Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “intelligence”

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 379 records · Page 21

MO-FG-BRA-08: Swarm Intelligence-Based Personalized Respiratory Gating in Lung SAbR

Purpose: Respiratory gating is widely deployed as a clinical motion-management strategy in lung radiotherapy. In conventional gating, the beam is turned on during a pre-determined phase window; typically, around end-exhalation. In this work, we challenge the notion that end-exhalation is always the optimal gating phase. Specifically, we use a swarm-intelligence-based, inverse planning approach to determine the optimal respiratory phase and MU for each beam with respect to (i) the state of the anatomy at each phase and (ii) the time spent in that state, estimated from long-term monitoring of the patient’s breathing motion. Methods: In a retrospective study of five lung cancer patients, we compared the dosimetric performance of our proposed personalized gating (PG) with that of conventional end-of-exhale gating (CEG) and a previously-developed, fully 4D-optimized plan (combined with MLC tracking delivery). For each patient, respiratory phase probabilities (indicative of the time duration of the phase) were estimated over 2 minutes from lung tumor motion traces recorded previously using the Synchrony system (Accuray Inc.). Based on this information, inverse planning optimization was performed to calculate the optimal respiratory gating phase and MU for each beam. To ensure practical deliverability, each PG beam was constrained to deliver the assigned MU over a time duration comparable to that of CEG delivery. Results: Maximum OAR sparing for the five patients achieved by the PG and the 4D plans compared to CEG plans was: Esophagus Dmax [PG:57%, 4D:37%], Heart Dmax [PG:71%, 4D:87%], Spinal cord Dmax [PG:18%, 4D:68%] and Lung V13 [PG:16%, 4D:31%]. While patients spent the most time in exhalation, the PG-optimization chose end-exhale only for 28% of beams. Conclusion: Our novel gating strategy achieved significant dosimetric improvements over conventional gating, and approached the upper limit represented by fully 4D optimized planning while being significantly simpler and more clinically translatable. This work was partially supported through research funding from National Institutes of Health (R01CA169102) and Varian Medical Systems, Palo Alto, CA, USA.

60 APPLIED LIFE SCIENCES↗

Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences

Data science has primarily focused on big data, but for many physics, chemistry, and engineering applications, data are often small, correlated and, thus, low dimensional, and sourced from both computations and experiments with various levels of noise. Typical statistics and machine learning methods do not work for these cases. Expert knowledge is essential, but a systematic framework for incorporating it into physics-based models under uncertainty is lacking. Here, we develop a mathematical and computational framework for probabilistic artificial intelligence (AI)–based predictive modeling combining data, expert knowledge, multiscale models, and information theory through uncertainty quantification and probabilistic graphical models (PGMs). We apply PGMs to chemistry specifically and develop predictive guarantees for PGMs generally. Our proposed framework, combining AI and uncertainty quantification, provides explainable results leading to correctable and, eventually, trustworthy models. The proposed framework is demonstrated on a microkinetic model of the oxygen reduction reaction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Electricity Pricing aware Deep Reinforcement Learning based Intelligent HVAC Control

Recently, deep reinforcement learning (DRL) based intelligent control of Heating, Ventilation, and Air Conditioning (HVAC) has gained a lot of attention due to DRL's ability to optimally control HVAC for minimizing operational cost while maintaining resident's comfort. The success of such DRL-based techniques largely depends on the articulation of the problem in terms of states, actions, and reward function. Inclusion of the electricity pricing information in the problem formulation can play an important role in saving the cost of HVAC operation. However, less attention has been given in the literature on formulating well-crafted state features based on electricity pricing. In this work, we propose an approach for training the DRL model with a specific focus on feature engineering based on electricity pricing. During training, we generate random but sufficiently realistic electricity price signals so that the pre-trained DRL model is robust and adaptive to the dynamic and variable electricity prices. The validation results are encouraging and show the potential of ≈12%-15% savings in the one day cost of HVAC operation, proving the usefulness of including electricity pricing related features as state features.

Kurte, Kuldeep↗

AIIO: Using Artificial Intelligence for Job-Level and Automatic I/O Performance Bottleneck Diagnosis

Manually diagnosing the I/O performance bottleneck for a single application (hereinafter referred to as the "job level'') is a tedious and error-prone procedure requiring domain scientists to have deep knowledge of complex storage systems. However, existing automatic methods for I/O performance bottleneck diagnosis have one major issue: the granularity of the analysis is at the platform or group level and the diagnosis results cannot be applied to the individual application. To address this issue, we designed and developed a method named "Artificial Intelligence for I/O"(AIIO), which uses AI and its interpretation technology to diagnose I/O performance bottlenecks at the job level automatically. By considering the sparsity of I/O log files, employing multiple AI models for performance prediction, merging diagnosis results across multiple models, and generalizing its performance prediction and diagnosis functions, AIIO can accurately and robustly identify the bottleneck of an even unseen application. Experimental results show that real and unseen applications can use the diagnosis results from AIIO to improve their I/O performance by at most 146 times.

