Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning control”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,783 records · Page 99
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Detection of Outliers in LiDAR Data Acquired by Multiple Platforms over Sorghum and Maize

High-resolution point cloud data acquired with a laser scanner from any platform contain random noise and outliers. Therefore, outlier detection in LiDAR data is often necessary prior to analysis. Applications in agriculture are particularly challenging, as there is typically no prior knowledge of the statistical distribution of points, plant complexity, and local point densities, which are crop-dependent. The goals of this study were first to investigate approaches to minimize the impact of outliers on LiDAR acquired over agricultural row crops, and specifically for sorghum and maize breeding experiments, by an unmanned aerial vehicle (UAV) and a wheel-based ground platform; second, to evaluate the impact of existing outliers in the datasets on leaf area index (LAI) prediction using LiDAR data. Two methods were investigated to detect and remove the outliers from the plant datasets. The first was based on surface fitting to noisy point cloud data via normal and curvature estimation in a local neighborhood. The second utilized the PointCleanNet deep learning framework. Both methods were applied to individual plants and field-based datasets. To evaluate the method, an F-score was calculated for synthetic data in the controlled conditions, and LAI, the variable being predicted, was computed both before and after outlier removal for both scenarios. Results indicate that the deep learning method for outlier detection is more robust than the geometric approach to changes in point densities, level of noise, and shapes. The prediction of LAI was also improved for the wheel-based vehicle data based on the coefficient of determination (R2) and the root mean squared error (RMSE) of the residuals before and after the removal of outliers.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Use Machine Learning to Improve Burnup Measurement in Pebble Bed Reactors

Advanced pebble bed reactor (PBR) designs post new challenges in material control and accountancy (MC&A) because the fuel materials, distributed in many discrete pebbles, are continuously circulated through the reactor core and the refueling path compared to the bulk fuel assembly design in conventional reactors, e.g., light water reactors. In pebble bed reactors, there are hundreds of thousands of fuel pebbles in the reactor core during the normal operation, and the burnup of each pebble is measured when ejected from the core. Accurate burnup measurement is an important step in material control and spent fuel disposition. The measurement is usually based on detection of radiation signatures of fission products accumulated in the pebble fuel over irradiation in the core. Previous research has shown that height of photopeaks of fission products, such as 134 Cs, 137 Cs, 154 Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of pebbles undergoing burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2026

Machine learning-enhanced MPC for demand flexibility in small commercial buildings: An experimental study

Small- and medium-sized commercial buildings (SMCBs) represent the majority of U.S. commercial building stock and a significant share of peak electricity demand, yet they often lack centralized building automation systems, representing a significant untapped resource for urban energy management. This infrastructure gap makes advanced control implementation challenging, limiting the potential for widespread demand flexibility. Model Predictive Control (MPC) has shown strong potential for load shifting, peak demand reduction, and cost savings, but its effectiveness is hindered by unmeasured disturbances such as internal heat gains. This paper presents a Hybrid MPC framework that integrates a physics-based gray-box building thermal model, identified using a lumped disturbance (LD) approach, with a machine learning (ML) model for forecasting unmeasured disturbances. The hybrid approach is designed for buildings with multiple individually controlled heat pump and thermostat pairs, common in SMCBs, and aims to optimize coordinated scheduling of multiple heat pumps under dynamic electricity pricing while respecting comfort constraints. The methodology is validated through both simulations of case study buildings and experimental studies at a highly-instrumented test facility. Simulation results show that the Hybrid MPC achieves substantial load shifting and peak demand reduction, approaching the performance of an ideal MPC with perfect disturbance knowledge, and outperforming a conventional MPC without disturbance forecasting. In experiments, the Hybrid MPC reduced daily HVAC energy costs by 8.7%, peak-price time load (load shifting) by 41.7%, and peak demand by 29.2% compared to baseline control, demonstrating comparable benefits to the 11.6% cost savings, 42.9% load shifting, and 23.2% peak reduction of the ideal MPC. These results demonstrate that the proposed hybrid modeling approach can significantly improve MPC performance in real-world SMCB applications without requiring additional disturbance measurements.

