Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Intelligent Systems”

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 1,639 records · Page 91

Issues in knowledge representation to support maintainability: A case study in scientific data preparation

Scientific data preparation is the process of extracting usable scientific data from raw instrument data. This task involves noise detection (and subsequent noise classification and flagging or removal), extracting data from compressed forms, and construction of derivative or aggregate data (e.g. spectral densities or running averages). A software system called PIPE provides intelligent assistance to users developing scientific data preparation plans using a programming language called Master Plumber. PIPE provides this assistance capability by using a process description to create a dependency model of the scientific data preparation plan. This dependency model can then be used to verify syntactic and semantic constraints on processing steps to perform limited plan validation. PIPE also provides capabilities for using this model to assist in debugging faulty data preparation plans. In this case, the process model is used to focus the developer's attention upon those processing steps and data elements that were used in computing the faulty output values. Finally, the dependency model of a plan can be used to perform plan optimization and runtime estimation. These capabilities allow scientists to spend less time developing data preparation procedures and more time on scientific analysis tasks. Because the scientific data processing modules (called fittings) evolve to match scientists' needs, issues regarding maintainability are of prime importance in PIPE. This paper describes the PIPE system and describes how issues in maintainability affected the knowledge representation used in PIPE to capture knowledge about the behavior of fittings.

Chien, Steve↗

Data Mining and Knowledge Discover - IBM Cognitive Alternatives for NASA KSC

Skillful tools in cognitive computing to transform industries have been found favorable and profitable for different Directorates at NASA KSC. In this study is shown how cognitive computing systems can be useful for NASA when computers are trained in the same way as humans are to gain knowledge over time. Increasing knowledge through senses, learning and a summation of events is how the applications created by the firm IBM empower the artificial intelligence in a cognitive computing system. NASA has explored and applied for the last decades the artificial intelligence approach specifically with cognitive computing in few projects adopting similar models proposed by IBM Watson. However, the usage of semantic technologies by the dedicated business unit developed by IBM leads these cognitive computing applications to outperform the functionality of the inner tools and present outstanding analysis to facilitate the decision making for managers and leads in a management information system.

Cognitive computing↗

Study of application of adaptive systems to the exploration of the solar system. Volume 1: Summary

The field of artificial intelligence to identify practical applications to unmanned spacecraft used to explore the solar system in the decade of the 80s is examined. If an unmanned spacecraft can be made to adjust or adapt to the environment, to make decisions about what it measures and how it uses and reports the data, it can become a much more powerful tool for the science community in unlocking the secrets of the solar system. Within this definition of an adaptive spacecraft or system, there is a broad range of variability. In terms of sophistication, an adaptive system can be extremely simple or as complex as a chess-playing machine that learns from its mistakes.

Source record↗

Designing Agent Collectives For Systems With Markovian Dynamics

The "Collective Intelligence" (COIN) framework concerns the design of collectives of agents so that as those agents strive to maximize their individual utility functions, their interaction causes a provided "world" utility function concerning the entire collective to be also maximized. Here we show how to extend that framework to scenarios having Markovian dynamics when no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. Our approach transforms the (time-extended) argument of each agent's utility function before evaluating that function. This transformation has benefits in scenarios not involving Markovian dynamics, in particular scenarios where not all of the arguments of an agent's utility function are observable. We investigate this transformation in simulations involving both linear and quadratic (nonlinear) dynamics. In addition, we find that a certain subset of these transformations, which result in utilities that have low "opacity (analogous to having high signal to noise) but are not "factored" (analogous to not being incentive compatible), reliably improve performance over that arising with factored utilities. We also present a Taylor Series method for the fully general nonlinear case.

