Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Machine”

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 1,351 records · Page 75

Machine learning for domain transfer between simulated and experimental 2D X-ray diffraction patterns using generative adversarial networks

X-ray diffraction (XRD) is a well-established technique for analyzing materials at an atomic level. Dynamic compression experiments (DCE), in which materials are subject to extreme pressures, can provide fundamental understanding to pressure-induced phase transitions and compression of the crystal lattice. The analysis of XRD patterns from highly compressed samples is non-trivial given the sparsity of data, high experimental costs, and the fact that the data is often marred with X-ray background and other artifacts. While accurate computational frameworks exist, they solve the forward problem—from structures and orientations to XRD patterns. Solving the inverse problem for 2D experimental diffraction patterns is currently a complex manual process of matching and comparing experimentally observed patterns to computationally generated ones. Machine learning is a promising tool for automating the matching process but often requires data-intensive architectures. Here, in this study, we use a CycleGAN to translate the domain of limited experimental data to a domain in which there is readily available simulated data. This domain shift allows data-intensive machine learning models that have only been trained on simulated XRD patterns to be used in the analysis of experiments.

Brozak, Samantha Jean [Sandia National Laboratorie↗

A novel implicit hybrid machine learning model and its application for reinforcement learning

A novel methodology to develop implicit hybrid models is presented. PyTorch is used to integrate physics-based equations with machine learning models. Automatic differentiation of the hybrid model is leveraged to solve the implicit equations. Iterative solving enables gradient based updates to the machine learning model. The novel methodology is compared to an explicit hybrid approach on a continuously stirred tank reactor (CSTR). The novel method results in a lower modelling error. Both hybrid models effectively train with noisy data. To test the implicit hybrid model, it is employed as a reinforcement learning (RL) training model. The RL algorithm trained on the hybrid model outperforms real time optimization of the CSTR and performs nearly as well as RL trained directly on the CSTR and a traditional gradient based approach. Training RL directly on the CSTR requires over 60,000 system interactions compared to 6000 historical data points for hybrid model development.

42 ENGINEERING↗

eqtools: Modular, extensible, open-source, cross-machine Python tools for working with magnetic equilibria

As plasma physics research for fusion energy transitions to an increasing emphasis on cross-machine collaboration and numerical simulation, it becomes increasingly important that portable tools be developed to enable data from diverse sources to be analyzed in a consistent manner. This paper presents eqtools, a modular, extensible, open-source toolkit implemented in the Python programming language for handling magnetic equilibria and associated data from tokamaks. eqtools provides a single interface for working with magnetic equilibrium data, both for handling derived quantities and mapping between coordinate systems, extensible to function with data from different experiments, data formats, and magnetic reconstruction codes, replacing the diverse, non-portable solutions currently in use. Moreover, while the open-source Python programming language offers a number of advantages as a scripting language for research purposes, the lack of basic tokamak-specific functionality has impeded the adoption of the language for regular use. Implementing equilibrium-mapping tools in Python removes a substantial barrier to new development in and porting legacy code into Python. In this paper, we introduce the design of the eqtools package and detail the workflow for usage and expansion to additional devices. Additionally, the implementation of a novel three-dimensional spline solution (in two spatial dimensions and in time) is also detailed. Finally, verification and benchmarking for accuracy and speed against existing tools are detailed. Wider deployment of these tools will enable efficient sharing of data and software between institutions and machines as well as self-consistent analysis of the shared data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Using machine learning for particle track identification in the CLAS12 detector

Particle track reconstruction is the most computationally intensive process in nuclear physics experiments. Traditional algorithms use a combinatorial approach that exhaustively tests track measurements ("hits") to identify those that form an actual particle trajectory. In this article, we describe the development of four machine learning (ML) models that assist the tracking algorithm by identifying valid track candidates from the measurements in drift chambers. Several types of machine learning models were tested, including: Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), Extremely Randomized Trees (ERT) and Recurrent Neural Networks (RNN). As a result of this work, an MLP network classifier was implemented as part of the CLAS12 reconstruction software to provide the tracking code with recommended track candidates. The resulting software achieved accuracy of greater than 99% and resulted in an end-to-end speedup of 35% compared to existing algorithms.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DeePKS-kit: A package for developing machine learning-based chemically accurate energy and density functional models

