SEARCH · Engineering Papers

Results for “Embedded computing”

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.

SourceResearch connectionFrom yearThrough year

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

1,267 records · Page 71

All sources NASA NTRS DOE OSTI

DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗

DOE OSTI2026

Stakeholder-guided holistic, Adaptive Framework for enhancing community Energy Resilience (SAFER) (Final Technical Report)

The Stakeholder-guided holistic, Adaptive Framework for enhancing community Energy Resilience (SAFER) project advances resilience science and engineering by addressing challenges in rural Kansas communities where aging infrastructure, extreme weather, and socioeconomic disparities heighten vulnerability to energy disruptions. Traditional approaches often focus on technical performance while overlooking community concerns and priorities. SAFER responds by integrating community perspectives with advanced analytical frameworks to create a holistic model for measuring and improving resilience. Project objectives included developing novel resilience metrics, advancing modeling frameworks that capture interdependencies across infrastructures, and embedding community-centric indicators directly into planning processes for distributed energy resources. The key technical innovations included the creation of self-organizing map (SOM)-based indices for objective resilience quantification, hetero-functional graph theory (HFGT) models linking power, water, transportation, and community assets, and graph neural network (GNN) tools for identifying critical nodes in complex systems. Community-centric energy planning was demonstrated through optimal siting and sizing of (photovoltaic) PV and battery storage, ensuring resilience enhancements also addressed energy burden and energy insecurity. SAFER engaged community partners in Dodge City and Ford County through surveys, focus groups, and workshops, generating more than 600 responses that established baseline measures of energy burden, financial insecurity, and willingness-to-pay to avoid outages. This data, organized in terms of a community capitals framework, informed the development of weighted reliability indices that better reflect community costs than traditional utility metrics. SAFER’s GNN-based critical node identification framework identified expert-labelled critical nodes with over 99% accuracy, while also uncovering additional functionalities essential for proactive resilience planning. The project’s models demonstrated that optimal PV and storage deployment could improve resilience indices by over 11 percent, with dispatch strategies further enhancing outcomes, confirming both the technical effectiveness and economic feasibility of these approaches. Through its combined emphasis on rigorous modeling, community-focused planning, and community engagement, SAFER advances the state of resilience research while delivering direct benefits to rural communities. The project provides tools, guidelines, and resilience heatmaps that help utilities, local governments, and residents better anticipate disruptions, prioritize investments, and strengthen the capacity to withstand and recover from energy-related hazards. Furthermore, the developed HFG and GNN frameworks are designed for transferability, allowing them to be adapted for resilience planning in other communities with minimal retraining. This inductive learning capability provides a scalable pathway to extend the SAFER project’s impact. Thus, creating a foundation for a nationally applicable model of infrastructure resilience. Additionally, the HFG can also be extended to include other FEMA community lifelines.

14 SOLAR ENERGY↗

DOE OSTI2026

An AI-driven framework for evaluating local and state authorities’ permitting processes

The demand for new energy infrastructure is increasing across the United States, but heterogenous permitting processes and embedded requirements across different local jurisdictions can cause project delays, increase “soft costs,” and hinder developer expansion. This study analyzes the variability in local permitting requirements across the U.S. and develops a quantitative approach to describe their clarity and effectiveness in enabling infrastructure project development. By using an Energy Language Model (ELM), a large language model (LLM) for energy technologies, we systematically gathered permitting information from nearly 300 state-, county-, and city-level documents, creating a structured dataset of requirements and procedures on an unprecedented scale and speed. Our analysis revealed that local (city and county) permitting requirement documents are underrepresented compared to state-level guidance documents, which can impede timely and cost-effective installation of new electric infrastructure. Our validation process showed that the final database has an accuracy of approximately 95%. We, further, created a new quantitative method to score permitting requirements for clarity and efficiency, with electric vehicle supply equipment as an initial use case. The average local permitting document scored a 1.8 out of 5, which we interpret as meaning that half of the requirements developers face when installing electric infrastructure are ambiguous, increasing both cost and time. We also created a “Generalized Permit Process”, highlighting common procedural steps and identifying specific opportunities for municipalities to improve their documentation. This research establishes a systematic and scalable framework for evaluating the complexities of local infrastructure permitting processes by combining LLM-powered data collection and quantitative scoring. The framework enables policymakers and developers to identify and mitigate procedural bottlenecks, with the expectation that these improvements can accelerate application review and approval, reduce project costs, and expedite connection to utility distribution grids. As a foundational approach for streamlining local project development processes, this study’s methods are intended to be extended to a wide range of energy applications.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2025

