Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “vision”

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 451 records · Page 25

The role of driver head pose dynamics and instantaneous driving in safety critical events: Application of computer vision in naturalistic driving

This paper investigates the role of driver behavior especially head pose dynamics in safety–critical events (SCEs). Using a large dataset collected in a naturalistic driving study, this paper analyzes the head pose dynamics and driving behavior in moments leading up to crashes or near-crashes. The study uses advanced computer vision and mixed logit modeling techniques to identify patterns and relationships between drivers’ head pose dynamics and crash involvement. The results suggest that driver-head pose dynamics, especially poses that indicate distraction and movement volatility, are important factors that can contribute to undesirable safety outcomes. Marginal effects show that angular deviation for head pose dynamics indicated by yaw, pitch and roll increase the likelihood of crash intensity by 4.56%, 4.92% and 8.26% respectively. Furthermore, traffic flow and lane changing also contribute to increase in likelihood of crash intensity. These findings provide new insights into pre-crash factors, especially human factors and safety–critical events. The study highlights the importance of considering human factors in designing driver assistance systems and developing safer vehicles. This research contributes by examining naturalistic driving data at the microscopic level with early detection of behaviors that lead to SCEs and provides a basis for future research on automation.

33 ADVANCED PROPULSION SYSTEMS↗

In-situ TEM investigation of void swelling in nickel under irradiation with analysis aided by computer vision

Understanding the stability of irradiation-induced voids in materials is important for engineering material's swelling behavior under irradiation. In-situ TEM offers a spatial and temporal resolution that is suitable for investigating the evolution of voids under irradiation. However, the in-situ videos have often been too large to be analyzed manually, leaving the valuable data underutilized. For this work, we developed a deep learning-based semantic segmentation model to consistently study the growth and shrinkage of voids in nickel under 1 MeV krypton ion irradiation at various temperatures from 525 °C to 650 °C. With a foil thickness near 100 nm and ion flux of 6.3 × 10 11 ions∙ cm –2 ∙s –1 , the pre-existing voids, which were created beforehand by irradiation at 600 °C to 0.5 dpa, shrank at low temperatures and grew at high temperatures under irradiation, where the transition occurred at 575 °C (~0.5 T M ). The observed stability transition provided new insight for the shrinkage mechanism of voids under irradiation. In addition, an annealing experiment on nickel, previously irradiated at 600 °C to 3 dpa, was performed sequentially at 650 °C to 720 °C to reveal the shrinkage rate of void as a function of temperature and void size. The advantage of combining computer vision and in-situ TEM to obtain comprehensive void evolution was demonstrated.

36 MATERIALS SCIENCE↗

Advances in solar forecasting: Computer vision with deep learning

Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilities, conventional modeling methods rely on numerical weather prediction or physical models, which have difficulties in assimilating cloud information and learning systematic biases. Augmenting computer vision with machine learning overcomes some of these limitations by fusing real-time cloud cover observations with surface measurements acquired from multiple sources. This Review summarizes recent progress in solar forecasting from multisensor Earth observations with a focus on deep learning, which provides the necessary theoretical framework to develop architectures capable of extracting relevant information from data generated by ground-level sky cameras, satellites, weather stations, and sensor networks. Overall, machine learning has the potential to significantly improve the accuracy and robustness of solar energy meteorology; however, more research is necessary to realize this potential and address its limitations.

14 SOLAR ENERGY↗

Utilizing computer vision and artificial intelligence algorithms to predict and design the mechanical compression response of direct ink write 3D printed foam replacement structures