We introduce DeePKS-kit, an open-source software package for developing machine learning based energy and density functional models. DeePKS-kit is interfaced with PyTorch, an open-source machine learning library, and PySCF, an ab initio computational chemistry program that provides simple and customized tools for developing quantum chemistry codes. It supports the DeePHF and DeePKS methods. In addition to explaining the details in the methodology and the software, we also provide an example of developing a chemically accurate model for water clusters.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales

As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.

Houben, Nikolaus↗

Hamiltonian methods of modeling and control of AC microgrids with spinning machines and inverters

This study presents a novel approach to the modeling and control of AC microgrids that contain spinning machines, power electronic inverters and energy storage devices. The inverters in the system can adjust their frequencies and power angles very quickly, so the modeling focuses on establishing a common reference frequency and angle in the microgrid based on the spinning machines. From this dynamic model, nonlinear Hamiltonian surface shaping and power flow control method is applied and shown to stabilize. From this approach the energy flow in the system is used to show the energy storage device requirements and limitations for the system. This paper first describes the model for a single bus AC microgrid with a Hamiltonian control, then extends this model and control to a more general class of multiple bus AC microgrids. Finally, simulation results demonstrate the efficacy of the approach in stabilizing and optimization of the microgrid.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Support Vector Machine-Based Prediction of Local Tumor Control After Stereotactic Body Radiation Therapy for Early-Stage Non-Small Cell Lung Cancer

Background: Several prognostic factors for local tumor control probability (TCP) after stereotactic body radiation therapy (SBRT) for early stage non-small cell lung cancer (NSCLC) have been described, but no attempts have been undertaken to explore whether a nonlinear combination of potential factors might synergistically improve the prediction of local control. Methods and Materials: We investigated a support vector machine (SVM) for predicting TCP in a cohort of 399 patients treated at 13 German and Austrian institutions. Among 7 potential input features for the SVM we selected those most important on the basis of forward feature selection, thereby evaluating classifier performance by using 10-fold cross-validation and computing the area under the ROC curve (AUC). The final SVM classifier was built by repeating the feature selection 10 times with different splitting of the data for cross-validation and finally choosing only those features that were selected at least 5 out of 10 times. It was compared with a multivariate logistic model that was built by forward feature selection. Results: Local failure occurred in 12% of patients. Biologically effective dose (BED) at the isocenter (BED{sub ISO}) was the strongest predictor of TCP in the logistic model and also the most frequently selected input feature for the SVM. A bivariate logistic function of BED{sub ISO} and the pulmonary function indicator forced expiratory volume in 1 second (FEV1) yielded the best description of the data but resulted in a significantly smaller AUC than the final SVM classifier with the input features BED{sub ISO}, age, baseline Karnofsky index, and FEV1 (0.696 ± 0.040 vs 0.789 ± 0.001, P<.03). The final SVM resulted in sensitivity and specificity of 67.0% ± 0.5% and 78.7% ± 0.3%, respectively. Conclusions: These results confirm that machine learning techniques like SVMs can be successfully applied to predict treatment outcome after SBRT. Improvements over traditional TCP modeling are expected through a nonlinear combination of multiple features, eventually helping in the task of personalized treatment planning.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Automated Segmentation of the Parotid Gland Based on Atlas Registration and Machine Learning: A Longitudinal MRI Study in Head-and-Neck Radiation Therapy

