Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Learning Theory”

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 127 records · Page 7

Coarse-Grained Density Functional Theory Predictions via Deep Kernel Learning

Scalable electronic predictions are critical for soft materials design. Recently, the Electronic Coarse-Graining (ECG) method was introduced to renormalize all-atom quantum chemical (QC) predictions to coarse-grained (CG) resolutions using deep neural networks (DNNs). While DNNs can learn complex representations that prove challenging for kernel-based methods, they are susceptible to overfitting and the overconfidence of uncertainty estimations. Here, we develop ECG within a GPU-accelerated Deep Kernel Learning (DKL) framework to enable CG QC predictions using range-separated hybrid density functional theory (DFT), obtaining a 107 speedup relative to naive all-atom QC. By treating the predicted electronic properties as random Gaussian Processes, DKL incorporates CG mapping degeneracy by learning the distribution of electronic energies as a function of CG configuration. DKL-ECG accurately reproduces molecular orbital energies from range-separated DFT while facilitating efficient training via active learning using the uncertainties provided by DKL. Further, we show that while active learning algorithms enable efficient sampling of a more diverse configurational space relative to random sampling, all explored query methods exhibit comparable performance for the examined system. We attribute this result to the significant overlap of the feature space and output property distributions across multiple temperatures.

97 MATHEMATICS AND COMPUTING↗

AEOLUS: Advances in Experimental Design, Optimal Control, and Learning for Uncertain Complex Systems

Sustained advances in the mathematics of modeling and simulation have resulted in the capability today for routine simulation of a number of large scale complex DOE-relevant systems. As remarkable as this capability for solving the so-called forward problem is, it is typically only the first step-an inner loop within an outer loop that explores the simulation model's parameter space and decision space to characterize uncertainty in the model's predictions, learn unknown model parameters from data, design the most informative experiments, determine optimal control strategies, and create optimal designs. Broadly, what unifies all of these outer loop problems is that they are, in one form or another, optimization problems over parameter/control/design space that are constrained by complex uncertain models. To fully realize the power of scientific simulation as a basis for scientific discovery, technological innovation, and rational decision-making, it is imperative to move beyond simulation to tackle the outer loop of optimization for learning from data, experimental design, and control with complex uncertain models. When the models under consideration are large-scale and complex, and when the optimization variable and uncertain parameter spaces are high (or infinite) dimensional, this constitutes a grand challenge of the highest order, and is intractable with conventional methods. To overcome these challenges, the AEOLUS Center was established to develop a unified mathematical, computational, and statistical framework for (1) Learning predictive models from complex data via Bayesian inference and optimization, and (2) Optimizing experiments, processes, and designs using the resulting uncertain models. These problems are intractable with conventional methods, for several reasons: (1) The simulation problems that govern the inner loops of the optimization problems are expensive to execute (due to severe nonlinearity, heterogeneity, multiphysics/multiscale coupling); (2) The optimization variable and uncertain parameter spaces are high dimensional, often stemming from discretizations of infinite dimensional fields such as initial conditions, sources, or material properties. We argue that the key to overcoming these challenges is to develop new mathematical, computational, and statistical methods that exploit the structure of the Bayesian inference and optimization problems mediated by their underlying complex uncertain models. This structure includes the regularity, sparsity, geometry, low intrinsic dimensionality, and multifidelity nature of the maps from uncertain parameter/optimization variable spaces to the specific objectives targeted: Bayesian inference, optimal experimental design, and optimal control design. Black box methods developed as generic tools are incapable of exploiting this structure. To be successful, we must create, integrate, and cross-fertilize ideas across multiple areas of applied math--including approximation theory, Bayesian inference, data science, experimental design, information theory, machine learning, model reduction, optimal control theory, parallel algorithms, PDE-constrained optimization, randomized algorithms, stochastic optimization, and uncertainty quantification--all while exploiting the structure of the problems at hand. With this goal in mind, we have marshaled a team of leading authorities in these areas. While the methods we develop will be broadly applicable across a wide spectrum of DOE problems in which experiments inform models and the systems those models describe must be optimized under uncertainty, we have chosen a specific area, advanced manufacturing and materials, to drive our work. AMM is characterized by complex models across multiple scales, and is a rich source of challenging problems in inference, experimental design, and optimal control, requiring multifaceted and integrated advances in applied mathematics. As such, AMM serves as an excellent vehicle to motivate and demonstrate the advances in applied mathematics developed by our center.

