Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning 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.

At least 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

A Learning Framework for Control-Oriented Modeling of Buildings

Buildings consume a significant amount of energy worldwide. Several building optimization and control use cases require models of energy consumption which are control oriented, have high predictive capability, imposes minimal data pre-processing requirements, and have the ability to be adapted continuously to account for changing conditions as new data becomes available. Data driven modeling techniques, that have been investigated so far, while promising in the context of buildings, have been unable to simultaneously satisfy all the requirements mentioned above. In this context, deep learning techniques such as Recurrent Neural Networks (RNNs) hold promise, empowered by advanced computational capabilities and big data opportunities. In this paper, we propose a deep learning based methodology for the development of control oriented models for building energy management and test in on data from a real building. Results show that the proposed methodology outperforms other data driven modeling techniques significantly. We perform a detailed analysis of the proposed methodology along dimensions such as topology, sensitivity, and downsampling. Lastly, we conclude by envisioning a building analytics suite empowered by the proposed deep framework, that can drive several use cases related to building energy management.

buildings↗
NASA NTRSDate not supplied

Simultaneous Trajectory Tracking Control and Online Mass Estimation for a Regolith Excavating Robot via Integral Concurrent Learning

An adaptive controller is developed for a regolith excavation robot to determine the mass of excavated material and to account for the effects of gravity and friction while on the surface of other celestial bodies. A data-based integral concurrent learning (ICL) parameter update law accounts for and estimates the unknown mass, gravity, and friction parameters. A Lyapunov-based analysis proves that the trajectory tracking error and the parameter estimate errors exponentially converge to zero. An estimation of the mass of regolith excavated by the robot is calculated from the estimated parameters. A simulation study is performed to show the performance of the developed technique. Simulation results show that for 3 kilograms of excavated material, the mass estimate has an error of 4.9 grams.

Max L. Greene↗
DOE OSTI2023

Dynamic Model Agnostic Reliability Evaluation of Machine-Learning Models Integrated in Instrumentation & Control Systems

In recent years, the field of machine learning (ML), specifically neural networks, has grown significantly and has spurred research in its applicability to digital instrumentation and control systems (DI&C). While ML models have shown promise in operational contexts, the trustworthiness of using such algorithms has not been adequately assessed. Failures of ML integrated systems are not well understood, and the lack of comprehensive risk modeling can degrade the trustworthiness in these systems. In recent reports by the National Institute for Standards and Technology (NIST) [1] and the Nuclear Regulatory Commission (NRC) [2], they indicate that trustworthiness in ML is a critical barrier and will play a vital role in the safe, accountable, and secure operation of intelligent systems. Thus, in this work, we demonstrate a dynamic model-agnostic method to quantify the relative reliability of AI/ML predictions by incorporating out-of-distribution (OOD) detection on the training dataset. It is well documented that most ML algorithms excel at interpolation (or near-interpolation) tasks but experience significant performance degradation at extrapolation. The method, referenced as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets which can used to the relative reliability of AI/ML predictions. LADDR is then demonstrated on a feedforward neural network based digital twin used for the prediction of safety significant factors during a loss-of-flow transient. LADDR is used to demonstrate how training data can be used as evidence to support the relative reliability of ML/AI predictions enhancing the overall trustworthiness of the system.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Adaptive Machine Learning for Robust Diagnostics and Control of Time-Varying Particle Accelerator Components and Beams

Machine learning (ML) is growing in popularity for various particle accelerator applications including anomaly detection such as faulty beam position monitor or RF fault identification, for non-invasive diagnostics, and for creating surrogate models. ML methods such as neural networks (NN) are useful because they can learn input-output relationships in large complex systems based on large data sets. Once they are trained, methods such as NNs give instant predictions of complex phenomenon, which makes their use as surrogate models especially appealing for speeding up large parameter space searches which otherwise require computationally expensive simulations. However, quickly time varying systems are challenging for ML-based approaches because the actual system dynamics quickly drifts away from the description provided by any fixed data set, degrading the predictive power of any ML method, and limits their applicability for real time feedback control of quickly time-varying accelerator components and beams. In contrast to ML methods, adaptive model-independent feedback algorithms are by design robust to un-modeled changes and disturbances in dynamic systems, but are usually local in nature and susceptible to local extrema. In this work, we propose that the combination of adaptive feedback and machine learning, adaptive machine learning (AML), is a way to combine the global feature learning power of ML methods such as deep neural networks with the robustness of model-independent control. We present an overview of several ML and adaptive control methods, their strengths and limitations, and an overview of AML approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Learning Provably Stable Local Volt/Var Controllers for Efficient Network Operation

