Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Continual 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 469 records · Page 26

The AP1000{sup R} China projects move forward to construction completion and equipment installation

The AP1000 design is the only Generation III+ technology to receive design certification from the U.S. Nuclear Regulatory Commission. This evolutionary design provides the highest safety and performance standards and has several distinct advantages over other designs, including improved operations and reduced construction schedule risks through the use of modern, modular, engineering principles that allow construction and fabrication tasks traditionally performed in sequence to be undertaken in parallel. Since the first granting of Design Certification in 2005 by the NRC, the AP1000 design has been modified to meet emergent NRC requirements such as those requiring the design to withstand the impact of an aircraft crash. Both domestic and foreign utilities have turned to the Westinghouse AP1000 plant design to meet their near - and long-term sustainable energy needs. The first ever deployment of this advanced U.S. nuclear power technology began in China in 2007 with the award of a contract to build four AP1000 units, constructed in pairs at the coastal sites of Sanmen (Zhejiang Province) and Haiyang (Shandong Province). Currently, all four units are at an advanced stage of construction. The commercial operation date for Sanmen Unit 1 is November 2013 followed by Haiyang Unit 1 being operational in May 2014. Construction and equipment manufacture is at an advanced stage. Sanmen Unit 1 equipment that has been delivered includes the reactor vessel, the reactor vessel closure head, the passive residual heat removal heat exchanger, the integrated head package, the polar crane, and the refueling machine. The steam generators are also completed. The RV was installed within the containment vessel building in September 2011. The installation of this major equipment will allow the setting of the containment vessel top head. Haiyang Unit 1 is also achieving significant progress. Significant benefits continue to be realized as a result of lessons learned and experience gained from the first-of-a-kind activities for Sanmen Unit 1 and AP1000 equipment design and manufacturing. For example, the nuclear island basemat at Haiyang Units 1 and 2 and Sanmen Unit 2 was laid in less time than that of Sanmen Unit 1, the ultra-large steam generator and RV forging lead times were reduced for the follow on units, and the fabrication of the auxiliary building module for Haiyang Unit 1 took less time than for the Sanmen first unit. These benefits are also being realized by the United States AP1000 project construction and fabrication modules, and equipment. Some difficulties arise from building this first-of-a-kind (advanced passive) type of plant; however, these difficulties are being overcome and the overall schedule remains achievable. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Using Reinforcement Learning to Design Missed Thrust Resilient Trajectories

From ion thrusters to solar sails, spacecraft continue to adopt new and more efficient forms of propulsion. As these low-thrust propulsion meth- ods have become more prevalent, new challenges have arisen. Depending on the mission, low-thrust propulsion elements may need to thrust con- tinuously for days/months. During these thrusting periods, external fac- tors, such as a micro-meteoroid impact or a software glitch, may cause the spacecraft to prematurely cease its thrust stage. Half of all deep space missions enter a safe mode where they cannot thrust every four months. These missed thrust events can result in the complete loss of a space- craft for time-dependent trajectories like planetary rendezvous. This paper demonstrates how neural networks, trained using reinforcement learning, can autonomously correct for missed thrust events during an interplanetary trajectory.

Laipert, Frank E.↗

PhILMs: Collaboratory on Mathematics and Physics-Informed Learning Machines for Multiscale and Multiphysics Problems

The landscape of computational science and engineering is continually evolving, with the challenge of high-dimensional regression problems standing as a significant hurdle in numerous scientific endeavors. Addressing this challenge, our research, funded by this award, has led to the development of an innovative computational framework known as Probabilistic Partition of Unity Networks (PPOU-Nets). This initiative represents a collaborative effort to harness the potential of mathematics and physics-informed machine learning in tackling multiscale and multiphysics problems prevalent in high-dimensional spaces. Through this work, we have proposed a novel methodology that seamlessly integrates adaptive dimensionality reduction and a mixture of experts model, thereby facilitating a more efficient and accurate approximation of complex functions. This research effort has not only advanced the state of computational science but also opened new avenues for exploration in quantum computing and beyond. This report outlines the motivation, methodology, key findings, and implications of our work, underscoring our contributions to the broader scientific community and the potential pathways for future research.