PDF Entity Annotation Tool (PEAT)

While different text mining approaches – including the use of Artificial Intelligence (AI) and other machine based methods - continue to expand at a rapid pace, the tools used by researchers to create the labeled datasets required for training, modeling, and evaluation remain rudimentary. Labeled datasets contain the target attributes the machine is going to learn; for example, training an algorithm to delineate between images of a car or truck would generally require a set of images with a quantitative description of the underlying features of each vehicle type. Development of labeled textual data that can be used to build natural language machine learning models for scientific literature is not currently integrated into existing manual workflows used by domain experts. Published literature is rich with important information, such as different types of embedded text, plots, and tables that can all be used as inputs to train ML/natural language processing (NLP) models, when extracted and prepared in machine readable formats. Currently, both normalized data extraction of use to domain experts and extraction to support development of ML/NLP models are labor intensive and cumbersome manual processes. Automatic extraction of data and information from formats such as PDFs that are optimized for layout and human readability, not machine readability. The PDF (Portable Document Format) Entity Annotation Tool (PEAT) was developed with the goal of allowing users to annotate publications within their current print format, while also allowing those annotations to be captured in a machine-readable format. One of the main issues with traditional annotation tools is that they require transforming the PDF into plain text to facilitate the annotation process. While doing so lessens the technical challenges of annotating data, the user loses all structure and provenance that was inherent in the underlying PDF. Also, textual data extraction from PDFs can be an error prone process. Challenges include identifying sequential blocks of text and a multitude of document formats (multiple columns, font encodings, etc.). As a result of these challenges, using existing tools for development of NLP/ML models directly from PDFs is difficult because the generated outputs are not interoperable. We created a system that allows annotations to be completed on the original PDF document structure, with no plain text extraction. The result is an application that allows for easier and more accurate annotations. In addition, by including a feature that grants the user the ability to easily create a schema, we have developed a system that can be used to annotate text for different domain-centric schemas of relevance to subject matter experts. Different knowledge domains require distinct schemas and annotation tags to support machine learning.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Acoustic-based monitoring and machine learning of component status for microreactor applications

This report provides a description and assessment of recent efforts to couple acoustic-based experimental measurements and characterization with machine learning models in order to enhance structural health monitoring capabilities for nuclear microreactors. With resilient embedded sensors in development by others supported by programs funded by the US Department of Energy’s Office of Nuclear Energy, the work described herein builds upon ongoing efforts to improve non-destructive testing technology that relates measured acoustic signatures to component stresses and/or structural defects, using a combination of new experimental measurements and machine learning architectures. The experimental procedure remained similar to that developed for the previous year’s demonstration of damage detection by the authors, with the same damaged sample tested under similar applied stress conditions. Notably, a new mounting fixture was designed and implemented to improve measurement consistency and a more sophisticated laser Doppler vibrometer was employed to make high-fidelity vibration measurements. Two nominally identical sets of training data were collected for each experimental setup to better understand the repeatability of the experiment and to better test the generality of trained neural network models. Additionally, we obtained new high-quality 3D mode shapes of the damaged test article at various stress and excitation levels, providing greater insights into the physical response of the sample during testing. Previously, we demonstrated that a machine learning model based on a convolutional neural network can predict structural details of an artificially introduced interface (intact, rough cut, smooth cut), and the applied torque level. In this study, we have transitioned to graph-based neural network architectures to better develop and test a flexible framework that is more suitable to being transferred away from controlled benchtop experiments and into more applied settings where less-structured data inputs may be expected. In general, performance testing of a graph neural network on frequency-domain representations of the data indicates strong and consistent identification of test conditions for datasets recorded on damaged components. With goals of predicting damage location and other changing experimental conditions using limited datasets, predictive models using a graph neural network architecture correctly predicted the applied torque level with an accuracy of 85% using only a single measurement point and predicted within one torque level in 95% of test windows. Predictions of damage location had limited success due to the symmetry and minimal number of the damage scenarios presented during model training. Results were ambiguous as to whether the model could detect the location of the artificial damage, or if it was instead learning the location of a given measurement point on the part and subsequently detecting which points were closest to the location of the damage. This finding will be factored into upcoming planned work on damaged graphite components, where new experimental tests with a larger number and variety of damage scenarios are expected to provide improved validation of recent developments in monitoring methodology.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2019