Wolpert, David H.↗

Designing Agent Collectives For Systems With Markovian Dynamics

The Collective Intelligence (COIN) framework concerns the design of collectives of agents so that as those agents strive to maximize their individual utility functions, their interaction causes a provided world utility function concerning the entire collective to be also maximized. Here we show how to extend that framework to scenarios having Markovian dynamics when no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. Our approach transforms the (time-extended) argument of each agent's utility function before evaluating that function. This transformation has benefits in scenarios not involving Markovian dynamics of an agent's utility function are observable. We investigate this transformation in simulations involving both hear and quadratic (nonlinear) dynamics. In addition, we find that a certain subset of these transformations, which result in utilities that have low opacity (analogous to having high signal to noise) but are not factored (analogous to not being incentive compatible), reliably improve performance over that arising with factored utilities. We also present a Taylor Series method for the fully general nonlinear case.

Wolpert, David H.↗

Advancing Industry 4.0: Multimodal Sensor Fusion for AI-Based Fault Detection in 3D Printing

Additive manufacturing, particularly fused deposition modeling, is transforming modern production by enabling rapid prototyping and complex part fabrication. However, its layer-by-layer process remains vulnerable to faults such as nozzle clogging, filament runout, and layer misalignment, which compromise print quality and reliability. Traditional inspection methods are costly, time-intensive, and often limited to post-process analysis, making them unsuitable for real-time intervention. In this current study, the authors developed a novel, low-cost, and portable faultdetection system that leverages multimodal sensor fusion and artificial intelligence for real-time monitoring in FDM-based 3D printing. The system integrates acoustic, vibration, and thermal sensing into a non-intrusive architecture, capturing complementary data streams that reflect both mechanical and process-related anomalies. Acoustic and thermal sensors operate in a fully contactless manner, while the vibration sensor requires minimal attachment such that it will not interfere with printer hardware, thereby preserving portability and ease of deployment. The multimodal signals are processed into spectrograms and time-frequency features, which are classified using convolutional neural networks for intelligent fault detection. The proposed system advances Industry 4.0 objectives by offering an affordable, scalable, and practical monitoring solution that improves faultdetection accuracy, reduces waste, and supports sustainable, adaptive manufacturing.

42 ENGINEERING↗

Sensor Fusion-Based Vehicle Detection and Tracking Using a Single Camera and Radar at a Traffic Intersection

Recent advancements in sensor technologies, in conjunction with signal processing and machine learning, have enabled real-time traffic control systems to adapt to varying traffic conditions. This paper introduces a new sensor fusion approach that combines data from a single camera and radar to achieve cost-effective and efficient vehicle detection and tracking. Initially, vehicles are independently detected and classified using the camera and radar. Then, the constant-velocity model within a Kalman filter is employed to predict vehicle locations, while the Hungarian algorithm is used to associate these predictions with sensor measurements. Finally, vehicle tracking is accomplished by merging kinematic information from predictions and measurements through the Kalman filter. A case study conducted at an intersection demonstrates the effectiveness of the proposed sensor fusion method for traffic detection and tracking, including performance comparisons with individual sensors.

47 OTHER INSTRUMENTATION↗

Cycles-L: A Coupled, 3-D, Land Surface, Hydrologic, and Agroecosystem Landscape Model

Managing landscapes to increase agricultural productivity and environmental stewardship can be informed by spatially-distributed models that operate at spatial and temporal scales that are intervention-relevant. This paper presents Cycles-L, a landscape-scale agroecosystem and hydrologic modeling system, using as a test case a watershed in Pennsylvania. Cycles-L emerges from melding the landscape and hydrology structure of Flux-PIHM, a 3-D land surface hydrologic model, with the agroecosystem processes in the Cycles model. Consequently, Cycles-L can simulate processes affected by topography, soil heterogeneity, and management practices, owing to its physically-based hydrology that can simulate horizontal and vertical transport of solutes with water. The model was tested at a 730-ha experimental watershed within the Mahantango Creek watershed. Cycles-L simulated well stream water and mineral nitrogen discharge (Nash-Sutcliffe coefficient 0.55 and 0.60, respectively) and grain yield (root mean square error 1.2 Mg ha -1 ). Cycles-L outputs are as good or better than those obtained with the uncoupled Flux-PIHM (water discharge) and Cycles (grain yield) models. Modeled spatial patterns of nitrogen fluxes like denitrification illustrate the combined control of crop management and topography. For example, denitrification is almost twice as high when simulated with Cycles-L than when simulated with Cycles 1-D. Due to its spatial and temporal resolution, Cycles-L fills a gap in the availability of models that operate at a scale relevant to evaluate interventions in the landscape. Cycles-L can become a central component in tools for climate change scenario analysis, precision agriculture, precision conservation, and artificial intelligence-based decision support systems.