Dong, Bin↗

FiberFlex: Real-time FPGA-based Intelligent and Distributed Fiber Sensor System for Pedestrian Recognition

In recent years, security monitoring of public places and critical infrastructure has heavily relied on the widespread use of cameras, raising concerns about personal privacy violations. To balance the need for effective security monitoring with the protection of personal privacy, we explore the potential of optical fiber sensors for this application. This article proposes FiberFlex, an intelligent and distributed fiber sensor system. Ultizing Field Programmable Gate Arrays (FPGA) high-level synthesis (HLS) acceleration, FiberFlex offers real-time pedestrian detection by co-designing the entire pipeline of optical signal acquisition, processing, and recognition networks based on the principles of optical fiber sensing. As a promising alternative to traditional camera-based monitoring systems, FiberFlex achieves pedestrian detection by analyzing the vibration patterns caused by pedestrian footsteps, enabling security monitoring while preserving individual privacy. FiberFlex comprises three modules: First , fiber-optic sensing system: A fiber-optic distributed acoustic sensing (DAS) system is built and used to measure the ground vibration waves generated by people walking. Second , algorithms: We first collect the training data by measuring the ground vibration waves, label the data, and use the data to train the neural network models to perform pedestrian recognition. Third , hardware accelerators: We use HLS tools to design hardware modules on FPGA for data collection and pre-processing and integrate them with the downstream neural network accelerators to perform in-line real-time pedestrian detection. The final detection results are sent back from FPGA to the host CPU. We implement our system FiberFlex with the in-house built DAS system and AMD/Xilinx Kintex7 FPGA KC705 board and verify the whole system using the real-world collected data. We conduct recognition tests on five test subjects of varying ages, heights, and weights in a fixed sensing area. Each subject experienced 20 real-time recognition tests using their daily walking habits, and the subjects were given adequate rest between tests. After 100 tests on five test subjects, the overall real-time recognition accuracy exceeded \(88.0\%\) . The whole system uses 55 W of power, 33 W in the optical DAS system and 22 W in the FPGA. Relying on its end-to-end interdisciplinary design, FiberFlex seamlessly combines fiber-optic sensors with FPGA accelerators to enable low-power real-time security monitoring without compromising privacy, making it a valuable addition to the existing security monitoring network. According to FiberFlex, more valuable research can be conducted in the future, such as fall monitoring for the elderly, migration of identification networks between different application scenarios, and improvement of anti-interference performance in more complex environments. In future perception networks, where the “eyes” are not feasible, let’s use fiber optic touch instead.

Distributed↗

Robotic Intelligence Kernel: Architecture

The INL Robotic Intelligence Kernel Architecture (RIK-A) is a multi-level architecture that supports a dynamic autonomy structure. The RIK-A is used to coalesce hardware for sensing and action as well as software components for perception, communication, behavior and world modeling into a framework that can be used to create behaviors for humans to interact with the robot.

Few, DougA.↗

Robotic Intelligence Kernel: Communications

The INL Robotic Intelligence Kernel-Comms is the communication server that transmits information between one or more robots using the RIK and one or more user interfaces. It supports event handling and multiple hardware communication protocols.

Walton, MikeC.↗

Robotic Intelligence Kernel: Visualization

The INL Robotic Intelligence Kernel-Visualization is the software that supports the user interface. It uses the RIK-C software to communicate information to and from the robot. The RIK-V illustrates the data in a 3D display and provides an operating picture wherein the user can task the robot.

Nielsen, CurtisW.↗

Autonomic Intelligent Cyber Sensor (AICS) Version 1.0.1

The Autonomic Intelligent Cyber Sensor (AICS) provides cyber security and industrial network state awareness for Ethernet based control network implementations. The AICS utilizes collaborative mechanisms based on Autonomic Research and a Service Oriented Architecture (SOA) to: 1) identify anomalous network traffic; 2) discover network entity information; 3) deploy deceptive virtual hosts; and 4) implement self-configuring modules. AICS achieves these goals by dynamically reacting to the industrial human-digital ecosystem in which it resides. Information is transported internally and externally on a standards based, flexible two-level communication structure.

Vollmer, DenisTodd↗

Hydropower Fleet Intelligence

The Hydropower Fleet Intelligence application can integrate hydropower facilities data sources to perform analyses on asset age, reliability and costs, as well as produce visualizations that combine time series data collected by mechanical component sensors with event history.

