Search NASA⌕ Search

SEARCH · Search NASA

Results for “Sensor Network Design”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Smart Pixels: In-pixel AI for on-sensor data filtering

We present a smart pixel prototype readout integrated circuit (ROIC) designed in CMOS 28 nm bulk process, with in-pixel implementation of an artificial intelligence (AI) / machine learning (ML) based data filtering algorithm designed as proof-of-principle for a Phase III upgrade at the Large Hadron Collider (LHC) pixel detector. The first version of the ROIC consists of two matrices of 256 smart pixels, each 25$\times$25 $\mu$m$^2$ in size. Each pixel consists of a charge-sensitive preamplifier with leakage current compensation and three auto-zero comparators for a 2-bit flash-type ADC. The frontend is capable of synchronously digitizing the sensor charge within 25 ns. Measurement results show an equivalent noise charge (ENC) of $\sim$30e$^-$ and a total dispersion of $\sim$100e$^-$ The second version of the ROIC uses a fully connected two-layer neural network (NN) to process information from a cluster of 256 pixels to determine if the pattern corresponds to highly desirable high-momentum particle tracks for selection and readout. The digital NN is embedded in-between analog signal processing regions of the 256 pixels without increasing the pixel size and is implemented as fully combinatorial digital logic to minimize power consumption and eliminate clock distribution, and is active only in the presence of an input signal. The total power consumption of the neural network is $\sim$ 300 $\mu$W. The NN performs momentum classification based on the generated cluster patterns and even with a modest momentum threshold, it is capable of 54.4% - 75.4% total data rejection, opening the possibility of using the pixel information at 40MHz for the trigger. The total power consumption of analog and digital functions per pixel is $\sim$ 6 $\mu$W per pixel, which corresponds to $\sim$ 1 W/cm$^2$ staying within the experimental constraints.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Illuminating the Night: A Survey of Super-Resolution Methods for Nighttime Light Images

Nighttime Light (NTL) images provide critical insights into urbanization, disaster response, and energy consumption. The VIIRS Day/Night Band (DNB) sensor offers high-quality NTL imagery with daily revisit rates, but the available spatial resolution hinders fine-grained accurate analysis. Super-resolution techniques aim to increase the resolution of NTL images, enabling more detailed assessments of infrastructure, light pollution, economic activity, and power outages. However, existing state-of-the-art super-resolution methods designed for natural images struggle with the unique characteristics of NTL data. This work provides a comprehensive review of super-resolution methods across multiple image modalities, evaluates their effectiveness on VIIRS DNB data, and proposes a multi-modal super-resolution approach tailored to NTL imagery. The proposed approach integrates VIIRS DNB data with road networks and land use information to improve reconstruction accuracy and spatial detail. Code is available for this project at https://code.ornl.gov/viirs-sr/sr-demos.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2022

TruePAL – An AI Assistant for First Responder Safety

This paper presents the development of an AI assistant, Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL), to provide real-time warning of risks of potential crashes to the first responders. The TruePAL system employs an AI and deep learning technology for saving first responders and roadside crews lives in and around active traffic. A deep neural network (DNN) and a Non-Axiomatic Reasoning System (NARS) are implemented as an AI system. A mobile app with AI interface is developed to perform verbal communication with the first responders. The TruePAL team has developed an explainable AI approach by opening up the DNN blackbox to extract the activation filters of various features and parts of the targeted objects. The combination of DNN and NARS makes the TruePAL system explainable to the users. TruePAL ingests on-board cameras, radar, and other sensor signals, analyzes the environment and traffic patterns to generate timely warning to drivers and roadside crews to avoid crashes. The TruePAL team, in collaboration with the Miami/Dade Police Dept., has designed five use cases and multiple sub-scenarios in a CARLA driving simulator to test the capability of TruePAL in timely warning to the first responder drivers in potential crash scenarios. We have successfully demonstrated its capability of timely warning in over a dozen scenarios based on the use cases. The preliminary test simulation results show that TruePAL could provide the drivers and crew members advanced warning before a crash occurs.

