Machine learning for orders of magnitude speedup in multiobjective optimization of particle accelerator systems
Not Available
43 PARTICLE ACCELERATORS↗
SEARCH · Search NASA
Results for “Learning systems”
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.
Compton Gamma Ray Observatory: Lessons Learned in Propulsion
The Compton Gamma Ray Observatory was the second of NASA's Great Observatories. At 17 1/2 tons. it was the heaviest astrophysical payload ever flown at the time of its launch on April 5, 1991 aboard the Space Shuttle. During initial, on-orbit priming of the spacecraft's monopropellant hydrazine propulsion system, a severe waterhammer transient was experienced. At that time, anomalous telemetry readings were received from on-board propulsion system instrumentation. This led to ground analyses and laboratory investigations as to the root cause of the waterhammer, potential damage to system integrity and functionality, and risks for switching from the primary (A-side) propulsion system to the redundant (B-side) system. The switchover to B-side was ultimately performed successfully and the spacecraft completed its basic and extended missions in this configuration. Nine years later, following a critical control gyroscope failure, Compton was safely deorbited and re-entered the Earth's atmosphere on June 4, 2000. Additional risk assessments concerning viability of A- and B-sides were necessary to provide confidence in attitude and delta-V authority and reliability to manage the precisely controlled reentry. This paper summarizes the design and operation of the propulsion system used on the spacecraft and provides "lessons learned" from the system engineering investigations into the propellant loading procedures, the initial priming anomaly, mission operations, and the commanded re-entry following the gyro failure.
Dressler, G. A.↗
Automatic Determination of the Need for Intravenous Contrast in Musculoskeletal MRI Examinations Using IBM Watson’s Natural Language Processing Algorithm
Magnetic resonance imaging (MRI) protocoling can be time- and resource-intensive, and protocols can often be suboptimal dependent upon the expertise or preferences of the protocoling radiologist. Providing a best-practice recommendation for an MRI protocol has the potential to improve efficiency and decrease the likelihood of a suboptimal or erroneous study. The goal of this study was to develop and validate a machine learning-based natural language classifier that can automatically assign the use of intravenous contrast for musculoskeletal MRI protocols based upon the free-text clinical indication of the study, thereby improving efficiency of the protocoling radiologist and potentially decreasing errors. We utilized a deep learning-based natural language classification system from IBM Watson, a question-answering supercomputer that gained fame after challenging the best human players on Jeopardy! in 2011. We compared this solution to a series of traditional machine learning-based natural language processing techniques that utilize a term-document frequency matrix. Each classifier was trained with 1240 MRI protocols plus their respective clinical indications and validated with a test set of 280. Ground truth of contrast assignment was obtained from the clinical record. For evaluation of inter-reader agreement, a blinded second reader radiologist analyzed all cases and determined contrast assignment based on only the free-text clinical indication. In the test set, Watson demonstrated overall accuracy of 83.2% when compared to the original protocol. This was similar to the overall accuracy of 80.2% achieved by an ensemble of eight traditional machine learning algorithms based on a term-document matrix. When compared to the second reader’s contrast assignment, Watson achieved 88.6% agreement. When evaluating only the subset of cases where the original protocol and second reader were concordant (n = 251), agreement climbed further to 90.0%. The classifier was relatively robust to spelling and grammatical errors, which were frequent. Implementation of this automated MR contrast determination system as a clinical decision support tool may save considerable time and effort of the radiologist while potentially decreasing error rates, and require no change in order entry or workflow.