Foley, Molly↗

Intelligent Cyber Sensor

A network security and information solution that utilizes intelligent mechanisms to recognize anomalous network traffic, identify network hosts and dynamically instantiate deceptive virtual honeypots.

Vollmer, DenisT.↗

Artificial Intelligence–Enabled Digital Twin for U.S. Cities

Over 50 participants—including national laboratory researchers, academic scholars, industry representatives, and stakeholders from the City of Chicago—convened in person and online to assess the readiness and potential of an Artificial Intelligence–Enabled Digital Twin (AIDT) for urban systems, with the Greater Chicago area serving as the benchmark location. The workshop underscored that the Chicago Urban Integrated Field Laboratory provides an unparalleled testbed for developing and validating urban DTs—combining dense, multiscale observations, advanced physics-based and AI modeling capabilities, and strong stakeholder and industry engagement. Discussions highlighted available datasets, AI architectures for high resolution, multipurpose urban DTs, key applications, and near- and long-term priorities for scaling this framework within Chicago and to other U.S. and global cities.

AIDT↗

Trust in Artificial Intelligence: Meta-Analytic Findings

Objective The present meta-analysis sought to determine significant factors that predict trust in artificial intelligence (AI). Such factors were divided into those relating to (a) the human trustor, (b) the AI trustee, and (c) the shared context of their interaction. Background There are many factors influencing trust in robots, automation, and technology in general, and there have been several meta-analytic attempts to understand the antecedents of trust in these areas. However, no targeted meta-analysis has been performed examining the antecedents of trust in AI. Method Data from 65 articles examined the three predicted categories, as well as the subcategories of human characteristics and abilities, AI performance and attributes, and contextual tasking. Lastly, four common uses for AI (i.e., chatbots, robots, automated vehicles, and nonembodied, plain algorithms) were examined as further potential moderating factors. Results Results showed that all of the examined categories were significant predictors of trust in AI as well as many individual antecedents such as AI reliability and anthropomorphism, among many others. Conclusion Overall, the results of this meta-analysis determined several factors that influence trust, including some that have no bearing on AI performance. Additionally, we highlight the areas where there is currently no empirical research. Application Findings from this analysis will allow designers to build systems that elicit higher or lower levels of trust, as they require.

Behavioral Sciences↗

HUMAN-ARTIFICIAL INTELLIGENCE TEAMING FOR THE U.S. NAVY: DEVELOPING A HOLISTIC RESEARCH ROADMAP

With the ever-increasing deluge of data and demand for warfighters to make decisions upon its analysis, U.S. defense strategy has prioritized the development of artificial intelligence (AI)/machine learning (ML) systems that can analyze multi-source data streams and suggest courses of action. However, there is a history of systems that have failed to be adopted by the warfighter due not only to unsolved technical challenges, but also a lack of usability or contributions to mission effectiveness, perceived or otherwise. To avoid this, research into human-AI teaming shows promise for developing AI systems that work with frontline operators. A recent National Academies of Sciences, Engineering, and Medicine report (NASEM, 2022) presented 57 research objectives in this area; however, the U.S. Navy requires a more-focused set of priorities, as it is impossible to tackle every priority. A workshop involving 23 human factors scientists, computer scientists, and active-duty sailors was organized at the Naval Information Warfare Center Pacific, resulting in a set of five research priorities spanning near-, mid-, and far-term time frames. This panel will summarize the results of this workshop, with a focus on the big questions both going into this workshop and coming out of it. The panel participants come from government, academia, and industry, providing perspective from the different kinds of organizations required to accomplish these research goals.

Wong, Jason↗

Human-Centered and Explainable Artificial Intelligence in Nuclear Operations

Nuclear power plants in the United States are critical to the nation’s energy security, accounting for 20% of all electricity produced for the power grid. As energy needs grow, 100 gigawatts of additional nuclear power will be necessary by 2050, more than double the current capacity. Realizing this target requires cutting-edge technology like artificial intelligence (AI) and machine learning (ML) that can bring about significant increases in the level of automation. Human-centered AI (HCAI) is a combination of human-centered design (human factors, human-in-the-loop, etc.) with AI/ML to help produce an efficient and reliable system with full consideration for human engagement. This paper provides a comprehensive and novel discussion of HCAI considerations in nuclear power, introducing unique applications for the existing fleet as well as new advanced reactor designs. We include real-life use cases of AI applications to work management processes at nuclear power sites and highlight lessons learned for HCAI.

