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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

An Open, Cloud-Based Platform for Whole-Building Fault Detection and Diagnostics

Small commercial buildings in the U.S. waste an estimated 300 Trillion BTU (approximately $6 billion in energy costs) annually due to faults, but lack cost-effective automated fault detection and diagnosis (AFDD) tools. NREL and GE Global Research are partnering to develop hybrid AFDD algorithms tailored to the unique needs of small commercial buildings (</=10,000 sq. ft.). The approach combines physics-based energy modeling tools with state-of-the-art machine learning algorithms to enable diagnostics using modeled input data. NREL, in partnership with Purdue University, has adapted DOE's physics-based modeling software EnergyPlus and OpenStudio to simulate common building faults. Cloud-based implementations of these physics-based models were used to generate data for multiple climate zones. The data were then used to train machine learning algorithms, such as those available in GE's Predix platform, to detect and diagnose building faults. Key features of the system including the automated, cloud-implementation of EnergyPlus, genetic algorithms for automated model feature selection, multiclass detection and diagnosis models, and anomaly detection algorithms will be presented.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

A theory of quark vs. gluon discrimination

Understanding jets initiated by quarks and gluons is of fundamental importance in collider physics. Efficient and robust techniques for quark versus gluon jet discrimination have consequences for new physics searches, precision αs studies, parton distribution function extractions, and many other applications. Numerous machine learning analyses have attacked the problem, demonstrating that good performance can be obtained but generally not providing an understanding for what properties of the jets are responsible for that separation power. In this paper, we provide an extensive and detailed analysis of quark versus gluon discrimination from first-principles theoretical calculations. Working in the strongly-ordered soft and collinear limits, we calculate probability distributions for fixed N-body kinematics within jets with up through three resolved emissions (O(α$3\atop{s}$)). This enables explicit calculation of quantities central to machine learning such as the likelihood ratio, the area under the receiver operating characteristic curve, and reducibility factors within a well-defined approximation scheme. Further, we relate the existence of a consistent power counting procedure for discrimination to ideas for operational flavor definitions, and we use this relationship to construct a power counting for quark versus gluon discrimination as an expansion in e C F -C A $\ll$1, the exponential of the fundamental and adjoint Casimirs. Our calculations provide insight into the discrimination performance of particle multiplicity and show how observables sensitive to all emissions in a jet are optimal. We compare our predictions to the performance of individual observables and neural networks with parton shower event generators, validating that our predictions describe the features identified by machine learning

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2019

A two-step short-term probabilistic wind forecasting methodology based on predictive distribution optimization

With increasing wind penetrations into electric power systems, probabilistic wind forecasting becomes more critical to power system operations because of its capability of quantifying wind uncertainties. In this paper, a two-step probabilistic wind forecasting approach based on pinball loss optimization is developed. First, a multimodel machine learning-based ensemble deterministic forecasting framework is adopted to generate deterministic forecasts. The deterministic forecast is assumed to be the mean value of the predictive distribution at each forecasting time stamp. Then, the optimal unknown parameter (i.e., standard deviation) of the predictive distribution is estimated by a support vector regression surrogate model based on the deterministic forecasts. Lastly, probabilistic forecasts are generated from the predictive distribution. Numerical results of case studies at eight locations show that the developed two-step probabilistic forecasting methodology has improved the pinball loss metric score by up to 35% compared to a baseline quantile regression forecasting model.

17 WIND ENERGY↗
DOE OSTI2024

Deep Generative Models in Energy System Applications: Review, Challenges, and Future Directions

In recent years, with the advent of mature machine learning products like ChatGPT, Stable Diffusion, and Sora, the world has witnessed tremendous changes driven by the rapid development of generative artificial intelligence (GAI). Beyond applications in text, speech, image, and video creation, deep generative models (DGMs) underpinning these cutting-edge technologies have also been employed by domain researchers to address scientific and engineering challenges. This paper aims to fill a gap in the research community by providing a systematic review of how DGMs have been utilized in energy system applications. After introducing four most popular DGMs, we review and categorize 196 research articles into five focus areas: data generation, forecasting, situational awareness, modeling, and optimal decision-making. Through this classification, we uncover trends in how DGMs are employed for each type of problem, highlighting GAI techniques that contribute to breakthroughs over traditional methods. We discuss limitations in existing literature, engineering challenges, and propose future directions, all tailored to the unique nature of problems in energy system engineering. Our goal is to offer insights for energy system domain researchers, providing a comprehensive view of existing studies and potential future opportunities.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Bayesian Learning of Adatom Interactions from Atomically Resolved Imaging Data