97 MATHEMATICS AND COMPUTING↗

Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging: Theory, algorithms, and applications

Plug-and-play (PnP) priors constitute one of the most widely used frameworks for solving computational imaging problems through the integration of physical models and learned models. PnP leverages high-fidelity physical sensor models and powerful machine learning methods for prior modeling of data to provide state-of-the-art reconstruction algorithms. PnP algorithms alternate between minimizing a data fidelity term to promote data consistency and imposing a learned regularizer in the form of an image denoiser. Recent highly successful applications of PnP algorithms include biomicroscopy, computerized tomography (CT), magnetic resonance imaging (MRI), and joint ptychotomography. This article presents a unified and principled review of PnP by tracing its roots, describing its major variations, summarizing main results, and discussing applications in computational imaging. Additionally, we also point the way toward further developments by discussing recent results on equilibrium equations that formulate the problem associated with PnP algorithms.

97 MATHEMATICS AND COMPUTING↗

Development of the Mathematics of Learning Curve Models for Evaluating Small Modular Reactor Economics

The cost of nuclear power is a straightforward yet complicated topic. It is straightforward in that the cost of nuclear power is a function of the cost to build the nuclear power plant, the cost to operate and maintain it, and the cost to provide fuel for it. It is complicated in that some of those costs are not necessarily known, introducing uncertainty into the analysis. For large light water reactor (LWR)-based nuclear power plants, the uncertainty is mainly contained within the cost of construction. The typical costs of operations and maintenance (O&M), as well as fuel, are well known based on the current fleet of LWRs. However, the last currently operating reactor to come online was Watts Bar 1 in May 1996; thus, the expected construction costs for gigawatt (GW)-class reactors in the United States are based on information nearly two decades old. Extrapolating construction, O&M, and fuel costs from GW-class LWRs to LWR-based small modular reactors (SMRs) introduces even more complication. The per-installed-kilowatt construction costs for SMRs are likely to be higher than those for the GW-class reactors based on the property of the economy of scale. Generally speaking, the economy of scale is the tendency for overall costs to increase slower than the overall production capacity. For power plants, this means that doubling the power production capacity would be expected to cost less than twice as much. Applying this property in the opposite direction, halving the power production capacity would be expected to cost more than half as much. This can potentially make the SMRs less competitive in the electricity market against the GW-class reactors, as well as against other power sources such as natural gas and subsidized renewables. One factor that can potentially aid the SMRs in achieving economic competitiveness is an economy of numbers, as opposed to the economy of scale, associated with learning curves. The basic concept of the learning curve is that the more a new process is repeated, the more efficient the process can be made. Assuming that efficiency directly relates to cost means that the more a new process is repeated successfully and efficiently, the less costly the process can be made. This factor ties directly into the factory fabrication and modularization aspect of the SMR paradigm—manufacturing serial, standardized, identical components for use in nuclear power plants can allow the SMR industry to use the learning curves to predict and optimize deployment costs. Thus, SMR deployment cost estimates can be modeled using learning curve theory to provide some insight into how and when SMRs would be competitive with both the GW-class reactors and other mutual competitors. However, assuming static learning curve behavior for all aspects of SMR construction is likely an invalid approach—not all components and systems in SMRs will be subject to learning, and those that are subject to learning may not learn at the same rate. A learning curvebased model must be capable of tracking these unique behaviors. At the same time, the behavior of the aggregated and integrated SMR deployment is a more useful metric for discussion and comparison—ultimately, the most useful learning curve information is that which describes power plant deployment as a whole. Therefore, the goal of SMR component and systems learning modeling includes a method to produce an overall power plant learning model. This report describes the mathematics of learning curves that can be used for estimating unit cost in future production for individual components and aggregated systems. All necessary assumptions are provided to support the derivations presented. Future work will demonstrate the implementation of this methodology and provide example calculations of SMR cost

