Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “COMPARATIVE EVALUATIONS”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,333 records · Page 74
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Dynamic energy system modeling using hybrid physics-based and machine learning encoder–decoder models

Three model configurations are presented for multi-step time series predictions of the heat absorbed by the water and steam in a thermal power plant. The models predict over horizons of 2, 4, and 6 steps into the future, where each step is a 5-minute increment. The evaluated models are a pure machine learning model, a novel hybrid machine learning and physics-based model, and the hybrid model with an incomplete dataset. The hybrid model deconstructs the machine learning into individual boiler heat absorption units: economizer, water wall, superheater, and reheater. Each configuration uses a gated recurrent unit (GRU) or a GRU-based encoder–decoder as the deep learning architecture. Mean squared error is used to evaluate the models compared to target values. The encoder–decoder architecture is over 11% more accurate than the GRU only models. The hybrid model with the incomplete dataset highlights the importance of the manipulated variables to the system. The hybrid model, compared to the pure machine learning model, is over 10% more accurate on average over 20 iterations of each model. Automatic differentiation is applied to the hybrid model to perform a local sensitivity analysis to identify the most impactful of the 72 manipulated variables on the heat absorbed in the boiler. The models and sensitivity analyses are used in a discussion about optimizing the thermal power plant.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

GrainGNN: A dynamic graph neural network for predicting 3D grain microstructure

We propose GrainGNN, a surrogate model for the evolution of polycrystalline grain structure under rapid solidification conditions in metal additive manufacturing. High fidelity simulations of solidification microstructures are typically performed using multicomponent partial differential equations (PDEs) with moving interfaces. The inherent randomness of the PDE initial conditions (grain seeds) necessitates ensemble simulations to predict microstructure statistics, e.g., grain size, aspect ratio, and crystallographic orientation. Here, currently such ensemble simulations are prohibitively expensive and surrogates are necessary.In GrainGNN, we use a dynamic graph to represent interface motion and topological changes due to grain coarsening. We use a reduced representation of the microstructure using hand-crafted features; we combine pattern finding and altering graph algorithms with two neural networks, a classifier (for topological changes) and a regressor (for interface motion). Both networks have an encoder-decoder architecture; the encoder has a multi-layer transformer long-short-term-memory architecture; the decoder is a single layer perceptron.We evaluate GrainGNN by comparing it to high-fidelity phase field simulations for in-distribution and out-of-distribution grain configurations for solidification under laser power bed fusion conditions. GrainGNN results in 80%–90% pointwise accuracy; and nearly identical distributions of scalar quantities of interest (QoI) between phase field and GrainGNN simulations compared using Kolmogorov-Smirnov test. GrainGNN's inference speedup (PyTorch on single x86 CPU) over a high-fidelity phase field simulation (CUDA on a single NVIDIA A100 GPU) is 150×–2000× for 100-initial grain problem. Further, using GrainGNN, we model the formation of 11,600 grains in 220 seconds on a single CPU core.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Exciton Delocalization in Indolenine Squaraine Aggregates Templated by DNA Holliday Junction Scaffolds

Exciton delocalization plays a prominent role in the photophysics of molecular aggregates, ultimately governing their particular function or application. DNA is a compelling scaffold in which to template molecular aggregates and promote exciton delocalization. As individual dye molecules are the basis of exciton delocalization in molecular aggregates, their judicious selection is important. Motivated by their excellent photostability and spectral properties, here we examine the ability of squaraine dyes to undergo exciton delocalization when aggregated via a DNA Holliday junction (HJ) template. A commercially available indolenine squaraine dye was chosen for the study given its strong structural resemblance to Cy5, a commercially available cyanine dye previously shown to undergo exciton delocalization in DNA HJs. Three types of DNA-dye aggregate configurations—transverse dimer, adjacent dimer, and tetramer—were investigated. Signatures of exciton delocalization were observed in all squaraine-DNA aggregates. Specifically, strong blue shift and Davydov splitting were observed in steady-state absorption spectroscopy and exciton-induced features were evident in circular dichroism spectroscopy. Strongly suppressed fluorescence emission provided additional, indirect evidence for exciton delocalization in the DNA-templated squaraine dye aggregates. To quantitatively evaluate and directly compare the excitonic Coulombic coupling responsible for exciton delocalization, the strength of excitonic hopping interactions between the dyes were obtained by simultaneous fitting the experimental steady-state absorption and CD spectra via a Holstein-like Hamiltonian in which, following the theoretical approach of Kühn, Renger, and May, the dominant vibrational mode is explicitly considered. The excitonic hopping strength within indolenine squaraines was found to be comparable to that of the analogous Cy5 DNA-templated aggregate. The squaraine aggregates adopted primarily an H-type (dyes oriented parallel to each other) spatial arrangement. Extracted geometric details of dye mutual orientation in the aggregates enabled close comparison of aggregate configurations and the elucidation of the influence of dye angular relationship on excitonic hopping interactions in squaraine aggregates. Furthermore, these results encourage the application of squaraine-based aggregates in next generation systems driven by molecular excitons.

