Differentiable predictive control: Deep learning alternative to explicit model predictive control for unknown nonlinear systems
Not Available
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “data predictive control”
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.
Data-Enabled Fusion Technology (Final Scientific/Technical Report)
Advancing Scientific Understanding in Fusion Energy and Machine Learning This research represented a significant step forward in machine learning (ML) applications for fusion energy experiments. The project integrated advanced data-driven modeling, optimization techniques, and artificial intelligence to enhance the predictive capabilities and operational efficiency of plasma-based fusion systems. Specifically, tasks focused on ML-enhanced diagnostics, operator guidance tools, and predictive modeling helped improve the ability to interpret complex fusion experiments. Key areas of advancement included: 1) data-driven plasma control, i.e., using ML algorithms to optimize experimental conditions and classify plasma behaviors based on historical data; 2) spectroscopy and diagnostics, i.e., applying AI models to extract previously inaccessible insights from experimental spectroscopy data; and 3) configuration mapping and operator guidance, i.e., developing a predictive framework to assist scientists in identifying the most effective experimental parameters, reducing reliance on manual adjustments. By refining these ML-driven techniques, the project contributed to the broader scientific community’s understanding of plasma dynamics and fusion energy viability. Technical Effectiveness and Economic Feasibility The methods investigated demonstrated high technical effectiveness, as reflected in milestones assessing the predictive accuracy, performance, and optimization of fusion configurations. The development of an Operator Guidance Tool (OGT), for example, led to more precise control of plasma conditions by learning from experimental data and offering real-time adjustments. From an economic standpoint, DeFT provided: 1) the ability to reduce trial-and-error experimentation, which lowered operational costs; 2) improved data interpretation methods, which enabled more efficient resource allocation in large-scale fusion research projects; and 3) the automation of key diagnostic tasks, which reduced manual labor and human error, increasing overall efficiency. 13 The final assessments of predictive models and optimization strategies demonstrated that these approaches were scalable and could be implemented across multiple fusion energy research programs. Public Benefit and Societal Impact This project contributed directly to the broader goal of achieving sustainable and commercially viable fusion energy, which had profound implications for clean energy production and climate change mitigation. The integration of AI-driven solutions into fusion research: 1) sped up scientific discovery, accelerating progress towards achieving energy breakthroughs; 2) reduced the cost of experimentation, making fusion research more accessible; and 3) provided a framework for future AI applications in high-energy physics, benefiting adjacent fields like space exploration, material science, and renewable energy. Additionally, by fostering collaborations between AI researchers and plasma physicists, this project promoted interdisciplinary innovation that could lead to broader applications beyond fusion research.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Data-driven model for divertor plasma detachment prediction
We present a fast and accurate data-driven surrogate model for divertor plasma detachment prediction leveraging the latent feature space concept in machine learning research. Our approach involves constructing and training two neural networks: an autoencoder that finds a proper latent space representation (LSR) of plasma state by compressing the multi-modal diagnostic measurements and a forward model using multi-layer perception (MLP) that projects a set of plasma control parameters to its corresponding LSR. By combining the forward model and the decoder network from autoencoder, this new data-driven surrogate model is able to predict a consistent set of diagnostic measurements based on a few plasma control parameters. In order to ensure that the crucial detachment physics is correctly captured, highly efficient 1D UEDGE model is used to generate training and validation data in this study. The benchmark between the data-driven surrogate model and UEDGE simulations shows that our surrogate model is capable of providing accurate detachment prediction (usually within a few per cent relative error margin) but with at least four orders of magnitude speed-up, indicating that performance-wise, it has the potential to facilitate integrated tokamak design and plasma control. Comparing with the widely used two-point model and/or two-point model formatting, the new data-driven model features additional detachment front prediction and can be easily extended to incorporate richer physics. This study demonstrates that the complicated divertor and scrape-off-layer plasma state has a low-dimensional representation in latent space. Understanding plasma dynamics in latent space and utilising this knowledge could open a new path for plasma control in magnetic fusion energy research.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Digitalization of an experimental electrochemical reactor via the smart manufacturing innovation platform
