Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “generative machine learning”

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 1,693 records · Page 94

An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation

The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.

Bayesian neural network↗

Infrared spectroscopy data- and physics-driven machine learning for characterizing surface microstructure of complex materials

There is a need to characterize complex materials and their dynamics under reaction conditions to accelerate materials design. Adsorbate vibrational excitations are selective to adsorbate/surface interactions and infrared (IR) spectra associated with activating adsorbate vibrational modes are accurate, capture details of most modes, and can be obtained operando. Current interpretation depends on heuristic peak assignments for simple spectra, precluding the possibility of obtaining detailed structural information. Here, we combine data-based approaches with chemistry-dependent problem formulation to develop physics-driven surrogate models that generate synthetic IR spectra from first-principles calculations. Using synthetic IR spectra of carbon monoxide on platinum, we implement multinomial regression via neural network ensembles to learn probability distributions functions (pdfs) that describe adsorption sites and quantify uncertainty. We use these pdfs to infer detailed surface microstructure from experimental spectra and extend this methodology to other systems as a first step towards characterizing complex interfaces and closing the materials gap.

Science & Technology - Other Topics↗

Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme

A major challenge to achieving industry-scale biomanufacturing of therapeutic alkaloids is the slow process of biocatalyst engineering. Amaryllidaceae alkaloids, such as the Alzheimer’s medication galantamine, are complex plant secondary metabolites with recognized therapeutic value. Due to their difficult synthesis they are regularly sourced by extraction and purification from the low-yielding daffodil Narcissus pseudonarcissus. Here, we propose an efficient biosensor-machine learning technology stack for biocatalyst development, which we apply to engineer an Amaryllidaceae enzyme in Escherichia coli. Directed evolution is used to develop a highly sensitive (EC 50 = 20 μM) and specific biosensor for the key Amaryllidaceae alkaloid branchpoint 4’-O-methylnorbelladine. A structure-based residual neural network (MutComputeX) is subsequently developed and used to generate activity-enriched variants of a plant methyltransferase, which are rapidly screened with the biosensor. Functional enzyme variants are identified that yield a 60% improvement in product titer, 2-fold higher catalytic activity, and 3-fold lower off-product regioisomer formation. A solved crystal structure elucidates the mechanism behind key beneficial mutations.

60 APPLIED LIFE SCIENCES↗

A Data-Driven Methodology for Probabilistic Wind Power Ramp Forecasting

With increasing wind penetration, wind power ramps (WPRs) are currently drawing great attention to balancing authorities, since these wind ramps largely affect power system operations. To help better manage and dispatch the wind power, this paper develops a data-driven probabilistic WPR forecasting (p-WPRF) method based on a large number of simulated scenarios. A machine learning technique is first adopted to forecast the basic wind power forecasting scenario and produce the historical forecasting errors. To accurately model the distribution of wind power forecasting errors, a generalized Gaussian mixture model is developed and the cumulative distribution function (CDF) is also analytically deduced. The inverse transform method based on the CDF is used to generate a large number of forecasting error scenarios. An optimized swinging door algorithm is adopted to extract all the WPRs from the complete set of wind power forecasting scenarios. The p-WPRF is generated based on all generated scenarios under different weather and time conditions. Numerical simulations on publicly available wind power data show that the developed p-WPRF method can predict WPRs with a high level of reliability and accuracy.

17 WIND ENERGY↗

Uncertainty-aware photovoltaic generation estimation through fusion of physics with harmonics information using Bayesian neural networks

We develop an aggregate photovoltaic generation estimation methodology that uses diverse inputs and can reason on its current input-dependent predictive uncertainty. Named PVPHEst, for PhotoVoltaic Physics- & Harmonics-driven Estimator, the resulting tool is intelligently weighing and fusing information carried by the output of physics models, harmonics, and line sensors, using Bayesian neural networks and related techniques aimed at solving machine learning problems with intrinsic uncertainty quantification. As each of the three input classes carries heterogeneous information that only sheds light on one facet of the estimation problem but its value can diminish in the face of diverse grid phenomena, PV-PHEst with its estimation and uncertainty reasoning capabilities perform a nontrivial and potentially mission-critical task of value to grid operators.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Reducing Sample Size While Improving Equity in Vaccine Clinical Trials: A Machine Learning-Based Recruitment Methodology with Application to Improving Trials of Hepatitis C Virus Vaccines in People Who Inject Drugs

