SEARCH · Search NASA

Results for “Deep Operator Network”

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 1,171 records · Page 65

All sources NASA NTRS DOE OSTI

DOE OSTI2024

D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators

Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems. However, challenges arise when dealing with input functions that exhibit heterogeneous properties, requiring multiple sensors to handle functions with minimal regularity. To address this issue, discretization-invariant neural operators have been used, allowing the sampling of diverse input functions with different sensor locations. However, existing frameworks still require an equal number of sensors for all functions. We propose a novel distributed approach to further relax the discretization requirements and solve the heterogeneous dataset challenges. Our method involves partitioning the input function space and processing individual input functions using independent and separate neural networks. A centralized neural network is used to handle shared information across all output functions. This distributed methodology reduces the number of gradient descent back-propagation steps, improving efficiency while maintaining accuracy. Here, we demonstrate that the corresponding neural network is a universal approximator of continuous nonlinear operators and present three numerical examples to validate its performance.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Wavelet and Deep-Learning-Based Approach for Generation System Problematic Parameters Identification and Calibration

Accurate models of generation systems are critical for maintaining reliable and secure grid operations. In this paper, a novel and systematic approach is proposed to identify and calibrate the generation system problematic parameters using continuous wavelet transform (CWT) and advanced deep-learning technology. The phasor measurement unit (PMU) data are used through “event playback” to check whether the parameter calibration is required, and if yes, a group of suspicious parameters will be identified as the primary problematic parameter candidates (PPCs). These primary PPCs are randomly perturbed to generate the event playback simulation data, which are used by the CWT and convolutional neural networks (CNNs) to further narrow down the primary PPCs into a smaller set of candidates. Then, the identified candidates are perturbed again to generate massive event playback simulation data for training a parameter calibration neural network. Here, we designed a multi-output neural network structure to find the mappings between the perturbed parameters and the simulation data using both CNN and long short-term memory (LSTM) models. Finally, the well-trained and tested CNN-LSTM model is used to estimate the accurate value of the suspicious parameters with actual PMU measurements. The proposed CNN-LSTM network can accurately and reliably estimate the generation-system problematic parameters, and has better performance when compared to other machine-learning methods, such as the multilayer perceptron network and the conditional variational autoencoder method. The accuracy and effectiveness of the proposed approach have been validated through simulation and real-world data.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS1987

Sorption compressor/mechanical expander hybrid refrigeration

Experience with Deep Space Network (DSN) ground-based cryogenic refrigerators has proved the reliability of the basic two-stage Gifford-McMahon helium refrigerator. A very long life cryogenic refrigeration system appears possible by combining this expansion system or a turbo expansion system with a hydride sorption compressor in place of the usual motor driven piston compressor. To test the feasibility of this system, a commercial Gifford-McMahon refrigerator was tested using hydrogen gas as the working fluid. Although no attempt was made to optimize the system for hydrogen operation, the refrigerator developed 1.3 W at 30 K and 6.6 W at 60 K. The results of the test and of theoretical performances of the hybrid compressor coupled to these expansion systems are presented.

Jones, J. A.↗

NASA NTRS2010

Delay/Disruption Tolerance Networking (DTN) Implementation and Utilization Options on the International Space Station

The International Space Station (ISS) is in an operational configuration and nearing final assembly. With its maturity and diverse payloads onboard, the opportunity exists to extend the orbital lab into a facility to exercise and demonstrate Delay/Disruption Tolerant Networking (DTN). DTN is an end-to-end network service providing communications through environments characterized by intermittent connectivity, variable delays, high bit error rates, asymmetric links and simplex links. The DTN protocols, also known as bundle protocols, provide a store-and-forward capability to accommodate end-to-end network services. Key capabilities of the bundling protocols include: the Ability to cope with intermittent connectivity, the Ability to take advantage of scheduled and opportunistic connectivity (in addition to always up connectivity), Custody Transfer, and end-to-end security. Colorado University at Boulder and the Huntsville Operational Support Center (HOSC) have been developing a DTN capability utilizing the Commercial Generic Bioprocessing Apparatus (CGBA) payload resources onboard the ISS, at the Boulder Payload Operations Center (POC) and at the HOSC. The DTN capability is in parallel with and is designed to augment current capabilities. The architecture consists of DTN endpoint nodes on the ISS and at the Boulder POC, and a DTN node at the HOSC. The DTN network is composed of two implementations; the Interplanetary Overlay Network (ION) and the open source DTN2 implementation. This paper presents the architecture, implementation, and lessons learned. By being able to handle the types of environments described above, the DTN technology will be instrumental in extending networks into deep space to support future missions to other planets and other solar system points of interest. Thus, this paper also discusses how this technology will be applicable to these types of deep space exploration missions.

