timeline for end-to-end therapeutic discovery and optimization upon the arrival of any novel zoonotic transmission event. Our article serves as a guide for medicinal, computational chemistry and biology, analytical chemistry, and the ML community to practice autonomous molecular design in precision medicine and drug discovery.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRSDate not supplied

Relevant Environment Additive Construction Technology (REACT)

Project Overview This project is focused on developing technologies that enable construction of a Lunar Safe Haven type structure on the moon. A full scale architectural and structural design will be completed based on lunar conditions and Artemis mission needs. A scaled structure will be 3D printed in simulated lunar environments. Technical Approach Polymer bound regolith composite materials will be developed and characterized for lunar additive construction applications. A full scale architectural and structural design will be completed based on the latest scientific data on lunar environments including radiation, meteoroids, thermal conditions, reduced gravity, and moonquakes. The project will culminate with a demonstration of additive construction in simulated lunar vacuum, thermal, regolith, and UV conditions. Results/Summary Preliminary material specifications have been developed and an initial batch has been produced. A first iteration of the architectural and structural designs have been completed. Hardware for 3D printing in simulated lunar conditions is under development. Contributing Partners AI Space Factory – Winner of the NASA 3D Printed Habitat Centennial Challenge Infusion and Transition Plan On-surface construction of infrastructure is a critical capability of the sustainable phase of the Artemis Program and eventual sustainable human presence on Mars. It provides the ability to create protective shelters on-demand using local resources. The 3D-printing technology will achieve TRL 6 in 1g/vacuum tests with thermal/UV exposure in this project. CLPS missions will be pursued for infusion to demonstrate vertical construction with lunar regolith and conditions. Modeling and simulation will be used to define the pilot-scale shelter construction mission for long-term exposure on the lunar surface to validate the system for Artemis operational deployment.

Lunar Construction↗
NASA NTRS2007

Real-Time Data Display

RT-Display is a MATLAB-based data acquisition environment designed to use a variety of commercial off-the-shelf (COTS) hardware to digitize analog signals to a standard data format usable by other post-acquisition data analysis tools. This software presents the acquired data in real time using a variety of signal-processing algorithms. The acquired data is stored in a standard Operator Interactive Signal Processing Software (OISPS) data-formatted file. RT-Display is primarily configured to use the Agilent VXI (or equivalent) data acquisition boards used in such systems as MIDDAS (Multi-channel Integrated Dynamic Data Acquisition System). The software is generalized and deployable in almost any testing environment, without limitations or proprietary configuration for a specific test program or project. With the Agilent hardware configured and in place, users can start the program and, in one step, immediately begin digitizing multiple channels of data. Once the acquisition is completed, data is converted into a common binary format that also can be translated to specific formats used by external analysis software, such as OISPS and PC-Signal (product of AI Signal Research Inc.). RT-Display at the time of this reporting was certified on Agilent hardware capable of acquisition up to 196,608 samples per second. Data signals are presented to the user on-screen simultaneously for 16 channels. Each channel can be viewed individually, with a maximum capability of 160 signal channels (depending on hardware configuration). Current signal presentations include: time data, fast Fourier transforms (FFT), and power spectral density plots (PSD). Additional processing algorithms can be easily incorporated into this environment.

Pedings, Marc↗
NASA NTRS1990

Space Station module Power Management And Distribution (PMAD) system

This project consists of several tasks which are unified toward experimentally demonstrating the operation of a highly autonomous, user-supportive power management and distribution system for Space Station Freedom (SSF) habitation/laboratory modules. This goal will be extended to a demonstration of autonomous, cooperative power system operation for the whole SSF power system through a joint effort with NASA's Lewis Research Center, using their Autonomous Power System. Short term goals for the space station module power management and distribution include having an operational breadboard reflecting current plans for SSF, improving performance of the system communications, and improving the organization and mutability of the artificial intelligence (AI) systems. In the middle term, intermediate levels of autonomy will be added, user interfaces will be modified, and enhanced modeling capabilities will be integrated in the system. Long term goals involve conversion of all software into Ada, vigorous verification and validation efforts and, finally, seeing an impact of this research on the operation of SSF. Conversion of the system to a DC Star configuration is now in progress, and should be completed by the end of October, 1989. This configuration reflects the latest SSF module architecture. Hardware is now being procured which will improve system communications significantly. The Knowledge-Based Management System (KBMS) is initially developed and the rules from FRAMES have been implemented in the KBMS. Rules in the other two AI systems are also being grouped modularly, making them more tractable, and easier to eventually move into the KBMS. Adding an intermediate level of autonomy will require development of a planning utility, which will also be built using the KBMS. These changes will require having the user interface for the whole system available from one interface. An Enhanced Model will be developed, which will allow exercise of the system through the interface without requiring all of the power hardware to be operational. The functionality of the AI systems will continue to be advanced, including incipient failure detection. Ada conversion will begin with the lowest level processor (LLP) code. Then selected pieces of the higher level functionality will be recorded in Ada and, where possible, moved to the LLP level. Validation and verification will be done on the Ada code, and will complete sometimes after completion of the Ada conversion.