The exponential increase in data produced over the last two decades has revolutionized the way we collect, store, process, analyze, model, and interpret information to improve profitability. Manufacturing is no exception. How- ever, Smart Manufacturing, the digital practice, organization, workforce, and infrastructure transformation for collection and deployment of data and models at scale and at all levels of manufacturing, is a complex, costly, and labor-intensive journey that is still seeing slow adoption. The Clean Energy Smart Manufacturing Innovation Institute (CESMII), a national Manufacturing USA public-private partnership sponsored by the Department of Energy, is addressing this scaled use of data and modeling in manufacturing. CESMII has focused on how to col- lect and use operating data for numerous applications that improve productivity, precision, and performance of manufacturing operations from factory floor to supply chain using process simulation, predictive analytics, mon- itoring and control, and real-time optimization. Because contextualized data are key, CESMII has developed the Smart Manufacturing Innovation Platform (SMIP) to lower the barriers to the data that are needed to accelerate data-based model building, improve data visualization, and more quickly gain insights. Reusable, standards-based ways of doing data collection, ingestion, and contextualization are particularly important for scaling access and use of data. The SMIP uses a standards-based definition and construct for reusable information models called an SM Profile. When an SM Profile is used in conjunction with the SMIP, the SMIP ensures the availability of contextualized, operational data for model building. The present work demonstrates Smart Manufacturing and the application of the SMIP for building several data-centered models for the operation and control of an ex- perimental electrochemical reactor that reduces carbon dioxide (CO 2 ) gas to valuable liquid and gas chemicals, such as alcohols, olefins, and syngas. We describe how the SMIP plays a central role in more effective model building and we demonstrate how the electochemical reactor can be controlled and optimized for the desired products. Use of the SMIP involves the transmission of real-time sensor measurements to a cloud resource so that the operating data are available to all model building experts. The data collection and transmission process is fully automated to greatly reduce the need for manual manipulation of the data. Data-driven machine learning models are used for advanced real-time state estimation, real-time optimization, and model-based feedback control for the reactor. The application models are implemented as a system to monitor the data flow and control the electrochemical reactor with a single visualization interface. SM Profiles are used to demonstrate reusability of the information models for the reactor and the instrumentation. The application packages, algorithms, and user interfaces developed are cast as Docker images in a library to facilitate reusability of the application models.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Scalable Wind Turbine Generator Bearing Fault Prediction Using Machine Learning: A Case Study
Operation and maintenance (O&M) costs for wind turbines pose a risk to competitiveness and asset owners. With machine-learning technologies and digitalization rapidly maturing, the wind industry is actively investigating these new technologies to optimize O&M practices and reduce costs. This paper reviews recent work on machine-learning approaches to generator bearing failure prediction and presents a relevant real-world case study through a collaboration between the National Renewable Energy Laboratory and Envision Digital Corporation. In the case study, we evaluate the performance of representative machine-learning algorithms for predicting wind turbine generator bearing failures. Operational supervisory control and data acquisition data from one wind power plant was used to train and test the machine-learning models. The investigated data channels are chosen based on whether physically they reflect the failed generator bearing conditions and the component historical usage, including both environmental and operational conditions. Benefits and drawbacks of different methods are identified.
generator bearing failures↗
Optimising the processing and storage of visibilities using lossy compression
The next-generation radio astronomy instruments are providing a massive increase in sensitivity and coverage, largely through increasing the number of stations in the array and the frequency span sampled. The two primary problems encountered when processing the resultant avalanche of data are the need for abundant storage and the constraints imposed by I/O, as I/O bandwidths drop significantly on cold storage. An example of this is the data deluge expected from the SKA Telescopes of more than 60 PB per day, all to be stored on the buffer filesystem. While compressing the data is an obvious solution, the impacts on the final data products are hard to predict. In this paper, we chose an error-controlled compressor – MGARD – and applied it to simulated SKA-Mid and real pathfinder visibility data, in noise-free and noise-dominated regimes. As the data have an implicit error level in the system temperature, using an error bound in compression provides a natural metric for compression. MGARD ensures the compression incurred errors adhere to the user-prescribed tolerance. To measure the degradation of images reconstructed using the lossy compressed data, we proposed a list of diagnostic measures, exploring the trade-off between these error bounds and the corresponding compression ratios, as well as the impact on science quality derived from the lossy compressed data products through a series of experiments. We studied the global and local impacts on the output images for continuum and spectral line examples. We found relative error bounds of as much as 10%, which provide compression ratios of about 20, have a limited impact on the continuum imaging as the increased noise is less than the image RMS, whereas a 1% error bound (compression ratio of 8) introduces an increase in noise of about an order of magnitude less than the image RMS. For extremely sensitive observations and for very precious data, we would recommend a 0.1% error bound with compression ratios of about 4. These have noise impacts two orders of magnitude less than the image RMS levels. At these levels, the limits are due to instabilities in the deconvolution methods. We compared the results to the alternative compression tool DYSCO, in both the impacts on the images and in the relative flexibility. MGARD provides better compression for similar error bounds and has a host of potentially powerful additional features.
