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.
As artificial intelligence (AI) computing densities continue to increase, industry is pursuing megawatt-scale rack architectures that require tightly coordinated advances in electrical power delivery, thermal management, operations, and infrastructure integration. This document summarizes the primary technical challenges for achieving this target.
Digital twins are emerging as powerful tools for supporting innovation as well as optimizing the in-service performance of a broad range of complex physical machines, devices, and components. A digital twin is generally designed to provide accurate in-silico representation of the form (i.e., appearance) and the functional response of a specified (unique) physical twin. This paper offers a new perspective on how the emerging concept of digital twins could be applied to accelerate materials innovation efforts. Specifically, it is argued that the material itself can be considered as a highly complex multiscale physical system whose form (i.e., details of the material structure over a hierarchy of material length) and function (i.e., response to external stimuli typically characterized through suitably defined material properties) can be captured suitably in a digital twin. Accordingly, the digital twin can represent the evolution of structure, process, and performance of the material over time, with regard to both process history and in-service environment. This paper establishes the foundational concepts and frameworks needed to formulate and continuously update both the form and function of the digital twin of a selected material physical twin. The form of the proposed material digital twin can be captured effectively using the broadly applicable framework of n-point spatial correlations, while its function at the different length scales can be captured using homogenization and localization process-structure-property surrogate models calibrated to collections of available experimental and physics-based simulation data.
Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.
The objectives of this project were: (1) to investigate the implications of qualitative modeling techniques for problems arising in the monitoring, diagnosis, and design of Space Station subsystems and procedures; (2) to identify the issues involved in using qualitative models to enhance and automate engineering functions. These issues include representing operational criteria, fault models, alternate ontologies, and modeling continuous signals at a functional level of description; and (3) to develop a prototype collection of qualitative models for fluid and thermal systems commonly found in Space Station subsystems. Potential applications of qualitative modeling to space-systems engineering, including the notion of intelligent computer-aided engineering are summarized. Emphasis is given to determining which systems of the proposed Space Station provide the most leverage for study, given the current state of the art. Progress on using qualitative models, including development of the molecular collection ontology for reasoning about fluids, the interaction of qualitative and quantitative knowledge in analyzing thermodynamic cycles, and an experiment on building a natural language interface to qualitative reasoning is reported. Finally, some recommendations are made for future research.
These proceedings contain papers presented at the NASA Conference on Space Telerobotics held in Pasadena, January 31 to February 2, 1989. The theme of the Conference was man-machine collaboration in space. The Conference provided a forum for researchers and engineers to exchange ideas on the research and development required for application of telerobotics technology to the space systems planned for the 1990s and beyond. The Conference: (1) provided a view of current NASA telerobotic research and development; (2) stimulated technical exchange on man-machine systems, manipulator control, machine sensing, machine intelligence, concurrent computation, and system architectures; and (3) identified important unsolved problems of current interest which can be dealt with by future research.
The theme of the Conference was man-machine collaboration in space. The Conference provided a forum for researchers and engineers to exchange ideas on the research and development required for application of telerobotics technology to the space systems planned for the 1990s and beyond. The Conference: (1) provided a view of current NASA telerobotic research and development; (2) stimulated technical exchange on man-machine systems, manipulator control, machine sensing, machine intelligence, concurrent computation, and system architectures; and (3) identified important unsolved problems of current interest which can be dealt with by future research.
Ahab, an intelligent computer-aided instruction (ICAI) program, illustrates an architecture for simulator-based ICAI programs to teach troubleshooting in complex, dynamic environments. The architecture posits three elements of a computerized instructor: the task model, the student model, and the instructional module. The task model is a prescriptive model of expert performance that uses symptomatic and topographic search strategies to provide students with directed problem-solving aids. The student model is a descriptive model of student performance in the context of the task model. This student model compares the student and task models, critiques student performance, and provides interactive performance feedback. The instructional module coordinates information presented by the instructional media, the task model, and the student model so that each student receives individualized instruction. Concept and metaconcept knowledge that supports these elements is contained in frames and production rules, respectively. The results of an experimental evaluation are discussed. They support the hypothesis that training with an adaptive online system built using the Ahab architecture produces better performance than training using simulator practice alone, at least with unfamiliar problems. It is not sufficient to develop an expert strategy and present it to students using offline materials. The training is most effective if it adapts to individual student needs.
