Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “real-time simulation”

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 1,279 records · Page 71
All sourcesNASA NTRSDOE OSTI
NASA NTRS2003

A Physical Validation Program for the GPM Mission

The GPM mission is currently planned for start in the late 2007 - early 2008 time frame. Its main scientific goal is to help answer pressing scientific problems arising within the context of global and regional water cycling. These problems cut across a hierarchy of scales and include climate-water cycle interactions, techniques for improving weather and climate predictions, and better methods for combining observed precipitation with hydrometeorological prediction models for applications to hazardous flood-producing storms, seasonal flood draught conditions, and fresh water resource assessments. The GPM mission will expand the scope of precipitation measurement through the use of a constellation of some 9 satellites, one of which will be an advanced TRMM-like core satellite carrying a dual-frequency Ku-Ka band precipitation radar and an advanced, multifrequency passive microwave radiometer with vertical-horizontal polarization discrimination. The other constellation members will include new dedicated satellites and co-existing operational/research satellites carrying similar (but not identical) passive microwave radiometers. The goal of the constellation is to achieve approximately 3-hour sampling at any spot on the globe -- continuously. The constellation's orbit architecture will consist of a mix of sun-synchronous and non-sun-synchronous satellites with the core satellite providing measurements of cloud-precipitation microphysical processes plus calibration-quality rainrate retrievals to be used with the other retrieval information to ensure bias-free constellation coverage. A major requirement before the retrieved rainfall information generated by the GPM mission can be used effectively by prognostic models to improve weather forecasts, hydrometeorological forecasts, and climate model reanalysis simulations is a capability to quantify the error characteristics of the retrievals. A solution for this problem has been upheld in past precipitation missions because of the lack of suitable error modeling systems incorporated into the validation programs and data distribution systems. An overview of how NASA intends to overcome this problem for the GPM mission using a physically-based error modeling approach within a multi-faceted validation program is described. The solution is to first identify specific user requirements and then determine the most stringent of these requirements that embodies all essential error characterization information needed by the entire user community. In the context of NASA s scientific agenda for the GPM mission, the most stringent user requirement is found within the data assimilation community. The fundamental theory of data assimilation vis-a-vis ingesting satellite precipitation information into the pre-forecast initializations is based on quantifying the conditional bias and precision errors of individual rain retrievals, and the space-time structure of the precision error (i.e., the spatial-temporal error covariance). By generating the hardware and software capability to produce this information in a near real-time fashion, and to couple the derived quantitative error properties to the actual retrieved rainrates, all key validation users can be satisfied. The talk will describe the essential components of the hardware and software systems needed to generate such near real-time error properties, as well as the various paradigm shifts needed within the validation community to produce a validation program relevant to the precipitation user community.

Smith, Eric A.↗
NASA NTRS2003

Development of an Efficient Binaural Simulation for the Analysis of Structural Acoustic Data

Applying binaural simulation techniques to structural acoustic data can be very computationally intensive as the number of discrete noise sources can be very large. Typically, Head Related Transfer Functions (HRTFs) are used to individually filter the signals from each of the sources in the acoustic field. Therefore, creating a binaural simulation implies the use of potentially hundreds of real time filters. This paper details two methods of reducing the number of real-time computations required by: (i) using the singular value decomposition (SVD) to reduce the complexity of the HRTFs by breaking them into dominant singular values and vectors and (ii) by using equivalent source reduction (ESR) to reduce the number of sources to be analyzed in real-time by replacing sources on the scale of a structural wavelength with sources on the scale of an acoustic wavelength. The ESR and SVD reduction methods can be combined to provide an estimated computation time reduction of 99.4% for the structural acoustic data tested. In addition, preliminary tests have shown that there is a 97% correlation between the results of the combined reduction methods and the results found with the current binaural simulation techniques

Johnson, Marty E.↗
NASA NTRS2004

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

The NASA F-15 Intelligent Flight Control System project team has developed a series of flight control concepts designed to demonstrate the benefits of a neural network-based adaptive controller. The objective of the team is to develop and flight-test control systems that use neural network technology to optimize the performance of the aircraft under nominal conditions as well as stabilize the aircraft under failure conditions. Failure conditions include locked or failed control surfaces as well as unforeseen damage that might occur to the aircraft in flight. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to the baseline aerodynamic derivatives in flight. This set of open-loop flight tests was performed in preparation for a future phase of flights in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed a pitch frequency sweep and an automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. An examination of flight data shows that addition of the flight-identified aerodynamic derivative increments into the simulation improved the pitch handling qualities of the aircraft.