Techniques: interferometric↗
Baseline Validation of Unstructured Grid Reynolds-Averaged Navier-Stokes Toward Flow Control
The value of the use of the Reynolds-averaged Navier-Stokes methodology for active flow control applications is assessed. An experimental flow control database exists for a NACA0015 airfoil modified at the leading edge to implement a fluidic actuator; hence, this configuration is used. Computational results are documented for the baseline wing configuration (no control) with the experimental results and assumes two-dimensional flow. The baseline wing configuration has discontinuities at the leading edge, trailing edge, and aft of midchord on the upper surface. A limited number of active flow control applications have been tested in the laboratory and in flight. These applications include dynamic stall control using a deformable leading edge, separation control for takeoff and landing flight conditions using piezoelectric devices, pulsed vortex generators, zero-net-mass oscillations, and thrust vectoring with zero-net-mass piezoelectric-driven oscillatory actuation. As yet, there is no definitive comparison with experimental data that indicates current computational capabilities can quantitatively predict the large aerodynamic performance gains achieved with active flow control in the laboratory. However, one study using the Reynolds-averaged Navier-Stokes (RANS) methodology has shown good quantitative agreement with experimental results for an isolated zero-net-mass actuator. In addition, some recent studies have used RANS to demonstrate qualitative performance gains compared with the experimental data for separation control on an airfoil. Those quantitative comparisons for both baseline and flow control cases indicated that computational results were in poor quantitative agreement with the experiments. The current research thrust will investigate the potential use of an unstructured grid RANS approach to predict aerodynamic performance for active flow control applications building on the early studies. First the computational results must quantitatively match experiments for the no-control case before proceeding to the time-dependent flow control case. This paper documents the baseline (no-control) case using an unswept airfoil configuration. The next section describes the configurations used for the computations and the experimentals. The computational approach is then described followed by results and concluding remarks.
Joslin, Ronald D.↗
Handling qualities effects of display latency
Display latency is the time delay between aircraft response and the corresponding response of the cockpit displays. Currently, there is no explicit specification for allowable display lags to ensure acceptable aircraft handling qualities in instrument flight conditions. This paper examines the handling qualities effects of display latency between 70 and 400 milliseconds for precision instrument flight tasks of the V-22 Tiltrotor aircraft. Display delay effects on the pilot control loop are analytically predicted through a second order pilot crossover model of the V-22 lateral axis, and handling qualities trends are evaluated through a series of fixed-base piloted simulation tests. The results show that the effects of display latency for flight path tracking tasks are driven by the stability characteristics of the attitude control loop. The data indicate that the loss of control damping due to latency can be simply predicted from knowledge of the aircraft's stability margins, control system lags, and required control bandwidths. Based on the relationship between attitude control damping and handling qualities ratings, latency design guidelines are presented. In addition, this paper presents a design philosophy, supported by simulation data, for using flight director display augmentation to suppress the effects of display latency for delays up to 300 milliseconds.
