SEARCH · Engineering Papers

Results for “Operator 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.

SourceResearch connectionFrom yearThrough year

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

At least 685 records · Page 38

All sources NASA NTRS DOE OSTI

DOE OSTI2017

Brentwood Lessons Learned Project Report

The purpose of this report is to document lessons learned in the installation of the hydrogen fueling station at the National Park Service Brentwood site in Washington, D.C., to help further the deployment of hydrogen infrastructure required to support hydrogen and other fuel cell technologies. Hydrogen fueling is the most difficult infrastructure component to build and permit. Hydrogen fueling can include augmenting hydrogen fueling capability to existing conventional fuel fueling stations as well as building brand new hydrogen fueling stations. This report was produced as part of the Brentwood Lessons Learned project. The project consisted of transplanting an existing modular hydrogen fueling station from Connecticut to the National Park Service Brentwood site. This relocation required design and construction at the Brentwood site to accommodate the existing station design as well as installation and validation of the updated station. One of the most important lessons learned was that simply moving an existing modular station to an operating site was not necessarily straight-forward - performing the relocation required significant effort and cost. The station has to function at the selected operating site and this functionality requires a power supply, building supports connecting to an existing alarm system, electrical grounding and lighting, providing nitrogen for purging, and providing deionized water if an electrolyzer is part of the station package. Most importantly, the station has to fit into the existing site both spatially and operationally and not disrupt existing operations at the site. All of this coordination and integration requires logistical planning and project management. The idea that a hydrogen fueling station can be simply dropped onto a site and made immediately operational is generally not realistic. Other important lessons learned include that delineating the boundaries of the multiple jurisdictions that have authority over a project for all parties involved in the project are key to an efficient approval process; and site investigation is necessary when integrating a new station design onto an existing site, particularly an older existing site that may have limited documentation on the site history and operations. The lessons learned for permitting and subcontracting construction work can be applied to other similar sites and to commercial sites.

30 DIRECT ENERGY CONVERSION↗

DOE OSTI2024

Detecting Important Drivers of Gridded Population Modeling With Machine Learning

High-resolution population datasets have been lever-aged across a broad swath of domains, such as climate change, public policy, humanitarian aid, and rescue operations, among others. Machine learning methods were adopted to generate high-resolution or gridded population estimates by using various geospatial input features such as buildings, roads, and nighttime lights. In this study, we evaluate the importance of population features using Random Forest models across three levels of analysis, utilizing permutation measures. Our research aims to address key questions to enhance our understanding of high-resolution population modeling, such as: Are certain features globally (10 countries collectively) more important than others? Do optimal features vary by country? Within each country, do feature importance differ across administrative units? What similarities exist in feature importance at the global, country, and administrative unit levels? To answer these questions, we leverage the Kneedle algorithm to automate the selection of optimum features. We find that there are patterns displayed by features across spatial boundaries, evidenced by the same feature being the most important indicator of population across 7 of the 10 countries modeled. Our findings indicate that while important features may vary across geographies, certain features consistently hold greater importance than others agnostic of geography.

Lebakula, Viswadeep [ORNL] (ORCID:0000000152935914↗

DOE OSTI2026

SRF cavity instability detection with machine learning at CEBAF

During the operation of the Continuous Electron Beam Accelerator Facility (CEBAF), one or more unstable superconducting radio-frequency (SRF) cavities often cause beam loss trips while the unstable cavities themselves do not necessarily trip off. The present RF controls for the legacy cavities report at only 1 Hz, which is too slow to detectfast transient instabilities during these trip events. These challenges make the identification of an unstable cavity out of the hundreds installed at CEBAF a difficult and time-consuming task. To tackle these issues, a fast data acquisition system (DAQ) for the legacy SRF cavities has been developed, which records the sample at 5 kHz. An unsupervised learning framework has been developed to identify anomalous SRF cavity behavior. We will discuss the present status of the DAQ system and our framework, along with recent successes in detecting anomalous cavity behavior. Overall, our method offers a practical solution for identifying unstable SRF cavities, contributing to increased beam availability and machine reliability.