Williams, Peggy S.↗
NASA NTRS2001

Measurement of persistence in 1D diffusion

Using a novel NMR scheme we observed persistence in 1D gas diffusion. Analytical approximations and numerical simulations have indicated that for an initially random array of spins undergoing diffusion, the probability p(t) that the average spin magnetization in a given region has not changed sign (i.e., "persists") up to time t follows a power law t(-straight theta), where straight theta depends on the dimensionality of the system. Using laser-polarized 129Xe gas, we prepared an initial "quasirandom" 1D array of spin magnetization and then monitored the ensemble's evolution due to diffusion using real-time NMR imaging. Our measurements are consistent with analytical and numerical predictions of straight theta approximately 0.12.

NASA Discipline Life Sciences Technologies↗
NASA NTRS1993

An Application of a New Electromagnetic Sensor to Real-Time Monitoring of Fatigue Crack Growth in Thin Metal Plates

A major part of fracture mechanics is concerned with studying the initiation and propagation of fatigue cracks. This typically requires constant monitoring of crack growth during fatigue cycles which necessitates automation of the whole process. If the rate of crack growth can be determined the experimenter can vary externally controlled parameters such as load level, load cycle frequency and so on. Hence, knowledge of the precise location of the crack tip at any given time is very valuable. One technique currently available for measuring fatigue crack length is the DC potential drop method. The method, however, may be inaccurate if the direction of crack growth deviates considerably from what was assumed initially or the curvature of the crack becomes significant. Another approach is to digitize an optical image of the test specimen surface and then apply a pattern recognition technique to locate the crack tip, but this method is still under development. The present work is an initial study on applying eddy current-type probes to monitoring fatigue crack growth. The performance of two types of electromagnetic probes, a conventional eddy current probe and a newly developed self-nulling probe, was evaluated for the detection characteristics at and near the tips of fatigue cracks. The scan results show that the latter probe provides a very well defined local maximum in its output in the crack tip region suggesting the definite possibility of precisely locating the tip, while the former provides a somewhat ambiguous distribution of the sensor output in the same region. The paper is organized as follows: We start by reviewing the design and performance characteristics of the self-nulling probe and then describe the scan results which demonstrate the basic properties of the self-nulling probe. Next, we provide a brief description of the software developed for tracing a simulated crack and give a brief discussion of the main results of the test. The final section summarizes the major accomplishments of the present work and the elements of the future R&D needs.

Namkung, M.↗
NASA NTRS2005

Middleware Evaluation and Benchmarking for Use in Mission Operations Centers

Middleware technologies have been promoted as timesaving, cost-cutting alternatives to the point-to-point communication used in traditional mission operations systems. However, missions have been slow to adopt the new technology. The lack of existing middleware-based missions has given rise to uncertainty about middleware's ability to perform in an operational setting. Most mission architects are also unfamiliar with the technology and do not know the benefits and detriments to architectural choices - or even what choices are available. We will present the findings of a study that evaluated several middleware options specifically for use in a mission operations system. We will address some common misconceptions regarding the applicability of middleware-based architectures, and we will identify the design decisions and tradeoffs that must be made when choosing a middleware solution. The Middleware Comparison and Benchmark Study was conducted at NASA Goddard Space Flight Center to comprehensively evaluate candidate middleware products, compare and contrast the performance of middleware solutions with the traditional point- to-point socket approach, and assess data delivery and reliability strategies. The study focused on requirements of the Global Precipitation Measurement (GPM) mission, validating the potential use of middleware in the GPM mission ground system. The study was jointly funded by GPM and the Goddard Mission Services Evolution Center (GMSEC), a virtual organization for providing mission enabling solutions and promoting the use of appropriate new technologies for mission support. The study was broken into two phases. To perform the generic middleware benchmarking and performance analysis, a network was created with data producers and consumers passing data between themselves. The benchmark monitored the delay, throughput, and reliability of the data as the characteristics were changed. Measurements were taken under a variety of topologies, data demands, and data characteristics, using several middleware products. All results were compared to systems using traditional point-to-point socket communication. By comparing performance results under Merent settings, inferences could be made about each middleware's ability to meet certain requirements of the GPM mission. The second phase simulated a middleware-based mission operations center. Actual mission support tools were either used or simulated to create real world demands on the middleware. Network and computer demands were watched closely to verify that no specific idiosyncrasies of mission operations activities would prove unsupportable by the middleware. In our presentation, we will address some commonly accepted misconceptions concerning middleware in mission support architectures. Specifically, we will focus on the perception that middleware solutions are too slow or impose too much overhead for real-time mission operations, and that middleware solutions are too expensive for small