King, David W.↗
Using Historical Data to Automatically Identify Air-Traffic Control Behavior
This project seeks to develop statistical-based machine learning models to characterize the types of errors present when using current systems to predict future aircraft states. These models will be data-driven - based on large quantities of historical data. Once these models are developed, they will be used to infer situations in the historical data where an air-traffic controller intervened on an aircraft's route, even when there is no direct recording of this action.
trajectory generation↗
Data Driven UAM Flight Energy Consumption Prediction and Risk Assessment
With the current technological advancements revolutionizing the concept of Urban Air Mobility (UAM) and package delivery, there is also, a concurrent need to quantify the operational safety of these vehicles in terms of their associated risk. Conducting safe flight operations is critical for UAM vehicles which are electrically Vertical Takeoff and Landing (eVTOL) vehicles, to operate in current Air traffic control. In this paper, a data-driven method for UAM vehicle energy consumption prediction and risk quantification with conditional value-at-risk based on energy consumption distribution is presented. Significant factors affecting energy consumption, such as density altitude, aircraft design, airspeed, and collision avoidance algorithms, are considered in the data-driven based energy consumption prediction of different eVTOL
Data-driven↗
Research study on stabilization and control modern sampled-data control theory
The methods of continuous and discrete describing function analysis were applied to predicting the existence of self-sustained oscillations in the single-axis model of the large space telescope system with nonlinear control moment gyroscope friction characteristics. It is shown that the stability equations may be solved by a numerical-iterative technique using the describing function analysis, instead of the usual graphical methods. The numerical method is found to be effective in leading to a convergent solution rapidly, with an appropriate guess of the initial condition.
Kuo, B. C.↗
Conceptual definition of Automated Power Systems Management
Automated Power Systems Management (APSM) is defined as the capability of a spacecraft power system to automatically perform monitoring, computational, command, and control functions without ground intervention. Power systems for future planetary spacecraft must have this capability because they must perform up to 10 years, and accommodate real-time changes in mission execution autonomously. Specific APSM functions include fault detection, isolation, and correction; system performance and load profile prediction; power system optimization; system checkout; and data storage and transmission control. This paper describes the basic method of implementing these specific functions. The APSM hardware includes a central power system computer and a processor dedicated to each major power system subassembly along with digital interface circuitry. The major payoffs anticipated are in enhancement of spacecraft reliability and life and reduction of overall spacecraft program cost.
Imamura, M. S.↗
Forward and inverse predictive transient models of TREAT using surrogate reactivity models
In this work, we present two novel approaches for predicting the power evolution and control rod height of the Transient Reactor Test Facility (TREAT) to support experiment modeling; specifically, transient analysis of the NASA-sponsored Sirius series of experiments. These approaches utilize steady-state Monte Carlo model, point kinetics model, and surrogate models to predict power evolution and control rod axial position during transient experiments. Both approaches were tested and validated against several Sirius experiments that were performed in the TREAT facility at different power levels. The validation test results show very good agreement with the experimental data, and the models were able to accurately predict the power evolution and the axial control rod position with an average error within 3.0%. Finally, this indicates that these approaches will help the reactor engineering team of the TREAT facility in preparing and predicting the power and temperature of the experiment.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
Design and Testing of Flight Control Laws on the RASCAL Research Helicopter
Two unique sets of flight control laws were designed, tested and flown on the Army/NASA Rotorcraft Aircrew Systems Concepts Airborne Laboratory (RASCAL) JUH-60A Black Hawk helicopter. The first set of control laws used a simple rate feedback scheme, intended to facilitate the first flight and subsequent flight qualification of the RASCAL research flight control system. The second set of control laws comprised a more sophisticated model-following architecture. Both sets of flight control laws were developed and tested extensively using desktop-to-flight modeling, analysis, and simulation tools. Flight test data matched the model predicted responses well, providing both evidence and confidence that future flight control development for RASCAL will be efficient and accurate.