97 MATHEMATICS AND COMPUTING↗

Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning

Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system’s resilience against cyber attacks. However, adversary emulation is typically a manual process, making it costly and hard to deploy in cyber-physical systems (CPS) with complex dynamics, vulnerabilities, and operational uncertainties. In this paper, we develop an automated, domain-aware approach to adversary emulation for CPS. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph with cyber (discrete) and physical (continuous) components and related physical dynamics. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion. As a baseline, we also develop a greedy attack algorithm and compare it with the RL procedures. We summarize our findings through a numerical study on sensor deception attacks in buildings to compare the performance and solution quality of the proposed algorithms.

Bhattacharya, Arnab↗

Harnessing the Materials Project for machine-learning and accelerated discovery

We present that improvements in computational resources over the last decade are enabling a new era of computational prediction and design of novel materials. The resulting resources are databases such as the Materials Project (www.materialsproject.org), which is harnessing the power of supercomputing together with state-of-the-art quantum mechanical theory to compute the properties of all known inorganic materials, to design novel materials, and to make the data available for free to the community, together with online analysis and design algorithms. The current release contains data derived from quantum mechanical calculations for more than 70,000 materials and millions of associated materials properties. The software infrastructure carries out thousands of calculations per week, enabling screening and predictions for both novel solids as well as molecular species with targeted properties. As the rapid growth of accessible computed materials properties continues, the next frontier is harnessing that information for automated learning and accelerated discovery. Here, we highlight some of the emerging and exciting efforts, and successes, as well as current challenges using descriptor-based and machine-learning methods for data-accelerated materials design.

36 MATERIALS SCIENCE↗

SRF CAVITY FAULT PREDICTION USING DEEP LEARNING AT JEFFERSON LAB

In this study, we present a deep learning-based pipeline for predicting superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelera-tor Facility (CEBAF) at Jefferson Lab. We leverage pre-fault RF signals from C100-type cavities and employ deep learning to predict faults in advance of their onset. We train a binary classifier model to distinguish between stable and impending fault signals. Test results show accuracies exceeding 99% for distinguishing between normal signals and pre-fault signals from a class of more slowly developing fault types, such as microphonics. We describe results from a proof-of-principle demonstration on a realistic, imbalanced data set and report performance metrics. Encouraging results suggest that future SRF systems could leverage this framework and implement measures to mitigate the onset in more slowly developing fault types.

Rahman, M.↗

Intergovernmental Advanced Stationary PEM Fuel Cell System Demonstration (Final Report)

A program to complete the design, construction and demonstration of a PEMFC system fuelled by Ethanol, LPG or NG for telecom applications was initiated in October 2007. Early in the program the economics for Ethanol were shown to be unfeasible and permission was given by DOE to focus on LPG only. The design and construction of a prototype unit was completed in Jun 2009 using commercially available PEM FC stack from Ballard Power Systems. During the course of testing, the high pressure drop of the stack was shown to be problematic in terms of control and stability of the reformer. Also, due to the power requirements for air compression the overall efficiency of the system was shown to be lower than a similar system using internally developed low pressure drop FC stack. In Q3 2009, the decision was made to change to the Plug power stack and a second prototype was built and tested. Overall net efficiency was shown to be 31.5% at 3 kW output. Total output of the system is 6 kW. Using the new stack hardware, material cost reduction of 63% was achieved over the previous Alpha design. During a November 2009 review meeting Plug Power proposed and was granted permission, to demonstrate the new, commercial version of Plug Power's telecom system at CERL. As this product was also being tested as part of a DOE Topic 7A program, this part of the program was transferred to the Topic 7A program. In Q32008, the scope of work of this program was expanded to include a National Grid demonstration project of a micro-CHP system using hightemperature PEM technology. The Gensys Blue system was cleared for unattended operation, grid connection, and power generation in Aug 2009 at Union College in NY state. The system continues to operate providing power and heat to Beuth House. The system is being continually evaluated and improvements to hardware and controls will be implemented as more is learned about the system's operation. The program is instrumental in improving the efficiency and reducing costs of PEMFC based power systems using LPG fuel and continues to makes steps towards meeting DOE's targets. Plug Power would like to thank DOE for their support of this program.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NNMC–DP Continuing Education Summary [Slides]

DP technicians voiced a desire for more development and learning opportunities. DP management and technician partners identified the opportunity to expand the knowledge of the technicians through employee development to strengthen the collaboration.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Diagnostics, Prognostics, and Optimization for Lithium-Ion Battery Systems