36 MATERIALS SCIENCE↗
DOE OSTI2023

A proposed method for addressing large unphysical uncertainties in mubar

Mubar uncertainties in Section MF 34 MT 2 of ENDF/B-VIII.0 data are sometimes too large. Physical limitations of the bounds of mubar limit the maximum uncertainty to be < 1.0 and usually $\ll$ 1.0. Two ad hoc methods are proposed to artificially constrain the randomly sampled values of mubar to allowable values. The application of NJOY’s mubar covariance matrix to the “sandwich rule” is also discussed and a consistent way to apply sensitivity coefficients is described. Mubar uncertainties for the Jezebel k eff were found to be 156 pcm – a value comparable to other evaluated cross section uncertainties.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Life Cycle Assessment and Life Cycle Cost Analysis of Repurposing Decommissioned Wind Turbine Blades as High-Voltage Transmission Poles

Wind energy is widely deployed and will likely grow in service of reducing the world’s dependency on fossil fuels. The first generation of wind turbines are now coming to the end of their service lives, and there are limited options for the reuse or recycling of the composite materials they are made of. Current literature has verified that there is no existing recycling pathway (i.e., mechanical, chemical, thermal methods of recovery, etc.) for end-of-life materials in wind blades that can meet cost parity with landfilling in the US. However, to the authors’ knowledge there is no study to date that uncovers the cost structures associated with repurposing wind turbine blades in the US. Repurposing could offer a cost-competitive advantage through displacement of higher-value products, rather than materials or chemical constituents alone. This study implements life cycle assessment (LCA) and life cycle cost analysis (LCC) to assess the environmental and financial implications at each stage of repurposing wind turbine blades as the primary load-carrying elements for high-voltage transmission line structures in the United States. This case study contribution to knowledge is based on the successful management of construction waste by analyzing an application for repurposing construction demolition waste. Specifically, this study presents an environmental and financial analysis of repurposing wind turbine blades as transmission line poles. Under this case study, our results show that BladePoles have lower greenhouse gas emissions than steel poles, and we anticipate BladePoles will be less costly than steel poles. Overall emissions are most sensitive to combustion emissions, driven primarily by transportation distance and hours of required crane operations during the installation process. Compared to other evaluated recycling methods, repurposing wind blades as BladePoles has the least overall global warming potential.

42 ENGINEERING↗
DOE OSTI2022

Modeling of transient conduction in building envelope assemblies: A review

As buildings age, retrofits are becoming an increasingly important topic for the ever-growing and aging existing building stock. To compare designs or evaluate in-service building envelopes, thermal modeling is utilized to evaluate the thermal performance of envelope assemblies; however, it can be difficult to model the thermal performance of as-built assemblies due to degradation or missing documentation. To address this issue, inverse modeling can be applied to infer the properties of as-built envelope assemblies. This paper presents a review of the literature and published methods to model and infer the transient conductive performance of building envelopes. This review serves as a survey of existing transient conduction algorithms to evaluate performance, computational speed, and relevance for inverse modeling applications. In addition to the literature review, this work also evaluates the computational performance of the most prevalent transient conduction algorithms against the ASHRAE 1052RP toolkit to assess inverse modeling potential. This methodology serves as a foundation for future research to characterize the transient thermal performance of as-built building envelope assemblies.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Determination of β -decay feeding patterns of 88 Rb and 88 Kr using the Modular Total Absorption Spectrometer at ORNL HRIBF