Chow, Edward↗
DOE OSTI2017

Design and implementation of wearable devices in machine tools monitoring system - 279

The world's fourth industrial revolution has finally opened after the term Industry 4.0 was proposed by Germany at the Hannover Industrial Fair in 2011, which combined industrial production with an unmanned plant to perform automated production. With the rise of Internet of Things (IoT), cloud computing, and wearing computerized devices has brought more convenience to mankind with the immediate accessibility of the Internet and technology. For example, the development of mobile devices and network technology has inspired the rapid development of wearable devices on mobile devices. Thus, to enhance the current prospects of Taiwan's unmanned machinery factory's monitoring and maintenance capabilities, this paper studies the use of Google glass Machine Tools Monitoring system, GMTM system, to be implemented in Taiwan's machinery factories. GMTM system, via the Internet, monitors sensor tools to collect tool work data to be transferred to cloud computing for analysis, processing and show the actual working conditions of each machine tool. Furthermore, the proposed system uses the monitoring data in the database to inform the factory supervisors the working status of each machine to determine whether there is a need for machine tool maintenance. This system combines real-time monitoring of material with the presentation of Google Glass wearable devices and iBeacon interior space positioning technology. GMTM system can improve the quality of machine tool production and productivity as well as enhance Taiwan's industrial competitiveness. (authors)

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Smart Pixels: In-pixel AI for on-sensor data filtering

We present a smart pixel prototype readout integrated circuit (ROIC) designed in CMOS 28 nm bulk process, with in-pixel implementation of an artificial intelligence (AI) / machine learning (ML) based data filtering algorithm designed as proof-of-principle for a Phase III upgrade at the Large Hadron Collider (LHC) pixel detector. The first version of the ROIC consists of two matrices of 256 smart pixels, each 25$\times$25 µm\textsuperscript{2} in size. Each pixel consists of a charge-sensitive preamplifier with leakage current compensation and three auto-zero comparators for a 2-bit flash-type ADC. The frontend is capable of synchronously digitizing the sensor charge within 25 ns. Measurement results show an equivalent noise charge (ENC) of $\sim$30e\textsuperscript{-} and a total dispersion of $\sim$100e\textsuperscript{-} The second version of the ROIC uses a fully connected two-layer neural network (NN) to process information from a cluster of 256 pixels to determine if the pattern corresponds to highly desirable high-momentum particle tracks for selection and readout. The digital NN is embedded in-between analog signal processing regions of the 256 pixels without increasing the pixel size and is implemented as fully combinatorial digital logic to minimize power consumption and eliminate clock distribution, and is active only in the presence of an input signal. The total power consumption of the neural network is $\sim$ 300 $\mu$W. The NN performs momentum classification based on the generated cluster patterns and even with a modest momentum threshold, it is capable of 54.4\% – 75.4\% total data rejection, opening the possibility of using the pixel information at 40MHz for the trigger. The total power consumption of analog and digital functions per pixel is $\sim$ 6 $\mu$W per pixel, which corresponds to $\sim$ 1 W/cm\textsuperscript{2} staying within the experimental constraints.

Parpillon, Benjamin↗
NASA NTRS2013

Bulk Moisture and Salinity Sensor

Measurement and feedback control of nutrient solutions in plant root zones is critical to the development of healthy plants in both terrestrial and reduced-gravity environments. In addition to the water content, the amount of fertilizer in the nutrient solution is important to plant health. This typically requires a separate set of sensors to accomplish. A combination bulk moisture and salinity sensor has been designed, built, and tested with different nutrient solutions in several substrates. The substrates include glass beads, a clay-like substrate, and a nutrient-enriched substrate with the presence of plant roots. By measuring two key parameters, the sensor is able to monitor both the volumetric water content and salinity of the nutrient solution in bulk media. Many commercially available moisture sensors are point sensors, making localized measurements over a small volume at the point of insertion. Consequently, they are more prone to suffer from interferences with air bubbles, contact area of media, and root growth. This makes it difficult to get an accurate representation of true moisture content and distribution in the bulk media. Additionally, a network of point sensors is required, increasing the cabling, data acquisition, and calibration requirements. measure the dielectric properties of a material in the annular space of the vessel. Because the pore water in the media often has high salinity, a method to measure the media moisture content and salinity simultaneously was devised. Characterization of the frequency response for capacitance and conductance across the electrodes was completed for 2-mm glass bead media, 1- to 2-mm Turface (a clay like media), and 1- to 2-mm fertilized Turface with the presence of root mass. These measurements were then used to find empirical relationships among capacitance (C), the dissipation factor (D), the volumetric water content, and the pore water salinity.