Accelerator Physics↗

DOE OSTI2022

Neural operator prediction of linear instability waves in high-speed boundary layers

Here, we investigate if neural operators can predict the linear evolution of instability waves in high-speed boundary layers. To this end, we extend the design of the DeepOnet to ensure accurate and robust predictions, and also to perform data assimilation. In particular, we train DeepONet to take as inputs an upstream disturbance and a downstream location of interest, and to provide as output the perturbation field downstream in the boundary layer. DeepONet thus approximates the linearized and parabolized Navier-Stokes operator for this flow. For successful application to the high-speed boundary layer problem, we add sample weighting and Fourier input features to the regular DeepONet formulation. Once trained, the DeepOnet can perform fast and accurate predictions of the downstream disturbances within the range of training frequencies (inside the distribution). In addition, we show that DeepONet can solve the inverse problem, where downstream wall measurements are adopted as input, and a trained network can predict the upstream disturbances that led to these observations. This capability, along with the forward predictions, allows us to perform a full data assimilation cycle efficiently: starting from wall-pressure data, we predict the upstream disturbance using the inverse DeepONet and its evolution using the forward DeepONet. Finally, we introduce three new metrics to benchmark the training, evaluation and break-even cost of neural operators.

42 ENGINEERING↗

DOE OSTI2021

A Safety and Management Framework to Enable Automated Mobility Districts in Urban Areas

Automated mobility technology is beginning to emerge as a viable means to create sustainable and effective public mobility systems within denser urban environments. Automated mobility districts (AMDs) describe major urban districts or activity centers in which deployments of multiple automated vehicle (AV) transit and ride-hailing fleets are supported to meet public mobility needs. The authors put forward a framework to enable AMDs and their governing and management jurisdictional authorities to manage safety of AV operations based on lessons learned from the last century of automated guideway transit and roadway intersection traffic control systems. The essential concept is that of operational management and safety-critical control of multiple AV fleets using a “system-of-systems” approach to system safety analysis. The safety analysis would focus on safe passage of the AV fleet vehicles through complex roadway intersections and junctions, especially in the presence of other non-automated modes such as pedestrians and manually operated vehicles.

47 OTHER INSTRUMENTATION↗

NASA NTRS2003

LabVIEW Serial Driver Software for an Electronic Load

A LabVIEW-language computer program enables monitoring and control of a Transistor Devices, Inc., Dynaload WCL232 (or equivalent) electronic load via an RS-232 serial communication link between the electronic load and a remote personal computer. (The electronic load can operate at constant voltage, current, power consumption, or resistance.) The program generates a graphical user interface (GUI) at the computer that looks and acts like the front panel of the electronic load. Once the electronic load has been placed in remote-control mode, this program first queries the electronic load for the present values of all its operational and limit settings, and then drops into a cycle in which it reports the instantaneous voltage, current, and power values in displays that resemble those on the electronic load while monitoring the GUI images of pushbuttons for control actions by the user. By means of the pushbutton images and associated prompts, the user can perform such operations as changing limit values, the operating mode, or the set point. The benefit of this software is that it relieves the user of the need to learn one method for operating the electronic load locally and another method for operating it remotely via a personal computer.

Scullin, Vincent↗

NASA NTRS1973

Performance improvement in remote manipulation with time delay by means of a learning system.

A teleoperating system is presented that involves shared control between a human operator and a general-purpose computer-based learning machine. This setup features a trainable control network termed the autonomous control subsystem (ACS) which is able to observe the operator's control actions, learn the task at hand, and take appropriate control actions. A working ACS system is described that has been put in operation for the purpose of exploring the uses of a remote intelligence of this type. The expansion of the present system into a multifunctional learning machine capable of a greater degree of autonomy is also discussed.