Health management of lithium-ion battery systems presents a host of challenges due to their complex physics, large numbers of components, and a wide variety of degradation behaviors across different battery types. Dr. Paul Gasper will present on research from the Electrochemical Energy Storage Group on Lithium-ion battery diagnostics, prognostics, and optimization. Diagnostics research, including state-estimation via machine-learning from electrochemical impedance spectroscopy and DC pulses as well as continuous state-estimation via Kalman filters, will highlight the ongoing challenges for accurately measuring the state of batteries without performing time-consuming characterization tests. NLR's industry-recognized battery prognostics work, which predicts real-world battery degradation by identifying degradation rate models from accelerated aging data using statistical modeling and machine-learning, will be used to demonstrate the critical impact of battery controls, thermal management, and operating strategy on durability and lifetime. Finally, the use of prognostic models for financial or lifetime optimization will be discussed.

25 ENERGY STORAGE↗

Cross-domain digital twin architecture for predictive maintenance via machine learning and Large Language Models

This research introduces a comprehensive framework for creating and deploying a digital twin platform for continuous monitoring and predictive maintenance within industrial settings. Through utilizing advanced technologies, including Unreal Engine 5, Unity 3D, the Message Queue Telemetry Transport protocol, Random Forest machine learning algorithms, and Large Language Models (LLMs), we establish a platform that digitally reproduces physical equipment and translates digital controls into real-world actions. This facilitates preventive maintenance approaches and improves operational effectiveness. The digital twin platform gathers sensor data from operational equipment, analyzes it using machine learning, and delivers practical insights to prevent potential malfunctions and enhance equipment performance. Furthermore, the incorporation of a web portal enables efficient monitoring and access to historical data, educational materials, and equipment status information. Preliminary findings indicate that digital twins can transform industrial equipment management and maintenance methodologies.

97 MATHEMATICS AND COMPUTING↗

Surrogate construction via weight parameterization of residual neural networks

Surrogate model development is a critical step for uncertainty quantification or other sample-intensive tasks for complex computational models. Here, in this work, we develop a multi-output surrogate form using a class of neural networks (NNs) that employ shortcut connections, namely Residual NNs (ResNets). ResNets are known to regularize the surrogate learning problem and improve the efficiency and accuracy of the resulting surrogate. Inspired by the continuous, Neural ODE analogy, we augment ResNets with weight parameterization strategy with respect to ResNet depth. Weight-parameterized ResNets regularize the NN surrogate learning problem and allow better generalization with a drastically reduced number of learnable parameters. We demonstrate that weight-parameterized ResNets are more accurate and efficient than conventional feed-forward multi-layer perceptron networks. We also compare various options for parameterization of the weights as functions of ResNet depth. We demonstrate the results on both synthetic examples and a large scale earth system model of interest.

97 MATHEMATICS AND COMPUTING↗

Roadmap for Advanced Power System Measurements

Conditions in the electric power grid are changing rapidly. Changes are driven, in particular, by the increased penetration of renewable resources in the generation mix. Part of the solution to dealing with the changing conditions is the better use of measurement systems, taking advantage of the better understanding of measurements that was heralded by digital technology. Another part of the solution is the communication of samples of the directly observable voltages and currents by means of continuous point-on-wave values. The increased bandwidth capability of such a system allows more complicated measurement models to be built at the point of use. Additional measurements and analyses can then be performed. This Roadmap hinges on these two aspects of measuring: improved measurements supported by high-bandwidth (raw data) communications. Following an introduction to the overall subject, the report explores the impact of what can be thought of as the digital revolution in measurement. In essence, that revolution has served to clarify ideas about measurement and is continuing to lead to improved processes. An extensive survey of the relevant literature was performed . Webinars were held to learn from the wider community of practitioners. Based on this information, a number of gaps were identified whose continued existence would hamper the solution of the challenges now facing measurement and communication in the power grid. The underlying value propositions are interoperability (presently not very satisfactory in many measurements); greater (and less challenging) adoption of distributed energy resources; and improved international competitiveness. Underlying all that, of course, is progress toward a more reliable and resilient power system. The identified gaps were addressed in four major thrusts: technology deployment and demonstration, education, instrumentation testing and standards, and analytical methods. For each of the thrusts, multiple goals are defined to guide the implementation. The thrusts were designed to close gaps and unlock high-value use cases. After discussing the literature review, gap analysis, high-value use cases, and research thrusts in chapters 2-5, the report culminates in chapter 6 with a roadmap that links each aspect together to form a unified plan. Developing a research portfolio aligned with this plan will ensure that advanced measurement systems are in place to support reliable operation of the power system as it modernizes.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Facilitating Machine Learning Collaborations Between Labs, Universities, And Industry