Holbrook, Mark↗

DOE OSTI2022

DNN-based policies for stochastic AC OPF

We report a prominent challenge to the safe and optimal operation of the modern power grid arises due to growing uncertainties in loads and renewables. Stochastic optimal power flow (SOPF) formulations provide a mechanism to handle these uncertainties by computing dispatch decisions and control policies that maintain feasibility under uncertainty. Most SOPF formulations consider simple control policies such as affine policies that are mathematically simple and resemble many policies used in current practice. Motivated by the efficacy of machine learning (ML) algorithms and the potential benefits of general control policies for cost and constraint enforcement, we put forth a deep neural network (DNN)-based policy that predicts the generator dispatch decisions in real time in response to uncertainty. The weights of the DNN are learnt using stochastic primal–dual updates that solve the SOPF without the need for prior generation of training labels and can explicitly account for the feasibility constraints in the SOPF. The advantages of the DNN policy over simpler policies and their efficacy in enforcing safety limits and producing near optimal solutions are demonstrated in the context of a chance constrained formulation on a number of test cases.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2018

Automated Labeling of Electron Microscopy Images Using Deep Learning

© 2018 IEEE. Searching for scientific data requires metadata providing a relevant context. Today, generating metadata is a time and labor intensive manual process that is often neglected, and important datasets are not accessible through search. We investigate the use of machine learning to generalize metadata from a subset of labeled data, thus increasing the availability of meaningful metadata for search. Specifically, we consider electron microscopy images collected at the National Center for Electron Microscopy (NCEM) at the Lawrence Berkeley National Laboratory (LBNL) and use deep learning to discern characteristics from a small subset of labeled images and transfer labels to the entire image corpus. Relatively small training set sizes and a minimum resolution of 512\times 512 pixels required by the application domain pose unique challenges. We overcome these challenges by using a simple yet powerful convolutional network architecture that limits the number of free parameters to lower the required amount of computational power and reduce the risk of overfitting. We achieve a classification accuracy of approximately 80% in discerning between images recorded in two operating modes of the electron microscope-transmission electron microscopy (TEM) and scanning transmission electron microscopy (STEM). We use transfer learning-i.e., re-using the pre-trained convolution layers from the TEM vs. STEM classification problem-to generalize labels and achieve an accuracy of approximately 70 % despite current experiments being limited to small training data sets. We present these predictions as suggestions to domain scientists through a web-based tool to accelerate the labeling process with the goal of further validating our approach and improving the accuracy of automatically created labels.

Weber, Gunther H↗

DOE OSTI2024

TwinMe4AD: WGAN-based Digital Twins for Anomaly Detection

SAND2024-08373O TwinMe4AD is a Python-based software tool designed for anomaly detection using digital twins that closely mimic real, wearable healthcare datasets. The tool is invaluable for scenarios where collecting data is either expensive or impractical, serving as a privacy-preserving solution. Sensitive information is protected by training deep learning models on synthetic data derived from real datasets. One of TwinMe4AD's key features is its anomaly detection capability, which is based on fourth-order moments of parameters. This versatile approach can be applied across a range of datasets, from univariate to multivariate, making it compatible with various types of data. It also generates synthetic twins using Wasserstein Generative Adversarial Networks (WGANs), allowing users to create a small cohort of a population similar to that of a village population. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Poorey, Kunal↗

DOE OSTI2025

Towards automated and real-time multi-object detection of anguilliform fishes from sonar data using YOLOv8 deep learning algorithm

Eels (Anguilla spp.), including American eels (Anguilla rostrata), European eels (Anguilla anguilla), and Japanese eels (Anguilla japonica), are species of critical management and regulatory concern due to their vulnerability to various stressors during downstream migrations. Accurate and efficient detection of migrating eels can improve our understanding of fish behaviors and fish-hydraulic structure interactions, thereby facilitating the design, operation, and optimization of more effective downstream passage facilities from both biological and economic perspectives. However, a real-time, automated framework for detecting migrating eels in real-world applications is currently lacking. Leveraging imaging sonar as a reliable technology for fish passage monitoring, field data are acquired using imaging sonar and then converted to single sonar frames/images for subsequent analysis. In this study, a framework based on the You Only Look Once Version 8 (YOLOv8)-based convolutional neural network is proposed for multi-object detection of eels and non-eel fish using the sonar images after image subtraction and additional wavelet denoising. The results from both training and testing phases demonstrate that the framework's ability can successfully detect both eels and non-eel fish in preprocessed sonar images, achieving F1-scores and mAP@0.50 exceeding 0.84. Additionally, the incorporation of wavelet denoising during preprocessing slightly improve detection performance. Furthermore, the transferability of this framework from eel to lamprey detection is demonstrated to be feasible given the similar morphological characteristics of these two species. Overall, the proposed framework achieves accurate and efficient detection of migrating eels, providing reliable and real-time information that can help conserve vulnerable eel and eel-like populations.