Additive Manufacturing (AM) of porous polymeric materials, such as foams, recently became a topic of intensive research due their unique combination of low density, impressive mechanical properties, and stress dissipation capabilities. Conventional methods for fabricating foams rely on complex and stochastic processes, making it challenging to achieve precise architectural control of structured porosity. In contrast, AM provides access to a wide range of printable materials, where precise spatial control over structured porosity can be modulated during the fabrication process enabling the production of foam replacement structures (FRS). Current approaches for designing FRS are based on intuitive understanding of their properties or an extensive number of finite element method (FEM) simulations. These approaches, however, are computationally expensive and time consuming. As such, in this work, we present a novel methodology for determining the mechanical compression response of direct ink write (DIW) 3D printed FRS using a simple cross-sectional image. By obtaining measurement data for a relatively small number of samples, an artificial neural network (ANN) was trained, and a computer vision algorithm was used to make inferences about foam compression characteristics from a single cross-sectional image. Finally, a genetic algorithm (GA) was used to solve the inverse design problem, generating the AM printing parameters that an engineer should use to achieve a desired compression response from a DIW printed FRS. The methods developed herein present an avenue for entirely autonomous design and analysis of additively manufactured structures using artificial intelligence.

36 MATERIALS SCIENCE↗

Analysis of Vision Loss Caused by Radiation-Induced Optic Neuropathy After Particle Therapy for Head-and-Neck and Skull-Base Tumors Adjacent to Optic Nerves

Purpose: To assess the incident rates of vision loss (VL; based on counting fingers or more severe) caused by radiation-induced optic neuropathy (RION) after particle therapy for tumors adjacent to optic nerves (ONs), and to evaluate factors that may contribute to VL. Methods and Materials: From August 2001 to August 2006, 104 patients with head-and-neck or skull-base tumors adjacent to ONs were treated with carbon ion or proton radiotherapy. Among them, 145 ONs of 75 patients were irradiated and followed for greater than 12 months. The incident rate of VL and the prognostic factors for occurrence of VL were evaluated. The late effects of carbon ion and proton beams were compared on the basis of a biologically effective dose at alpha/beta = 3 gray equivalent (GyE{sub 3}). Results: Eight patients (11%) experienced VL resulting from RION. The onset of VL ranged from 17 to 58 months. The median follow-up was 25 months. No significant difference was observed between the carbon ion and proton beam treatment groups. On univariate analysis, age (>60 years), diabetes mellitus, and maximum dose to the ON (>110 GyE{sub 3}) were significant, whereas on multivariate analysis only diabetes mellitus was found to be significant for VL. Conclusions: The time to the onset of VL was highly variable. There was no statistically significant difference between carbon ion and proton beam treatments over the follow-up period. Based on multivariate analysis, diabetes mellitus correlated with the occurrence of VL. A larger study with longer follow-up is warranted.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Vision-based inspection of prefabricated components using camera poses: Addressing inherent limitations of image-based 3D reconstruction

Modular construction can lead to additional cost overruns and delays when a defect is found on the construction site and is not easily repairable. Researchers have developed various methods that use image-based 3D reconstruction for quality assessment, but they have inherent limitations, such as inconsistency and dealing with surfaces with reflectivity and limited visual features. Therefore, this paper presents a vision-based quality assessment method using cameras for prefabricated components by addressing these limitations. Specifically, this paper proposes a novel quality inspection method with sub-millimeter accuracy using cameras focused on leveraging camera poses (as opposed to 3D point clouds that are often not consistent in quality) from the image-based 3D reconstruction. The 3D point estimation by computing triangulation was used for achieving accurate measurement. The proposed method is validated using six different variances and two case studies – an aluminum pipe with a reflective surface and a fabricated concrete column. Furthermore, the results demonstrate the accuracy and effectiveness of the proposed method.

42 ENGINEERING↗

Tracking Dendritic Growth in Hydrogen-Based Hematite Reduction via Computer Vision

The reduction of hematite to metallic iron using hydrogen (H2) as a reducing agent presents a promising pathway for decarbonizing steel production. In this study, we employ a combination of in situ confocal scanning laser microscopy (CSLM) and advanced computer vision techniques to quantitatively analyze dendritic growth of ferrite during H2-based reduction of iron oxide at high temperatures. A workflow integrating Watershed Image Segmentation (WIS) and Lucas-Kanade Optical Flow (LKOF) is developed to extract both global and local kinetic information from time-resolved micrograph sequences. H2 reduction experiments conducted at 1400 degrees C and 1500 degrees C demonstrate a clear correlation between temperature and reduction rate, as evidenced by accuracy of fitted Johnson-Mehl-Avrami-Kolmogorov (JMAK) parameters. Optical flow analysis further elucidates the anisotropic and branched nature of dendritic growth, providing spatially resolved velocity fields that correlate well with global transformation kinetics. The proposed methodology demonstrates strong agreement with experimental measurements and literature values, offering a robust framework for automated image-based analysis to study kinetics through microstructural evolution in the reduction of iron ore, and likely other reaction-diffusion phenomena.