Despite the availability of direct-acting antivirals that cure individuals infected with the hepatitis C virus (HCV), developing a vaccine is critically needed in achieving HCV elimination. HCV vaccine trials have been performed in populations with high incidence of new HCV infection such as people who inject drugs (PWID). Developing strategies of optimal recruitment of PWID for HCV vaccine trials could reduce sample size, follow-up costs and disparities in enrollment. We investigate trial recruitment informed by machine learning and evaluate a strategy for HCV vaccine trials termed PREDICTEE—Predictive Recruitment and Enrichment method balancing Demographics and Incidence for Clinical Trial Equity and Efficiency. PREDICTEE utilizes a survival analysis model applied to trial candidates, considering their demographic and injection characteristics to predict the candidate’s probability of HCV infection during the trial. The decision to recruit considers both the candidate’s predicted incidence and demographic characteristics such as age, sex, and race. We evaluated PREDICTEE using in silico methods, in which we first generated a synthetic candidate pool and their respective HCV infection events using HepCEP, a validated agent-based simulation model of HCV transmission among PWID in metropolitan Chicago. We then compared PREDICTEE to conventional recruitment of high-risk PWID who share drugs or injection equipment in terms of sample size and recruitment equity, with the latter measured by participation-to-prevalence ratio (PPR) across age, sex, and race. Comparing conventional recruitment to PREDICTEE found a reduction in sample size from 802 (95%: 642–1010) to 278 (95%: 264–294) with PREDICTEE, while also reducing screening requirements by 30%. Simultaneously, PPR increased from 0.475 (95%: 0.356–0.568) to 0.754 (95%: 0.685–0.834). Even when targeting a dissimilar maximally balanced population in which achieving recruitment equity would be more difficult, PREDICTEE is able to reduce sample size from 802 (95%: 642–1010) to 304 (95%: 288–322) while improving PPR to 0.807 (95%: 0.792–0.821). PREDICTEE presents a promising strategy for HCV clinical trial recruitment, achieving sample size reduction while improving recruitment equity.

60 APPLIED LIFE SCIENCES↗

NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

28 NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning: Preprint

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

Using Ultrasound Image Augmentation and Ensemble Predictions to Prevent Machine-Learning Model Overfitting

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network—termed ShrapML—blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.

60 APPLIED LIFE SCIENCES↗

Enhancement of operational Flexibility of Power Plants Using IN740

Headers are crucial components within diverse industries, especially in the energy sector, as they enable the efficient transfer of fluids. The selection of materials for headers is determined by their specific applications; for example, Grade 91 and Grade 92 steels are commonly utilized. In our research, we recommend the adoption of INCONEL alloy 740 due to its exceptional robustness and heat-resistant characteristics. One critical parameter in header systems is the heat transfer coefficient, which directly influences the efficiency of heat exchange processes and can thereby impact the structural integrity of the headers. This coefficient is closely linked with factors such as the Nusselt number, which is influenced by fluid flow characteristics and thermal properties. The flow direction within headers, whether unidirectional or multidirectional—significantly affects the overall dynamics of heat transfer. This research focuses on exploring the behavior of headers, a specific pipeline system component, using ANSYS simulation software. The study aims to predict heat transfer and mechanical behavior within headers under various conditions through steady-state and transient simulations (parts 1 and 2 of the report). Key parameters such as heat transfer coefficient, velocity, and temperature are examined with the goal of optimizing header design. Part 3 of the report addresses the critical yet underexplored relationship between pressure drop and heat transfer coefficients in the transient flow regime within headers, specifically focusing on smooth horizontal circular tubes. Limited experimental work has been conducted in this area, prompting the need for comprehensive analysis. By leveraging machine learning techniques, this research aims to establish a correlation between pressure drop and heat transfer across various flow conditions, including laminar, transient, quasi-turbulent, and turbulent regimes. The data utilized for this analysis were meticulously gathered from existing literature, capturing simultaneous measurements of pressure drops and heat transfer. Part 4: In the context of power plants, header pipes are essential components that significantly influence system performance by facilitating the collection and distribution of steam. This report highlights the critical role of header pipes in enhancing reliability, efficiency, and overall power plant performance. A key aspect of this investigation is shape optimization, which aims to maximize performance while minimizing material usage. By focusing on shape optimization, this research contributes to improved efficiency and a reduced environmental footprint for power plant installations. The methodology developed in this study emphasizes optimizing header shapes to decrease reliance on expensive alloy materials and lower maintenance costs. Furthermore, a case study was conducted using a header from an operational power plant to validate the proposed optimization techniques. Finally, part 5 addresses the challenges associated with flexible operations in boiler systems, the study outlines several strategies for enhancing the durability and reliability of steam headers. Key approaches include material selection, which involves utilizing advanced materials with superior high-temperature properties and enhanced fatigue resistance to extend the lifespan of steam headers. Design modifications are also recommended, focusing on implementing changes that mitigate thermal stress and cyclic loading to reduce the likelihood of failures under varying operating conditions. Additionally, the study emphasizes the importance of regular inspection and monitoring by establishing rigorous protocols to detect early signs of damage, allowing for timely maintenance and minimizing the risks of catastrophic failures. Furthermore, operational guidelines are developed to minimize the frequency and severity of thermal transients, ensuring stable and efficient operations. Collectively, these strategies provide a robust framework for overcoming the unique challenges posed by flexible operation in boiler systems, ultimately contributing to improved reliability and performance in power plant operations. Through this comprehensive approach, the study not only enhances the understanding of pressure drop and heat transfer relationships but also promotes advancements in design and operation that will benefit the entire power generation industry.