Deep learning↗

NASA NTRS2019

Small target detection for search and rescue operations using distributed deep learning and synthetic data generation

It is important to find the target as soon as possible for search and rescue operations. Surveillance camera systems and unmanned aerial vehicles (UAVs) are used to support search and rescue. Automatic object detection is important because a person cannot monitor multiple surveillance screens simultaneously for 24 hours. Also, the object is often too small to be recognized by the human eye on the surveillance screen. This study used UAVs around the Port of Houston and fixed surveillance cameras to build an automatic target detection system that supports the US Coast Guard (USCG) to help find targets (e.g., person overboard). We combined image segmentation, enhancement, and convolution neural networks to reduce detection time to detect small targets. We compared the performance between the auto-detection system and the human eye. Our system detected the target within 8 seconds, but the human eye detected the target within 25 seconds. Our systems also used synthetic data generation and data augmentation techniques to improve target detection accuracy. This solution may help the search and rescue operations of the first responders in a timely manner.

Chow, Edward↗

DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗

DOE OSTI2024

Deep Multitask Learning Models for Radiation Estimation at High Energy Accelerator Facility

Controlling the dose of radiation exposure in potential radioactive facilities is critical for ensuring the safety of staff and the public. Here, in this paper, we developed machine learning models to estimate radiation exposure efficiently at the Thomas Jefferson National Accelerator Facility (JLab), aiming to enhance safety in both accelerator facilities and public areas. Multiple sensors were deployed around the three experimental halls at JLab. Data on single-beam currents, energy levels, and radiation values at the sensor locations were collected during accelerator operation. We proposed a multi-task learning model for radiation estimation, utilizing either one-dimensional convolutional neural networks (1-D CNNs) or long short-term memory networks (LSTMs) as the backbone. The proposed model was trained to simultaneously estimate radiation levels at the sensor locations. Experimental results demonstrated that the proposed model with LSTM backbone achieved the best estimation performance, with an average R 2 score of 0.7557 for estimation within the same year and 0.7157 for estimation across different years. These results significantly surpassed those of competing models.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Machine learning for nonintrusive model order reduction of the parametric inviscid transonic flow past an airfoil

Fluid flow in the transonic regime finds relevance in aerospace engineering, particularly in the design of commercial air transportation vehicles. Computational fluid dynamics models of transonic flow for aerospace applications are computationally expensive to solve because of the high degrees of freedom as well as the coupled nature of the conservation laws. While these issues pose a bottleneck for the use of such models in aerospace design, computational costs can be significantly minimized by constructing special, structure-preserving surrogate models called reduced-order models. In this work, we propose a machine learning method to construct reduced-order models via deep neural networks and we demonstrate its ability to preserve accuracy with a significantly lower computational cost. In addition, our machine learning methodology is physics-informed and constrained through the utilization of an interpretable encoding by way of proper orthogonal decomposition. Application to the inviscid transonic flow past the RAE2822 airfoil under varying freestream Mach numbers and angles of attack, as well as airfoil shape parameters with a deforming mesh, shows that the proposed approach adapts to high-dimensional parameter variation well. Notably, the proposed framework precludes the knowledge of numerical operators utilized in the data generation phase, thereby demonstrating its potential utility in the fast exploration of design space for diverse engineering applications. Comparison against a projection-based nonintrusive model order reduction method demonstrates that the proposed approach produces comparable accuracy and yet is orders of magnitude computationally cheap to evaluate, despite being agnostic to the physics of the problem.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1991

Mark 4A antenna control system data handling architecture study

A high-level review was conducted to provide an analysis of the existing architecture used to handle data and implement control algorithms for NASA's Deep Space Network (DSN) antennas and to make system-level recommendations for improving this architecture so that the DSN antennas can support the ever-tightening requirements of the next decade and beyond. It was found that the existing system is seriously overloaded, with processor utilization approaching 100 percent. A number of factors contribute to this overloading, including dated hardware, inefficient software, and a message-passing strategy that depends on serial connections between machines. At the same time, the system has shortcomings and idiosyncrasies that require extensive human intervention. A custom operating system kernel and an obscure programming language exacerbate the problems and should be modernized. A new architecture is presented that addresses these and other issues. Key features of the new architecture include a simplified message passing hierarchy that utilizes a high-speed local area network, redesign of particular processing function algorithms, consolidation of functions, and implementation of the architecture in modern hardware and software using mainstream computer languages and operating systems. The system would also allow incremental hardware improvements as better and faster hardware for such systems becomes available, and costs could potentially be low enough that redundancy would be provided economically. Such a system could support DSN requirements for the foreseeable future, though thorough consideration must be given to hard computational requirements, porting existing software functionality to the new system, and issues of fault tolerance and recovery.

