Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “artificial”

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 919 records · Page 51
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Volumetric nondestructive evaluation for damage in carbon fiber reinforced polymer panels subjected to artificial lightning strikes

Aircrafts and wind turbine blades often get hit by lightning strikes due to their operating locations. With increasing incidents of lightning flashes every year due to global warming, damage assessment of CFRP structures after lightning strike to aircrafts and wind turbine blades is getting increasingly important. Many researchers are involved in designing better and more resilient lighting strike protection materials and often utilize non-destructuve evaluation (NDE) methods such as ultrasonic testing (UT), high-speed digital videograpgy, and high-speed IR thermography. In particular, UT is widely used due to its cost-effectiveness compared to other methods. Using UT imaging can obtain any potential damaged locations caused by lightning strike through the thickness of the composite specimens. Traditional UT and visual inspections only display the damage in units area, when in fact the UT data is volumetric. This study optimized the UT data to measure and display the volumetric damage after artificial lightning strike and is compared to the standardized visual inspection.

Spencer, Ryan↗
DOE OSTI2014

SU-E-T-206: Improving Radiotherapy Toxicity Based On Artificial Neural Network (ANN) for Head and Neck Cancer Patients

Purpose/Objective(s): The aim of this study is to build the estimator of toxicity using artificial neural network (ANN) for head and neck cancer patients Materials/Methods: An ANN can combine variables into a predictive model during training and considered all possible correlations of variables. We constructed an ANN based on the data from 73 patients with advanced H and N cancer treated with external beam radiotherapy and/or chemotherapy at our institution. For the toxicity estimator we defined input data including age, sex, site, stage, pathology, status of chemo, technique of external beam radiation therapy (EBRT), length of treatment, dose of EBRT, status of post operation, length of follow-up, the status of local recurrences and distant metastasis. These data were digitized based on the significance and fed to the ANN as input nodes. We used 20 hidden nodes (for the 13 input nodes) to take care of the correlations of input nodes. For training ANN, we divided data into three subsets such as training set, validation set and test set. Finally, we built the estimator for the toxicity from ANN output. Results: We used 13 input variables including the status of local recurrences and distant metastasis and 20 hidden nodes for correlations. 59 patients for training set, 7 patients for validation set and 7 patients for test set and fed the inputs to Matlab neural network fitting tool. We trained the data within 15% of errors of outcome. In the end we have the toxicity estimation with 74% of accuracy. Conclusion: We proved in principle that ANN can be a very useful tool for predicting the RT outcomes for high risk H and N patients. Currently we are improving the results using cross validation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

SU-E-T-131: Artificial Neural Networks Applied to Overall Survival Prediction for Patients with Periampullary Carcinoma

Purpose: Artificial neural networks (ANN) can be used to discover complex relations within datasets to help with medical decision making. This study aimed to develop an ANN method to predict two-year overall survival of patients with peri-ampullary cancer (PAC) following resection. Methods: Data were collected from 334 patients with PAC following resection treated in our institutional pancreatic tumor registry between 2006 and 2012. The dataset contains 14 variables including age, gender, T-stage, tumor differentiation, positive-lymph-node ratio, positive resection margins, chemotherapy, radiation therapy, and tumor histology.After censoring for two-year survival analysis, 309 patients were left, of which 44 patients (∼15%) were randomly selected to form testing set. The remaining 265 cases were randomly divided into training set (211 cases, ∼80% of 265) and validation set (54 cases, ∼20% of 265) for 20 times to build 20 ANN models. Each ANN has one hidden layer with 5 units. The 20 ANN models were ranked according to their concordance index (c-index) of prediction on validation sets. To further improve prediction, the top 10% of ANN models were selected, and their outputs averaged for prediction on testing set. Results: By random division, 44 cases in testing set and the remaining 265 cases have approximately equal two-year survival rates, 36.4% and 35.5% respectively. The 20 ANN models, which were trained and validated on the 265 cases, yielded mean c-indexes as 0.59 and 0.63 on validation sets and the testing set, respectively. C-index was 0.72 when the two best ANN models (top 10%) were used in prediction on testing set. The c-index of Cox regression analysis was 0.63. Conclusion: ANN improved survival prediction for patients with PAC. More patient data and further analysis of additional factors may be needed for a more robust model, which will help guide physicians in providing optimal post-operative care. This project was supported by PA CURE Grant.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