Freedy, A.↗

DOE OSTI2023

Development of a Multi Sensor Data Science System for Monitoring a Solvent Extraction Process

Idaho National Laboratory is designing and constructing a solvent extraction test bed, Beartooth, as part of a nuclear fuel cycle stewardship initiative. The test bed will provide facilities and equipment for testing novel extraction processes and give early career scientists opportunities to gain skills in performing separations chemistry. The test bed is being uniquely designed to enable machine learning capabilities for the characterization of chemical process operations. One of the intentions of incorporating machine learning methods is to provide process operators with enhanced situational awareness for the optimization of separations techniques and possible detection of a diversion event. As a result, the objective of this Laboratory Directed Research and Development project is to develop a multi-sensor data collections system and implement machine learning techniques on signals from an existing centrifugal contactor cascade to identify equipment usage and process events. This presentation will provide an overview of sensors used and experiments conducted to date.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

SRF cavity instability detection with machine learning at CEBAF

Accelerator Physics↗

DOE OSTI2022

Improving Predictions Under Uncertainty of Material Plasma Device Operations

Understanding the properties of materials when exposed to various plasma temperatures and fluxes is essential to the building and operating of fusion reactors. The Material Plasma Exposure eXperiment (MPEX) is an instrument currently being developed by the Department of Energy (DOE) for this purpose. MPEX is expected to come online in stages over the next five years. Proto-MPEX, the predecessor to MPEX, operated from 2014 to 2021, and was designed to understand the generation of plasma temperatures and fluxes at orders of magnitude below what will be obtained by MPEX. This work uses the recently developed stochastic neural network (SNN), a machine learning technique capable of operating under uncertainty to provide a surrogate model for the Proto-MPEX device. We demonstrate that SNN outperforms Bayesian neural network (BNN), a standard in the field of machine learning with uncertainty. The development of a robust surrogate of the Proto-MPEX will aid in the commissioning and operation of the MPEX device.

Archibald, Rick↗

DOE OSTI2025

Decayheatml

This code is designed to predict and analyze the decay heat generated in molten salt reactors (MSRs) using a hybrid approach that combines machine learning and segmented polynomial fitting. The accurate prediction of decay heat is essential for reactor safety and the optimization of spent fuel storage. The code operates through several key components: 1) Data Architecture: It incorporates a modular data architecture that handles various MSR-specific operational parameters such as power density, humidity content, and air ingress. These parameters are sampled using Sobol sequences to ensure comprehensive coverage of operational uncertainties. 2) Machine Learning Framework: The code employs a diverse set of machine learning models, including polynomial regression, decision trees, random forests, gradient boosting, support vector regression, k-nearest neighbors, multi-layer perceptrons, and symbolic regression. These models are trained to predict decay heat over a wide temporal range, from immediate shutdown up to 10,000 years. 3) Region-Optimized Training: The temporal domain is divided into multiple regions, each modeled separately to capture distinct decay heat characteristics across different time scales. This approach significantly improves the accuracy and interpretability of predictions. 4) Segmented Polynomial Interpretation (SPI): The SPI method translates machine learning predictions into piecewise polynomial equations. These equations are physically interpretable and can be directly integrated into existing engineering workflows and safety analyses. 5) Front-End Interfaces: The code includes both a Jupyter notebook interface for research development and a Streamlit web application for operational deployment. These interfaces allow users to interactively explore decay heat predictions, adjust operational parameters, and visualize results in real-time. 6) Applications: The framework supports various applications, including safety system validation and spent fuel container optimization. It enables real-time evaluation of worst-case decay heat scenarios, informing the design of passive safety systems and optimizing container designs for long-term storage. Overall, this code provides a robust, accurate, and user-friendly tool for predicting decay heat in MSRs, enhancing reactor safety, and optimizing spent fuel management.