Briggs, H. C.↗

NASA NTRS2015

Multi-Spacecraft Autonomous Positioning System

As the number of spacecraft in simultaneous operation continues to grow, there is an increased dependency on ground-based navigation support. The current baseline system for deep space navigation utilizes Earth-based radiometric tracking, requiring long-duration observations to perform orbit determination and generate a state update. The age, complexity, and high utilization of the ground assets pose a risk to spacecraft navigation performance. In order to perform complex operations at large distances from Earth, such as extraterrestrial landing and proximity operations, autonomous systems are required. With increasingly complex mission operations, the need for frequent and Earth-independent navigation capabilities is further reinforced. The Multi-spacecraft Autonomous Positioning System (MAPS) takes advantage of the growing interspacecraft communication network and infrastructure to allow for Earth-autonomous state measurements to enable network-based space navigation. A notional concept of operations is given in figure 1. This network is already being implemented and routinely used in Martian communications through the use of the Mars Reconnaissance Orbiter and Mars Odyssey spacecraft as relays for surface assets. The growth of this communications architecture is continued through MAVEN, and future potential commercial Mars telecom orbiters. This growing network provides an initial Marslocal capability for inter-spacecraft communication and navigation. These navigation updates are enabled by cross-communication between assets in the network, coupled with onboard navigation estimation routines to integrate packet travel time to generate ranging measurements. Inter-spacecraft communication allows for frequent state broadcasts and time updates from trusted references. The architecture is a software-based solution, enabling its implementation on a wide variety of current assets, with the operational constraints and measurement accuracy determined by onboard systems.

Anzalone, Evan↗

NASA NTRS2019

NASA Platform for Autonomous Systems (NPAS)

NASA Platform for Autonomous Systems (NPAS) is a disruptive software platform and processes being developed by SSC Autonomous Systems Laboratory (ASL). Autonomous operations are critical for the success, safety and crew survival of NASA deep space missions beyond low Earth orbit, including Lunar Orbital Platform-Gateway, and for the future of cost-effective ground mission operations. NPAS represents the embodiment of an innovative implementation for "thinking" autonomy in contrast to brute-force autonomy. It also uniquely addresses the requirements and integrates five primary functionalities for autonomous operations including: (1) Integrated System Health Management (ISHM), (2) autonomy, guided by health and system concepts of operations; (3) knowledge models of applications; (4) infrastructure to create, schedule, and execute mission plans; and (5) infrastructure to integrate distributed autonomous applications across networks.

Figueroa, Fernando↗

NASA NTRSDate not supplied

Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning

The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.

Ruixuan Han↗

NASA NTRSDate not supplied

Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning

Ruixuan Han↗

NASA NTRS2012

Entry, Descent, and Landing Communications for the 2011 Mars Science Laboratory

The Mars Science Laboratory (MSL), established as the most advanced rover to land on the surface of Mars to date, launched on November 26th, 2011 and arrived to the Martian Gale Crater during the night of August 5th, 2012 (PDT). MSL will investigate whether the landing region was ever suitable to support carbon-based life, and examine rocks, soil, and the atmosphere with a sophisticated suite of tools. This paper addresses the flight system requirement by which the vehicle transmitted indications of the following events using both X-band tones and UHF telemetry to allow identification of probable root causes should a mission anomaly have occurred: Heat-Rejection System (HRS) venting, completion of the cruise stage separation, turn to entry attitude, atmospheric deceleration, bank angle reversal commanded, parachute deployment, heatshield separation, radar ground acquisition, powered descent initiation, rover separation from the descent stage, and rover release. During Entry, Descent, and Landing (EDL), the flight system transmitted a UHF telemetry stream adequate to determine the state of the spacecraft (including the presence of faults) at 8 kbps initiating from cruise stage separation through at least one minute after positive indication of rover release on the surface of Mars. The flight system also transmitted X-band semaphore tones from Entry to Landing plus one minute although since MSL was occulted, as predicted, by Mars as seen from the Earth, Direct-To-Earth (DTE) communications were interrupted at approximately is approx. 5 min after Entry ( approximately 130 prior to Landing). The primary data return paths were through the Deep Space Network (DSN) for DTE and the existing Mars network of orbiting assets for UHF, which included the Mars Reconnaissance Orbiter (MRO), Mars Odyssey (ODY), and Mars Express (MEX) elements. These orbiters recorded the telemetry data stream and returned it back to Earth via the DSN. The paper also discusses the total power received during EDL and the robustness of the telecom design strategy used to ensure EDL communications coverage.

relay operations↗