Atomic structures and adatom geometries of surfaces encode information about the thermodynamics and kinetics of the processes that lead to their formation, and which can be captured by a generative physical model. In this work, we develop a workflow based on a machine-learning-based analysis of scanning tunneling microscopy images to reconstruct the atomic and adatom positions, and a Bayesian optimization procedure to minimize statistical distance between the chosen physical models and experimental observations. We optimize the parameters of a 2- and 3-parameter Ising model describing surface ordering and use the derived generative model to make predictions across the parameter space. For concentration dependence, we compare the predicted morphologies at different adatom concentrations with the dissimilar regions on the sample surfaces that serendipitously had different adatom concentrations. The proposed workflow can be used to reconstruct the thermodynamic models and associated uncertainties from the experimental observations of materials microstructures. The code used in the manuscript is available at https://github.com/saimani5/Adatom_interactions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

‘Flux+Mutability’: a conditional generative approach to one-class classification and anomaly detection

Abstract Anomaly Detection is becoming increasingly popular within the experimental physics community. At experiments such as the Large Hadron Collider, anomaly detection is growing in interest for finding new physics beyond the Standard Model. This paper details the implementation of a novel Machine Learning architecture, called Flux+Mutability, which combines cutting-edge conditional generative models with clustering algorithms. In the ‘flux’ stage we learn the distribution of a reference class. The ‘mutability’ stage at inference addresses if data significantly deviates from the reference class. We demonstrate the validity of our approach and its connection to multiple problems spanning from one-class classification to anomaly detection. In particular, we apply our method to the isolation of neutral showers in an electromagnetic calorimeter and show its performance in detecting anomalous dijets events from standard QCD background. This approach limits assumptions on the reference sample and remains agnostic to the complementary class of objects of a given problem. We describe the possibility of dynamically generating a reference population and defining selection criteria via quantile cuts. Remarkably this flexible architecture can be deployed for a wide range of problems, and applications like multi-class classification or data quality control are left for further exploration.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Confidentiality-preserving machine learning algorithms for soft-failure detection in optical communication networks

Automated fault management is at the forefront of next-generation optical communication networks. The increase in complexity of modern networks has triggered the need for programmable and software-driven architectures to support the operation of agile and self-managed systems. In these scenarios, the European Telecommunications Standards Institute zero-touch network and service management approach is imperative. The need for machine learning algorithms to process the large volume of telemetry data brings safety concerns as distributed cloud-computing solutions become the preferred approach for deploying reliable communication network automation. This paper’s contribution is twofold. First, we propose a simple yet effective method to guarantee the confidentiality of the telemetry data based on feature scrambling. The method allows the operation of third-party computational services without direct access to the full content of the collected data. Additionally, the effectiveness of four unsupervised machine learning algorithms for soft-failure detection is evaluated when applied to the scrambled telemetry data. The methods are based on factor analysis, principal component analysis, nonlinear principal component analysis, and singular value decomposition. Most dimensionality reduction algorithms have the common property that they can maintain similar levels of fault classification performance while hiding the data structure from unauthorized access. Evaluations of the proposed algorithms demonstrate this capability.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Machine learning in electronic-quantum-matter imaging experiments

For centuries, the scientific discovery process has been based on systematic human observation and analysis of natural phenomena. Today, however, automated instrumentation and large-scale data acquisition are generating datasets of such large volume and complexity as to defy conventional scientific methodology. Radically different scientific approaches are needed, and machine learning (ML) shows great promise for research fields such as materials science. Given the success of ML in the analysis of synthetic data representing electronic quantum matter (EQM), the next challenge is to apply this approach to experimental data—for example, to the arrays of complex electronic-structure images17 obtained from atomic-scale visualization of EQM. Here we report the development and training of a suite of artificial neural networks (ANNs) designed to recognize different types of order hidden in such EQM image arrays. These ANNs are used to analyse an archive of experimentally derived EQM image arrays from carrier-doped copper oxide Mott insulators. In these noisy and complex data, the ANNs discover the existence of a lattice-commensurate, four-unit-cell periodic, translational-symmetry-breaking EQM state. Further, the ANNs determine that this state is unidirectional, revealing a coincident nematic EQM state. Here, strong-coupling theories of electronic liquid crystals are consistent with these observations.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters

High-precision calorimeter simulation at current and future colliders imposes rapidly growing computational demands, motivating the development of machine-learning surrogates for traditional Monte Carlo tools such as Geant4. Flow matching and diffusion-based generative models have become leading approaches for high-dimensional fast simulation because of their sample quality, but typically require ${\cal O}(100)$ function evaluations at inference and often rely on auxiliary networks to constrain global observables, compromising streamlined end-to-end generation. We introduce a unified framework that improves the balance between speed, shower quality, and physics fidelity. The method combines: (i) an average velocity field integrator that enables sampling in one or a few evaluations; (ii) a learned generative prior in shower space, constructed from data rather than random noise; and (iii) physics-guided loss terms that impose inductive biases on key observables during training. These elements are training time regularizers, preserving end-to-end inference with no additional cost. With only one or a few evaluation steps, the model achieves shower quality competitive with state-of-the-art flow and diffusion approaches, tested on several public high granularity calorimeter datasets. The results demonstrate inter-layer shower structure consistent with the underlying physics, providing a strong candidate for future fast simulation workflows.

Jiang, Cheng [Edinburgh U.]↗
DOE OSTI2022

Integrated Computational Materials and Mechanical Modeling for Additive Manufacturing of Alloys with Graded Structure Used in Fossil Fuel Power Plants

Wire-arc additive manufacturing (WAAM) has demonstrated its unique capability of producing large-size alloy components with a significantly reduced fabrication time and enhanced geometry design freedom. In this project, the team has developed an ICME (Integrated Computational Materials Engineering) modeling framework, which supports the WAAM of the AUSC (Advanced Ultra-Supercritical) power plant components. The manufacturing design has been applied to Inconel 740H, steel P91, as well as the dissimilar alloy components between steel P91 and Inconel 740H. The ICME model framework is developed by considering two types of modeling. First, mechanistic modeling has been applied to control the printing quality and understand the sequence of the dissimilar printing of the wall structure. The following models have been included in the developed ICME framework: finite element thermal model, grain structure model, residual stress simulation, crystal plasticity model, CALPHAD-based precipitation kinetic model, phase stability prediction, thermal expansion predictive model, and heuristic creep model. Secondary, a physics-based machine learning model has also been developed based on the ICME model structure. The machine learning model development is based on the ICME model prediction with calibration of the experiments. In addition, the WAAM has been utilized as a high-throughput experimental tool rapidly generating a gradient of alloy composition to facilitate experimental database generation for process-structure-property relationships. Such a database directly supported the ICME-enhanced machine learning, which further assisted in intermediate composition block design between P91 and 740H. A high-throughput screening study of the oxidation resistance has been performed based on such high-throughput experimentation. Based on the computational design, several dissimilar alloy manufacturing with post-heat treatment have been performed with a comprehensive evaluation of mechanical performance, including hardness mapping, yield strength, creep resistance. In this project, the single component of P91 and 740H processed by WAAM after heat treatment designed by ICME has demonstrated higher performance in yield strength and creep resistance than the wrought materials. The P91 sample prepared by WAAM with ICME-designed heat treatment performs better than P92 in creep resistance. The designed graded alloy printing with intermediate block shows a promising performance that exceeds the traditional welding. Moreover, the current research indicates the high need for location-specific design analysis with uncertainty quantification, an important topic that deserves more dedicated research. The achievement of this project demonstrated the promising future of WAAM in structural alloy manufacturing for energy power plant development. Successful printing requires synergetic efforts made by manufacturing, mechanical, and materials sciences.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2023

Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Toward ML-Assisted Advanced Manufacturing