Retamales, Mauricio Eduardo Tano [Idaho National L↗

NASA NTRS2004

Mars Exploration Rover Mission

Two rovers with a sophisticated geological payload have been operating on the surface of Mars since January of 2004. Future missions and their related technology developments will benefit from the lessons learned during these surface operations. The planning cycle was dictated by the communications opportunities and the times of day that the rovers could operate, and the team and tools were tuned to optimize the mission return for that cycle time. The ability to traverse and to approach and perform in situ investigations on targets was limited in speed by the same cycle time, due to required human involvement in the related planning and risk decisions. In addition traverse was limited by the speed of the on-board terrain and hazard assessment, and in situ operations were limited by a lack of autonomy. Different planning cycles and levels of autonomy should be considered for future surface missions, which will result in different approaches to science decision making.

Adler, M.↗

DOE OSTI2022

SRF Cavity Instability Detection with Machine Learning at CEBAF

During the operation of CEBAF, one or more unstable superconducting radio-frequency (SRF) cavities often cause beam loss trips while the unstable cavities themselves do not necessarily trip off. Identifying an unstable cavity out of the hundreds of cavities installed at CEBAF is difficult and time-consuming. The present RF controls for the legacy cavities report at only 1 Hz, which is too slow to detect fast transient instabilities. A fast data acquisition system for the legacy SRF cavities is being developed which samples and reports at 5 kHz to allow for detection of transients. A prototype chassis has been installed and tested in CEBAF. An autoencoder based machine learning model is being developed to identify anomalous SRF cavity behavior. The model is presently being trained on the slow (1 Hz) data that is currently available, and a separate model will be developed and trained using the fast (5 kHz) DAQ data once it becomes available. This paper will discuss the present status of the new fast data acquisition system and results of testing the prototype chassis. This paper will also detail the initial performance metrics of the autoencoder model.

Carpenter, A.↗

DOE OSTI2022

SRF Cavity Instability Detection with Machine Learning at CEBAF

Carpenter, A.↗

NASA NTRS2015

Software Defined Radio Architecture Contributions to Next Generation Space Communications

Space communications architecture concepts, comprising the elements of the system, the interactions among them, and the principles that govern their development, are essential factors in developing National Aeronautics and Space Administration (NASA) future exploration and science missions. Accordingly, vital architectural attributes encompass flexibility, the extensibility to insert future capabilities, and to enable evolution to provide interoperability with other current and future systems. Space communications architectures and technologies for this century must satisfy a growing set of requirements, including those for Earth sensing, collaborative observation missions, robotic scientific missions, human missions for exploration of the Moon and Mars where surface activities require supporting communications, and in-space observatories for observing the earth, as well as other star systems and the universe. An advanced, integrated, communications infrastructure will enable the reliable, multipoint, high-data-rate capabilities needed on demand to provide continuous, maximum coverage for areas of concentrated activity. Importantly, the cost/value proposition of the future architecture must be an integral part of its design; an affordable and sustainable architecture is indispensable within anticipated future budget environments. Effective architecture design informs decision makers with insight into the capabilities needed to efficiently satisfy the demanding space-communication requirements of future missions and formulate appropriate requirements. A driving requirement for the architecture is the extensibility to address new requirements and provide low-cost on-ramps for new capabilities insertion, ensuring graceful growth as new functionality and new technologies are infused into the network infrastructure. In addition to extensibility, another key architectural attribute of the space communication equipment's interoperability with other NASA communications systems, as well as those communications and navigation systems operated by international space agencies and civilian and government agencies. In this paper, we review the philosophies, technologies, architectural attributes, mission services, and communications capabilities that form the structure of candidate next-generation integrated communication architectures for space communications and navigation. A key area that this paper explores is from the development and operation of the software defined radio for the NASA Space Communications and Navigation (SCaN) Testbed currently on the International Space Station (ISS). Evaluating the lessons learned from development and operation feed back into the communications architecture. Leveraging the reconfigurability provides a change in the way that operations are done and must be considered. Quantifying the impact on the NASA Space Telecommunications Radio System (STRS) software defined radio architecture provides feedback to keep the standard useful and up to date. NASA is not the only customer of these radios. Software defined radios are developed for other applications, and taking advantage of these developments promotes an architecture that is cost effective and sustainable. Developments in the following areas such as an updated operating environment, higher data rates, networking and security can be leveraged. The ability to sustain an architecture that uses radios for multiple markets can lower costs and keep new technology infused.