Nurge, Mark↗
NASA NTRS2011

Circuit for Communication Over Power Lines

Many distributed systems share common sensors and instruments along with a common power line supplying current to the system. A communication technique and circuit has been developed that allows for the simple inclusion of an instrument, sensor, or actuator node within any system containing a common power bus. Wherever power is available, a node can be added, which can then draw power for itself, its associated sensors, and actuators from the power bus all while communicating with other nodes on the power bus. The technique modulates a DC power bus through capacitive coupling using on-off keying (OOK), and receives and demodulates the signal from the DC power bus through the same capacitive coupling. The circuit acts as serial modem for the physical power line communication. The circuit and technique can be made of commercially available components or included in an application specific integrated circuit (ASIC) design, which allows for the circuit to be included in current designs with additional circuitry or embedded into new designs. This device and technique moves computational, sensing, and actuation abilities closer to the source, and allows for the networking of multiple similar nodes to each other and to a central processor. This technique also allows for reconfigurable systems by adding or removing nodes at any time. It can do so using nothing more than the in situ power wiring of the system.

Krasowski, Michael J.↗
DOE OSTI2024

"Traffic Control via Connected and Automated Vehicles: An Open-Road Field Experiment with 100 CAVs"

The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. These "phantom jams" or "stop-and-go waves,"are a significant source of wasted energy. Toward this goal, the CIRCLES project designed a control system referred to as the MegaController by the CIRCLES team, that could be deployed in real traffic. Our field experiment leveraged a heterogeneous fleet of 100 longitudinally-controlled vehicles as Lagrangian traffic actuators, each of which ran a controller with the architecture described in this paper. The MegaController is a hierarchical control architecture, which consists of two main layers. The upper layer is called Speed Planner, and is a centralized optimal control algorithm. It assigns speed targets to the vehicles, conveyed through the LTE cellular network. The lower layer is a control layer, running on each vehicle. It performs local actuation by overriding the stock adaptive cruise controller, using the stock on-board sensors. The Speed Planner ingests live data feeds provided by third parties, as well as data from our own control vehicles, and uses both to perform the speed assignment. The architecture of the speed planner allows for modular use of standard control techniques, such as optimal control, model predictive control, kernel methods and others, including Deep RL, model predictive control and explicit controllers. Depending on the vehicle architecture, all onboard sensing data can be accessed by the local controllers, or only some. Control inputs vary across different automakers, with inputs ranging from torque or acceleration requests for some cars, and electronic selection of ACC set points in others. The proposed architecture allows for the combination of all possible settings proposed above. Most configurations were tested throughout the ramp up to the MegaVandertest.

Lee, Jonathan↗
DOE OSTI2025

Traffic Control via Connected and Automated Vehicles (CAVs): An Open-Road Field Experiment with 100 CAVs