Abstract The research and development cycle of advanced manufacturing processes traditionally requires a large investment of time and resources. Experiments can be expensive and are hence conducted on relatively small scales. This poses problems for typically data-hungry machine learning tools which could otherwise expedite the development cycle. We build upon prior work by applying conditional generative adversarial networks (GANs) to scanning electron microscope (SEM) imagery from an emerging advanced manufacturing process, shear-assisted processing and extrusion (ShAPE). We generate realistic images conditioned on temper and either experimental parameters or material properties. In doing so, we are able to integrate machine learning into the development cycle, by allowing a user to immediately visualize the microstructure that would arise from particular process parameters or properties. This work forms a technical backbone for a fundamentally new approach for understanding manufacturing processes in the absence of first-principle models. By characterizing microstructure from a topological perspective, we are able to evaluate our models’ ability to capture the breadth and diversity of experimental scanning electron microscope (SEM) samples. Our method is successful in capturing the visual and general microstructural features arising from the considered process, with analysis highlighting directions to further improve the topological realism of our synthetic imagery.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Sensor Anomaly Detection for Nuclear Reactor Systems Utilizing Linear Regression and K-Means Unsupervised Machine Learning

Nuclear reactors and related systems are becoming increasingly complex due to advancing technologies in next-generation power reactors. This increased complexity necessitates enhanced automation and data management capabilities. To successfully realize autonomous systems, methods must be developed to handle vast volumes of data and effectively distinguish anomalous data from noise and expected data. While impressive models utilizing digital twins and similar approaches are under development, here we propose a simplified model for analyzing fundamental methods and techniques. Initially, we created a general dataset by using initial data from PCTRAN in order to represent ideal steady-state conditions. We then inserted anomalies based on prevalent sensor anomaly types (e.g., point anomalies, linear drift, and downward deviations), along with unusual anomalies such as exponential drift and upward deviations. To detect anomalies, we developed a program that employs data partitioning and linear regression to preprocess and filter the anomalous data. A K-Means machine learning (ML) method was then applied to separate and count the data within the anomalous partition. The results from all datasets—apart from exponential growth—demonstrated positive outcomes, with each returning multiple instances of greaterthan-95% accuracy. We conducted further investigations using Idaho National Laboratory’s RAVEN software to perform a sensitivity analysis on the input variables (R 2 Tolerance, Slope Tolerance, and Window Size) and found that the output variables (Accuracy and Time) were most sensitive to the Window Size. Despite the promising results published, further development is required to effectively apply these methods to nuclear systems. Nevertheless, the strengths of this approach are evident and hold promise for future applications in the field.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2021

Investigating 3,4-bis(3-nitrofurazan-4-yl)furoxan detonation with a rapidly tuned density functional tight binding model

In this work, we describe a machine learning approach to rapidly tune density functional tight binding models for the description of detonation chemistry in organic molecular materials. Resulting models enable simulations on the several 10s of ps scales characteristic to these processes, with “quantum-accuracy.” We use this approach to investigate early shock chemistry in 3,4-bis(3-nitrofurazan-4-yl)furoxan, a hydrogen-free energetic material known to form onion-like nanocarbon particulates following detonation. We find that the ensuing chemistry is significantly characterized by the formation of large C x N y O z species, which are likely precursors to the experimentally observed carbon condensates. Beyond utility as a means of investigating detonation chemistry, the present approach can be used to generate quantum-based reference data for the development of full machine-learned interatomic potentials capable of simulation on even greater time and length scales, i.e., for applications where characteristic time scales exceed the reach of methods including Kohn–Sham density functional theory, which are commonly used for reference data generation.

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

Prediction of Carbon Dioxide Adsorption via Deep Learning

Porous carbons with different textural properties exhibit great differences in CO 2 adsorption capacity. It is generally known that narrow micropores contribute to higher CO 2 adsorption capacity. However, it is still unclear what role each variable in the textural properties plays in CO 2 adsorption. Herein, a deep neural network is trained as a generative model to direct the relationship between CO 2 adsorption of porous carbons and corresponding textural properties. The trained neural network is further employed as an implicit model to estimate its ability to predict the CO 2 adsorption capacity of unknown porous carbons. Interestingly, the practical CO 2 adsorption amounts are in good agreement with predicted values using surface area, micropore and mesopore volumes as the input values simultaneously. This unprecedented deep learning neural network (DNN) approach, a type of machine learning algorithm, exhibits great potential to predict gas adsorption and guide the development of next-generation carbons.