Purpose: To develop an automated magnetic resonance imaging (MRI) parotid segmentation method to monitor radiation-induced parotid gland changes in patients after head and neck radiation therapy (RT). Methods and Materials: The proposed method combines the atlas registration method, which captures the global variation of anatomy, with a machine learning technology, which captures the local statistical features, to automatically segment the parotid glands from the MRIs. The segmentation method consists of 3 major steps. First, an atlas (pre-RT MRI and manually contoured parotid gland mask) is built for each patient. A hybrid deformable image registration is used to map the pre-RT MRI to the post-RT MRI, and the transformation is applied to the pre-RT parotid volume. Second, the kernel support vector machine (SVM) is trained with the subject-specific atlas pair consisting of multiple features (intensity, gradient, and others) from the aligned pre-RT MRI and the transformed parotid volume. Third, the well-trained kernel SVM is used to differentiate the parotid from surrounding tissues in the post-RT MRIs by statistically matching multiple texture features. A longitudinal study of 15 patients undergoing head and neck RT was conducted: baseline MRI was acquired prior to RT, and the post-RT MRIs were acquired at 3-, 6-, and 12-month follow-up examinations. The resulting segmentations were compared with the physicians' manual contours. Results: Successful parotid segmentation was achieved for all 15 patients (42 post-RT MRIs). The average percentage of volume differences between the automated segmentations and those of the physicians' manual contours were 7.98% for the left parotid and 8.12% for the right parotid. The average volume overlap was 91.1% ± 1.6% for the left parotid and 90.5% ± 2.4% for the right parotid. The parotid gland volume reduction at follow-up was 25% at 3 months, 27% at 6 months, and 16% at 12 months. Conclusions: We have validated our automated parotid segmentation algorithm in a longitudinal study. This segmentation method may be useful in future studies to address radiation-induced xerostomia in head and neck radiation therapy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Machine learning reveals sequence-function relationships in family 7 glycoside hydrolases

Family 7 glycoside hydrolases (GH7) are among the principal enzymes for cellulose degradation in nature and industrially. These important enzymes are often bimodular, including a catalytic domain and carbohydrate binding module (CBM) attached via a flexible linker, and exhibit an active site that binds cello-oligomers of up to ten glucosyl moieties. GH7 cellulases consist of two major subtypes: cellobiohydrolases (CBH) and endoglucanases (EG). Despite the critical importance of GH7 enzymes, there remain gaps in our understanding of how GH7 sequence and structure relate to function. Here, we employed machine learning to gain data-driven insights into relationships between sequence, structure, and function across the GH7 family. Machine-learning models, trained only on the number of residues in the active-site loops as features, were able discriminate GH7 CBHs and EGs with up to 99% accuracy, demonstrating that the lengths of loops A4, B2, B3, and B4 strongly correlate with functional subtype across the GH7 family. Classification rules were derived such that specific residues at 42 different sequence positions each predicted the functional subtype with accuracies surpassing 87%. A random forest model trained on residues at 19 positions in the catalytic domain predicted the presence of a CBM with 89.5% accuracy. Our ML results recapitulate, as top-performing features, a substantial number of the sequence positions determined by previous experimental studies to play vital roles in GH7 activity. We surmise that the yet-to-be-explored sequence positions among the top-performing features also contribute to GH7 functional variation and may be exploited to understand and manipulate function.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Machine learning models for estimating contamination across different curbside collection strategies

Contaminated recyclables, which are frequently discarded as waste, pose a significant challenge to the implementation of a circular economy. These contaminated recyclables impede the circulation of resources, resulting in higher processing costs at material recovery facilities (MRFs). Over the past few decades, machine learning (ML) models such as linear regression (LR), support vector machine (SVM), and random forest (RF) have evolved to provide new methods for predicting inbound contamination rates in addition to traditional statistical models. In this study, we applied ML models to predict inbound contamination rates using demographic features from 15 counties in the U.S. with different curbside collection strategies. In general, we found that ML models outperformed linear mixed models. Specifically, SVM models had the highest performance (R 2 = 0.75; mean absolute error (MAE) = 0.06), which may be due to their ability to model nonlinear relationships between features and inbound contamination rates. Further, the key predictor was population, with poverty rate being positively correlated and median age negatively correlated with inbound contamination rates. To improve the management of contamination and enhance the implementation of a circular economy, better models are needed to understand and estimate inbound contamination rates as well as identify critical factors in the present and future.