It is clear from numerous recent community reports, papers, and proposals that machine learning is of tremendous interest for particle accelerator applications. The quickly evolving landscape continues to grow in both the breadth and depth of applications including physics modeling, anomaly detection, controls, diagnostics, and analysis. Consequently, laboratories, universities, and companies across the globe have established dedicated machine learning (ML) and data science efforts aiming to make use of these new state-of-the-art tools. The current funding environment in the U.S. is structured in a way that supports specific application spaces rather than larger collaboration on community software. Here, we discuss the existing collaboration bottlenecks and how a shift in the funding environment, and how we develop collaborative tools, can help fuel the next wave of ML advancements for particle accelerators.

Edelen, J.P.↗

NASA Earth Systems Digital Twins (ESDT)

"Similarly to artificial intelligence, which is now revolutionizing many aspects of our daily lives, Earth system digital twin technologies have the potential to revolutionize the way Earth Science research will be conducted in the future, and how results and knowledge from this research will provide information to support decision making and yield impactful societal benefits. An Earth System Digital Twin or ESDT is a dynamic and interactive information system that first provides a digital replica of the past and current states of the Earth or Earth system as accurately and timely as possible; second, allows for computing forecasts of future states under nominal assumptions and based on the current replica; and third, offers the capability to investigate many hypothetical scenarios under varying impact assumptions. In other words, an ESDT provides the integrated What-Now, What-Next, and What-If pictures of the Earth or Earth system, by continuously ingesting newly observed data and by leveraging multiple interconnected models, machine learning as well advanced computing and visualization capabilities. Digital twins have been developed in engineering since 2002, but the interest in digital twins for the Earth domain is more recent and stems from the convergence of several developments: - The huge amount of diverse data that has now been collected continuously for more than 50 years, and that is becoming more and more difficult to access, understand, and utilize. - At the same time, because of climate change and its impacts the information produced by all of this data is becoming of interest to many new non-traditional users for analyzing and predicting various phenomena. - Because of advances in computational and visualization capabilities and the parallel unprecedented development of machine learning (ML), extracting relevant information from these large amounts of data and running complex models faster has become possible. As a result, it is becoming necessary and possible to build intuitive and interactive frameworks that will enable users with various skill levels and/or organizational hierarchy levels to easily access large amounts of targeted information along with the relevant tools and models (Earth system and human activity models), to support them in analyzing and visualizing this information, to help them understand interactions among models, to visualize the potential outcomes of various impacts, and to support decision or policy making. The full power of digital twins is that, through an integrated representation and standardized tools and software technologies, the same digital replica can address the needs of multiple users at various resolutions (spatial and temporal) and for various applications (science, economic, policy, etc.) – “from farmer to scientist”. With all these interests at stake, the challenges of building optimal digital twins are many and complex. The first challenge is to determine if a Digital Twin should be global or local, and multi-domain or thematic. For example, some domains such as Climate or Weather will require a global Digital Twin or Digital Twin capabilities while science areas such as Biodiversity might be more local. We can also envision that multiple thematic ESDTs, e.g., Air Quality, Wildfires, Hydrology could be federated or provide input to other ESDTs, either on a regional level or to a more global ESDT. Overall, we can imagine a future “web” of Digital Twins co-existing in a hierarchy or in a network, and capable of being connected or federated depending on the needs. This last point brings up the very important challenge of interoperability, including standards and protocols that will need to be built into these systems from the beginning. Each individual digital twin would have full flexibility in internal construction but would need standards-based interfaces (input and output) or hooks to make it compatible with others. Another challenge when building digital twins will be to decide how to organize each digital replica. Based on the applications targeted by the DT under implementation, various amounts and types of raw data, Analysis Ready Data (ARD) and information will need to be incorporated. Depending on the required latencies and needs of the users, various solutions can be considered, including Data Cubes, Data Lakes, pointers, or computing information on demand. We envision that each ESDT will choose a solution adapted to its specific objectives. Another important challenge is the type(s) of visualization that will be used, as well as the level of interactivity and refresh rate that will be required. Again, this will depend on the objectives of the ESDT, but also on the various users’ needs. In most cases, several types of visualizations and human interfaces will need to be offered depending on the projected users of that system. In parallel to the challenges highlighted above, there are also many tools and technologies that will need to be developed or improved for all types of digital twins. Among those are improved machine learning technologies, for example providing explainability, but also ML techniques for causality and providing a better integration of physics models. Additionally, reliable uncertainty quantification methods will be needed for all ESDT components, from validating data fusion and assimilation to assessing the accuracy of ML models and weighing the values of decisions supported by those systems. This presentation introduces the ESDT concept, presents several ESDT use cases, and a proposed ESDT architecture framework, as well as various technologies being developed by the Advanced Information Systems Technology (AIST) Program."