Frost, Chad R.↗
X-43A Flight-Test-Determined Aerodynamic Force and Moment Characteristics at Mach 7.0
The second flight of the Hyper-X program afforded a unique opportunity to determine the aerodynamic force and moment characteristics of an airframe-integrated scramjet-powered aircraft in hypersonic flight. These data were gathered via a repeated series of pitch, yaw, and roll doublets, frequency sweeps, and pushover-pullup maneuvers performed throughout the X-43A cowl-closed descent. Maneuvers were conducted at Mach numbers of 6.80-0.95 and at altitudes from 92,000 ft mean sea level to sea level. The dynamic pressure varied from 1300 to 400 psf with the angle of attack ranging from 0 to 14 deg. The flight-extracted aerodynamics were compared with preflight predictions based on wind-tunnel test data. The X-43A flight-derived axial force was found to be 10-15%higher than prediction. Underpredictions of similar magnitude were observed for the normal force. For Mach numbers above 4.0, the flight-derived stability and control characteristics resulted in larger-than-predicted static margins, with the largest discrepancy approximately 5 in. forward along the x-axis center of gravity at Mach 6.0. This condition would result in less static margin in pitch. The predicted lateral-directional stability and control characteristics matched well with flight data when allowance was made for the high uncertainty in angle of sideslip.
Davis, Mark C.↗
Control system testing
A three stage process of ground testing of the Space Telescope Pointing Control System is used for verification prior to on-orbit operation. First, development tests are conducted in a laboratory environment using flight/engineering model control sensor and actuators configured with an engineering model of the flight computer and data management system breadboards. These development tests validate the results of computer simulations predicting control system performance. Integration tests bring together flight system elements and software interfaced to a software simulation of vehicle dynamics to confirm closed loop performance. The final ground test phase, flight systems testing, is conducted on the fully assembled Space Telescope, verifies interfaces with the Fine Guidance Sensors and includes a thermal vacuum testing period. During the final test phase, the Point Control System is exercised with the dynamics simulator running in real time.
Whittler, W. H.↗
Standardized Data to Improve Understanding and Modeling of Soil Nitrogen at Continental Scale
Abstract Nitrogen (N) is a key limiting nutrient in terrestrial ecosystems, but there remain critical gaps in our ability to predict and model controls on soil N cycling. This may be in part due to lack of standardized sampling across broad spatial–temporal scales. Here, we introduce a continentally distributed, publicly available data set collected by the National Ecological Observatory Network (NEON) that can help fill these gaps. First, we detail the sampling design and methods used to collect and analyze soil inorganic N pool and net flux rate data from 47 terrestrial sites. We address methodological challenges in generating a standardized data set, even for a network using uniform protocols. Then, we evaluate sources of variation within the sampling design and compare measured net N mineralization to simulated fluxes from the Community Earth System Model 2 (CESM2). We observed wide spatiotemporal variation in inorganic N pool sizes and net transformation rates. Site explained the most variation in NEON’s stratified sampling design, followed by plots within sites. Organic horizons had larger pools and net N transformation rates than mineral horizons on a sample weight basis. The majority of sites showed some degree of seasonality in N dynamics, but overall these temporal patterns were not matched by CESM2, leading to poor correspondence between observed and modeled data. Looking forward, these data can reveal new insights into controls on soil N cycling, especially in the context of other environmental data sets provided by NEON, and should be leveraged to improve predictive modeling of the soil N cycle.
54 ENVIRONMENTAL SCIENCES↗
Flight-Test-Determined Aerodynamic Force and Moment Characteristics of the X-43A at Mach 7.0
The second flight of the Hyper-X program afforded a unique opportunity to determine the aerodynamic force and moment characteristics of an airframe-integrated scramjet-powered aircraft in hypersonic flight. These data were gathered via a repeated series of pitch, yaw, and roll doublets; frequency sweeps; and pushover-pullup maneuvers performed throughout the X-43A cowl-closed descent. Maneuvers were conducted at Mach numbers of 6.80 to 0.95 and altitudes from 92,000 ft msl to sea level. The dynamic pressure varied from 1300 psf to 400 psf with the angle of attack ranging from 0 deg to 14 deg. The flight-extracted aerodynamics were compared with preflight predictions based on wind-tunnel-test data. The X-43A flight-derived axial force was found to be 10 percent to 15 percent higher than prediction. Under-predictions of similar magnitude were observed for the normal force. For Mach numbers above 4.0, the flight-derived stability and control characteristics resulted in larger-than-predicted static margins, with the largest discrepancy approximately 5 in. forward along the x-axis center of gravity at Mach 6.0. This condition would result in less static margin in pitch. The predicted lateral-directional stability and control characteristics matched well with flight data when allowance was made for the high uncertainty in angle of sideslip.
Davis. Marl C.↗