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Using an operator training simulator in the undergraduate chemical engineering curriculim

An operator training simulator (OTS) is to the chemical engineer what a flight simulator is to the aerospace engineer. The basis of an OTS is a high-fidelity dynamic model of a chemical process that allows an engineer to simulate start-up, shut-down, and normal operation. It can also be used to test the skill and ability of an engineer or operator to respond and control some unforeseen situation(s) through the use of programmed malfunctions. West Virginia University (WVU) is a member of the National Energy Technology Laboratory’s Regional University Alliance (NETL-RUA). Working through the NETL-RUA, the authors have spent the last four years collaborating on the development of a high-fidelity OTS for an Integrated Gasification Combined Cycle (IGCC) power plant with CO{sub 2} capture that is the cornerstone of the AVESTARTM (Advanced Virtual Energy Simulation Training And Research) Center with sister facilities at NETL and WVU in Morgantown, WV. This OTS is capable of real-time dynamic simulation of IGCC plant operation, including start-up, shut-down, and power demand load following. The dynamic simulator and its human machine interfaces (HMIs) are based on the DYNSIM and InTouch software, respectively, from Invensys Operations Management. The purpose of this presentation is to discuss the authors’ experiences in using this sophisticated dynamic simulation-based OTS as a hands-on teaching tool in the undergraduate chemical engineering curriculum. At present, the OTS has been used in two separate courses: a new process simulation course and a traditional process control course. In the process simulation course, concepts of steady-state and dynamic simulations were covered prior to exposing the students to the OTS. Moreover, digital logic and the concept of equipment requiring one or more permissive states to be enabled prior to successful operation were also covered. Students were briefed about start-up procedures and the importance of following a predetermined sequence of actions in order to start-up the plant successfully. Student experience with the dynamic simulator consisted of a six-hour training session in which the Claus sulfur capture unit of the IGCC plant was started up. The students were able to operate the simulator through the InTouch-based HMI displays and study and understand the underlying dynamic modeling approach used in the DYNSIM-based simulator. The concepts learned during the training sessions were further reinforced when students developed their own DYNSIM models for a chemical process and wrote a detailed start-up procedure. In the process control course, students learned how the plant responds dynamically to changes in the manipulated inputs, as well as how the control system impacts plant performance, stability, robustness and disturbance rejection characteristics. The OTS provided the opportunity to study the dynamics of complicated, “real-life” process plants consisting of hundreds of pieces of equipment. Students implemented ideal forcing functions, tracked the time-delay through the entire plant, studied the response of open-loop unstable systems, and learned “good practices” in control system design by taking into account the real-world events where significant deviations from the “ideal” or “expected” response can occur. The theory of closed-loop stability was reinforced by implementing limiting proportional gain for stability limits of real plants. Finally, students were divided into several groups where each group was tasked to control a section of the plant within a set of operating limits in the face of disturbances and simulated process faults. At the end of this test, they suggested ways to improve the control system performance based on the theory they learned in class and the hands-on experience they earned while working on the OTS.

97 MATHEMATICS AND COMPUTING↗

Learning control system design based on 2-D theory - An application to parallel link manipulator

An approach to iterative learning control system design based on two-dimensional system theory is presented. A two-dimensional model for the iterative learning control system which reveals the connections between learning control systems and two-dimensional system theory is established. A learning control algorithm is proposed, and the convergence of learning using this algorithm is guaranteed by two-dimensional stability. The learning algorithm is applied successfully to the trajectory tracking control problem for a parallel link robot manipulator. The excellent performance of this learning algorithm is demonstrated by the computer simulation results.