WE-AB-204-06: Pseudo-CT Generation Using Undersampled, Single-Acquisition UTE-MDixon and Direct-Mapping Artificial Neural Networks for MR-Based Attenuation Correction and Radiation Therapy Planning

Purpose: Emerging technologies such as dedicated PET/MRI and MR-therapy systems require robust and clinically practical methods for determining photon attenuation. Herein, we propose using novel MR acquisition methods and processing for the generation of pseudo-CTs. Methods: A single acquisition, 190-second UTE-mDixon sequence with 25% (angular) sampling density and 3D radial readout was performed on nine volunteers. Three water-filled tubes were placed in the FOV for trajectory-delay correction. The MR data were reconstructed to generate three primitive images acquired at TEs of 0.1, 1.5 and 2.8 ms. In addition, three derived MR images were generated, i.e. two-point Dixon water/fat separation and R2* (1/T2*) map. Furthermore, two spatial features, i.e. local binary pattern (S-1) and relative spatial coordinates (S-2), were incorporated. A direct-mapping operator was generated using Artificial Neural Networks (ANNs) for transforming the MR features to a pseudo-CT. CT images served as the training data and, using a leave-one-out method, for performance evaluation using mean prediction deviation (MPD), mean absolute prediction deviation (MAPD), and correlation coefficient (R). Results: The errors between measured CT and pseudo-CT declined dramatically when the spatial features, i.e. S-1 and S-2, were included. The MPD, MAPD, and R were, respectively, 5±57 HU, 141±41 HU, and 0.815±0.066 for results generated by the ANN trained without the spatial features and were 32±26 HU, 115±18 HU, and 0.869±0.035 with the spatial features. The estimation errors of the pseudo-CT were smaller when both the S-1 and S-2 were used together than when either the S-1 or the S-2 was used. Pseudo-CT generation (256×256×256 voxels) by ANN took < 0.5 s using a computer having an Intel i7 3.4GHz CPU and 16 GB RAM. Conclusion: The proposed direct-mapping ANN approach is a technically accurate, clinically practical method for pseudo-CT generation and can potentially help improve the accuracy of MR-AC and MR-RTP applications. Please note that the project was completed with partial funding from the Ohio Department of Development grant TECH 11-063 and a sponsored research agreement with Philips Healthcare that is managed by Case Western Reserve University. As noted in the affiliations, some of the authors are Philips employees.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

A novel artificial condensed matter lattice and a new platform for one-dimensional topological phases

Engineered lattices in condensed matter physics, such as cold-atom optical lattices or photonic crystals, can have properties that are fundamentally different from those of naturally occurring electronic crystals. We report a novel type of artificial quantum matter lattice. Our lattice is a multilayer heterostructure built from alternating thin films of topological and trivial insulators. Each interface within the heterostructure hosts a set of topologically protected interface states, and by making the layers sufficiently thin, we demonstrate for the first time a hybridization of interface states across layers. In this way, our heterostructure forms an emergent atomic chain, where the interfaces act as lattice sites and the interface states act as atomic orbitals, as seen from our measurements by angle-resolved photoemission spectroscopy. By changing the composition of the heterostructure, we can directly control hopping between lattice sites. We realize a topological and a trivial phase in our superlattice band structure. We argue that the superlattice may be characterized in a significant way by a one-dimensional topological invariant, closely related to the invariant of the Su-Schrieffer-Heeger model. Our topological insulator heterostructure demonstrates a novel experimental platform where we can engineer band structures by directly controlling how electrons hop between lattice sites.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2017

Moiré excitons: From programmable quantum emitter arrays to spin-orbit–coupled artificial lattices