Antonucci, Rob↗
NASA NTRS1998

Time-Resolved Optical Measurements of Fuel-Air Mixedness in Windowless High Speed Research Combustors

Fuel distribution measurements in gas turbine combustors are needed from both pollution and fuel-efficiency standpoints. In addition to providing valuable data for performance testing and engine development, measurements of fuel distributions uniquely complement predictive numerical simulations. Although equally important as spatial distribution, the temporal distribution of the fuel is an often overlooked aspect of combustor design and development. This is due partly to the difficulties in applying time-resolved diagnostic techniques to the high-pressure, high-temperature environments inside gas turbine engines. Time-resolved measurements of the fuel-to-air ratio (F/A) can give researchers critical insights into combustor dynamics and acoustics. Beginning in early 1998, a windowless technique that uses fiber-optic, line-of-sight, infrared laser light absorption to measure the time-resolved fluctuations of the F/A (refs. 1 and 2) will be used within the premixer section of a lean-premixed, prevaporized (LPP) combustor in NASA Lewis Research Center's CE-5 facility. The fiber-optic F/A sensor will permit optical access while eliminating the need for film-cooled windows, which perturb the flow. More importantly, the real-time data from the fiber-optic F/A sensor will provide unique information for the active feedback control of combustor dynamics. This will be a prototype for an airborne sensor control system.

Nguyen, Quang-Viet↗
NASA NTRS2005

Lightning Mapping and the Nowcasting of Severe Storms

This paper describes a successful research and operational collaboration between NASA scientists and NWS forecasters to improve severe stor m warnings using real-time data from a regional VHF total lightning mapping array (LMA). Key objectives of our research using LMA data ar e: a) Identification of intensifying and weakening storms using the time rate-of-change of total flash rate; b) Improved severe storm poten tial situational awareness; c) Evaluation of the potential of total f lash rate trend to improve severe storm probability of detection (POD ) and lead time; and d) Validation of mesoscale model forecasts of th understorm initiation. The LMA data are distributed for ingest and di splay in the WFO AWIPS decision support system, and archived at each WFO for case studies, event playbacks, and assessments using the NWS Warning Event Simulator. The Huntsville WFO has upgraded severe thund erstorm warnings to verified tornado warnings and avoided a false ala rm on a severe storm through the added information on storm growth, intensification, and decay that can be deduced from the magnitude and temporal trend of total flash rates. We present detailed case studies of the observed relationships between lightning activity and tornadi c storm development as determined by radar reflectivity and velocity fields, and thunderstorms forecast by the Weather Research and Foreca st (WRF) model. From these collaborative studies, forecasters can eva luate the added value of total lightning data within the forecast and warning decision-making process (http://weather.msfc.nasa.gov/sport) .