Geng, Z.↗

Tracking particles by passing messages between images

Methods to extract information from the tracking of mobile objects/particles have broad interest in biological and physical sciences. Techniques based on the simple criterion of proximity in time-consecutive snapshots are useful to identify the trajectories of the particles. However, they become problematic as the motility and/or the density of the particles increases because of the uncertainties on the trajectories that particles have followed during the acquisition time of the images. Here, we report efficient methods for learning parameters of the dynamics of the particles from their positions in time-consecutive images. Our algorithm belongs to the class of message-passing algorithms, also known in computer science, information theory and statistical physics under the name of Belief Propagation (BP). The algorithm is distributed, thus allowing parallel implementation suitable for computations on multiple machines without significant inter-machine overhead. We test our method on the model example of particle tracking in turbulent flows, which is particularly challenging due to the strong transport that those flows produce. Our numerical experiments show that the BP algorithm compares in quality with exact Markov Chain Monte-Carlo algorithms, yet BP is far superior in speed. We also suggest and analyze a random-distance model that provides theoretical justification for BP accuracy. Methods developed here systematically formulate the problem of particle tracking and provide fast and reliable tools for its extensive range of applications.

99 GENERAL AND MISCELLANEOUS↗

Accelerating defect predictions in semiconductors using graph neural networks

First-principles computations reliably predict the energetics of point defects in semiconductors but are constrained by the expense of using large supercells and advanced levels of theory. Machine learning models trained on computational data, especially ones that sufficiently encode defect coordination environments, can be used to accelerate defect predictions. Here, we develop a framework for the prediction and screening of native defects and functional impurities in a chemical space of group IV, III–V, and II–VI zinc blende semiconductors, powered by crystal Graph-based Neural Networks (GNNs) trained on high-throughput density functional theory (DFT) data. Using an innovative approach of sampling partially optimized defect configurations from DFT calculations, we generate one of the largest computational defect datasets to date, containing many types of vacancies, self-interstitials, anti-site substitutions, impurity interstitials and substitutions, as well as some defect complexes. We applied three types of established GNN techniques, namely crystal graph convolutional neural network, materials graph network, and Atomistic Line Graph Neural Network (ALIGNN), to rigorously train models for predicting defect formation energy (DFE) in multiple charge states and chemical potential conditions. We find that ALIGNN yields the best DFE predictions with root mean square errors around 0.3 eV, which represents a prediction accuracy of 98% given the range of values within the dataset, improving significantly on the state-of-the-art. We further show that GNN-based defective structure optimization can take us close to DFT-optimized geometries at a fraction of the cost of full DFT. The current models are based on the semi-local generalized gradient approximation-Perdew–Burke–Ernzerhof (PBE) functional but are highly promising because of the correlation of computed energetics and defect levels with higher levels of theory and experimental data, the accuracy and necessity of discovering novel metastable and low energy defect structures at the PBE level of theory before advanced methods could be applied, and the ability to train multi-fidelity models in the future with new data from non-local functionals. The DFT-GNN models enable prediction and screening across thousands of hypothetical defects based on both unoptimized and partially optimized defective structures, helping identify electronically active defects in technologically important semiconductors.

Rahman, Md Habibur (ORCID:000000027705984X)↗

Generative model selection using a scalable and size-independent complex network classifier

Real networks exhibit nontrivial topological features, such as heavy-tailed degree distribution, high clustering, and small-worldness. Researchers have developed several generative models for synthesizing artificial networks that are structurally similar to real networks. An important research problem is to identify the generative model that best fits to a target network. In this paper, we investigate this problem and our goal is to select the model that is able to generate graphs similar to a given network instance. By the means of generating synthetic networks with seven outstanding generative models, we have utilized machine learning methods to develop a decision tree for model selection. Our proposed method, which is named “Generative Model Selection for Complex Networks,” outperforms existing methods with respect to accuracy, scalability, and size-independence.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Attractor comparisons based on density