We report precise determination of ground-state feeding in the β decay of fission products is an important but challenging component in modeling reactor antineutrino flux and reactor decay heat. The Modular Total Absorption Spectrometer (MTAS) is a versatile NaI(Tl) detector array that determines the true β-decay pattern free from the pandemonium effect, including precise ground-state feeding intensities. In this paper, we report MTAS results of the β feeding intensities of 88 Rb and 88 Kr, fission products with large cumulative yields in nuclear reactors. By comparing MTAS results with previous measurements, 88 Rb provides a validation of MTAS's ability to determine ground-state feedings in β decays, while the precision of 88 Kr ground-state feeding is improved when compared with the Evaluated Nuclear Structure Data File (ENSDF). The investigation of sources that contribute to β feeding branching uncertainties in MTAS experiments is discussed in detail. Lastly, the deconvolution of 88 Rb decay spectra suggests that MTAS can distinguish an allowed β spectral shape from a first forbidden unique β spectral shape.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

Feature Engineering and Ensemble Methods for Imbalanced ICS Intrusion Detection: Pipeline Audit and Constrained Evaluation

Industries are becoming increasingly connected and are more vulnerable to cyberattacks due to the widened attack surface. Industrial Control Systems (ICS) are among the most critical sectors that malicious actors can target, as such attacks can cause significant operational disruption and physical damage. It is imperative to detect such attacks as early as possible. This paper evaluates constraint-conditioned optimistic performance estimates for traditional ML models in ICS intrusion detection (i.e., estimates obtained under contiguous, non-shuffled temporal evaluation without test-set alteration, but with pre-split feature engineering that may introduce temporal leakage, due to dataset constraints). Our findings are threefold. First, we quantify how iterative feature engineering affects tree-based ensemble performance and examine how pipeline decisions (split strategy, sampling scope, and cleaning policy) can inflate or reduce reported IDS results under constraint-bound evaluation. Second, we compare intrinsic class-imbalance handling across ensemble models. Third, under our current pipeline constraints (including pre-split feature engineering), CatBoost achieves the best performance on Water Storage Tank (accuracy: 0.9831, class-1 F1: 0.9682), while Light- GBM achieves the best performance on Gas Pipeline (accuracy: 0.9618, class-1 F1: 0.9086).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Comparative Analysis of Capacitive Sensors with Different Geometrical layouts for Cable Insulation Degradation Detection

This paper presents a comparative analysis between an Interdigital Capacitor (IDC) sensor and a Serpentine Capacitive (SRC) sensor. The effects of electrode layouts on sensor performance are studied by means of finite element simulation where the geometrical dimensions (except electrode length) and material characteristics of both sensors are identical. Conformal IDC and SRC sensors with equal sensor area are modeled on a cable surface. The simulation results show a tradeoff between IDC and SRC sensors in terms of sensitivity and penetration depth. The SRC sensor shows 13.3% increase in sensitivity and 16.8% increase in capacitance compared to the IDC sensor, though the electric field penetration depth of the SRC sensor is 18.8% lower than the IDC sensor. In addition, the effects of change in electrode width, inter-electrode gap, and number of electrodes on SRC and IDC sensor comparative performance are evaluated.

Interdigital Capacitance, Serpentive Capacitive Se↗
DOE OSTI2020

Enhanced Explicit Congestion Notification (EECN) in TCP with P4 Programming

In current TCP/IP networks, TCP mainly relies on packet drops as an indication of congestion. With the emergence of Explicit Congestion Notification (ECN), TCP can detect the congestion through packets with marked bits instead of dropped packets. ECN thus reduces the unnecessary delay due to packet drops, especially for bandwidth-delay sensitive connections. However, ECN still relies on the receiver for congestion indication, which incurs a round trip time (RTT) before the sender can react to the congestion. In network environments with a high bandwidth-delay product (BDP), this could be problematic. In this paper, we present an enhanced ECN mechanism for the early detection of congestion using P4 programming. In our proposed scheme, the sender does not have to wait for the receiver to indicate congestion because switches in the network can indicate congestion. We evaluate our scheme comparing our proposed solution with standard TCP and TCP with the conventional ECN. Experimental results show that our scheme outperforms ECN as the RTT grows.