54 ENVIRONMENTAL SCIENCES↗

New architectural paradigms for multi-petabyte distributed storage systems

In the not too distant future, programs such as NASA's Earth Observing System, NSF/ARPA/NASA's Digital Libraries Initiative and Intelligence Community's (NSA, CIA, NRO, etc.) mass storage system upgrades will all require multi-petabyte (petabyte: 1015 bytes of bitfile data) (or larger) distributed storage solutions. None of these requirements, as currently defined, will meet their objectives utilizing either today's architectural paradigms or storage solutions. Radically new approaches will be required to not only store and manage veritable 'mountain ranges of data', but to make the cost of ownership affordable, much less practical in today's (and certainly the future's) austere budget environment! Within this paper we will explore new architectural paradigms and project systems performance benefits and dollars per petabyte of information stored. We will discuss essential 'top down' approaches to achieving an overall systems level performance capability sufficient to meet the challenges of these major programs.

Lee, Richard R.↗

Are humans still necessary? Expanding the discussion

The rise of automation, artificial intelligence (AI), and autonomous systems raises important questions about the future role of humans and the field of human factors/ergonomics in workplaces. This paper builds on Dr. Peter Hancock’s 2023 ‘Are Humans Still Necessary?’ article published in the Ergonomics journal. Using a multi-method approach that included a debate, opinion polling, roundtable discussions, and AI queries, the current effort examined the necessity of human involvement in future work environments. Debate team members presented arguments for and against the need for human workers, considering human factors, technology, and socioeconomic factors. Observations indicate that while AI may handle routine tasks, humans will likely remain essential for complex decision making, creativity, and ethical considerations. The paper advocates for viewing workplace dynamics as collaborative human-AI partnerships rather than competition, highlighting the need for a transdisciplinary approach in which human factors/ergonomics professionals play a vital role in enhancing these relationships.

99 - GENERAL AND MISCELLANEOUS↗

Expanding the KATE toolbox

KATE (Knowledge-based Autonomous Test Engineer) is a model-based software system developed in the Artificial Intelligence Laboratory at the Kennedy Space Center for monitoring, fault detection, and control of launch vehicles and ground support systems. In order to bring KATE to the level of performance, functionality, and integratability needed for firing room applications, efforts are underway to implement KATE in the C++ programming language using an X-windows interface. Two programs which were designed and added to the collection of tools which comprise the KATE toolbox are described. The first tool, called the schematic viewer, gives the KATE user the capability to view digitized schematic drawings in the KATE environment. The second tool, called the model editor, gives the KATE model builder a tool for creating and editing knowledge base files. Design and implementation issues having to do with these two tools are discussed. It will be useful to anyone maintaining or extending either the schematic viewer or the model editor.

Thomas, Stan J.↗

Enhancements to the KATE model-based reasoning system

KATE (Knowledge-based Autonomous Test Engineer) is a model-based software system developed in the Artificial Intelligence Laboratory at the Kennedy Space Center for monitoring, fault detection, and control of launch vehicles and ground support systems. This report describes two software efforts which enhance the functionality and usability of KATE. The first addition, a flow solver, adds to KATE a tool for modeling the flow of liquid in a pipe system. The second addition adds support for editing KATE knowledge base files to the Emacs editor. The body of this report discusses design and implementation issues having to do with these two tools. It will be useful to anyone maintaining or extending either the flow solver or the editor enhancements.