Intelligent computer-aided training system gives trainees same experience gained from best on-the-job training. Automated system designed to emulate behavior of experienced teacher devoting full time and attention to training novice. Proposes challenging training scenarios, monitors and evaluates trainee's actions, makes meaningful comments in response to errors, reponds to requests for information, gives hints when appropriate, and remembers strengths and weaknesses so it designs suitable exercises. Used to train flight-dynamics officers in deploying satellites from Space Shuttle. Adapted to training for variety of tasks and situations, simply by modifying one or at most two of its five modules. Helps to ensure continuous supply of trained specialists despite scarcity of experienced and skilled human trainers.
AI techniques are shown to have been useful in such aerospace industry tasks as vehicle configuration layouts, process planning, tool design, numerically-controlled programming of tools, production scheduling, and equipment testing and diagnosis. Accounts are given of illustrative experiences at the production facilities of three major aerospace defense contractors. Also discussed is NASA's autonomous Intelligent Computer-Aided Training System, for such ambitious manned programs as Space Station Freedom, which employs five different modules to constitute its job-independent training architecture.
Papers from the technical sessions of the Technology 2001 Conference and Exposition are presented. The technical sessions featured discussions of advanced manufacturing, artificial intelligence, biotechnology, computer graphics and simulation, communications, data and information management, electronics, electro-optics, environmental technology, life sciences, materials science, medical advances, robotics, software engineering, and test and measurement.
DeMAID (A Design Manager's Aid for Intelligent Decomposition) computer program is knowledge-based software system for ordering sequence of modules and identifying possible multilevel structure for design problem. Groups modular subsystems on basis of interactions among them. Saves considerable money and time in total design process, particularly in new design problem in which order of modules has not been defined. Available in two machine versions: Macintosh and Sun.
DeMAID (Design Manager's Aid for Intelligent Decomposition) computer program is knowledge-based software system for ordering sequence of modules and identifying possible multilevel structure for design problems such as large platforms in outer space. Groups modular subsystems on basis of interactions among them. Saves considerable amount of money and time in total design process, particularly in new design problem in which order of modules has not been defined. Originally written for design problems, also applicable to problems containing modules (processes) that take inputs and generate outputs. Available in three machine versions: Macintosh written in Symantec's Think C 3.01, Sun, and SGI IRIS in C language.
This paper details the MARBLE 2.0 system which provides a parallel environment for cooperating expert systems. The work has been done in conjunction with the development of an intelligent computer-aided design system, ICADS, by the CAD Research Unit of the Design Institute at California Polytechnic State University. MARBLE (Multiple Accessed Rete Blackboard Linked Experts) is a system of C Language Production Systems (CLIPS) expert system tool. A copied blackboard is used for communication between the shells to establish an architecture which supports cooperating expert systems that execute in parallel. The design of MARBLE is simple, but it provides support for a rich variety of configurations, while making it relatively easy to demonstrate the correctness of its parallel execution features. In its most elementary configuration, individual CLIPS expert systems execute on their own processors and communicate with each other through a modified blackboard. Control of the system as a whole, and specifically of writing to the blackboard is provided by one of the CLIPS expert systems, an expert control system.