ECN↗
DOE OSTI2021

A Hybrid System for Learning Classical Data in Quantum States

Deep neural network-powered artificial intelligence has rapidly changed our daily life with various applications. However, as one of the essential steps of deep neural networks, training a heavily-weighted network requires a tremendous amount of computing resources. Especially in the post Moore’s Law era, the limit of semiconductor fabrication technology has restricted the development of learning algorithms to cope with the increasing high intensity training data. Meanwhile, quantum computing has exhibited its significant potential in terms of speeding up the traditionally compute-intensive workloads. For example, Google illustrates quantum supremacy by completing a sampling calculation task in 200 seconds, which is otherwise impracticable on the world’s largest supercomputers. To this end, quantum-based learning becomes an area of interest, with the promising of a quantum speedup. In this paper, we propose GenQu, a hybrid and general-purpose quantum framework for learning classical data through quantum states. We evaluate GenQu with real datasets and conduct experiments on both simulations and real quantum computer IBM-Q. Our evaluation demonstrates that, comparing with classical solutions, the proposed models running on GenQu framework achieve similar accuracy with a much smaller number of qubits, while significantly reducing the parameter size by up to 95.86% and converging speedup by 66.67% faster.

Stein, Samuel A.↗
DOE OSTI2024

Quantum Circuit Partitioning for Scalable Noise-Aware Quantum Circuit Re-Synthesis

Re-synthesis techniques are utilized to optimize the quantum circuit. To enable scalable re-synthesis a divide-and-conquer approach is adopted that partitions the circuit into smaller blocks, which are optimized independently. Several algorithms have been proposed to minimize the block number while maximizing the gate count of each block. However, they vary in their performance and may not yield the highest output fidelity. We propose a reinforcement learning-based quantum circuit partitioning framework that incorporates the physical properties of the quantum hardware to maximize the output fidelity post-quantum circuit optimization. To accelerate the training, we also propose a noise injection method that enables on-the-fly optimization in the reinforcement learning environment, independent of the adopted optimization/re-synthesis method at the block level. We evaluate our approach compared to different partitioning techniques using various quantum benchmarks executed on IBM Q Hanoi quantum computer.

Charrwi, Mohammad Walid↗
DOE OSTI2021

On the use of air temperature and precipitation as surrogate predictors in soil respiration modelling

Soil respiration (R S ), the soil-to-atmosphere CO 2 flux that is a major component of the global carbon cycle, is strongly influenced by local soil temperature (T soil ) and water content (SWC). Regional to global-scale R S modelling thus requires this information at local scales, but few high-quality, wall-to-wall (global) T soil and SWC data exist. As a result, such modelling efforts commonly use air temperature (T air ) and monthly precipitation (P m ) as surrogate predictors, but their site-scale accuracy and potential bias are unknown. In this report we used monthly data from 880 sites across a wide variety of different environmental conditions (i.e., climate, ecosystem type, elevation, vegetation leaf habit and drainage conditions) to determine the suitability of T air as a surrogate for T soil , and data from 507 sites to examine the suitability of P m as a surrogate for SWC. Site-specific linear and second-order exponential non-linear models were compared using model evaluation metrics (i.e., slope, p-value of slope, root mean square error [RMSE], index of agreement and model efficiency). We found that T soil and T air are highly correlated and explain similar R S variability. In contrast, P m is not a good surrogate for SWC, even though P m explains a similar amount of R S variability to SWC. The wide variability in the site-specific relationships between R S and SWC means that no single relationship can be used for large-scale modelling. The results from this study support the use of T air in continental-to-global scale R S models, and highlight the urgent need for continental-to-global scale SWC datasets for the modelling and evaluation of future soil carbon dynamics under global climate change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

CO2ROpt (Feedstock Allocation Optimization Model) [SWR-22-13]

Reducing greenhouse gas emissions remains a critical challenge for the transportation and chemical sectors. The electrochemical reduction of carbon dioxide is a potential pathway for production of fuels and chemicals that uses atmospheric carbon dioxide as a feedstock. Here we present an analysis of the potential for carbon dioxide captured from point sources and via direct air capture to be utilized in electrochemical reduction under different market scenarios. Using a numerical optimization framework and national data sets, scenarios for nationwide production of ethylene, formate, and carbon monoxide are evaluated at scales comparable to current production of these molecules in the United States. We show that developing a network for production of these products at scale requires capture and utilization of significant portions of the carbon dioxide that is currently emitted from large stationary point sources. Because carbon dioxide point sources are spatially and compositionally variable, their use for carbon dioxide reduction depends on electricity prices, capture cost, and location. If the power sector in the United States is decarbonized, carbon dioxide supply decreases significantly, increasing the importance of utilizing other carbon dioxide streams, and increasing the likelihood that direct air capture plays a role in supplying carbon dioxide feedstocks. These findings provide a first insight into the feedstock and energy constraints for carbon dioxide reduction.