Here this paper develops a data-driven framework to synthesize local Volt/Var control strategies for distributed energy resources (DERs) in power distribution grids (DGs). Aiming to improve DG operational efficiency, as quantified by a generic optimal reactive power flow (ORPF) problem, we propose a two-stage approach. The first stage involves learning the manifold of optimal operating points determined by an ORPF instance. To synthesize local Volt/Var controllers, the learning task is partitioned into learning local surrogates (one per DER) of the optimal manifold with voltage input and reactive power output. Since these surrogates characterize efficient DG operating points, in the second stage, we develop local control schemes that steer the DG to these operating points. We identify the conditions on the surrogates and control parameters to ensure that the locally acting controllers collectively converge, in a global asymptotic sense, to a DG operating point agreeing with the local surrogates. We use neural networks to model the surrogates and enforce the identified conditions in the training phase. AC power flow simulations on the IEEE 37-bus network empirically bolster the theoretical stability guarantees obtained under linearized power flow assumptions. The tests further highlight the optimality improvement compared to prevalent benchmark methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Multi-Task Reinforcement Learning for Distribution System Voltage Control With Topology Changes

This letter proposes a multi-task deep reinforcement learning (DRL) approach for distribution system voltage regulation considering topology changes via PV smart inverter control. The key idea is to encode the topology as an additional state for the DRL and leverage the multi-task learning scheme for joint learning of all task control policies. Unlike other DRL-based methods, our approach is robust to different topologies. Comparison results on the modified IEEE 123-node system demonstrate the enhanced robustness of the proposed method.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Reinforcement learning for real-time process control in high-temperature superconductor manufacturing

With high efficiency and low energy loss, high-temperature superconductors (HTS) have demonstrated their profound applications in various fields, such as medical imaging, transportation, accelerators, microwave devices, and power systems. The high-field applications of HTS tapes have raised the demand for producing cost-effective tapes with long lengths in superconductor manufacturing. However, achieving the uniform and enhanced performance of a long HTS tape is challenging due to the unstable growth conditions in the manufacturing process. Although it is confirmed that the process parameters during the advanced metal organic chemical vapor deposition (A-MOCVD) process influence the uniformity of the produced HTS tapes, the high-dimensional process parameter signals and their complicated interactions make it difficult to develop an effective control policy. In this paper, we propose a local measure for the uniformity of HTS tapes to provide instant feedback for our control policy. Then, we model the manufacturing of HTS tapes as a Markov decision process (MDP) with continuous state and action spaces to assess the instant reward in real time in our feedback control model. As our MDP involves continuous and high-dimensional state and action spaces, a neural fitted Q-iteration (NFQ) algorithm is adopted to solve the MDP with artificial neural network (ANN) function approximation. The collinearity of process parameters can restrict our capability of adjusting the process parameters, which is addressed by the principal component analysis (PCA) in our method. The control policy adjusts the PCA of process parameters using the NFQ algorithm. In conclusion, based on our case studies on real A-MOCVD dataset, the obtained control policy increases the average uniformity of tapes by 5.6% and performs especially well on sample HTS tapes with a low uniformity.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

High Performance Adaptive Deep-Reinforcement-Learning-based Real-time Emergency Control (HADREC) to Enhance Power Grid Resilience in Stochastic Environment (Final Report)

The HADREC technology developed in this project features real-time, validated, and predictive emergency control capabilities needed to effectively safeguard the grid against costly disturbances from extreme weather and other disruptive events. It has the potential to revolutionize the emergency control by providing faster and more effective solution for power grid emergency control. The technology can reduce the grid emergency control action time from minutes to seconds and mitigate the impact of outages and reduce system recovery time. The evaluation results using the models and data from PacifiCorp system have shown ~20% improvement in responding time and 70% improved in tripped generator output, comparing against today’s industrial application. This performance can help reduce preventive measurements and improve network utilization and market efficiency, and help lead to a more reliable and resilient power grid with renewable integration. The project has generated significant interest from industry, academic and commercial companies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2002