Despite considerable progress in understanding human capabilities and limitations, incorporating human factors into aircraft design, operation, and certification, and the emergence of new technologies designed to reduce workload and enhance human performance in the system, most aviation accidents still involve human errors. Such errors occur as a direct or indirect result of untimely, inappropriate, or erroneous actions (or inactions) by apparently well-trained and experienced pilots, controllers, and maintainers. The field of human factors has solved many of the more tractable problems related to simple ergonomics, cockpit layout, symbology, and so on. We have learned much about the relationships between people and machines, but know less about how to form successful partnerships between humans and the information technologies that are beginning to play a central role in aviation. Significant changes envisioned in the structure of the airspace, pilots and controllers' roles and responsibilities, and air/ground technologies will require a similarly significant investment in human factors during the next few decades to ensure the effective integration of pilots, controllers, dispatchers, and maintainers into the new system. Many of the topics that will be addressed are not new because progress in crucial areas, such as eliminating human error, has been slow. A multidisciplinary approach that capitalizes upon human studies and new classes of information, computational models, intelligent analytical tools, and close collaborations with organizations that build, operate, and regulate aviation technology will ensure that the field of human factors meets the challenge.
C Language Integrated Production System (CLIPS), a NASA-developed software shell for developing expert systems, has been embedded in a PC-based expert system for training oil rig personnel in monitoring oil drilling. Oil drilling rigs if not properly maintained for possible blowouts pose hazards to human life, property and the environment may be destroyed. CLIPS is designed to permit the delivery of artificial intelligence on computer. A collection of rules is set up and, as facts become known, these rules are applied. In the Well Site Advisor, CLIPS provides the capability to accurately process, predict and interpret well data in a real time mode. CLIPS was provided to INTEQ by COSMIC.
As a space faring nation, we are at a critical juncture in the evolution of space exploration. NASA has announced its Vision for Space Exploration, a vision of returning humans to the Moon, sending robots and eventually humans to Mars, and exploring the outer solar system via automated spacecraft. However, mission concepts have become increasingly complex, with the potential to yield a wealth of scientific knowledge. Meanwhile, there are significant resource challenges to be met. Launch costs remain a barrier to routine space flight; the ever-changing fiscal and political environments can wreak havoc on mission planning; and technologies are constantly improving, and systems that were state of the art when a program began can quickly become outmoded before a mission is even launched. This Conference Publication describes the workshop and featured presentations by world-class experts presenting leading-edge technologies and applications in the areas of power and propulsion; communications; automation, robotics, computing, and intelligent systems; and transformational techniques for space activities. Workshops such as this one provide an excellent medium for capturing the broadest possible array of insights and expertise, learning from researchers in universities, national laboratories, NASA field Centers, and industry to help better our future in space.
This paper discusses the fundamental process for the computation of Flight Software (FSW) cost estimates. This process has been incorporated in a rule-based expert system [1] that can be used for Independent Cost Estimates (ICEs), Proposals, and for the validation of Cost Analysis Data Requirements (CADRe) submissions. A high-level directed graph (referred to here as a decision graph) illustrates the steps taken in the production of these estimated costs and serves as a basis of design for the expert system described in this paper. Detailed discussions are subsequently given elaborating upon the methodology, tools, charts, and caveats related to the various nodes of the graph. We present general principles for the estimation of FSW using SEER-SEM as an illustration of these principles when appropriate. Since Source Lines of Code (SLOC) is a major cost driver, a discussion of various SLOC data sources for the preparation of the estimates is given together with an explanation of how contractor SLOC estimates compare with the SLOC estimates used by JPL. Obtaining consistency in code counting will be presented as well as factors used in reconciling SLOC estimates from different code counters. When sufficient data is obtained, a mapping into the JPL Work Breakdown Structure (WBS) from the SEER-SEM output is illustrated. For across the board FSW estimates, as was done for the NASA Discovery Mission proposal estimates performed at JPL, a comparative high-level summary sheet for all missions with the SLOC, data description, brief mission description and the most relevant SEER-SEM parameter values is given to illustrate an encapsulation of the used and calculated data involved in the estimates. The rule-based expert system described provides the user with inputs useful or sufficient to run generic cost estimation programs. This system's incarnation is achieved via the C Language Integrated Production System (CLIPS) and will be addressed at the end of this paper.