Demand Flexibility↗
DOE OSTI2024

Adaptive nonequilibrium design of actin-based metamaterials: Fundamental and practical limits of control

The adaptive and surprising emergent properties of biological materials self-assembled in far-from-equilibrium environments serve as an inspiration for efforts to design nanomaterials. In particular, controlling the conditions of self-assembly can modulate material properties, but there is no systematic understanding of either how to parameterize external control or how controllable a given material can be. Here, we demonstrate that branched actin networks can be encoded with metamaterial properties by dynamically controlling the applied force under which they grow and that the protocols can be selected using multi-task reinforcement learning. These actin networks have tunable responses over a large dynamic range depending on the chosen external protocol, providing a pathway to encoding “memory” within these structures. Interestingly, we obtain a bound that relates the dissipation rate and the rate of “encoding” that gives insight into the constraints on control—both physical and information theoretical. Taken together, these results emphasize the utility and necessity of nonequilibrium control for designing self-assembled nanostructures.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Quasi-Stochastic Approximation and Off-Policy Reinforcement Learning: Preprint

The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning and often an efficient approach to solving (or approximating the solution to) complex optimal control problems. In many cases, however, practitioners are unable to apply these techniques because of an inherent high variance. This paper aims to provide a general foundation for 'quasi-stochastic approximation,' in which all of the processes under consideration are deterministic, much like quasi-Monte Carlo for variance reduction in simulation. The variance reduction can be substantial, subject to tuning of pertinent parameters in the algorithm. This paper introduces a new coupling argument to establish the optimal rate of convergence provided the gain is sufficiently large. These results are established for linear models and tested also in nonideal settings. A major application of these general results is a new class of reinforcement learning algorithms for deterministic state space models. In this setting, the main contribution is a class of algorithms for approximating the value function for a given policy, using a different policy designed to introduce exploration.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Adaptively Learned Modeling for a Digital Twin of Hydropower Turbines with Application to a Pilot Testing System

In the development of a digital twin (DT) for hydropower turbines, dynamic modeling of the system (e.g., penstock, turbine, speed control) is crucial, along with all the necessary data interface, virtualization, and dashboard designs. Since the DT must mimic the actual dynamics of the hydropower turbine accurately, adaptive learning is required to train these dynamic models online so that the models in the DT can effectively follow the representation of the actual hydropower turbine dynamics accurately and reliably. This study presents an adaptive learning method for obtaining the hydropower turbine models for DT development of hydropower systems using the recursive least squares algorithm. To simplify the formulation, the hydropower turbine under consideration was assumed to operate near a fixed operating point, where the system dynamics can be well represented by a set of linear differential equations with constant parameters. In this context, the well-known six-coefficient model for the Francis turbine was formulated as the starting point to obtain input and output models for the turbine. Then, an adaptive learning mechanism was developed to learn model parameters using real-time data from a hydropower turbine testing system. This led to semi-physical modeling, in which first principles and data-driven modeling are integrated to produce dynamic models for DT development. Applications to a pilot system at the Norwegian University of Science and Technology (NTNU) were made, and the models learned adaptively using the data collected from the university’s pilot system. Desired modeling and validation results were obtained.

13 HYDRO ENERGY↗
DOE OSTI2024

Smart Building Technology Training Modules for Academic and Professional Education

Smart building technologies are a new suite of resources that improve building energy efficiency and resilience, reduce carbon emissions, and provide load flexibility to the grid. However, in both college curricula and building professionals’ continuing education, there is a lack of systematic instruction on smart building technologies–topics that include smart building concepts, key components, smart building controls, “Internet of Things” (IoT) devices, and how to integrate multiple energy systems including distributed energy resources (DER). This major gap in smart building education prevents stakeholders from understanding and adopting smart building technologies in building design and operations. Slipstream leads a DOE-funded project developing a semester-long smart building curriculum for college students and adapting the contents into 16 training videos for building professionals and the general public. The education and training cover the drivers and benefits of smart building technologies, key building energy systems, the latest sensor technologies and IoT devices, and focus on topics related to smart building controls (i.e., energy management information systems, smart building control platforms, cybersecurity, grid-interactive-efficient buildings (GEBs), smart building control methods, and occupant-centric control. This paper describes the project approach, provides outlines of the training materials, and identifies lessons learned in creating the content. We also suggest ways to scale the instruction of smart building concepts to empower the workforce to accelerate the adoption of smart building technologies in the real world.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Complete Evaluation on Advanced Reactor Machine Learning Subversion Attacks (Final)