08 HYDROGEN↗

Revealing the evolution of order in materials microstructures using multi-modal computer vision

The development of high-performance materials for microelectronics, energy storage, and extreme environments depends on our ability to describe and direct property-defining microstructural order. Our present understanding is typically derived from laborious manual analysis of imaging and spectroscopy data, which is difficult to scale, challenging to reproduce, and lacks the ability to reveal latent associations needed for mechanistic models. Here, we demonstrate a multi-modal machine learning (ML) approach to describe order from electron microscopy analysis of the complex oxide La 1−x Sr x FeO 3 . We construct a hybrid pipeline based on fully and semi-supervised classification, allowing us to evaluate both the characteristics of each data modality and the value each modality adds to the ensemble. We observe distinct differences in the performance of uni- and multi-modal models, from which we draw general lessons in describing crystal order using computer vision.

36 MATERIALS SCIENCE↗

Computer vision models enable mixed linear modeling to predict arbuscular mycorrhizal fungal colonization using fungal morphology

Abstract The presence of Arbuscular Mycorrhizal Fungi (AMF) in vascular land plant roots is one of the most ancient of symbioses supporting nitrogen and phosphorus exchange for photosynthetically derived carbon. Here we provide a multi-scale modeling approach to predict AMF colonization of a worldwide crop from a Recombinant Inbred Line (RIL) population derived from Sorghum bicolor and S. propinquum . The high-throughput phenotyping methods of fungal structures here rely on a Mask Region-based Convolutional Neural Network (Mask R-CNN) in computer vision for pixel-wise fungal structure segmentations and mixed linear models to explore the relations of AMF colonization, root niche, and fungal structure allocation. Models proposed capture over 95% of the variation in AMF colonization as a function of root niche and relative abundance of fungal structures in each plant. Arbuscule allocation is a significant predictor of AMF colonization among sibling plants. Arbuscules and extraradical hyphae implicated in nutrient exchange predict highest AMF colonization in the top root section. Our work demonstrates that deep learning can be used by the community for the high-throughput phenotyping of AMF in plant roots. Mixed linear modeling provides a framework for testing hypotheses about AMF colonization phenotypes as a function of root niche and fungal structure allocations.

59 BASIC BIOLOGICAL SCIENCES↗

Popnet : computer vision based deep learning model for forecasting gridded population

Here, this study introduces Popnet, a deep learning model for forecasting 1 km-gridded populations, integrating U-Net, ConvLSTM, a Spatial Autocorrelation module and deep ensemble methods. Using spatial variables and population data from 2000 to 2020, Popnet predicts South Korea’s population trends by age groups (under 14, 15-64 and over 65) up to 2040. In validation, it outperforms traditional machine learning and state-of-the-art computer vision models. The output of this model discovered significant polarisation: population growth in urban areas, especially the capital region, and severe depopulation in rural areas. Popnet is a robust tool for offering significant insights to policymakers and related stakeholders about the detailed future population, which allows them to establish detailed, localised planning and resource allocations.

computer vision↗

Three-dimensional measurement of small mechanical parts under a complicated background based on stereo vision

We present an effective method for the accurate three-dimensional (3D) measurement of small industrial parts under a complicated noisy background, based on stereo vision. To effectively extract the nonlinear features of desired curves of the measured parts in the images, a strategy from coarse to fine extraction is employed, based on a virtual motion control system. By using the multiscale decomposition of gray images and virtual beam chains, the nonlinear features can be accurately extracted. By analyzing the generation of geometric errors, the refined feature points of the desired curves are extracted. Then the 3D structure of the measured parts can be accurately reconstructed and measured with least squares errors. Experimental results show that the presented method can accurately measure industrial parts that are represented by various line segments and curves.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

SunShot Vision Study: February 2012 (Book)

The objective of the SunShot Vision Study is to provide an in-depth assessment of the potential for solar technologies to meet a significant share of electricity demand in the United States during the next several decades. Specifically, it explores a future in which the price of solar technologies declines by about 75% between 2010 and 2020 - in line with the U.S. Department of Energy (DOE) SunShot Initiative's targets.