A New Look at NASA: Strategic Research In Information Technology

This viewgraph presentation provides information on research undertaken by NASA to facilitate the development of information technologies. Specific ideas covered here include: 1) Bio/nano technologies: biomolecular and nanoscale systems and tools for assembly and computing; 2) Evolvable hardware: autonomous self-improving, self-repairing hardware and software for survivable space systems in extreme environments; 3) High Confidence Software Technologies: formal methods, high-assurance software design, and program synthesis; 4) Intelligent Controls and Diagnostics: Next generation machine learning, adaptive control, and health management technologies; 5) Revolutionary computing: New computational models to increase capability and robustness to enable future NASA space missions.

Alfano, David↗
NASA NTRS2016

Real-Time Global Nonlinear Aerodynamic Modeling for Learn-To-Fly

Flight testing and modeling techniques were developed to accurately identify global nonlinear aerodynamic models for aircraft in real time. The techniques were developed and demonstrated during flight testing of a remotely-piloted subscale propeller-driven fixed-wing aircraft using flight test maneuvers designed to simulate a Learn-To-Fly scenario. Prediction testing was used to evaluate the quality of the global models identified in real time. The real-time global nonlinear aerodynamic modeling algorithm will be integrated and further tested with learning adaptive control and guidance for NASA Learn-To-Fly concept flight demonstrations.

Morelli, Eugene A.↗
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗
NASA NTRS2000

Separation Control at Flight Reynolds Numbers: Lessons Learned and Future Directions

Active separation control, using periodic excitation, was studied experimentally at high Reynolds numbers. The effects of compressibility, mild sweep, location o excitation slot and steady momentum transfer on the efficacy of the method were identified. Tests conducted at chord Reynolds numbers as high as 40 x 10(exp 6) demonstrated that active control using oscillatory flow excitation can effectively delay flow separation from and reattach separated flow to aerodynamic surfaces at flight conditions. The effective frequencies generate one to four vortices over the controlled region at all times, regardless of the Reynolds number. The vortices are initially amplified by the separated shear-layer, and after initiating reattachment, the strength of the vortices decay as they are convected downstream. Large amplitude, low frequency vortices break down to smaller ones upon introduction at the excitation slot. The effects of steady mass transfer were compared to those of periodic excitation. It was found that steady blowing is significantly inferior to periodic excitation in terms o performance benefits and that the response to steady blowing is abrupt, and therefore undesirable from a control point of view. Steady suction and periodic excitation are comparable in effectiveness and both exhibit a gradual response to changes in the magnitude of the control input. The combination of weak steady suction and periodic excitation is extremely effective while the addition of steady blowing could be detrimental. Compressibility effects are weak as long as separation is not caused by a shock-wave/boundary-layer interaction The undesirable effects of the shock-induced separation could be alleviated by the introduction of periodic excitation upstream of the shock wave, inside the region of supersonic flow. The effects of mild sweep were also studied and periodic excitation was found to be very effective in reattaching three-dimensional separated flow. Scaling laws that correlate 2D and 3D controlled flows were tested and verified. Several performance benefits could be gained by applying the method to existing configurations, but it is expected that the full potential of the method can only be realized through the design of new configurations. A comprehensive, fully turbulent, database was generated in order to guide the development, and enable validation, of candidate unsteady CFD design tools.

Seifert, Avi↗
NASA NTRS2000

Separation Control at Flight Reynolds Numbers: Lessons Learned and Future Directions