Earth Science Remote Sensing; Information Systems↗

Model-Free Voltage Control of Active Distribution System with PVs Using Surrogate Model-Based Deep Reinforcement Learning

Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage control performance, but this is difficult to obtain in practice. This paper proposes a physical-model-free voltage control method based on a surrogate-model-enabled deep reinforcement learning approach. Specifically, a surrogate model is trained in a supervised manner using the recorded limited number of historical data to learn the relationship between the power injections and voltage fluctuations of each node. Then, the deep reinforcement learning algorithm is applied to learn an optimal control strategy from the experiences obtained by continuous interactions with the surrogate model. The proposed method can achieve physical-model-free control of unbalanced distribution network and inform real-time decisions to deal with fast voltage fluctuations caused by the rapid variation of PV generation. Simulation results on an unbalance IEEE 123-bus system show that the proposed method can achieve similar performance as that of perfect physical-model-based approaches while being advantageous over other traditional methods.

active distribution network↗

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗

SU-E-I-41: Dictionary Learning Based Quantitative Reconstruction for Low-Dose Dual-Energy CT (DECT)

Purpose: DECT collects two sets of projection data under higher and lower energies. With appropriates composition methods on linear attenuation coefficients, quantitative information about the object, such as density, can be obtained. In reality, one of the important problems in DECT is the radiation dose due to doubled scans. This work is aimed at establishing a dictionary learning based reconstruction framework for DECT for improved image quality while reducing the imaging dose. Methods: In our method, two dictionaries were learned respectively from the high-energy and lowenergy image datasets of similar objects under normal dose in advance. The linear attenuation coefficient was decomposed into two basis components with material based composition method. An iterative reconstruction framework was employed. Two basis components were alternately updated with DECT datasets and dictionary learning based sparse constraints. After one updating step under the dataset fidelity constraints, both high-energy and low-energy images can be obtained from the two basis components. Sparse constraints based on the learned dictionaries were applied to the high- and low-energy images to update the two basis components. The iterative calculation continues until a pre-set number of iteration was reached. Results: We evaluated the proposed dictionary learning method with dual energy images collected using a DECT scanner. We re-projected the projection data with added Poisson noise to reflect the low-dose situation. The results obtained by the proposed method were compared with that obtained using FBP based method and TV based method. It was found that the proposed approach yield better results than other methods with higher resolution and less noise. Conclusion: The use of dictionary learned from DECT images under normal dose is valuable and leads to improved results with much lower imaging dose.

60 APPLIED LIFE SCIENCES↗

Entanglement engineering of optomechanical systems by reinforcement learning

Entanglement is fundamental to quantum information science and technology, yet controlling and manipulating entanglement—so-called entanglement engineering—for arbitrary quantum systems remains a formidable challenge. There are two difficulties: the fragility of quantum entanglement and its experimental characterization. We develop a model-free deep reinforcement-learning (RL) approach to entanglement engineering, in which feedback control together with weak continuous measurement and partial state observation is exploited to generate and maintain desired entanglement. We employ quantum optomechanical systems with linear or nonlinear photon–phonon interactions to demonstrate the workings of our machine-learning-based entanglement engineering protocol. In particular, the RL agent sequentially interacts with one or multiple parallel quantum optomechanical environments, collects trajectories, and updates the policy to maximize the accumulated reward to create and stabilize quantum entanglement over an arbitrary amount of time. The machine-learning-based model-free control principle is applicable to the entanglement engineering of experimental quantum systems in general.

97 MATHEMATICS AND COMPUTING↗