The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. Also called “phantom jams” or “stop-and-go waves,” these instabilities are a significant source of wasted energy. Toward this goal, the CIRCLES project designed a control system, referred to as the MegaController by the CIRCLES team, that could be deployed in real traffic. Our field experiment, the MegaVanderTest (MVT), leveraged a heterogeneous fleet of 100 longitudinally controlled vehicles as Lagrangian traffic actuators, each of which ran a controller with the architecture described in this article. The MegaController is a hierarchical control architecture that consists of two main layers. The upper layer is called the Speed Planner and is a centralized optimal control algorithm. It assigns speed targets to the vehicles, conveyed through the LTE cellular network. The lower layer is a control layer, running on each vehicle. It performs local actuation by overriding the stock adaptive cruise controller, using the stock onboard sensors. The Speed Planner ingests live data feeds provided by third parties as well as data from our own control vehicles and uses both to perform the speed assignment. The architecture of the Speed Planner allows for the modular use of standard control techniques, such as optimal control, model predictive control (MPC), kernel methods, and others. The architecture of the local controller allows for the flexible implementation of local controllers. Corresponding techniques include deep reinforcement learning (RL), MPC, and explicit controllers. Depending on the vehicle architecture, all onboard sensing data can be accessed by the local controllers or only some. Likewise, control inputs vary across different automakers, with inputs ranging from torque or acceleration requests for some cars to electronic selection of adaptive cruise control (ACC) setpoints in others. The proposed architecture technically allows for the combination of all possible settings proposed previously, that is {Speed Planner algorithms} × {local Vehicle Controller algorithms} × {full or partial sensing} × {torque or speed control}. As a result, most configurations were tested throughout the ramp up to the MegaVandertest (MVT).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
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]↗
NASA NTRS2008

Ground-based Network and Supersite Measurements for Studying Aerosol Properties and Aerosol-Cloud Interactions

From radiometric principles, it is expected that the retrieved properties of extensive aerosols and clouds from reflected/emitted measurements by satellite (and/or aircraft) should be consistent with those retrieved from transmitted/emitted radiance observed at the surface. Although space-borne remote sensing observations contain large spatial domain, they are often plagued by contamination of surface signatures. Thus, ground-based in-situ and remote-sensing measurements, where signals come directly from atmospheric constituents, the sun, and the Earth-atmosphere interactions, provide additional information content for comparisons that confirm quantitatively the usefulness of the integrated surface, aircraft, and satellite datasets. The development and deployment of AERONET (AErosol RObotic NETwork) sunphotometer network and SMART-COMMIT (Surface-sensing Measurements for Atmospheric Radiative Transfer - Chemical, Optical & Microphysical Measurements of In-situ Troposphere) mobile supersite are aimed for the optimal utilization of collocated ground-based observations as constraints to yield higher fidelity satellite retrievals and to determine any sampling bias due to target conditions. To characterize the regional natural and anthropogenic aerosols, AERONET is an internationally federated network of unique sunphotometry that contains more than 250 permanent sites worldwide. Since 1993, there are more than 480 million aerosol optical depth observations and about 15 sites have continuous records longer than 10 years for annual/seasonal trend analyses. To quantify the energetics of the surface-atmosphere system and the atmospheric processes, SMART-COMMIT instrument into three categories: flux radiometer, radiance sensor and in-situ probe. Through participation in many satellite remote-sensing/retrieval and validation projects over eight years, SMART-COMMIT have gradually refine( and been proven vital for field deployment. In this paper, we will demonstrate the capability of AERONET SMART-COMMIT in current Asian Monsoon Year-2008 campaigns that are designed and being executed to study the compelling variability in temporal scale of both anthropogenic and natural aerosols (e.g., airborne dust, smoke, mega-city pollutant). Feedback mechanisms between aerosol radiative effects and monsoon dynamics have been recently proposed, however there is a lack of consensus on whether aerosol forcing would be more likely to enhance or reduce the strength of the monsoon circulation. We envision robust approaches which well-collocated ground-based measurements and space-borne observations will greatly advance our understanding of absorbing aerosols (e.g., "Global Dimming" vs. "Elevated Heat-Pump" effects) on aerosol cloud water cycle interactions.

Tsay, Si-Chee↗
DOE OSTI2020

High-Bandwidth Low-Inductance Current Shunt for Wide-Bandgap Devices Dynamic Characterization

High bandwidth sensors are required to measure the wide-bandgap devices' transient behavior because of their fast switching speed. In addition to high bandwidth, the current sensor must introduce little extra parasitic inductance to the switching power loop. The analysis of conventional shunt resistors shows the key to high bandwidth is the coaxial structure and its parasitic inductance is proportional to its transient heat energy rating. Additionally, by combining the structure of coaxial shunt resistor and alumina substrate surface mount thin film resistors, a novel surface mount coaxial shunt resistor is introduced. Experimental measurement verifies its capability of achieving very high bandwidth while introducing very low parasitic inductance. The design can achieve up to 2.23-GHz measurement bandwidth while keeping its parasitic inductance as low as 0.12 nH. Application in gallium nitride heterojunction-field-effect-transistors double pulse test shows it can faithfully capture the transient current waveform while introducing little interference to the switching behavior.