Goodman, S.↗
NASA NTRS2004

Icing Research Tunnel

The Icing Research Tunnel in Building 11 at the NASA Glenn Research Center is committed to researching the effects of in flight icing on aircraft and testing ways to stop the formation of hazardous icing conditions on planes. During this summer, I worked here with Richard DelRosa, the lead engineer for this area. address one of the major concerns of aviation: icing conditions. During the war, many planes crashed (especially supply planes going over the.Himalayas) because ice built up in their wings and clogged the engines. To this day, it remains the largest ice tunnel in the world, with a test section that measures 6 feet high, 9 feet long, and 20 feet wide. It can simulate airspeeds from 50 to 300 miles per hour at temperatures as low as -50 Fahrenheit. Using these capabilities, IRT can simulate actual conditions at high altitudes. The first thing I did was creating a cross reference in Microsoft Excel. It lists commands for the DPU units that control the pressure and temperature variations in the tunnel, as well as the type of command (keyboard, multiplier, divide, etc). The cross reference also contains the algorithm for every command, and which page it is listed in on the control sheet (visual Auto-CAD graphs, which I helped to make). I actually spent most of the time on the computer using Auto-CAD. I drew a diagram of the entire icing tunnel and then drew diagrams of its various parts. Between my mentor and me, we have drawings of every part of it, from the spray bars to the thermocouples, power cabinets, input-output connectors for power systems, and layouts of various other machines. I was also responsible for drawing schematics for the Escort system (which controls the spray bars), the power system, DPUs, and other electrical systems. In my spare time, I am attempting to build and program the "toddler". Toddler is a walking robot that I have to program in PBASIC language. When complete, it should be able to walk on level terrain while avoiding obstacles in real-time. It features an infrared detector that can keep it from falling over edges, as well as follow or avoid a light source. The toddler is giving me a much better understanding of the basics of electronic circuitry and computer programming.

Chennault, Jonathan↗
NASA NTRS2004

Strategy Developed for Selecting Optimal Sensors for Monitoring Engine Health

Sensor indications during rocket engine operation are the primary means of assessing engine performance and health. Effective selection and location of sensors in the operating engine environment enables accurate real-time condition monitoring and rapid engine controller response to mitigate critical fault conditions. These capabilities are crucial to ensure crew safety and mission success. Effective sensor selection also facilitates postflight condition assessment, which contributes to efficient engine maintenance and reduced operating costs. Under the Next Generation Launch Technology program, the NASA Glenn Research Center, in partnership with Rocketdyne Propulsion and Power, has developed a model-based procedure for systematically selecting an optimal sensor suite for assessing rocket engine system health. This optimization process is termed the systematic sensor selection strategy. Engine health management (EHM) systems generally employ multiple diagnostic procedures including data validation, anomaly detection, fault-isolation, and information fusion. The effectiveness of each diagnostic component is affected by the quality, availability, and compatibility of sensor data. Therefore systematic sensor selection is an enabling technology for EHM. Information in three categories is required by the systematic sensor selection strategy. The first category consists of targeted engine fault information; including the description and estimated risk-reduction factor for each identified fault. Risk-reduction factors are used to define and rank the potential merit of timely fault diagnoses. The second category is composed of candidate sensor information; including type, location, and estimated variance in normal operation. The final category includes the definition of fault scenarios characteristic of each targeted engine fault. These scenarios are defined in terms of engine model hardware parameters. Values of these parameters define engine simulations that generate expected sensor values for targeted fault scenarios. Taken together, this information provides an efficient condensation of the engineering experience and engine flow physics needed for sensor selection. The systematic sensor selection strategy is composed of three primary algorithms. The core of the selection process is a genetic algorithm that iteratively improves a defined quality measure of selected sensor suites. A merit algorithm is employed to compute the quality measure for each test sensor suite presented by the selection process. The quality measure is based on the fidelity of fault detection and the level of fault source discrimination provided by the test sensor suite. An inverse engine model, whose function is to derive hardware performance parameters from sensor data, is an integral part of the merit algorithm. The final component is a statistical evaluation algorithm that characterizes the impact of interference effects, such as control-induced sensor variation and sensor noise, on the probability of fault detection and isolation for optimal and near-optimal sensor suites.

Source record↗
NASA NTRS2004

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

The NASA F-15 Intelligent Flight Control System project team developed a series of flight control concepts designed to demonstrate neural network-based adaptive controller benefits, with the objective to develop and flight-test control systems using neural network technology to optimize aircraft performance under nominal conditions and stabilize the aircraft under failure conditions. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to baseline aerodynamic derivatives in flight. This open-loop flight test set was performed in preparation for a future phase in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed - pitch frequency sweep and automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. Flight data examination shows that addition of flight-identified aerodynamic derivative increments into the simulation improved aircraft pitch handling qualities.