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

Machine Learning for Geothermal Resource Exploration in the Tularosa Basin, New Mexico

Geothermal energy is considered an essential renewable resource to generate flexible electricity. Geothermal resource assessments conducted by the U.S. Geological Survey showed that the southwestern basins in the U.S. have a significant geothermal potential for meeting domestic electricity demand. Within these southwestern basins, play fairway analysis (PFA), funded by the U.S. Department of Energy’s (DOE) Geothermal Technologies Office, identified that the Tularosa Basin in New Mexico has significant geothermal potential. This short communication paper presents a machine learning (ML) methodology for curating and analyzing the PFA data from the DOE’s geothermal data repository. The proposed approach to identify potential geothermal sites in the Tularosa Basin is based on an unsupervised ML method called non-negative matrix factorization with custom k-means clustering. This methodology is available in our open-source ML framework, GeoThermalCloud (GTC). Using this GTC framework, we discover prospective geothermal locations and find key parameters defining these prospects. Our ML analysis found that these prospects are consistent with the existing Tularosa Basin’s PFA studies. This instills confidence in our GTC framework to accelerate geothermal exploration and resource development, which is generally time-consuming.

15 GEOTHERMAL ENERGY↗
DOE OSTI2026

Generative models on phase space

Deep generative models such as diffusion and flow matching are powerful machine learning tools capable of learning and sampling from high-dimensional distributions. They are particularly useful when the training data appears to be concentrated on a submanifold of the data embedding space. For high-energy physics data, consisting of collections of relativistic energy-momentum 4-vectors, this submanifold can enforce extremely strong physically-motivated priors, such as energy and momentum conservation. If these constraints are learned only approximately, rather than exactly, this can inhibit the interpretability and reliability of such generative models. To remedy this deficiency, we introduce generative models which are, by construction, confined at every step of their sampling trajectory to the manifold of massless N-particle Lorentz-invariant phase space in the center-of-momentum frame. In the case of diffusion models, the "pure noise" forward process endpoint corresponds to the uniform distribution on phase space, which provides a clear starting point from which to identify how correlations among the particles emerge during the reverse (de-noising) process. We demonstrate that our models are able to learn both few-particle and many-particle distributions with various singularity structures, paving the way for future interpretability studies using generative models trained on simulated jet data.

Bogorad, Zachary [Fermilab]↗
DOE OSTI2018

DEGAS: Dynamic Exascale Global Address Space Programming Environments

The Dynamic, Exascale Global Address Space programming environment (DEGAS) project will develop the next generation of programming models and runtime systems to meet the challenges of Exascale computing. The Berkeley part of the project concentrated on communication-optimal code generation to optimize speed and energy efficiency by reducing data movement. Our work developed communication lower bounds, and/or communication avoiding algorithms (that either meet the lower bound, or do much less communication than their conventional counterparts) for a variety of algorithms, including linear algebra, machine learning and genomics. The Berkeley part of the project concentrated on communication-optimal code generation to optimize speed and energy efficiency by reducing data movement. Our work developed communication lower bounds, and/or communication avoiding algorithms (that either meet the lower bound, or do much less communication than their conventional counterparts) for a variety of algorithms, including linear algebra, machine learning and genomics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

BatteryPro: A Python Toolkit for Battery Data Analysis and Machine Learning Predictions

Analyzing battery test data for research & development can be time-consuming since battery tests often run on the order of months to years, generating large volumes of data. BatteryPro is a comprehensive Python package and software designed to facilitate advanced analysis and performance predictions for battery test data. Developed for battery researchers, it supports data types from widely used battery testing instruments, including MACCOR and Biologic cycling systems. The software provides a variety of tools for extracting and plotting key battery parameters such as time, voltage, capacity, current, and pressure. In addition to its extensive data analysis capabilities, BatteryPro features a dedicated machine learning module that employs a Bayesian Gaussian Mixture Model (GMM) to predict battery performance and degradation. Users can generate synthetic capacity fade data, calculate fade metrics, and leverage predictive models to forecast long-term battery behavior. The software's graphical user interface (GUI) enhances usability, allowing researchers to upload, merge, and analyze multiple data files with full customizability. The GUI also supports machine learning predictions, enabling users to fit models and make predictions based on selected data and parameters. BatteryPro is built using QtDesigner, scikit-learn, matplotlib, and pandas, ensuring a high level of customization, flexibility, and accuracy in battery data analysis. This tool aims to empower researchers with the ability to perform detailed battery analysis and make informed predictions, ultimately advancing the field of battery research.

25 - ENERGY STORAGE↗