Highly uniform and ordered nanodot arrays are crucial for high-performance quantum optoelectronics, including new semiconductor lasers and single-photon emitters, and for synthesizing artificial lattices of interacting quasiparticles toward quantum information processing and simulation of many-body physics. Van der Waals heterostructures of two-dimensional semiconductors are naturally endowed with an ordered nanoscale landscape, that is, the moiré pattern that laterally modulates electronic and topographic structures. We find that these moiré effects realize superstructures of nanodot confinements for long-lived interlayer excitons, which can be either electrically or strain tuned from perfect arrays of quantum emitters to excitonic superlattices with giant spin-orbit coupling (SOC). Besides the wide-range tuning of emission wavelength, the electric field can also invert the spin optical selection rule of the emitter arrays. This unprecedented control arises from the gauge structure imprinted on exciton wave functions by the moiré, which underlies the SOC when hopping couples nanodots into superlattices. We show that the moiré hosts complex hopping honeycomb superlattices, where exciton bands feature a Dirac node and two Weyl nodes, connected by spin-momentum–locked topological edge modes.

36 MATERIALS SCIENCE↗
DOE OSTI2020

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↗
DOE OSTI2023

Nanowire photochemical diodes for artificial photosynthesis

Artificial photosynthesis can provide a solution to our current energy needs by converting small molecules such as water or carbon dioxide into useful fuels. This can be accomplished using photochemical diodes, which interface two complementary light absorbers with suitable electrocatalysts. Nanowire semiconductors provide unique advantages in terms of light absorption and catalytic activity, yet great control is required to integrate them for overall fuel production. In this review, we journey across the progress in nanowire photoelectrochemistry (PEC) over the past two decades, revealing design principles to build these nanowire photochemical diodes. To this end, we discuss the latest progress in terms of nanowire photoelectrodes, focusing on the interplay between performance, photovoltage, electronic band structure, and catalysis. Emphasis is placed on the overall system integration and semiconductor-catalyst interface, which applies to inorganic, organic, or biologic catalysts. Last, we highlight further directions that may improve the scope of nanowire PEC systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Periplasmic biomineralization for semi-artificial photosynthesis

Semiconductor-based biointerfaces are typically established either on the surface of the plasma membrane or within the cytoplasm. In Gram-negative bacteria, the periplasmic space, characterized by its confinement and the presence of numerous enzymes and peptidoglycans, offers additional opportunities for biomineralization, allowing for nongenetic modulation interfaces. We demonstrate semiconductor nanocluster precipitation containing single- and multiple-metal elements within the periplasm, as observed through various electron- and x-ray-based imaging techniques. The periplasmic semiconductors are metastable and display defect-dominant fluorescent properties. Unexpectedly, the defect-rich (i.e., the low-grade) semiconductor nanoclusters produced in situ can still increase adenosine triphosphate levels and malate production when coupled with photosensitization. We expand the sustainability levels of the biohybrid system to include reducing heavy metals at the primary level, building living bioreactors at the secondary level, and creating semi-artificial photosynthesis at the tertiary level. The biomineralization-enabled periplasmic biohybrids have the potential to serve as defect-tolerant platforms for diverse sustainable applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2018

Adjustment of Non-linear Interaction Parameters for Relativistic Mean Field Approach by Using Artificial Neural Networks

The relativistic mean field (RMF) model with a small number of adjusted parameters has been used successfully in the last thirty years for predictions of various ground-state nuclear properties of nuclei. In this model, Dirac and Klein–Gordon like equations obtained from application of variation principle on phenomenological Lagrangian density are solved iteratively for calculations of nuclear properties of nuclei. For this purpose, parameters such as masses of considered mesons, nucleon–meson coupling constants, and self-couplings of mesons are needed and they are fitted from experimental data. Some parameter sets for RMF model introduced to correct predictions of nuclear properties of nuclei cover nuclidic chart. Besides Artificial Neural Network (ANN) method is used successfully in many field of science as in nuclear physics. ANN is known as a very powerful tool that are used when standard techniques fail to estimate the correlation between the variables. In the present study, ANN method has been employed to check its understanding capability of relations between RMF model parameters and their predictions on the ground-state binding energies of some spherical nuclei. Understanding capability of ANN method for these relations of considered nuclei has been found well. Based on this success, new non-linear parameter set for RMF model called DEFNE by us have been produced by using ANN method. Furthermore, predictions of RMF model with DEFNE parameter set for ground-state binding energies and charge radii of nuclei cover nuclidic chart have been found as in agreement with the available experimental data.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2017