Navigating through the world of Artificial Intelligence (AI) in nuclear reactors and their Instrumentation and Control (I&C) systems demands a careful, deliberate journey. AI’s capability to manage massive datasets and streamline control systems has indeed carved out a significant role in various sectors, including nuclear energy. However, while AI, and particularly Large Language Models (LLMs), bring a lot to the table in terms of operational efficiency and anomaly detection, they also expose the sector to a new breed of cybersecurity threats, like Inference Attacks, Adversarial Attacks, and Trojan Attacks. This guide is designed to be a straightforward manual, diving deep into the intertwining worlds of AI and cybersecurity within nuclear reactors, and tailoring insights for three crucial audiences: I&C Vendors/Developers, Nuclear Regulators, and Nuclear Reactor Operators and Cyber Defense Teams. (1) Section 2, directed at I&C Vendors/Developers, will provide a clear and focused look at several cybersecurity attacks, offering practical recommendations and detailed scenarios related to AI cybersecurity. This section isn’t just about identifying problems but also about giving solid, usable solutions. (2) Section 3, meant for Nuclear Regulators, gets straight to the point about regulations, policy suggestions, and guidelines that are needed to lay down a robust, secure, and ethical foundation for the application of AI in nuclear operations. The focus is on making sure that everything adheres to international standards and laws while being practicable and clear-cut. (3) Section 4, aimed at Nuclear Reactor Operators and Cyber Defense Teams, offers an exhaustive exploration and technical reports, with clear recommendations and scenario analyses vital to protect operational environments and guarantee the secure application of AI in nuclear reactor operations. The goal is simple: as we step into an era where AI becomes a fundamental element of our technological and energy infrastructures, this guide is here to act as a clear, direct handbook, ensuring that AI is implemented within the nuclear sector in a manner that is secure, responsible, and practical. It’s about striking a balance – optimizing the undeniable benefits offered by AI while securing and shielding against potential cyber threats as we move through this new and complex landscape.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

IBR Black Model Lessons Learned (C45)

Blackbox modelling for SC analysis is a possible solution. Accuracy can be acceptable even without having vendor control diagrams. Blackbox modelling is not as user friendly as a generic model. Is an NDA required to share a vendor Blackbox model for SC analysis? Difference in VRT detection and injection logics. Angle rotation is not addressed. Current limitation logic during unbalanced faults is not clear.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

A Machine Learning-Based Method to Estimate Transformer Primary-Side Voltages with Limited Customer-Side AMI Measurements: Preprint

Distribution control applications such as volt/var optimization, network reconfiguration, and distribution automation require accurate knowledge of the distribution system state. The lack of sufficient sensors on the primary side of distribution networks often limits the accuracy of the control decisions by these applications. The deployment of advanced metering infrastructure (AMI) provides utilities an opportunity to translate the AMI data on the secondary onto the primary so that it can be used as pseudo-measurements to augment the limited existing measurements on the primary. This paper develops an approach for estimating service transformer primary-side voltages by using limited secondary-side AMI measurements. The estimated primary-side voltages can be used by utilities as pseudo-measurements for distribution control applications. The detailed secondary model topology, which is an essential input data for many existing algorithms, is not required for the proposed method. The performance of the proposed method is validated by using AMI measurements from the field and an actual distribution feeder model of San Diego Gas & Electric Company.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1990

Model-free distributed learning

Model-free learning for synchronous and asynchronous quasi-static networks is presented. The network weights are continuously perturbed, while the time-varying performance index is measured and correlated with the perturbation signals; the correlation output determines the changes in the weights. The perturbation may be either via noise sources or orthogonal signals. The invariance to detailed network structure mitigates large variability between supposedly identical networks as well as implementation defects. This local, regular, and completely distributed mechanism requires no central control and involves only a few global signals. Thus it allows for integrated on-chip learning in large analog and optical networks.