14 SOLAR ENERGY↗

Combined Heat and Power: A Decade of Progress, A Vision for the Future

Over the past 10 years, DOE has built a solid foundation for a robust CHP marketplace. We have aligned with key partners to produce innovative technologies and spearhead market-transforming projects. Our commercialization activities and Clean Energy Regional Application Centers have expanded CHP across the nation. More must be done to tap CHP’s full potential. Read more about DOE’s CHP Program in “Combined Heat and Power: A Decade of Progress, A Vision for the Future.”

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Reducing Wind Curtailment through Transmission Expansion in a Wind Vision Future

The Department of Energy's 2015 Wind Vision study, which analyzed an ambitious scenario where wind power served 35% of U.S. electricity consumption in 2050, showed the potential for wind energy to provide substantial health, environmental, and economic benefits. Using a commercial unit commitment and economic dispatch model, we build on this research by assessing the hourly operational feasibility of a similar high wind future in the Western United States. Our detailed simulations found no hours of unmet load or reserve violations with more than 35% potential wind (and 12% potential solar) available on the system, which highlights the technical possibility of integrating large amounts of wind energy. However, absent significant changes to the western grid, we find that substantial wind curtailment could be an issue, as it could degrade the potential for wind power to reduce fuel costs and lowering the emission benefits. To assess the value of transmission to mitigate wind curtailment, we model a suite of transmission expansion scenarios. We find that wind curtailment could be reduced by approximately half under a scenario where new transmission is based only on proposed projects. This avoided wind curtailment could lower annual production costs and reduce carbon dioxide emissions substantially. Greater transmission expansion was found to yield further benefits, although the marginal benefits of these new lines were found to decline. Overall, these results suggest that power systems operation can be realized with more than 35% wind penetration, but that transmission expansion is likely to play a vital role.

17 WIND ENERGY↗

IEA Wind TCP: Results of IEA Wind TCP Workshop on a Grand Vision for Wind Energy Technology

This report provides workshop findings including the future landscape of the electricity system with over 50% of the electricity supply from wind energy, a review of key innovation opportunities in different topic areas that will be embodied in the wind power plant of the future (including innovations that both reduce levelized cost of energy and increase system value of wind energy), and identification of the key R&D challenges that must be addressed to realize the wind power plant of the future and the Grand Vision.

17 WIND ENERGY↗

Clean Grid Vision: A U.S. Perspective - Executive Summary

Clean Grid Vision: A U.S. Perspective aims to present a range of possible pathways for future grid development and call attention to some common trends. It focuses on the lessons learned through NREL’s studies of the U.S. power sector that have measured the impacts of high-penetration VRE and have tested strategies for enhancing grid flexibility and reliability. As such, this report is limited in its scope and does not attempt to review or summarize all grid integration literature. While it refers to relevant external literature to provide context when needed, this report is primarily a summary of the National Renewable Energy Laboratory’s (NREL’s) research in the past 5 years on five key topics: grid planning and operation, grid reliability at the distribution level, grid reliability at the transmission level, demand-side resources, and power markets—each corresponds to a chapter in this report. The main insights of the report are presented in this executive summary.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Clean Grid Vision: A U.S. Perspective - Chapter 1. Clean Grid Scenarios

Chapter 1: Clean Grid Scenarios serves as a broad introduction to the type of future power systems envisioned in the Clean Grid Vision: one with high penetrations of variable renewable energy generation (for example, more than 53% nationally and up to 73% in the Eastern Interconnection) and significant share of natural gas. Our study shows that the conterminous United States has adequate resources to support such systems with current technologies, and these systems can be operated cost-effectively to meet all sub-hourly demand and reserve requirements.

24 POWER TRANSMISSION AND DISTRIBUTION↗