Search for sterile neutrinos in gallium experiments with artificial neutrino sources

The possibility of the BEST experiment on electron neutrino disappearance with intense artificial sources of electron neutrino {sup 51}Cr is considered. BEST has the great potential to search for transitions of active neutrinos to sterile states with Δm{sup 2} ∼ 1 eV{sup 2} and to set the limits on short baseline electron neutrino disappearance oscillation parameters. The possibility of the further constraints the oscillation parameters region with using {sup 65}Zn source is discussed.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2018

On the Application of Strain-Compensating GaAsP Layers for the Growth of InGaAs/GaAs Quantum-Well Laser Heterostructures Emitting at Wavelengths above 1100 nm on Artificial Ge/Si Substrates

Stressed InGaAs/GaAs quantum-well laser structures are grown by gas-phase epitaxy from organometallic compounds on GaAs substrates and artificial Ge/Si substrates based on Si(001) with an epitaxial metamorphic Ge layer. To suppress the relaxation of elastic stresses during the growth of InGaAs quantum wells with a high fraction of In, strain-compensating GaAsP layers are applied. The structural and radiative properties of the samples grown on substrates of various types are compared. Stimulated radiation at wavelengths up to 1.24 μm at 300 K is obtained for structures grown on GaAs substrates and at wavelengths up to 1.1 μm at 77 K, for structures grown on Ge/Si substrates.

36 MATERIALS SCIENCE↗
DOE OSTI2019

Simulation of a Detector of Visible and Near-IR Electromagnetic Radiation Based on Artificial Diamond

A method for calculation of the I–V characteristic is proposed for a detector of visible and near-IR electromagnetic radiation based on artificial diamond with allowance for vertical flow of electric current. The method can be used when the free-path length of carriers in diamond is less than the scale of variations in the concentration of carriers. The method is used to determine the following detector characteristics: the dependence of current on voltage, distribution of carrier concentration, and electric potential for a particular variant of a photodetector based on polycrystalline diamond film consisting of nanosized single crystals doped with boron.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2019

Using Artificial Neural Network in Nuclear Spin Echo Experiments

The possibility of using an artificial neural network for discriminating nuclear spin echo signals recorded under conditions where the echo signal intensity is comparable to the noise amplitude is demonstrated. It is proposed to teach the neural network using data obtained by superposition of the model Gaussian signals onto experimentally measured noise signals.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning

Here, we introduce a method to convert physics-informed neural networks (PINNs), commonly used in scientific machine learning, to spiking neural networks (SNNs), which are expected to have higher energy efficiency compared to traditional artificial neural networks (ANNs). We first extend the calibration technique of SNNs to arbitrary activation functions beyond ReLU, making it more versatile, and we prove a theorem that ensures the effectiveness of the calibration. We successfully convert PINNs to SNNs, enabling computational efficiency for diverse regression tasks in solving multiple differential equations, including the unsteady Navier–Stokes equations. We demonstrate great gains in terms of overall efficiency, including separable PINNs (SPINNs), which accelerate the training process. Overall, this is the first work of this kind and the proposed method achieves relatively good accuracy with low spike rates.

PINN↗
DOE OSTI2023

Artificial Intelligence for a Resilient and Flexible Power Grid

Recent widespread and extreme natural disasters as well as the drive towards clean sustainable energy sources necessitate a transformational operational and technological approaches to improve power grid resilience. Convergence of artificial intelligence (AI), distributed computing, and connectivity technologies enables these new approaches to deliver a sustainable electric grid. In particular, AI-based techniques can enable proactive decision-making by processing massive amounts of data to deliver intelligence at various levels of the system, edge devices to control room. In this chapter, we will explore the potential applications AI-based technology will unlock and challenges to address to achieve a sustainable, flexible power grid.

Omitaomu, Femi↗
DOE OSTI2023

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↗