Dembo, Amir↗
NASA NTRS1996

Integrated Aeropropulsion Control System Design

%T Integrated Aeropropulsion Control System Design%A C-F. Lin%A Francis X. Hurley%A Jie Huang%A F. Y. Hadaegh%J International Conference on Control and Information(psi)995%C Hong Kong%D June 1995%K aeropropulsion, control, system%U http://jpltrs.jpl.nasa.gov/1995/95-0658.pdfAn integrated intelligent control approach is proposed to design a high performance control system for aeropropulsion systems based on advanced sensor processing, nonlinear control and neural fuzzy control integration. Our approach features the following innovations:??e complexity and uncertainty issues are addressed via the distributed parallel processing, learning, and online reoptimization properties of neural networks.??e nonlinear dynamics and the severe coupling can be naturally incorporated into the design framework.??e knowledge base and decision making logic furnished by fuzzy systems leads to a human intelligence enhanced control scheme.In addition, fault tolerance, health monitoring and reconfigurable control strategies will be accommodated by this approach to ensure stability, graceful degradation and reoptimization in the case of failures, malfunctions and damage.!.

aeropropulsion control systems↗
DOE OSTI2020

Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides

The ability to predict the likelihood of impurity incorporation and their electronic energy levels in semiconductors is crucial for controlling its conductivity, and thus the semiconductor's performance in solar cells, photodiodes, and optoelectronics. The difficulty and expense of experimental and computational determination of impurity levels makes a data-driven machine learning approach appropriate. In this work, we show that a density functional theory-generated dataset of impurities in Cd-based chalcogenides CdTe, CdSe, and CdS can lead to accurate and generalizable predictive models of defect properties. By converting any semiconductor + impurity system into a set of numerical descriptors, regression models are developed for the impurity formation enthalpy and charge transition levels. These regression models can subsequently predict impurity properties in mixed anion CdX compounds (where X is a combination of Te, Se and S) fairly accurately, proving that although trained only on the end points, they are applicable to intermediate compositions. We make machine-learned predictions of the Fermi-level-dependent formation energies of hundreds of possible impurities in 5 chalcogenide compounds, and we suggest a list of impurities which can shift the equilibrium Fermi level in the semiconductor as determined by the dominant intrinsic defects. Machine learning predictions for the dominating impurities compare well with DFT predictions, revealing the power of machine-learned models in the quick screening of impurities likely to affect the optoelectronic behavior of semiconductors.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Design Space Exploration of Emerging Memory Technologies for Machine Learning Applications

Memory design space exploration methods study memory systems’ performances and limitations before implementation. The computer memory design space has grown exponentially because of the enormous growth of memory types, memory controllers, and application software. Computer simulators are commonly used for memory design space exploration. However, complex memory simulations take an enormous amount of time. Hence, in this paper, we proposed a machine learning-based design space exploration method for dynamic random-access memory and non-volatile memory systems. We applied our method to the CosmoGAN and LeNet applications to predict the following six memory response parameters: (i) bandwidth, (ii) power, (iii) average latency, (iv) average total latency, (v) memory reads, and (vi) memory writes. Our experimental results show that machine learning models can predict memory response parameter values faster than simulations. We used support vector machine, random forest, and gradient boosting machine learning models. We observed that the support vector machine provides better performance for bandwidth, average latency, and average total latency. The random forest model works better for memory reads and writes. The gradient boosting model provides superior prediction performance for power. We provide a detailed discussion on learning curve characteristics, error analysis, and memory type recommendation.

Hasan, S M Shamimul↗
DOE OSTI2020

Lessons Learned from Hanford's Purex Tunnel 2 Structural Stabilization Project - 20509

In 2019, U.S. Department of Energy (DOE) contractor CH2M Hill Plateau Remediation Company (CHPRC) completed structurally stabilizing the Plutonium Uranium Extraction Plant (Purex) waste storage Tunnel 2 with engineered grout. This action significantly reduced risk to Hanford workers, the surrounding community and environment by preventing future collapse of the tunnel and possible release of radioactive materials. Decades of plutonium production at the Purex facility required construction of two large underground tunnels for storage of highly contaminated plutonium processing equipment that had failed during the operation of Purex and other facilities across the Hanford Site. Following the partial collapse of Purex Tunnel 1 on May 9, 2017, DOE and CHPRC took immediate action to safely stabilize the collapsed section of the tunnel. The hole in the tunnel was filled the next day as a temporary stabilization measure, and no contamination was detected as a result of the partial collapse of the tunnel. Workers then stabilized Tunnel 1 in its entirety by filling with engineered grout, which also encapsulated the radioactive equipment and railcars within the tunnel. Grouting eliminated the risk of further collapse and stabilized the tunnel contents, all while not precluding future remedial actions or final closure decisions. While conducting an integrity analysis of Tunnel 1 by using construction drawings, photos and other historical documents, project teams also analyzed the much larger Purex Tunnel 2. The analysis found Tunnel 2 did not meet current codes for structural integrity, and it may not be able to bear the weight of the soil above the tunnel. Therefore, it was determined that Tunnel 2 was also at risk of collapse. DoE's independent panel of experts determined grouting to be the best choice for stabilizing Tunnel 2 because it provides the highest level of stability and protection, and does not preclude future remedial actions. DOE authorized CHPRC to commence work and the Purex Tunnel 2 Structural Stabilization Project was launched in December of 2017. The paper will discuss the process of recognizing the following critical aspects and risks associated with stabilizing Tunnel 2, and the actions taken by the project team to mitigate these risks, including: - Tunnel investigation and data collection to assist with future remediation; - On-site batching and mock-ups to provide the large quantity of grout required for stabilizing the tunnel; - Workforce involvement and innovative actions that mitigated the project's most significant potential hazards, including traffic control; - Project team high level of execution translated into successful project execution. Sharing lessons learned from this critical risk-reduction effort can enhance the safety and efficiency of other complex and hazardous projects across the DOE complex. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