Thomas, Stan J.↗

Cooling Matters: Benchmarking Large Language Models and Vision-Language Models on Liquid-Cooled Versus Air-Cooled H100 GPU Systems

The unprecedented growth in artificial intelligence (AI) workloads, recently dominated by large language models (LLMs) and vision-language models (VLMs), has intensified power and cooling demands in data centers. This study benchmarks LLMs and VLMs on two HGX nodes, each with 8× NVIDIA H100 graphics processing units (GPUs), using liquid and air cooling. Leveraging GPU Burn, Weights & Biases, and IPMItool, we collect detailed thermal, power, and computation data. Results show that the liquid-cooled systems maintain GPU temperatures between 41-50$^\circ$C, while the air-cooled counterparts fluctuate between 54-72$^\circ$C under load. This thermal stability of liquid-cooled systems yields 17% higher performance (54 TFLOPs/ GPU vs. 46 TFLOPs/GPU), performance-per-watt, reduced energy overhead, and greater system efficiency than the air-cooled counterparts. These findings underscore the energy and sustainability benefits of liquid cooling, offering a compelling path forward for hyperscale data centers seeking to optimize AI infrastructure. https://github.com/iscaas/Cooling-Matters.

Latif, Imran↗

Determining the twist angle of stacked MoS 2 layers using machine learning-assisted low-frequency interlayer Raman fingerprints

The investigation of twisted stacked few-layer MoS 2 has revealed novel electronic, optical, and vibrational properties over an extended period. For the successful integration of twisted stacked few-layer MoS 2 into a wide range of applications, it is crucial to employ a noninvasive, versatile technique for characterizing the layered architecture of these complex structures. Here, in this work, we introduce a machine learning-assisted low-frequency Raman spectroscopy method to characterize the twist angle of few-layer stacked MoS 2 samples. A feedforward neural network (FNN) is utilized to analyze the low-frequency breathing mode as a function of the twist angle. Moreover, using finite difference method (FDM) and density functional theory (DFT) calculations, we show that the low-frequency Raman spectra of MoS 2 are mainly influenced by the effect of the nearest and second nearest layers. A new improved linear chain model (TA-LCM) with taking the twist angle into the consideration is developed to understand the interlayer breathing modes of stacked few-layer MoS 2 . This approach can be extended to other 2D materials systems and provides an intelligent way to investigate naturally stacked and twisted interlayer interactions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A characterization of recombinant Arabidopsis FRIABLE1 (FRB1) reveals robust rhamnogalacturonan-I rhamnosyltransferase activity and critical catalytic residues

Plant cell walls are glycan-rich extracellular matrices that fundamentally impact essential cellular processes, such as growth, adhesion, and cell shape acquisition. Understanding plant cell wall glycans requires the identification and characterization of the biosynthetic enzymes that produce these polymers. Most successful in vitro protein expression studies of plant cell wall glycosyltransferases have relied on insect, fungal/yeast, or human cell expression systems, whereas prokaryotic expression systems have been generally unsuccessful. Here, we show that Arabidopsis FRIABLE1 (FRB1)/rhamnogalacturonan-I rhamnosyltransferase 8 (RRT8) can be produced in Escherichia coli RosettaGami2 cells as N-terminal maltose-binding protein fusion proteins containing C-terminal 6X-His-tags. We also report the catalytic constants of FRB1/RRT8 with apparent K M and K cat values of 226 μM and 33 min -1 for UDP-Rhamnose and 117 μM and 28.7 min -1 for rhamnogalacturonan-I (RG-I), respectively. We examine the catalytic activities of mutated FRB1/RRT8 proteins based on an AlphaFold 3-generated FRB1/RRT8 protein structural model with a virtually docked UDP-Rha donor. Enzymatic characterization of the mutated and wildtype FRB1/RRT8 protein confirmed that mutation of predicted catalytic site amino acid residues resulted in a 20-fold reduction in RRT activity. FRB1 also robustly polymerizes RG-I in combination with RG-I galacturonosyltransferase 1. These results show how a robust E. coli expression system combined with artificial intelligence tools can be used to increase understanding of plant cell wall glycosyltransferase structure and function.