Lessons Learned↗

NASA NTRS2014

On-Orbit Performance of MODIS Solar Diffuser Stability Monitor

Moderate Resolution Imaging Spectroradiometer (MODIS) is currently operated on both the Terra and Aqua spacecraft. It collects data in 20 reflective solar bands (RSB) and 16 thermal emissive bands. MODIS RSB calibration is reflectance based via an on-board solar diffuser (SD). On-orbit changes in the SD bidirectional reflectance factor are tracked by an onboard solar diffuser stability monitor (SDSM). The SDSM functions as an independent ratioing radiometer with nine filtered detectors, covering wavelengths in the visible (VIS) and near-infrared (NIR) spectral regions. A brief overview of SDSM design functions, on-orbit operations, and performance for both Terra and Aqua MODIS is provided. In addition to the SD on-orbit degradation at different wavelengths, the changes in SDSM detector responses and their potential impact on tracking SD on-orbit degradation are examined. After more than 12 years of on-orbit operation, Aqua MODIS SD has shown degradation varying from 0.6% at 0.94 microns to 19.0% at 0.41 microns. Due to more frequent solar exposure and longer operation time, the Terra MODIS SD has experienced a much larger degradation, varying from 2.3% at 0.94 microns to 48.0% at 0.41 microns. For both Terra and Aqua MODIS, the SD has experienced more degradation at shorter wavelengths. Meanwhile, the SDSM detector responses have also experienced wavelength-dependent degradation. The largest change in the SDSM detector responses, however, occurred at longer NIR wavelengths. Since launch, the SDSM systems on both Terra and Aqua MODIS have continued their nominal operations, enabling critical parameters to be derived in support of the RSB on-orbit calibration. The calibration strategies developed for and lessons learned from MODIS SDSM operations, and a preliminary performance comparison with the S-NPP VIIRS SDSM are discussed.

MODIS↗

NASA NTRS2015

ISS Regenerative Life Support: Challenges and Success in the Quest for Long-Term Habitability in Space

The International Space Station's (ISS) Regenerative Environmental Control and Life Support System (ECLSS) was launched in 2008 to continuously recycle urine and crew sweat into drinking water and oxygen using brand new technologies. This functionality was highly important to the ability of the ISS to transition to the long-term goal of 6-crew operations as well as being critical tests for long-term space habitability. Through the initial activation and long-term operations of these systems, important lessons were learned about the importance of system redundancy and operational workarounds that allow Systems Engineers to maintain functionality with limited on-orbit spares. This presentation will share some of these lessons learned including how to balance water through the different systems, store and use water for use in system failures and creating procedures to operate the systems in ways that they were not initially designed to do.

Bazley, Jesse↗

NASA NTRS1978

An adaptive learning control system for aircraft

A learning control system and its utilization as a flight control system for F-8 Digital Fly-By-Wire (DFBW) research aircraft is studied. The system has the ability to adjust a gain schedule to account for changing plant characteristics and to improve its performance and the plant's performance in the course of its own operation. Three subsystems are detailed: (1) the information acquisition subsystem which identifies the plant's parameters at a given operating condition; (2) the learning algorithm subsystem which relates the identified parameters to predetermined analytical expressions describing the behavior of the parameters over a range of operating conditions; and (3) the memory and control process subsystem which consists of the collection of updated coefficients (memory) and the derived control laws. Simulation experiments indicate that the learning control system is effective in compensating for parameter variations caused by changes in flight conditions.

Mekel, R.↗