42 ENGINEERING↗
NASA NTRS2005

NASA's Next Generation Sunphotometer for Ground-based Remote Sensing Applications

Atmospheric aerosol concentrations and their optical properties, in terms of which cause differential warming/cooling effects in the atmosphere and on the surface, constitute one of the largest sources of uncertainty in current assessments and predictions of global climatic change. This is especially true over the regions of bright-reflecting surface, such as desert and urban areas. Under the name of AERONET since the 90's, Cimel's sunphotometers have been deployed worldwide as the standard instrument for aerosol monitoring network, developed to support NASA, CNES, and NASDA's Earth satellite systems. PREDE's skyradiometers, as deployed in SKYNET, serve the similar role. One of the key ingredients for achieving accurate aerosol retrievals from satellite observations is comprehensive understanding of surface spectral BRF's (Bidirectional Reflectance Factors), defined as a ratio of radiance measurements reflected from a targeted surface and from a spectral-angular featureless referencing plate. Although the weather-resistant, automatic, sun/sky-scanning spectroradiometers enable Frequent measurements of atmospheric aerosol optical properties and precipitable water at remote sites, they are too slow for surface BRF measurements (20-25 seconds per 360 degree scan, in addition to filter wheel rotation time). We have designed a next generation sun photometer whose sensor head has no moving parts. A dedicated detector for each channel enables 12 simultaneous measurements ranging from the UV (380 nm) to shortwave-IR (2.13 micron) regions. The scan platform will be capable of traveling 360 degrees in about 6 seconds. This is sufficient to finish a BRDF scan every 30 degrees in azimuth and 15 degrees in elevation in less than 4 minutes. More details about this instrument will be presented, together with its applications to the aerosol and trace gas studies. The current plan for this instrument is to deploy during the EAST-AIRE (East Asian Study of Tropospheric Aerosols: an International Regional Experiment) and BASE-ASIA (Biomass-burning Aerosols in South East-Asia: Smoke Impact Assessment).

Shu, Peter K.↗
NASA NTRS1995

Attitude determination using an adaptive multiple model filtering Scheme

Attitude determination has been considered as a permanent topic of active research and perhaps remaining as a forever-lasting interest for spacecraft system designers. Its role is to provide a reference for controls such as pointing the directional antennas or solar panels, stabilizing the spacecraft or maneuvering the spacecraft to a new orbit. Least Square Estimation (LSE) technique was utilized to provide attitude determination for the Nimbus 6 and G. Despite its poor performance (estimation accuracy consideration), LSE was considered as an effective and practical approach to meet the urgent need and requirement back in the 70's. One reason for this poor performance associated with the LSE scheme is the lack of dynamic filtering or 'compensation'. In other words, the scheme is based totally on the measurements and no attempts were made to model the dynamic equations of motion of the spacecraft. We propose an adaptive filtering approach which employs a bank of Kalman filters to perform robust attitude estimation. The proposed approach, whose architecture is depicted, is essentially based on the latest proof on the interactive multiple model design framework to handle the unknown of the system noise characteristics or statistics. The concept fundamentally employs a bank of Kalman filter or submodel, instead of using fixed values for the system noise statistics for each submodel (per operating condition) as the traditional multiple model approach does, we use an on-line dynamic system noise identifier to 'identify' the system noise level (statistics) and update the filter noise statistics using 'live' information from the sensor model. The advanced noise identifier, whose architecture is also shown, is implemented using an advanced system identifier. To insure the robust performance for the proposed advanced system identifier, it is also further reinforced by a learning system which is implemented (in the outer loop) using neural networks to identify other unknown quantities such as spacecraft dynamics parameters, gyro biases, dynamic disturbances, or environment variations.