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Physics informed machine learning for chemistry tabulation
Modeling of turbulent combustion system requires modeling the underlying chemistry and the turbulent transport. Solving both systems simultaneously is computationally prohibitive. Instead, given the difference in scales at which the two sub-systems evolve, the two sub-systems are typically (re)solved separately. Popular approaches such as the Flamelet Generated Manifolds (FGM) use a two-step strategy where the governing reaction kinetics are pre-computed and mapped to a low-dimensional manifold, characterized by a few reaction progress variables (model reduction) and the manifold is then “looked-up” during the run-time to estimate the high-dimensional system state by the turbulent transport system. While existing works have focused on these two steps independently, in this work we show that joint learning of the progress variables and the look-up model, can yield more accurate results. Here, we build on the base formulation and implementation to include the dynamically generated Thermochemical State Variables (Lower Dimensional Dynamic Source Terms). We discuss the challenges in the implementation of this deep neural network architecture and experimentally demonstrate its superior performance.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Machine Learning Analysis of Temperature-Strain Relationships for Structural Health Monitoring of Pipes: Self-powered wireless sensor system for health monitoring of liquid-sodium cooled fast reactors
This report presents machine learning (ML) analysis of temperature-strain relationships for structural health monitoring of nuclear reactor stainless steel (SS) pipes with the strain gauge sensor directly printed on the pipe with a 3D conformal aerosol jet printer. We investigate correlations for two sensor pairs installed on the same SS304 pipe: commercial K-type thermocouple with a printed gold strain gauge (TC3-SG3), and commercial K-type thermocouple with commercial Kyowa strain gauge (TC0-SG0). The temperature ranges for the sensor pairs TC0-SG0 and TC3-SG3 are 20.00°C to 266.37°C and 39.95°C to 219.28°C respectively. ML algorithms in this study include Linear Regression (baseline method), Ridge Regression, Lasso Regression, and Gradient Boosting. Performance evaluation metrics include Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE), R 2 Score, and Explained Variance. Using advanced feature engineering techniques, we extracted 27 temperature-based features and 30 strategic inclusion features. The best performance was obtained with the Gradient Boosting method, which achieves prediction accuracy of R 2 = 0.9999 and RMSE = 7.69 μStrain for TC0-SG0, and R 2 = 0.9998 and RMSE = 18.03 μStrain for TC3-SG3. While the temperature-strain correlations are weaker for the gauge directly printed on the pipe than for the commercial strain gauge, deployment-ready performance exceeding industry standards is achieved for both sensor pairs.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning
Effective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately creating integration and validation tools for such automation is difficult as the interactions between automation and their human counterparts is complex and unpredictable. This validation becomes even more difficult as we integrate wide-reaching technologies that affect the behavior of different decision makers in the system such as pilots, controllers and airlines. While overt short-term behavior changes can be explicitly modeled with traditional agent modeling systems, subtle behavior changes caused by the integration of new technologies may snowball into larger problems and be very hard to detect. To overcome these obstacles, we show how integration of new technologies can be validated by learning behavior models based on goals. In this framework, human participants are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. The main advantage to this approach is that modeling is done within the context of the entire system allowing for accurate modeling of all participants as they interact as a whole. In addition such an approach allows for efficient trade studies and feasibility testing on a wide range of automation scenarios. The goal of this paper is to test that such an approach is feasible. To do this we implement this approach using a simple discrete-state learning system on a scenario where 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast (ADS-B) information. In this scenario, we show how the approach can be used to predict the ability of pilots to adequately balance aircraft separation and fly efficient paths. We present results with several levels of complexity and airspace congestion.
Game Theory↗
Safe Tracking Control of an Uncertain Euler-Lagrange System with Full-State Constraints using Barrier Functions
This paper presents a novel, safe tracking control design method that learns the parameters of an uncertain Euler-Lagrange (EL) system online using adaptive learning laws. A barrier function (BF) is first used to transform the full-state constrained EL-dynamics into an equivalent unconstrained dynamics. An adaptive tracking controller is then developed along with the parameter update law in the transformed state space such that the states remain bounded for all time within a prescribed bound. A stability analysis is developed that considers the EL-dynamics’ uncertainty, yielding a semi-globally uniformly ultimately bounded (SGUUB) tracking error and the parameter estimation error. The controller design is validated in simulations using a two-link planar manipulator. The results show the proposed method’s ability to track the reference trajectory while remaining inside each of the predefined state bounds.
Robots↗
Space Shuttle Orbiter Structures and Mechanisms
The Space Shuttle Orbiter has performed exceptionally well over its 30 years of flight experience. Among the many factors behind this success were robust, yet carefully monitored, structural and mechanical systems. From highlighting key aspects of the design to illustrating lessons learned from the operation of this complex system, this paper will attempt to educate the reader on why some subsystems operated flawlessly and why specific vulnerabilities were exposed in others. Specific areas to be covered will be the following: high level configuration overview, primary and secondary structure, mechanical systems ranging from landing gear to the docking system, and windows.
Gilmore, Adam L.↗
Ansatz-Free Hamiltonian Learning with Heisenberg-Limited Scaling
Learning the unknown interactions that govern a quantum system is crucial for quantum information processing, device benchmarking, and quantum sensing. The problem, known as Hamiltonian learning, is well understood under the assumption that interactions are local, but this assumption may not hold for arbitrary Hamiltonians. Previous methods all require high-order inverse polynomial dependency with precision, unable to surpass the standard quantum limit and reach the gold-standard Heisenberg-limited scaling. Whether Heisenberg-limited Hamiltonian learning is possible without prior assumptions about the interaction structures, a challenge we term ansatz-free Hamiltonian learning , remains an open question. In this work, we present a quantum algorithm to learn arbitrary sparse Hamiltonians without any structure constraints using only black-box queries of the system’s real-time evolution and minimal digital controls to attain Heisenberg-limited scaling in estimation error. Our method is also resilient to state-preparation-and-measurement errors, enhancing its practical feasibility. We numerically demonstrate our ansatz-free protocol for learning physical Hamiltonians and validating analog quantum simulations, benchmarking our performance against the state-of-the-art Heisenberg-limited learning approach. Moreover, we establish a fundamental trade-off between total evolution time and quantum control on learning arbitrary interactions, revealing the intrinsic interplay between controllability and total evolution-time complexity for any learning algorithm. These results pave the way for further exploration into Heisenberg-limited Hamiltonian learning in complex quantum systems under minimal assumptions, potentially enabling new benchmarking and verification protocols.