Improving Energy Efficiency of Air Separation via Hollow Fiber Sorbents

This report summarizes the work performed under the Department of Energy’s National Energy Technology Laboratory (DOE-NETL) Advanced Energy Systems Program award number DE-FE0026163 Improving Energy Efficiency of Air Separation via Hollow Fiber Sorbents. The overall objective of the project was to develop technology to produce oxygen for use in coal gasification processes at a significantly lower cost than that of the commercial state-of-the-art technology. The focus of the project was development and optimization of hollow fiber sorbents for use in a pressure swing adsorption (PSA) process for producing oxygen from air. The key technical advancement under this program was the development of a hollow fiber sorbent capable of producing oxygen in a PSA process. PSAs produce oxygen by using a beaded zeolite material (typically lithium exchanged zeolites or LiX) that selectively adsorb nitrogen over oxygen. For a fiber to adsorb nitrogen, LiX needed to be integrated into a polymer fiber and then activated at over 350C to remove residual moisture. After screening multiple materials and process techniques, Matrimid/LiX hollow fibers were produced that were able to withstand the activation and had crystalline nitrogen capacity close to pure LiX crystals. The fibers were dual layer fibers with a barrier layer isolating the hollow bore from the LiX embedded layer. The barrier layer was formed from an Ultem® based solution. The hollow bore was intended for encapsulating phase change materials to ensure isothermal PSA operation. Modeling work from the project suggested that the benefits of this additional complexity were marginal, thus the team fabricated non-hollow fibers comprised of Matrimid and LiX. The Matrimid/LiX fibers were loaded into a module and tested on a bench scale PSA unit. The fibers were able to separate oxygen from air, but the purity and recovery were lower than expected and lower than traditional beaded LiX zeolites, although modeling results suggested that the bed sizes for fiber sorbents could be half the size of a beaded LiX bed. Additional work will be needed to understand the shortfall and to produce fiber sorbent modules with performance equal to the targets set for this program. In addition to producing fibers, modeling work was carried out at both the fiber level and process level to guide both fiber sorbent development and to determine the optimal process conditions for a PSA using fiber sorbents. A 2D hollow fiber model was developed in gPROMS Model Builder. This model was based on literature data for mass transfer and other parameters. This model used a basic single bed PSA process to determine important fiber properties and process conditions for achieving high oxygen recovery. The preliminary 2D fiber model was a valuable tool, however, for step-out technologies, such as a PSA process with fiber sorbents, intelligent optimization and plant control was needed to effectively determine minimum power designs. Therefore, a gPROMS Process Builder-based optimization tool was developed with an “Automated Cycle Optimizer” model that was able to determine optimal cycle conditions for a fiber sorbent PSA. The results from the optimizer were used in the final power analysis. Flow sheet analysis and techno-economic analysis (TEA) was carried out to determine a lower power solution versus the baseline case. The original project scope suggested that the fiber sorbent PSA could be used to debottleneck a cryogenic air separation plant (cryo-ASU) with the combined plant having lower power than a standalone cryo-ASU. However, early flowsheet analysis showed that the PSA/cryo-ASU concept would not lead to a lower power solution. However, further flowsheet analysis suggested that an oxygen PSA combined with a nitrogen PSA could have lower power versus state-of-the-art air separation technology. Work concluded with the TEA showing a fiber sorbent oxygen PSA combined with an advanced nitrogen PSA could be up to 8% lower power versus the base case cryo-ASU. Overall, there is significant potential remaining for the zeolite hollow fiber sorbent concept, and this project successfully identified -- and ultimately remedied -- many technical challenges associated with scale-up.