glycosyltransferase↗

Toward a systematic exploration of nano-bio interactions

Many studies of nanomaterials make non-systematic alterations of nanoparticle physicochemical properties. Given the immense size of the property space for nanomaterials, such approaches are not very useful in elucidating fundamental relationships between inherent physicochemical properties of these materials and their interactions with, and effects on, biological systems. Data driven artificial intelligence methods such as machine learning algorithms have proven highly effective in generating models with good predictivity and some degree of interpretability. They can provide a viable method of reducing or eliminating animal testing. However, careful experimental design with the modelling of the results in mind is a proven and efficient way of exploring large materials spaces. This approach, coupled with high speed automated experimental synthesis and characterization technologies now appearing, is the fastest route to developing models that regulatory bodies may find useful. We advocate greatly increased focus on systematic modification of physicochemical properties of nanoparticles combined with comprehensive biological evaluation and computational analysis. This is essential to obtain better mechanistic understanding of nano-bio interactions, and to derive quantitatively predictive and robust models for the properties of nanomaterials that have useful domains of applicability. - Highlights: • Nanomaterials studies make non-systematic alterations to nanoparticle properties. • Vast nanomaterials property spaces require systematic studies of nano-bio interactions. • Experimental design and modelling are efficient ways of exploring materials spaces. • We advocate systematic modification and computational analysis to probe nano-bio interactions.

60 APPLIED LIFE SCIENCES↗

Optimizing lane reversals in transportation networks to reduce traffic congestion: A global optimization approach

This paper studies how to reduce the overall travel time of commuters in a transportation network by reversing the direction of some lanes in the network using a macroscopic network-wide perspective. Similar to the Network Design Problem, the lane reversal problem has been shown to be NP-hard given the dependence of the users’ route selection on the lane direction decision. Herein, we propose and compare three efficient methods to solve the routing and lane reversal problem jointly. First, we introduce an alternating method that decouples the routing and lane assignment problems. Second, we propose a Frank–Wolfe method that jointly takes gradient steps to adjust both the lane assignment and routing decisions. Third, we propose a convex approximation method that uses a threshold-based approach to convexify the joint routing and lane reversal objective. The convex approximation method is advantageous since it finds a global optimum solution for the approximated problem and it enables the possibility to include linear constraints. Using this method, we extend the main formulation to be able to limit a maximum number of reversed lanes, as well as to incorporate multiple origin–destination (OD) patterns. We test the proposed methods in a case study using the transportation network of Eastern Massachusetts where our results indicate an overall reduction in travel times of 4.7% by selecting the best 15 reversals. Moreover, using a small test network, we investigate the performance of the lane reversal strategies as a function of the OD demand symmetry. As expected, we observe that when the OD demand is very asymmetric (e.g., for a single OD pair, evacuations, large events), the reduction in travel times is larger than the symmetric case, reaching travel time reductions of 60%.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

New Era Towards Autonomous Additive Manufacturing: A Review of Recent Trends and Future Perspectives

Abstract The Additive Manufacturing (AM) landscape has significantly transformed in alignment with Industry 4.0 principles, primarily driven by the integration of Artificial Intelligence (AI) and Digital Twin (DT). However, current Intelligent Additive Manufacturing (IAM) systems face limitations such as fragmented AI tool usage and suboptimal human-machine interaction (HMI). This paper reviews existing IAM solutions, emphasizing control, monitoring, process autonomy, and end-to-end integration, and identifies key limitations, such as the absence of a high-level controller for global decision-making. To address these gaps, we propose a transition from IAM to Autonomous Additive Manufacturing (AAM), featuring a hierarchical framework with four integrated layers: knowledge, generative solution, operational, and cognitive. In the cognitive layer, AI agents notably enable machines to independently observe, analyze, plan, and execute operations that traditionally require human intervention. These capabilities streamline production processes and expand the possibilities for innovation, particularly in sectors like in-space manufacturing (ISM). Additionally, this paper discusses the role of AI in self-optimization and lifelong learning, positing that the future of AM will be characterized by a symbiotic relationship between human expertise and advanced autonomy, fostering a more adaptive, resilient manufacturing ecosystem.

Fan, Haolin↗