machine learning↗
Exploring the Feasibility of INCONEL® ALLOY 740H® for Power Plant Headers: Integrating Machine Learning with Computational Fluid Dynamics (CFD)
This keynote presentation explores the behavior of headers—essential components of pipeline systems—using ANSYS simulation software and machine learning techniques. The study aims to predict the thermal and mechanical performance of headers under diverse conditions through both steady-state and transient simulations. We investigate critical parameters such as heat transfer coefficient, fluid velocity, and temperature to optimize header design. Conducted as part of a DOE project led by NCAT in collaboration with UNC Charlotte, this research encompasses multiple key topics. The initial section focuses on the behavior of header systems under steady-state conditions using ANSYS simulation. It underscores the importance of headers in industrial infrastructure, especially in the energy sector, and examines the implications of material selection and flow direction on heat transfer dynamics. Methodologically, we employ Computational Fluid Dynamics (CFD) analysis through ANSYS, detailing the development of models, material properties, geometry specifications, boundary conditions, and meshing strategies. Our simulations explore various operational parameters, including temperature and mass flow rates, crucial for predicting heat transfer coefficients and enhancing header design. Results from the study include parametric investigations into mesh sensitivity, viscosity model evaluations, and the effects of heat transfer locations, all validated against theoretical calculations. We conclude with insights on mesh optimization, the suitability of viscosity models, and recommendations for future research aimed at improving header system efficiency and sustainability in industrial applications.
20 FOSSIL-FUELED POWER PLANTS↗
Watch and learn—a generalized approach for transferrable learning in deep neural networks via physical principles
Transfer learning refers to the use of knowledge gained while solving a machine learning task and applying it to the solution of a closely related problem. Such an approach has enabled scientific breakthroughs in computer vision and natural language processing where the weights learned in state-of-the-art models can be used to initialize models for other tasks which dramatically improve their performance and save computational time. Here we demonstrate an unsupervised learning approach augmented with basic physical principles that achieves fully transferrable learning for problems in statistical physics across different physical regimes. By coupling a sequence model based on a recurrent neural network to an extensive deep neural network, we are able to learn the equilibrium probability distributions and inter-particle interaction models of classical statistical mechanical systems. Our approach, distribution-consistent learning, DCL, is a general strategy that works for a variety of canonical statistical mechanical models (Ising and Potts) as well as disordered interaction potentials. Using data collected from a single set of observation conditions, DCL successfully extrapolates across all temperatures, thermodynamic phases, and can be applied to different length-scales. This constitutes a fully transferrable physics-based learning in a generalizable approach.
97 MATHEMATICS AND COMPUTING↗
Acceleration display system for aircraft zero-gravity research
The features, design, calibration, and testing of Lewis Research Center's acceleration display system for aircraft zero-gravity research are described. Specific circuit schematics and system specifications are included as well as representative data traces from flown trajectories. Other observations learned from developing and using this system are mentioned where appropriate. The system, now a permanent part of the Lewis Learjet zero-gravity program, provides legible, concise, and necessary guidance information enabling pilots to routinely fly accurate zero-gravity trajectories. Regular use of this system resulted in improvements of the Learjet zero-gravity flight techniques, including a technique to minimize later accelerations. Lewis Gates Learjet trajectory data show that accelerations can be reliably sustained within 0.01 g for 5 consecutive seconds, within 0.02 g for 7 consecutive seconds, and within 0.04 g for up to 20 second. Lewis followed the past practices of acceleration measurement, yet focussed on the acceleration displays. Refinements based on flight experience included evolving the ranges, resolutions, and frequency responses to fit the pilot and the Learjet responses.