01 COAL, LIGNITE, AND PEAT↗

Data-driven assessment of magnetic charged particle confinement parameter scaling in magnetized liner inertial fusion experiments on Z

In magneto-inertial fusion, the ratio of the characteristic fuel length perpendicular to the applied magnetic field R to the α-particle Larmor radius $ϱ_α$ is a critical parameter setting the scale of electron thermal-conduction loss and charged burn-product confinement. Here, using a previously developed deep-learning-based Bayesian inference tool, we obtain the magnetic-field fuel-radius product BR ∝ R / $ϱ_α$ from an ensemble of 16 magnetized liner inertial fusion (MagLIF) experiments. Observations of the trends in BR are consistent with relative trade-offs between compression and flux loss as well as the impact of mix from 1D resistive radiation magneto-hydrodynamics simulations in all but two experiments, for which 3D effects are hypothesized to play a significant role. Finally, we explain the relationship between BR and the generalized Lawson parameter χ. Our results indicate the ability to improve performance in MagLIF through careful tuning of experimental inputs, while also highlighting key risks from mix and 3D effects that must be mitigated in scaling MagLIF to higher currents with a next-generation driver.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation

Non-intrusive reduced-order models (ROMs) have recently generated considerable interest for constructing computationally efficient counterparts of nonlinear dynamical systems emerging from various domain sciences. They provide a low-dimensional emulation framework for systems that may be intrinsically high-dimensional. This is accomplished by utilizing a construction algorithm that is purely data-driven. It is no surprise, therefore, that the algorithmic advances of machine learning have led to non-intrusive ROMs with greater accuracy and computational gains. However, in bypassing the utilization of an equation-based evolution, it is often seen that the interpretability of the ROM framework suffers. This becomes more problematic when black-box deep learning methods are used which are notorious for lacking robustness outside the physical regime of the observed data. In this article, we propose the use of a novel latent-space interpolation algorithm based on Gaussian process regression. Notably, this reduced-order evolution of the system is parameterized by control parameters to allow for interpolation in space. The use of this procedure also allows for a continuous interpretation of time which allows for temporal interpolation. The latter aspect provides information, with quantified uncertainty, about full-state evolution at a finer resolution than that utilized for training the ROMs. This research assesses the viability of this algorithm for an advection-dominated system given by the inviscid shallow water equations.

97 MATHEMATICS AND COMPUTING↗

One-shot gas detection with transformer paired neural networks in Mako collected longwave infrared hyperspectral imagery

To date, careful data treatment workflows and statistical detectors are used to perform hyperspectral image (HSI) detection of any gas contained in a spectral library, which is often expanded with physics models to incorporate different spectral characteristics. In general, surrounding evidence or known gas-release parameters are used to provide confidence in or confirm detection capability, respectively. This makes quantifying detection performance difficult as it is nearly impossible to develop an absolute ground truth for gas target pixel presence in collected HSI. Consequently, developing and comparing new detection methods, especially machine learning (ML)-based methods, is susceptible to subjectivity in derived detection map quality. Here, in this work, we demonstrate the first use of transformer-based paired neural networks (PNNs) for one-shot gas target detection for multiple gases while providing quantitative classification and detection metrics for their use on labeled data. Terabytes of training data are generated from a database of long-wave infrared HSI obtained from historical Mako sensor campaigns over Los Angeles. By incorporating labels, singular signature representations, and a model development pipeline, we can tune and select PNNs to detect multiple gas targets that are not seen in training on a quantitative basis. We additionally assess our test set detections using interpretability techniques widely employed with ML-based predictors, but less common with detection methods relying on learned latent spaces.

Hyperspectral imaging↗

Data and scripts associated with a manuscript on residence time distribution simulation in two 10-kilometer long river sections