Williams-Hayes, Peggy S.↗
NASA NTRS2005

Damage Accumulation and Failure of Plasma-Sprayed Thermal Barrier Coatings under Thermal Gradient Cyclic Conditions

Thermal barrier coatings will be more aggressively designed to protect gas turbine engine hot-section components in order to meet future engine higher fuel efficiency and lower emission goals. A fundamental understanding of the sintering and thermal cycling induced delamination of thermal barrier coating systems under engine-like heat flux conditions will potentially help to improve the coating temperature capability. In this study, a test approach is established to emphasize the real-time monitoring and assessment of the coating thermal conductivity, which can initially increase under the steady-state high temperature thermal gradient test due to coating sintering, and later decrease under the thermal gradient cyclic test due to coating cracking and delamination. Thermal conductivity prediction models have been established for a ZrO2-(7- 8wt%)Y2O3 model coating system in terms of heat flux, time, and testing temperatures. The coating delamination accumulation is then assessed based on the observed thermal conductivity response under the combined steady-state and cyclic thermal gradient tests. The coating thermal gradient cycling associated delaminations and failure mechanisms under simulated engine heat-flux conditions will be discussed in conjunction with the coating sintering and fracture testing results.

Zhu, Dongming↗
NASA NTRS2004

Low-Cost, User-Friendly, Rapid Analysis of Dynamic Data System Established

An issue of primary importance to the development of new jet and certain other airbreathing combined-cycle powered aircraft is the advancement of airframe-integrated propulsion technologies. Namely, engine inlets and their systems and subsystems are required to capture, convert, and deliver the atmospheric airflow demanded by such engines across their operating envelope in a form that can be used to provide efficient, stable thrust. This must be done while also minimizing aircraft drag and weight. Revolutionary inlet designs aided by new technologies are needed to enable new missions. An unwanted byproduct of pursuing these inlet technologies is increased time-variant airflow distortion. Such distortions reduce propulsion system stability, performance, operability, and life. To countermand these limitations and fully evaluate the resulting configurations, best practices dictate that this distortion be experimentally measured at large scale and analyzed. The required measurements consist of those made by an array of high-response pressure transducers located in the flow field at the aerodynamic interface plane (AIP) between the inlet and engine. Although the acquisition of the necessary pitot-pressure time histories is relatively straight-forward, until recent years, the analysis has proved to be very time-consuming, tedious, and expensive. To transform the analysis of these data into a tractable and timely proposition, researchers at the NASA Glenn Research Center created and established the Rapid Analysis of Dynamic Data (RADD) system. The system provides complete, near real-time analysis of time-varying inlet airflow distortion datasets with report quality output. This fully digital approach employs Institute of Electrical and Electronics Engineers (IEEE) binary data file format standardization to establish data-acquisition-system-independent processing on low cost personal computers. Features include invalid instrumentation code-out, logging, and multiple replacement schemes as needed for each channel of instrumentation. The AIP pressure distribution can be interpolated to simulate measurements by alternate AIP probe arrays, if desired. In addition, the RADD system provides for the application of filters that can be used to focus the analysis on the frequency range of interest.

Arend, David J.↗
NASA NTRS2004

Framework for Development of Object-Oriented Software

The Real-Time Control (RTC) Application Framework is a high-level software framework written in C++ that supports the rapid design and implementation of object-oriented application programs. This framework provides built-in functionality that solves common software development problems within distributed client-server, multi-threaded, and embedded programming environments. When using the RTC Framework to develop software for a specific domain, designers and implementers can focus entirely on the details of the domain-specific software rather than on creating custom solutions, utilities, and frameworks for the complexities of the programming environment. The RTC Framework was originally developed as part of a Space Shuttle Launch Processing System (LPS) replacement project called Checkout and Launch Control System (CLCS). As a result of the framework s development, CLCS software development time was reduced by 66 percent. The framework is generic enough for developing applications outside of the launch-processing system domain. Other applicable high-level domains include command and control systems and simulation/ training systems.

Perez-Poveda, Gus↗
DOE OSTI2025

Automating Sensor Characterization with Bayesian Optimization

The development of novel instrumentation requires an iterative cycle with three stages: design, prototyping, and testing. Recent advancements in simulation and nanofabrication techniques have significantly accelerated the design and prototyping phases. Nonetheless, detector characterization continues to be a major bottleneck in device development. During the testing phase, a significant time investment is required to characterize the device in different operating conditions and find optimal operating parameters. The total effort spent on characterization and parameter optimization can occupy a year or more of an expert's time. In this work, we present a novel technique for automated sensor calibration that aims to accelerate the testing stage of the development cycle. This technique leverages closed-loop Bayesian optimization (BO), using real-time measurements to guide parameter selection and identify optimal operating states. We demonstrate the method with a novel low-noise CCD, showing that the machine learning-driven tool can efficiently characterize and optimize operation of the sensor in a couple of days without supervision of a device expert.