Hall, Anna↗

Leveraging generative artificial intelligence to bridge domain gaps in wind turbine research

A central challenge in wind turbine health monitoring is the scarcity of real-world data due to limited instrumentation, leading researchers to rely on simulation models that often suffer from reduced fidelity. However, even within simulation environments, discrepancies arise because of modeling assumptions, and configuration fidelities, creating domain gaps that limit the transferability of learned representations. Here, to investigate domain translation under controlled conditions, this project explores the use of generative artificial intelligence, specifically cycle-consistent generative adversarial networks (CGANs), to bridge the gap between OpenFAST simulation models representing 1.5 MW and 5 MW wind turbines. A physics-informed CGAN architecture is introduced, where a simplified turbine tower dynamics model is incorporated into the training loss to ensure physically consistent outputs. Quantitative results showed moderate to high agreement in frequency-domain features. Incorporating the physics-informed loss function improved the R 2 values by 30%, reduced the RMSE from 1.39 to 1.1 m/s 2 , and reduced training time by 82%. Furthermore, under increased turbulence intensity (IEC Category A), the RMSE remained stable at approximately 1.1 m/s 2 . While the present study is entirely simulation-based, it establishes a pipeline for evaluating physics-informed generative domain translation, which may serve as a foundation for future simulation-to-reality validation studies.

17 WIND ENERGY↗

Application of artificial intelligence methods in the international roughness index prediction of rigid and composite pavements: a systematic review

The International Roughness Index (IRI) is a widely adopted metric for quantifying pavement roughness, directly influencing vehicle safety, ride comfort, and overall roadway performance. In recent years, the use of Machine Learning (ML) models for IRI prediction has gained momentum, with the goal of improving the allocation of maintenance and rehabilitation resources by enabling accurate assessments of pavement conditions. Most prior reviews, however, have concentrated on flexible pavements, leaving a notable gap regarding rigid and composite pavements. To address this gap, the present study conducts a systematic review of Artificial Intelligence (AI) methods applied to IRI prediction for rigid and composite pavements. Literature published between 2004 and 2025 is synthesized to highlight prevailing trends, methodological contributions, and directions for future research. Particular attention is given to the types of models employed, the datasets used for training and validation, and the role of input variables and data-processing strategies. Across the included studies, ensemble learning methods (especially gradient boosting variants such as XGBoost), artificial neural networks, and hybrid architectures frequently achieved high predictive skill, with several models reporting test-set coefficients of determination approaching 0.9–0.96, indicating strong potential for capturing the influence of traffic, pavement structure, and climatic factors. Since these results are obtained from heterogeneous datasets and evaluation protocols, they are interpreted qualitatively rather than as strict cross-study rankings. Analysis of input variables revealed that pavement age and initial IRI were included in 91% (21 of 23) and 78% (18 of 23) of studies, respectively. Climatic variables such as the freezing index appeared in 57% (13 of 23), while traffic-related factors were considered in 65% (15 of 23). The findings underscore the importance of standardized, high-quality datasets, such as those from the Long-Term Pavement Performance (LTPP) program, along with data consistency, model interpretability, computational efficiency, and replicability in enhancing IRI prediction. Future research should focus on incorporating input variable selection techniques to identify the most influential predictors, thereby improving accuracy and robustness. Integrating these approaches with advanced non-linear data-driven models, coupled with robust hyperparameter optimization, holds considerable promise for strengthening the reliability of IRI prediction and supporting resilient pavement management strategies.

42 ENGINEERING↗

Cultural intelligence support for military operations

It has long been recognized that military success relies on knowledge of the enemy. In the context of standard warfare, adequate knowledge of the enemy may be gained by analyzing observable, measurable data. In the context of modern counterinsurgency operations and the global war on terror, the task of predicting the behavior of the enemy is vastly more complex and difficult. Without an understanding of the ways individuals in the host nation interpret and react to events, no amount of objective information can provide the insight required to accurately predict behavior. US military doctrine has begun to recognize the importance of the many ways that local culture can affect operation success. Increasingly military decision makers use cultural information in the service of operation planning, and troops are provided with pre-deployment cultural training. However, no amount of training can cover the breadth and depth of potentially useful cultural information, and no amount of careful planning can avoid the need to adapt as situations develop. Therefore, a critical challenge is to provide useful tools to US personnel in their efforts to collect, analyze, and utilize cultural information. Essential functions for cultural support tools include the following: (1) to narrow down a broad range of available data and focus the user's attention on context-relevant information, (2) to present cultural information in an easily understood form, (3) to prompt the user to seek relevant information in the environment, (4) to synthesize information, and (5) to predict outcomes based on possible courses of operation. In this paper, we begin by reviewing the ways in which military operations can benefit from cultural intelligence. We then discuss frameworks for analyzing cultural information in the context of a military operation. We conclude with a demonstration of our current efforts to develop a tool that meets the aforementioned functional challenges.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