This data package is associated with the publication “On the Transferability of Residence Time Distributions in Two 10-km Long River Sections with Similar Hydromorphic Units” submitted to the Journal of Hydrology (Bao et al. 2024).Quantifying hydrologic exchange fluxes (HEFs) at the stream-groundwater interface, along with their residence time distributions (RTDs) in the subsurface, is crucial for managing water quality and ecosystem health in dynamic river corridors. However, directly simulating high-spatial resolution HEFs and RTDs can be a time-consuming process, particularly for watershed-scale modeling. Efficient surrogate models that link RTDs to hydromorphic units (HUs) may serve as alternatives for simulating RTDs in large-scale models. One common concern with these surrogate models, however, is the transferability of the relationship between the RTDs and HUs from one river corridor to another. To address this, we evaluated the HEFs and the resulting RTD-HU relationships for two 10-kilometer-long river corridors along the Columbia River, using a one-way coupled three-dimensional transient surface-subsurface water transport modeling framework that we previously developed. Applying this framework to the two river corridors with similar HUs allows for quantitative comparisons of HEFs and RTDs using both statistical tests and machine learning classification models. This data package includes the model inputs files and the simulation results data. This data package contains 10 folders. The modeling simulation results data are in the folders 100H_pt_data and 300area_pt_data, for the study domain Hanford 100H and 300 area respectively. The remaining eight folders contain the scripts and data to generate the manuscript figures. The file-level metadata file (Bao_2024_Residence_Time_Distribution _flmd.csv) includes a list of all files contained in this data package and descriptions for each. The data dictionary file (Bao_2024_Residence_Time_Distribution _dd.csv) includes column header definitions and units of all tabular files.

54 ENVIRONMENTAL SCIENCES↗

Unsupervised Process Anomaly Detection and Identification Using the Leave-One-Variable-Out Approach

Automated anomaly detection and identification can signal equipment issues and pinpoint causes in large-scale industrial systems. For systems with limited failure history, unsupervised machine learning methods can be utilized as they do not require past failures. This study introduces the leave-one-variable-out (LOVO) model, which masks one variable at a time to predict the others, learning underlying process correlations. Detection performance was assessed with synthetic and experimental data, while identification performance used only synthetic data due to its ability to generate labeled anomaly types. For detection using synthetic data, the LOVO model generally outperformed comparative models; while using experimental data, the comparative methods outperformed the LOVO model. However, the comparative methods required selecting a latent size, and these conclusions pertain to using the optimal size. In practice, it would not be feasible to always select the optimal value, and incorrect selections impacted performance. In contrast, the LOVO model does not require a latent space. For identification using synthetic data, the LOVO model was slightly outperformed in interpretability and repeatability but still demonstrated impressive results. These outcomes suggest that the LOVO model is an effective model and may be more easily implemented without the challenging tuning process of selecting a latent size.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A Boundary Topology Optimization Approach for Lightweighting Electric Machines Inspired by Additive Manufacturing

Minimizing the mass in electric machines while maintaining superior performance has become a new requirement for the advancement of drivetrains used in wind energy and electric mobility. Topology optimization for light-weighting electric machines using traditional approaches typically explore a restricted design space allowed by standard parametrizable geometry and manufacturing, while advanced methods like cell-based density approaches suffer from a lack of robust manufacturability constraints during the optimization process. To overcome these drawbacks, we explore a grid-independent, boundary TO where the outer shape of the magnet is parameterized using Bezier curves. We conduct a design of experiments (DOE) to study the effect of different magnet shapes on machine performance by varying the control points on the Bezier curves. A machine-learning based surrogate model is constructed using the data from the DOE to quantify the relationship between the control points, air-gap torque and mass. The control points are then optimized to maximize the torque density. The approach is used for minimizing electrical steel mass in the IEA-15MW radial flux direct-drive wind turbine generator. The free-from boundary TO resulted in smooth and concise shapes that can be easily additively manufactured with upto 20-ton reduction in electrical steel mass.

additive manufacturing↗

Dynamic calibration of differential equations using machine learning, with application to turbulence models

We present a methodology for calibration of parametric ordinary and partial differential equation models, using off-the-shelf software for back-propagation in Neural Networks (NN). As a prototypical example, we consider calibration of a Reynolds-averaged Navier-Stokes (RANS) turbulence closure model, against ground truth data from direct numerical simulations (DNS) of two different turbulent flows. Numerical time integration is represented as a custom NN, where only the RANS model parameters are trainable. A loss function is defined to quantify the mismatch between the NN prediction and the ground truth over a predefined, finite time integration window. This loss function is then minimized using a gradient descent method utilizing the back-propagation algorithm. Furthermore, this dynamic approach to training is to be contrasted with a static approach, wherein a least square regression estimate for parameters is obtained in the limit of an infinitesimal time integration window. In a first test of static and dynamic approaches against ground truth data generated by the model, the former proves to be significantly faster and more accurate than the latter at recovering the parameters. When both calibration approaches are tested against DNS data, for which it is known that the model cannot achieve a perfect fit, the static approach yields a good prediction only for short times, while the dynamic approach results in physical and stable predictions over the entire integration window. After optimization of the dynamic approach for time step, spatial resolution, stability, and physics-based constraints, we obtain a 50% improvement of outcomes over those obtained from the existing, manually calibrated set of parameters, demonstrating the merits of this systematic and automated procedure.

97 MATHEMATICS AND COMPUTING↗