Badgett, Alex↗
DOE OSTI2020

Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets

Abstract The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure–Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for > 10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F 1 score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman’s aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g., > 28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.

Idakwo, Gabriel↗
DOE OSTI2023

Uncertain of uncertainties? A comparison of uncertainty quantification metrics for chemical data sets

Abstract With the increasingly more important role of machine learning (ML) models in chemical research, the need for putting a level of confidence to the model predictions naturally arises. Several methods for obtaining uncertainty estimates have been proposed in recent years but consensus on the evaluation of these have yet to be established and different studies on uncertainties generally uses different metrics to evaluate them. We compare three of the most popular validation metrics (Spearman’s rank correlation coefficient, the negative log likelihood (NLL) and the miscalibration area) to the error-based calibration introduced by Levi et al. ( Sensors 2022 , 22 , 5540). Importantly, metrics such as the negative log likelihood (NLL) and Spearman’s rank correlation coefficient bear little information in themselves. We therefore introduce reference values obtained through errors simulated directly from the uncertainty distribution. The different metrics target different properties and we show how to interpret them, but we generally find the best overall validation to be done based on the error-based calibration plot introduced by Levi et al. Finally, we illustrate the sensitivity of ranking-based methods (e.g. Spearman’s rank correlation coefficient) towards test set design by using the same toy model ferent test sets and obtaining vastly different metrics (0.05 vs. 0.65).

Rasmussen, Maria H.↗
DOE OSTI2022

Alternative analysis of the MINERVE ZPR oscillation experiments

Delayed neutrons are of fundamental importance in the field of nuclear reactor dynamics and control. However, the precursor yield fraction for a given nuclear reactor are dependent on the properties of the reactor. Thus, in-pile experiments, such as oscillation experiments are conducted in order to measure those values. In this work, an alternative analysis of the piston oscillation experiments that have been conducted in the MINERVE reactor in 2013 is performed. A new method which evolves effective terms that cancel out undesired drifts of the flux during the experiments is presented. The evaluation of the uncertainty on the values of the response function is also presented. Moreover, the effective delayed neutron fraction β{sub eff} is evaluated and is compared to results in previous works. As the analysis has led to an estimation of β{sub eff} with a large uncertainty, it has been deduced that the oscillation experiments that have been conducted in MINERVE are not a reliable method of experimentation to determine the value of β{sub eff} in the reactor and that the noise experiments are better suited for that purpose.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2026

Constructing a High‐Resolution Aftershock Catalog for the 2017 Mw 8.2 Tehuantepec Earthquake Sequence Using a Machine Learning–Based Workflow

The 8 September 2017 Mw 8.2 Tehuantepec earthquake was the largest instrumentally recorded normal‐faulting earthquake in Mexico. The mainshock occurred offshore within the Tehuantepec seismic gap, generating >30,000 aftershocks in the following year. We applied an open‐source, machine learning (ML)–assisted workflow to construct a high‐resolution aftershock catalog using data from temporary and permanent seismic networks in southern Mexico. The workflow integrates PhaseNet for phase detection; GaMMA for phase association; and VELEST, HypoInverse, and HypoDD for velocity modeling and relocation. We processed seven months of continuous waveform data from 29 broadband stations, including a temporary rapid‐response deployment that improved station coverage of the offshore rupture zone. To evaluate performance, we compared our results against analyst‐reviewed picks and event locations from the Servicio Sismológico Nacional catalog. The resulting catalog contains 11,374 relocated earthquakes and represents the most comprehensive published dataset for this sequence, incorporating the first full use of the temporary network. Relocated hypocenters show improved depth control and align well with the Slab2.0 subduction geometry, revealing clearer separation between offshore slab events and onshore crustal seismicity. This study demonstrates that combining ML‐based detection with established methods provides a scalable and reproducible approach for constructing high‐quality earthquake catalogs in tectonically complex environments and offers practical guidance for adapting similar workflows to other earthquake sequences.

Garcia, Marc [The University of Texas at El Paso, ↗