Lam, Quang↗
NASA NTRS1989

SSME fault monitoring and diagnosis expert system

An expert system, called LEADER, has been designed and implemented for automatic learning, detection, identification, verification, and correction of anomalous propulsion system operations in real time. LEADER employs a set of sensors to monitor engine component performance and to detect, identify, and validate abnormalities with respect to varying engine dynamics and behavior. Two diagnostic approaches are adopted in the architecture of LEADER. In the first approach fault diagnosis is performed through learning and identifying engine behavior patterns. LEADER, utilizing this approach, generates few hypotheses about the possible abnormalities. These hypotheses are then validated based on the SSME design and functional knowledge. The second approach directs the processing of engine sensory data and performs reasoning based on the SSME design, functional knowledge, and the deep-level knowledge, i.e., the first principles (physics and mechanics) of SSME subsystems and components. This paper describes LEADER's architecture which integrates a design based reasoning approach with neural network-based fault pattern matching techniques. The fault diagnosis results obtained through the analyses of SSME ground test data are presented and discussed.

Ali, Moonis↗
DOE OSTI2025

Surrogate-driven Variance-based Sensitivity Analysis of Thermal Storage Tanks in Integrated Energy Systems

Sensitivity analysis and uncertainty quantification are essential steps for enhancing the accuracy of computational models by identifying and mitigating uncertainties. This study focuses on these steps for the Thermal Energy Delivery System at Idaho National Laboratory, specifically targeting the thermocline tank. Using a Modelica/Dymola simulation model, the study perturbed various design parameters and boundary conditions, including shape factor, porosity, outlet temperature, inlet mass flow rate, and system pressure, to predict and quantify uncertainty in the tank’s ax- ial temperature. A dataset of over 1,000 simulations was generated, and surrogate models were developed using the pyMAISE (Michigan Artificial Intelligence Standard Environment) library, which is an Automatic Machine Learning library for nuclear engineering applications. The optimal model, a feedforward neural network with two hidden layers, achieved an R2 score above 0.99 and a mean absolute error below 1 Kelvin. Sensitivity analyses using Sobol indices and Fourier amplitude sensitivity testing methods on this surrogate model revealed that the inlet mass flow rate at initial timestamps and porosity significantly impacts predicted temperatures across all sensors and time steps.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC

Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network (NN) autoencoder model can be implemented in a radiation-tolerant application-specific integrated circuit (ASIC) to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the Compact Muon Solenoid (CMS) experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the NN weights, a unique data compression algorithm can be deployed for each sensor in different detector regions and changing detector or collider conditions. To meet area, performance, and power constraints, we perform quantization-aware training to create an optimized NN hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework and was processed through synthesis and physical layout flows based on a low-power (LP)-CMOS 65-nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates and reports a total area of 3.6 mm 2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. Furthermore, this is the first radiation-tolerant on-detector ASIC implementation of an NN that has been designed for particle physics applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1994

Mission planning and scheduling concept for the Advanced X-ray Astrophysics Facility (AXAF)

Projected for launch in the latter part of 1998, the Advanced X-ray Astrophysics Facility (AXAF), the third satellite in the Great Observatory series, promises to dramatically open the x-ray sky as the Hubble and Compton observatories have done in their respective realms. Unlike its companions, however, AXAF will be placed in a high altitude, highly elliptical orbit (10,000 x 100,000 km), and will therefore be subject to its own unique environment, spacecraft and science instrument constraints and communication network interactions. In support of this mission, ground operations personnel have embarked on the development of the AXAF Offline System (OFLS), a body of software divided into four basic functional elements: (1) Mission Planning and Scheduling, (2) Command Management, (3) Altitude Determination and Sensor Calibration and (4) Spacecraft Support and Engineering Analysis. This paper presents an overview concept for one of these major elements, the Mission Planning and Scheduling subsystem (MPS). The derivation of this concept is described in terms of requirements driven by spacecraft and science instrument characteristics, orbital environment and ground system capabilities. The flowdown of these requirements through the systems analysis process and the definition of MPS interfaces has resulted in the modular grouping of functional subelements depicted in the design implementation approach. The rationale for this design solution is explained and capabilities for the initial prototype system are proposed from the user perspective.

Newhouse, M.↗