Recognizing a chaotic attractor can be seen as a problem in pattern recognition. Some feature vector must be extracted from the attractor and used to compare to other attractors. The field of machine learning has many methods for extracting feature vectors, including clustering methods, decision trees, support vector machines, and many others. In this work, feature vectors are created by representing the attractor as a density in phase space and creating polynomials based on this density. Density is useful in itself because it is a one dimensional function of phase space position, but representing an attractor as a density is also a way to reduce the size of a large data set before analyzing it with graph theory methods, which can be computationally intensive. The density computation in this paper is also fast to execute. In this paper, as a demonstration of the usefulness of density, the density is used directly to construct phase space polynomials for comparing attractors. Comparisons between attractors could be useful for tracking changes in an experiment when the underlying equations are too complicated for vector field modeling.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practice

Searches for new phenomena in complex scientific data are predominantly model-dependent, optimized for specific hypotheses, and therefore limited in their coverage of the space of possible signals. Recently, new AI-based model-agnostic search strategies, many of which have been pioneered in high-energy physics, have been proposed which provide a complementary paradigm, prioritizing broad exploration over tailored analyses. These techniques offer an opportunity to enhance the overall discovery potential of modern experiments, especially in regimes where theoretical guidance is scarce. In this document, we review the conceptual framework behind the main classes of AI-based model-agnostic strategies. We discuss the potential pitfalls of these methods, and strategies for their validation and interpretation. We aim for this document to serve as a useful reference both for practitioners and for researchers interested in learning more about these model-agnostic search strategies.

Amram, Oz [Fermilab] (ORCID:0000000237653123)↗

Inverse methods for design of soft materials

Functional soft materials, comprising colloidal and molecular building blocks that self-organize into complex structures as a result of their tunable interactions, enable a wide array of technological applications. Inverse methods provide a systematic means for navigating their inherently high-dimensional design spaces to create materials with targeted properties. Furthermore, while multiple physically motivated inverse strategies have been successfully implemented in silico, their translation to guiding experimental materials discovery has thus far been limited to a handful of proof-of-concept studies. In this perspective, we discuss recent advances in inverse methods for design of soft materials that address two challenges: (1) methodological limitations that prevent such approaches from satisfying design constraints and (2) computational challenges that limit the size and complexity of systems that can be addressed. Strategies that leverage machine learning have proven particularly effective, including methods to discover order parameters that characterize complex structural motifs and schemes to efficiently compute macroscopic properties from the underlying structure. We also highlight promising opportunities to improve the experimental realizability of materials designed computationally, including discovery of materials with functionality at multiple thermodynamic states, design of externally directed assembly protocols that are simple to implement in experiments, and strategies to improve the accuracy and computational efficiency of experimentally relevant models.

36 MATERIALS SCIENCE↗

Data analysis using the Gnu R system for statistical computation

R is a language system for statistical computation. It is widely used in statistics, bioinformatics, machine learning, data mining, quantitative finance, and the analysis of clinical drug trials. Among the advantages of R are: it has become the standard language for developing statistical techniques, it is being actively developed by a large and growing global user community, it is open source software, it is highly portable (Linux, OS-X and Windows), it has a built-in documentation system, it produces high quality graphics and it is easily extensible with over four thousand extension library packages available covering statistics and applications. This report gives a very brief introduction to R with some examples using lattice QCD simulation results. It then discusses the development of R packages designed for chi-square minimization fits for lattice n-pt correlation functions.