Millis, Marc G.↗
Program Helps In Analysis Of Failures
Failure Environment Analysis Tool (FEAT) computer program developed to enable people to see and better understand effects of failures in system. User selects failures from either engineering schematic diagrams or digraph-model graphics, and effects or potential causes of failures highlighted in color on same schematic-diagram or digraph representation. Uses digraph models to answer two questions: What will happen to system if set of failure events occurs? and What are possible causes of set of selected failures? Helps design reviewers understand exactly what redundancies built into system and where there is need to protect weak parts of system or remove them by redesign. Program also useful in operations, where it helps identify causes of failure after they occur. FEAT reduces costs of evaluation of designs, training, and learning how failures propagate through system. Written using Macintosh Programmers Workshop C v3.1. Can be linked with CLIPS 5.0 (MSC-21927, available from COSMIC).
Stevenson, R. W.↗
Scheduling Spitzer: The SIRPASS Story
NASA's Spitzer Space Telescope was launched on August 25, 2003 from Florida's Cape Canaveral Air Force Base. Drifting in a unique Earth-trailing orbit around the Sun, Spitzer sees an optically invisible universe dominated by dust and stars. Since 1997, the Spitzer Integrated Resource Planning and Scheduling System (SIRPASS) has helped produce spacecraft activity plans for the Spitzer Space Telescope. SIRPASS is used by members of the Observatory Planning and Scheduling Team to plan, schedule and sequence the Telescope from data made available to them from the science and engineering community. Because of the volume of data that needs to be scheduled, SIRPASS offers a variety of automated assistants to aid in this task. This paper will describe the functional elements of the SIRPASS software system -- emphasizing the role that automation plays in the system -- and will highlight lessons learned for the software developer from a decade of Spitzer Space Telescope operations experience.
flight systems↗
POINT: Partially Observable Imitation Network for Traffic Signal Control
Smart traffic signals bring together transportation infrastructure and advance technologies to improve the mobility and efficiency of urban transportation network. Adaptive traffic signal control studies can be categorized into modeling-based approaches and learning-based approaches. In order to take advantages of these two systems, this study developed an offline-online combined Partial Observable Imitation Network for Traffic signal control (POINT). In the offline system, the traffic signal timing optimization problem was formulated as a Mixed Integer Nonlinear Programming (MINLP) given complete traffic information, i.e., second-by-second speeds and locations of all vehicles. Furthermore, the objective of MINLP is to minimize total travel delays considering individual vehicle trajectories under Connected Vehicle (CV) environment. The calculated optimal solutions under various traffic conditions were considered as the ”expert” decisions. In the online system, an imitation neural network model was developed to learn the ”expert” signal plans generated from offline system. Given partial observable traffic conditions in real time, e.g., the aggregate-level of traffic volume, the POINT model can compute the signal timing parameters in the online system. The numerical results demonstrated that the proposed method outperformed other state-of-the-art signal control method under high and unbalanced traffic demand levels in terms of reducing travel delays and queue length.
33 ADVANCED PROPULSION SYSTEMS↗
SOFIA Program SE and I Lessons Learned
Once a "Troubled Project" threatened with cancellation, the Stratospheric Observatory for Infrared Astronomy (SOFIA) Program has overcome many difficult challenges and recently achieved its first light images. To achieve success, SOFIA had to overcome significant deficiencies in fundamental Systems Engineering identified during a major Program restructuring. This presentation will summarize the lessons learn in Systems Engineering on the SOFIA Program. After the Program was reformulated, an initial assessment of Systems Engineering established the scope of the problem and helped to set a list of priorities that needed to be work. A revised Systems Engineering Management Plan (SEMP) was written to address the new Program structure and requirements established in the approved NPR7123.1A. An important result of the "Technical Planning" effort was the decision by the Program and Technical Leadership team to re-phasing the lifecycle into increments. The reformed SOFIA Program Office had to quickly develop and establish several new System Engineering core processes including; Requirements Management, Risk Management, Configuration Management and Data Management. Implementing these processes had to consider the physical and cultural diversity of the SOFIA Program team which includes two Projects spanning two NASA Centers, a major German partnership, and sub-contractors located across the United States and Europe. The SOFIA Program experience represents a creative approach to doing "System Engineering in the middle" while a Program is well established. Many challenges were identified and overcome. The SOFIA example demonstrates it is never too late to benefit from fixing deficiencies in the System Engineering processes.
Ray, Ronald J.↗
167-PFlops Deep Learning for Electron Microscopy: From Learning Physics to Atomic Manipulation
An artificial intelligence system called MENNDL, which used 25,200 Nvidia Volta GPUs on Oak Ridge National Laboratory’s Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity toward nanofabricating materials automatically. Finally, MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.
97 MATHEMATICS AND COMPUTING↗
167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation
An artificial intelligence system called MENNDL, which used 25,200 NVIDIA Volta GPUs on Oak Ridge National Laboratory's Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity towards nanofabricating materials automatically. MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.
Patton, Robert↗