Cyote-attack Chain Estimator

Attack Chain Estimator (ACE) Application Overview The Attack Chain Estimator (ACE) Application is a sophisticated tool designed for the ingestion, classification, sequencing, and enrichment of cybersecurity threat reports. This application leverages advanced machine learning models and extensive historical data to provide comprehensive insights into cyber threats, specifically targeting Industrial Control Systems (ICS). Purpose The primary functions of the ACE Application include: Ingestion of Cybersecurity Threat Reporting: Capable of ingesting text-based threat reports in markdown or text file format. Supports ingestion of structured data from other sources in STIX/JSON format. Classification of Report’s Text-Based Events: Utilizes a DeBERTa classifier, specifically trained on cybersecurity data, to map the events to MITRE ATT&CK for ICS Tactics and Techniques. Classification is performed using multiple Jupyter notebooks and machine learning workflows hosted as FastAPI microservices: regex_data deberta_base_35_train_hft_classifier_mlflow.ipynb hft_regex_classifier_mlflow.ipynb param_train_hft_classifier_mlflow.ipynb regex_tactic_tech.ipynb Ordering of Tactics, Techniques, and Observable Events: Sequences the identified tactics, techniques, and events to form a coherent attack chain. Enrichment with Historical Attack Chain Details: Enhances the attack chain with details from historical attacks using a Markov model developed from CyOTE Precursor Analysis Report data. The Markov model is available as a FastAPI endpoint for seamless integration. Enrichment with Adversary Emulation Capabilities Data: Integrates adversary emulation capabilities data using MITRE Caldera for OT adversary abilities UUIDs. Export of Output Files: Provides options to export the enriched attack chain in JSON or CSV formats. Routing of Output to Other Applications: Facilitates routing of output to various platforms and applications, including: Threat Intelligence Platforms COREII Scout for Threat Intelligence Analysis COREII Modeling and Simulation for Adversary Emulation Technical Description The ACE Application is an advanced cybersecurity tool designed to provide detailed threat analysis and sequence generation. It is built on a robust architecture that integrates natural language processing, machine learning, and historical data modeling. Key Components: Data Ingestion Module: Handles the input of threat reports and data from various formats, ensuring flexibility in data sources. Classification Engine: Employs DeBERTa-based classifiers hosted as FastAPI microservices to analyze and classify threat report events in accordance with the MITRE ATT&CK framework for ICS. Sequence Generator: Orders the classified events into a logical attack chain, providing clear insight into the sequence of tactics and techniques used in the threat. Enrichment Engine: Integrates historical data and adversary emulation capabilities to enhance the attack chain with valuable context and additional details. The historical data enrichment is powered by a Markov model, which is available as a FastAPI endpoint. Export and Routing Module: Facilitates the export of the enriched attack chain in multiple formats and routes the output to designated applications for further analysis or emulation.

Paul, Tony [Idaho National Laboratory (INL), Idaho↗
NASA NTRS1990

The final days of Solar Max - Lessons learned from engineering evaluation tests

End-of-life engineering evaluation tests were performed on Solar Max between October and November 1989. The tests included four-wheel control law operation; reaction wheel rundowns; modular power subsystem standard power regulator unit voltage-temperature level tests; battery rundown/2nd plateau determination; high gain antenna retraction and jettison; and solar array jettison. This paper presents these tests, their results, and the lessons learned from them.

Donnelly, Michael L.↗