Walls, Bryan↗
NASA NTRS1991

Human factors issues in the use of artificial intelligence in air traffic control. October 1990 Workshop

The objective of the workshop was to explore the role of human factors in facilitating the introduction of artificial intelligence (AI) to advanced air traffic control (ATC) automation concepts. AI is an umbrella term which is continually expanding to cover a variety of techniques where machines are performing actions taken based upon dynamic, external stimuli. AI methods can be implemented using more traditional programming languages such as LISP or PROLOG, or they can be implemented using state-of-the-art techniques such as object-oriented programming, neural nets (hardware or software), and knowledge based expert systems. As this technology advances and as increasingly powerful computing platforms become available, the use of AI to enhance ATC systems can be realized. Substantial efforts along these lines are already being undertaken at the FAA Technical Center, NASA Ames Research Center, academic institutions, industry, and elsewhere. Although it is clear that the technology is ripe for bringing computer automation to ATC systems, the proper scope and role of automation are not at all apparent. The major concern is how to combine human controllers with computer technology. A wide spectrum of options exists, ranging from using automation only to provide extra tools to augment decision making by human controllers to turning over moment-by-moment control to automated systems and using humans as supervisors and system managers. Across this spectrum, it is now obvious that the difficulties that occur when tying human and automated systems together must be resolved so that automation can be introduced safely and effectively. The focus of the workshop was to further explore the role of injecting AI into ATC systems and to identify the human factors that need to be considered for successful application of the technology to present and future ATC systems.

Hockaday, Stephen↗
DOE OSTI2026

Smart Hydro: AI Applications

This presentation provides an overview of artificial intelligence (AI) applications in hydropower.

13 HYDRO ENERGY↗
DOE OSTI2024

Intelligent Hierarchical Resilient Operation of Distribution Systems: Implementation and Validation in a Power Hardware-in-the-Loop Simulation Testbed

This paper reports on the structure of a power hardware-in-the-loop (PHIL) simulation testbed that implements, tests, and validates a novel AI-based hierarchical resilient operation model for distribution systems. The testbed implements the central and distributed controllers of the hierarchical resilient operation model and integrates a Digital Real-Time Simulator (DRTS), protective relays, a Real-Time Automation Controller (RTAC), a Software Defined Network (SDN) switch, and a battery energy storage (BES) system. The testbed provides comprehensive real-time visualization and monitoring capability as an advanced situational awareness and operator interface solution. The IEEE 33-node system is used as a test case to test and validate the operation of the model in normal operation and recovery operation after major outages in a fully automated fashion.

Ganjkhani, Mehdi↗
NASA NTRS1991

Robotic control and inspection verification

Three areas of possible commercialization involving robots at the Kennedy Space Center (KSC) are discussed: a six degree-of-freedom target tracking system for remote umbilical operations; an intelligent torque sensing end effector for operating hand valves in hazardous locations; and an automatic radiator inspection device, a 13 by 65 foot robotic mechanism involving completely redundant motors, drives, and controls. Aspects concerning the first two innovations can be integrated to enable robots or teleoperators to perform tasks involving orientation and panal actuation operations that can be done with existing technology rather than waiting for telerobots to incorporate artificial intelligence (AI) to perform 'smart' autonomous operations. The third robot involves the application of complete control hardware redundancy to enable performance of work over and near expensive Space Shuttle hardware. The consumer marketplace may wish to explore commercialization of similiar component redundancy techniques for applications when a robot would not normally be used because of reliability concerns.