01 COAL, LIGNITE, AND PEAT↗

DOE OSTI2016

Exe-Guard Project

The exe-Guard Project is an alliance between Dominion Virginia Power (DVP), Sandia National Laboratories (SNL), Dartmouth University, and Schweitzer Engineering Laboratories (SEL). SEL is primary recipient on this project. The exe-Guard project was selected for award under DE-FOA-0000359 with CFDA number 81.122 to address Topic Area of Interest 4: Hardened platforms and Systems. The exe-Guard project developed an antivirus solution for control system embedded devices to prevent the execution of unauthorized code and maintain settings and configuration integrity. This project created a white list antivirus solution for control systems capable of running on embedded Linux® operating systems. White list antivirus methods allow only credible programs to run through the use of digital signatures and hash functions. Once a system’s secure state is baselined, white list antivirus software denies deviations from that state because of the installation of malicious code as this changes hash results. Black list antivirus software has been effective in traditional IT environments but has negative implications for control systems. Black list antivirus uses pattern matching and behavioral analysis to identify system threats while relying on regular updates to the signature file and recurrent system scanning. Black list antivirus is vulnerable to zero day exploits which have not yet been incorporated into a signature file update. System scans hamper the performance of high availability applications, as revealed in NIST special publication 1058 which summarizes the impact of blacklist antivirus on control systems: Manual or “on-demand” scanning has a major effect on control processes in that they take CPU time needed by the control process (Sometimes close to 100% of CPU time). Minimizing the antivirus software throttle setting will reduce but not eliminate this effect. Signature updates can also take up to 100% of CPU time, but for a much shorter period than a typical manual scanning process. Control systems are vulnerable to performance losses if off-the-shelf blacklist antivirus solutions aren’t implemented with care. This investment in configuration in addition to constant decommissioning to perform manual signature file updates is unprecedented and impractical. Additionally, control systems are often disconnected or islanded from the network making the delivery of signature updates difficult. Exe-Guard project developed a white list antivirus solution that mitigated the above drawbacks and allows control systems to cost-effectively apply malware protection while maintaining high reliability. The application of security patches can also be minimized since white listing maintains constant defense against unauthorized code execution. Security patches can instead be applied in less frequent intervals where system decommissioning can be scheduled and planned for. Since control systems are less dynamic than IT environments, the feasibility of maintaining a secure baselined state is more practical. Because upgrades are performed in infrequent, calculated intervals, it allows a new security baseline to be established before the system is returned to service. Exe-Guard built on the efforts of SNL under the Code Seal project. SNL demonstrated prototype Trust Anchors on the project which are independent monitoring and control devices that can be integrated into untrustworthy components. The exe-Guard team started with the lessons learned under this project then designed commercial solution for white list malware protection. Malware is a real threat, even on islanded or un-networked installations, since operators can unintentionally install infected files, plug in infected mass storage devices, or infect a piece of equipment on the islanded local area network that can then spread to other connected equipment. Protection at the device level is one of the last layers of defense in a security-in-depth defense model before an asset becomes compromised. This project provided non-destructive intrusion, isolation and automated response solution, achieving a goal of the Department of Energy (DOE) Roadmap to Secure Control Systems. It also addressed CIP-007-R4 which requires asset owners to employ malicious software prevention tools on assets within the electronic security perimeter. In addition, the CIP-007-R3 requirement for security patch management is minimized because white listing narrows the impact of vulnerabilities and patch releases. The exe-Guard Project completed all tasks identified in the statement of project objective and identified additional tasks within scope that were performed and completed within the original budget. The cost share was met and all deliverables were successfully completed and submitted on time. Most importantly the technology developed and commercialized under this project has been adopted by the Energy sector and thousands of devices with exe-Guard technology integrated in them have now been deployed and are protecting our power systems today

24 POWER TRANSMISSION AND DISTRIBUTION↗