54 ENVIRONMENTAL SCIENCES↗

PARIS: Predicting application resilience using machine learning

The traditional method to study application resilience to errors in HPC applications uses fault injection (FI), a time-consuming approach. Furthermore, while analytical models have been built to overcome the inefficiencies of FI, they lack accuracy. In this paper, we present PARIS, a machine-learning method to predict application resilience that avoids the time-consuming process of random FI and provides higher prediction accuracy than analytical models. PARIS captures the implicit relationship between application characteristics and application resilience, which is difficult to capture using most analytical models. We overcome many technical challenges for feature construction, extraction, and selection to use machine learning in our prediction approach. Our evaluation on 16 HPC benchmarks shows that PARIS achieves high prediction accuracy. PARIS is up to 450x faster than random FI (49x on average). Compared to the state-of-the-art analytical model, PARIS is at least 63% better in terms of accuracy and has comparable execution time on average.

97 MATHEMATICS AND COMPUTING↗

The plastic flow machining: A new SPD process for producing metal sheets with gradient structures

Highlights: • A new process named Plastic Flow Machining is presented to produce thin sheets by an extrusion operation from bulk material. • The produced sheets present ultra-fine grain structures, good mechanical properties and high formability. • A deformation gradient was found across the thickness of the sheet regarding plastic strain, microstructure and texture. - Abstract: A new severe plastic deformation process is presented – the plastic flow machining – an extrusion process during which a sheet is formed through a lateral opening of the die in a single operation. The sheet is heavily deformed presenting an ultra-fine grain structure. Experimental results are presented for commercially pure aluminum concerning microstructures, textures and mechanical properties. A gradient structure was found across the thickness of the sheet concerning plastic strain, grain size and texture. Only simple shear textures were seen. The material strength increased by a factor of three with significant ductility and with relatively high Lankford parameter.

36 MATERIALS SCIENCE↗

Solidification cracking of refractory alloys: a computational and machine learning study to investigate composition-dependence for improved weldability and additive manufacturability

Large-batch numerical, CALculation of PHAse Diagrams (CALPHAD)-based solidification cracking calculations are performed and then analyzed with machine learning methods to generate models that relate chemistry of refractory alloys to cracking susceptibility. Kou’s solidification cracking index is used to study the refractory alloys including O, N, C binary mixtures with Mo, Ta, Nb, and W, the molybdenum-based TZM, Niobium-based C103, and Tantalum-based T111 and Ta-10 W, as well as hypothetical refractory ternary alloys. Findings strongly validate Kou’s Crack Susceptibility Index (CSI) against Varestraint test data for Nb- and Ta-based alloys, establishing CSI thresholds where refractory alloys with CSI < 15,000 K are likely weldable, CSI > 15,000 K are prone to cracking, and CSI > 25,000 K are likely unweldable (or unprintable). Furthermore, interstitial elements C, N, and O significantly increase crack susceptibility, with some existing material specifications coinciding with peak cracking susceptibility concentrations. Finally, machine learning-derived elemental potency factors enable rapid prediction of CSI from alloy chemistry for C103, TZM, Ta-10 W, and T-111 alloys. These results provide practical guidance for feedstock selection, powder reuse limits, and alloy specification amendments for welding and additive manufacturing applications.

36 MATERIALS SCIENCE↗

GMFOLD: Subgraph matching for high-throughput DNA-aptamer secondary structure classification and machine learning interpretability

Aptamers are oligonucleotide receptors that bind to their targets with high affinity. Here, we consider aptamers comprised of single-stranded DNA that undergo target-binding-induced conformational changes, giving rise to unique secondary and tertiary structures. Given a specific aptamer primary sequence, there are well-established computational tools (notably mfold) to predict the secondary structure via free energy minimization algorithms. While mfold generates secondary structures for individual sequences, there is a need for a high-throughput process whereby thousands of DNA structures can be predicted in real-time for use in an interactive setting, when combined with aptamer selections that generate candidate pools that are too large to be experimentally interrogated. We developed a new Python code for high-throughput aptamer secondary structure determination (GMfold). GMfold uses subgraph matching methods to group aptamer candidates by secondary structure similarities. We also improve an open-source code, SeqFold, to incorporate subgraph matching concepts. We represent each secondary structure as a lowest-energy bipartite subgraph matching of the DNA graph to itself. These new tools enable thousands of DNA sequences to be compared based on their secondary structures, using machine-learning algorithms. This process is advantageous when analyzing sequences that arise from aptamer selections via systematic evolution of ligands by exponential enrichment (SELEX). This work is a building block for future machine-learning-informed DNA-aptamer selection processes to identify aptamers with improved target affinity and selectivity and advance aptamer biosensors and therapeutics.