99 GENERAL AND MISCELLANEOUS↗

Continental-Scale Controls on Hyporheic Respiration Revealed by Knowledge-Guided Machine Learning

Hyporheic zone sediments regulate organic matter turnover and in-stream respiration, yet controls on sediment respiration remain poorly constrained across heterogeneous river networks, limiting prediction of stream metabolism and carbon processing at continental scales. Here, we integrate observations from ~90 river corridors across the United States in the WHONDRS consortium with a knowledge-guided machine learning (KGML) framework that couples thermodynamic rate theory with machine learning to identify dominant controls on hyporheic respiration. Diagnostic analyses show that organic matter concentration and thermodynamic favorability define an upper bound on respiration potential, whereas biological catalytic capacity and physical accessibility jointly govern realized respiration rates through interaction effects. To represent unmeasurable accessibility constraints, we use the mechanistic model as a scaffold for KGML, allowing machine learning to target residual structure not explained by process theory. This hybrid framework improves predictive skill relative to both the mechanistic model alone and fully data-driven models while preserving interpretability. These results indicate that variability in hyporheic respiration is largely mechanistically structured and demonstrate how integrating process theory with explainable AI enhances predictive performance while enabling scalable synthesis of river corridor observations.

Zheng, Jianqiu↗

Sensor enabled data-driven predictive analytics for modeling and control with high penetration of DERs in distribution systems

The electric power grid is undergoing a tremendous transformation due to the increasing penetration of renewable energy resources beginning with wind and more recently with the distributed energy resources (DERs) such as solar and battery storage. DERs have dramatically changed the role of the distribution systems in the overall power grid, and they are expected to contribute a significant portion of power generation in the future. If current trends for DERs continue, system operation and control will need to change dramatically for improved grid reliability and resiliency. As renewable resources increase in penetration, new and challenging operational, planning, and design problems are expected to emerge. Some of the key challenges that arise in the planning and operation of the future grid are: 1) Quantifying the impact of high DER penetration in distribution systems on bulk grid behavior over multiple time scales. 2) Identifying whether a particular DER configuration/settings have a large impact on the overall grid behavior. These challenges can be addressed in an offline manner using detailed T&D grid models and they can also be addressed in an online manner using sensor measurements. In particular, the advancement and planned growth in sensor technology in power grid over various voltage levels provide us with a unique opportunity to tackle these challenges from a data analytic perspective without needing detailed T&D grid models. A few questions that naturally arise when addressing the challenges from DERs using sensor data are: 1) How can we use limited sensor measurements to monitor & control voltage stability and small signal stability of the bulk system? 2) How can we ensure that the developed data analytic methods are robust to data availability and quality issues? 3) How can we compute the developed analytics in a scalable manner using streaming measurements? In this project, we addressed the aforementioned challenges arising from DERs and answered the questions raised above on how to effectively use the sensor measurements to enhance the reliability and performance of the electric grid. Thus, the overarching goal of this project is to develop effective reduced/representative system models from data that make the computational complexity sufficiently manageable so as to be useful to simulate, analyze, and even control complex non-linear power systems dynamics with large penetrations of DERs. In order to achieve the objective, the project team established a four-fold technical approach 1) Formulated a combined transmission-distribution co-simulation framework for data generation and validation, 2) Derived reduced/representative models of power systems based on data-driven methods for efficient computation and appropriate representation of system behavior, 3) Developed data driven characterization of power system behavior based on transfer operator theory, machine learning and optimization for model estimation, 4) Incorporated a scalable data management and processing architecture using distributed Kafka streaming applications that coordinate input data streams to the developed data analytics. The key accomplishments of the project are: 1) Development of a scalable multi-timescale T&D co-simulation framework (both for steady state and for dynamic co-simulation) using commercial solvers (PSSE and GridLAB-D). The steady-state T&D co-simulation interface is shared with our industry partner (PJM). 2) A structured reduced order dynamic model of distribution systems that can represent partial motor stalling along with a systematic procedure to derive the model parameters. 3) A PMU based online method to monitor, localize and mitigate fault-induced delayed voltage recovery using DER reactive support and load control in distribution systems. 4) Development of linear operator based robust methodologies for dynamic state estimation, uncertainty quantification, system identification and trajectory prediction for power system dynamics. 5) An adaptive damping control for utilizing wind energy resources to provide oscillation damping and system stability. 6) Implementation of Kafka-based framework for efficient processing of streaming data using Linux-based local virtual environment.

DER integration↗