Davis, Virgil Leon↗
NASA NTRS1990

ART/Ada and CLIPS/Ada

Although they have reached a point of commercial viability, expert systems were originally developed in artificial intelligence (AI) research environments. Many of the available tools still work best in such environments. These environments typically utilize special hardware such as LISP machines and relatively unfamiliar languages such as LISP or Prolog. Space Station applications will require deep integration of expert system technology with applications developed in conventional languages, specifically Ada. The ability to apply automation to Space Station functions could be greatly enhanced by widespread availability of state-of-the-art expert system tools based on Ada. Although there have been some efforts to examine the use of Ada for AI applications, there are few, if any, existing products which provide state-of-the-art AI capabilities in an Ada tool. The goal of the ART/Ada Design Project is to conduct research into the implementation in Ada of state-of-the-art hybrid expert systems building tools (ESBT's). This project takes the following approach: using the existing design of the ART-IM ESBT as a starting point, analyze the impact of the Ada language and Ada development methodologies on that design; redesign the system in Ada; and analyze its performance. The research project will attempt to achieve a comprehensive understanding of the potential for embedding expert systems in Ada systems for eventual application in future Space Station Freedom projects. During Phase 1 of the project, initial requirements analysis, design, and implementation of the kernel subset of ART-IM functionality was completed. During Phase 2, the effort has been focused on the implementation and performance analysis of several versions with increasing functionality. Since production quality ART/Ada tools will not be available for a considerable time, and additional subtask of this project will be the completion of an Ada version of the CLIPS expert system shell developed by NASA. This tool will provide full syntactic compatibility with any eventual products of the ART/Ada design while allowing SSFP developers early access to this technology.

Culbert, Chris↗
NASA NTRSDate not supplied

A NASA Perspective on Quantum AI, Error Correction, and Beyond

Quantum computing is one of the most enticing computational paradigms with the potential to revolutionize diverse areas of future-generation computational systems. While quantum computing hardware has advanced rapidly, from tiny laboratory experiments to quantum chips that can outperform even the largest supercomputers on specialized computational tasks, these noisy-intermediate scale quantum (NISQ) processors are still too small and non-robust to be directly useful for any real-world applications. We discuss the prospects for quantum computing and AI, highlighting advances in algorithms, both near- and longer-term. Quantum error correction is critical to the realization of any such vision. The talk with touch on some recent exciting advanced in quantum error correction, particularly in dynamical codes. The talk will conclude with an example of how the combination of quantum computing and artificial intelligence can help probe fundamental aspect of quantum physics.

quantum optimization algorithms and sampling↗
DOE OSTI2026

Flexible AI Models for Grid Resilience

The rapid growth in size and complexity of artificial intelligence (AI) and machine learning (ML) models has led to increased energy demands, posing a threat to the reliability of the existing power grid. This project addresses the challenge of highly intermittent and energy-intensive inference workloads by (1) developing fidelity-adaptive neural networks capable of dynamic response to grid conditions and (2) integrating these networks with power flow simulations to assess their impact on power grid reliability. We will explore both top-down and bottom-up approaches to create hierarchies of submodels that provide a controlled trade-off between power draw and prediction accuracy. The top-down method utilizes NN pruning to reduce a flagship model into progressively smaller, energy-efficient variants. The bottom-up approach employs geometrically principled weight setting strategies to construct depth-efficient models from the ground up. A real-time hardware-in-the-loop (HIL) platform will be developed to simulate a scaled AC power grid, integrating live AI workload power draw and enabling dynamic model switching in response to grid feedback. This work will provide a novel framework for evaluating the impact of flexible AI/ML workloads on grid performance and establish new methodologies for energy-aware computing in data centers. The outcomes will demonstrate that adaptive AI/ML can play a critical role in improving grid stability while advancing NREL's leadership in energy-efficient computing research.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

In-situ TEM EELS analysis of memristive thin films for neuromorphic computing

Neuromorphic computing stands as a promising frontier for advancing AI algorithms and applications like ChatGBT, offering significant energy efficiency gains. This paper delves into the hardware design intricacies of memristive thin films and their elementary switching mechanisms, including anion migration, electron migration, and phase transitions. Through comprehensive analysis of electron energy loss spectroscopy (EELS) data via in-situ transmission electron microscopy (TEM), we will deduce the primary memristive switching mechanisms vital for optimizing thin film fabrication parameters and achieving desired film thickness, conductivity, and memory retention. A single crystal ptype Si substrate was used with TiN as the bottom metal electrode, TiO x as the insulating dielectric layer, and Pt as the top metal electrode. In-situ TEM was able to tell us the thin film didn’t behave like a filamentary or phase transition material. EELS data deduced that electron trapping/detrapping was one of the primary switching mechanisms. By shedding light on these elementary mechanisms, our study aims to catalyze the development of more 2 efficient and effective neuromorphic computing systems to be deployed into mainstream technologies.

97 MATHEMATICS AND COMPUTING↗