Aptamer↗

Machine learning for reactor power monitoring with limited labeled data

Real-time reactor power monitoring is critical for a variety of nuclear applications, spanning safety, security, operations, and maintenance. While machine learning methods have shown promise in monitoring reactor power levels, there is limited research on their efficacy in label-starved environments. The goal of this work is to assess the feasibility of classifying nuclear reactor power level using multisource data in scenarios with limited labels. Data were collected using low-resolution multisensors at four nuclear reactor facilities: two large research reactors and two TRIGA reactors. Within each pair, one reactor dataset served as the source and the other as the target in a transfer learning paradigm. Twenty-three supervised models were trained on labeled sequences of magnetic field and acceleration data from each of the target sites. Self-learning and transfer learning methods were applied to the top performing models to assess their classification performance with increasing amounts of labeled data. While reactor power level classification was achieved with a Matthews Correlation Coefficient of up to 0.739 ± 0.003 and 0.622 ± 0.009 with only 400 sequences per power state for the large research reactor and TRIGA target sites, respectively, self-learning and transfer learning leveraging source site data did not improve target classification performance. These findings suggest that alternative methods, such as higher sensitivity sensors, digital twins, or the use of physics-informed models, are required to enable high-performance classification in machine learning approaches to reactor monitoring with a dearth of target ground truth.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Inter-ELM pedestal localized fluctuations in tokamaks: Summary of multi-machine observations

A variety of experimental studies on pedestal localized fluctuations appearing in between crashes of edge localized modes (ELMs) across several tokamaks have been reviewed and summarized. The onset of the inter-ELM fluctuations is correlated with the evolution of the pedestal gradients. Three profile recovery phases are extracted, which are interlinked with the onsets of different kinds of pedestal fluctuations. Across machines it is found that the pedestal fluctuations can be assorted into at least three categories. These are determined by the fluctuation onset in the ELM cycle, observed frequency range and radial location in the pedestal. Further, the categories might be also related to different instabilities. Similar observations at various machines may point to a underlying generation mechanism that acts similarly for presently accessible pedestal parameter ranges.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Uncertainty quantification for Multiphase-CFD simulations of bubbly flows: a machine learning-based Bayesian approach supported by high-resolution experiments

In this paper, we developed a machine learning-based Bayesian approach to inversely quantify and reduce the uncertainties of multiphase computational fluid dynamics (MCFD) simulations for bubbly flows. The proposed approach is supported by high-resolution two-phase flow measurements, including those by double-sensor conductivity probes, high-speed imaging, and particle image velocimetry. Local distributions of key physical quantities of interest (QoIs), including the void fraction and phasic velocities, are obtained to support the Bayesian inference. In the process, the epistemic uncertainties of the closure relations are inversely quantified while the aleatory uncertainties from stochastic fluctuations of the system are evaluated based on experimental uncertainty analysis. The combined uncertainties are then propagated through the MCFD solver to obtain uncertainties of the QoIs, based on which probability-boxes are constructed for validation. The proposed approach relies on three machine learning methods: feedforward neural networks and principal component analysis for surrogate modeling, and Gaussian processes for model form uncertainty modeling. The whole process is implemented within the framework of an open-source deep learning library PyTorch with graphics processing unit (GPU) acceleration, thus ensuring the efficiency of the computation. The results demonstrate that with the support of high-resolution data, the uncertainties of MCFD simulations can be significantly reduced. The proposed approach has the potential for other applications that involve numerical models with empirical parameters.

42 ENGINEERING↗