Cuevas-Zepeda, Julian [Chicago U., KICP; Chicago U↗
DOE OSTI2025

Enhancing Security and Resiliency in Operational Technology Environments Through Network Slicing and Federated Learning

The growing convergence of Information Technology (IT) and Operational Technology (OT) within Industry 4.0 environments has introduced new demands on industrial network infrastructure. As cyber-physical systems become increasingly interconnected, ensuring the secure, timely, and efficient exchange of critical data is essential. This thesis explores how network slicing, a method of creating isolated virtual network segments, can be applied within OT environments to address challenges such as latency, security, and resource allocation. The first research question addressed in this thesis is: How can OT networks take advantage of NFV and SDN technology to become cyber resilient? This study examines the operational, security, and architectural implications of introducing network slicing into traditionally static OT infrastructures such as Industrial Control Systems (ICS) and SCADA. Through simulated deployments and case studies, the research demonstrates how slicing enables better isolation between critical and non-critical services, thereby improving response time, throughput, and security in sensitive environments. The second question considers: How to dynamically implement network slicing and take advantage of network resources towards integrating decentralized machine learning? In response, this thesis proposes a framework that combines Software-Defined Networking (SDN), Network Function Virtualization (NFV), and Federated Learning (FL) to enable real-time analytics while maintaining data locality. The proposed approach reduces the burden on centralized infrastructure and minimizes privacy risks by supporting on-site training of models across distributed OT nodes, coordinated through dynamically allocated network slices. The third focus explores: How slicing helps to increase the resiliency of OT networks through the orchestration of a dynamic DMZ? To answer this, the thesis presents a method for creating and managing Dynamic Demilitarized Zones (DMZs) using network slicing. This enables flexible and automated isolation of sensitive subsystems during threat scenarios or high-risk operations. Coupled with intelligent orchestration and containerized security services, the dynamic DMZ significantly enhances the system's ability to respond to cyber incidents without halting production. Ultimately, this thesis contributes a comprehensive architecture that blends network slicing with machine learning, secure segmentation, and automation, paving the way for resilient, adaptive, and intelligent OT environments. Performance evaluations across multiple scenarios show improvements in system reliability, threat response time, model accuracy, and resource utilization, providing a strong foundation for future industrial automation systems.

Rodiles Delgado, Brian G↗
DOE OSTI2026

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48% ($H_T$) and 28% (AD), with a cumulative gain of up to 2% in signal efficiency on those in-tolerance intervals. Transferring from simulation to \emph{real} collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56% ($H_T$) and 28% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the \emph{first} demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).

Ding, Zixin [Chicago U.]↗
DOE OSTI2026

Exploration of Real Time Inference for MI-RR Deblending on GPU/TPU Systems

The Fermilab Main Injector (MI) and Recycler Ring (RR) share a common beam loss monitor (BLM) system, making loss events difficult to attribute to their source machine when beam is present in both simultaneously. The Real-time Edge AI for Distributed Systems (READS) project addresses this by deblending BLM readings in real time using machine learning (ML). The current FPGA based implementation meets the sub-3 ms latency requirement but carries a resource intensive hls4ml development cycle, motivating exploration of GPU based deployment. This paper characterizes inference latency on an NVIDIA Jetson Orin Nano and introduces a packet organization scheme for assembling synchronized event frames from seven distributed BLM DAQ streams. Using a Python based DAQ simulation with injected timing jitter in place of unavailable live beam data, the pipeline achieved an average end to end latency of 0.456 ms (σ = 0.122 ms) across 167,000 test frames, comfortably meeting the timing constraint. Early outliers were attributed to TensorRT warm-up rather than steady state limitations, suggesting GPU based inference is a viable alternative to the existing FPGA implementation.

Yu, Kellen [Fermilab; Cornell U.]↗