Active separation control, using periodic excitation, was studied experimentally at high Reynolds numbers. The effects of compressibility, mild sweep, location of excitation slot and steady momentum transfer on the efficacy of the method were identified. Tests conducted at chord Reynolds numbers as high as 40 x 10(exp 6) demonstrated that active control using oscillatory flow excitation can effectively delay flow separation from, and reattach separated flow to aerodynamic surfaces at flight conditions. The effective frequencies generate one to four vortices over the controlled region at all times, regardless of the Reynolds number. The vortices are initially amplified by the separated shear-layer, and after initiating reattachment, the strength of the vortices decay as they are convected downstream. Large amplitude, low frequency vortices break down to smaller ones upon introduction at the excitation slot. The effects of steady mass transfer were compared to those of periodic excitation. It was found that steady blowing is significantly inferior to periodic excitation in terms of performance benefits and that the response to steady blowing is abrupt, and therefore undesirable from a control point of view. Steady suction and periodic excitation are comparable in effectiveness and both exhibit a gradual response to changes in the magnitude of the control input. The combination of weak steady suction and periodic excitation is extremely effective while the addition of steady blowing could be detrimental. Compressibility effects are weak as long as separation is not caused by a shock-wave/boundary-layer interaction. The undesirable effects of the shock-induced separation could be alleviated by the introduction of periodic excitation upstream of the shock wave, inside the region of supersonic flow. The effects of mild sweep were also studied and periodic excitation was found to be very effective in reattaching three-dimensional separated flow. Scaling laws that correlate 2D and 3D controlled flows were tested and verified. Several performance benefits could be gained by applying the method to existing configurations, but it is expected that the full potential of the method can only be realized through the design of new configurations. A comprehensive, fully turbulent, database was generated in order to guide the development, and enable validation, of candidate unsteady CFD design tools.

Pack, LaTunia G.↗
DOE OSTI2024

Visibility-enhanced model-free deep reinforcement learning algorithm for voltage control in realistic distribution systems using smart inverters

Increasing integration of distributed solar photovoltaic (PV) into distribution networks could result in adverse effects on grid operation. Traditional model-based control algorithms require accurate model information that is difficult to acquire and thus are challenging to implement in practice. Here, this paper proposes a surrogate model-enabled grid visibility scheme to empower deep reinforcement learning (DRL) approach for distribution network voltage regulation using PV inverters with minimal system knowledge. In contrast to existing DRL methods, this paper presents and corroborates the adverse impact of missing load information on DRL performance and, based on this finding, proposes a surrogate model methodology to impute load information utilizing observable data. Additionally, a multi-fidelity neural network is utilized to construct the DRL training environment, chosen for its efficient data utilization and enhanced robustness to data uncertainty. The feasibility and effectiveness of the proposed algorithm are assessed by considering DRL testing across varying degrees of observable load information and diverse training environments on a realistic power system.

14 SOLAR ENERGY↗
NASA NTRS1991

Neural Architectures for Control

The cerebellar model articulated controller (CMAC) neural architectures are shown to be viable for the purposes of real-time learning and control. Software tools for the exploration of CMAC performance are developed for three hardware platforms, the MacIntosh, the IBM PC, and the SUN workstation. All algorithm development was done using the C programming language. These software tools were then used to implement an adaptive critic neuro-control design that learns in real-time how to back up a trailer truck. The truck backer-upper experiment is a standard performance measure in the neural network literature, but previously the training of the controllers was done off-line. With the CMAC neural architectures, it was possible to train the neuro-controllers on-line in real-time on a MS-DOS PC 386. CMAC neural architectures are also used in conjunction with a hierarchical planning approach to find collision-free paths over 2-D analog valued obstacle fields. The method constructs a coarse resolution version of the original problem and then finds the corresponding coarse optimal path using multipass dynamic programming. CMAC artificial neural architectures are used to estimate the analog transition costs that dynamic programming requires. The CMAC architectures are trained in real-time for each obstacle field presented. The coarse optimal path is then used as a baseline for the construction of a fine scale optimal path through the original obstacle array. These results are a very good indication of the potential power of the neural architectures in control design. In order to reach as wide an audience as possible, we have run a seminar on neuro-control that has met once per week since 20 May 1991. This seminar has thoroughly discussed the CMAC architecture, relevant portions of classical control, back propagation through time, and adaptive critic designs.

Peterson, James K.↗
DOE OSTI2024

Reinforcement learning pulses for transmon qubit entangling gates

The utility of a quantum computer is highly dependent on the ability to reliably perform accurate quantum logic operations. For finding optimal control solutions, it is of particular interest to explore model-free approaches, since their quality is not constrained by the limited accuracy of theoretical models for the quantum processor—in contrast to many established gate implementation strategies. In this work, we utilize a continuous control reinforcement learning algorithm to design entangling two-qubit gates for superconducting qubits; specifically, our agent constructs cross-resonance and CNOT gates without any prior information about the physical system. Using a simulated environment of fixed-frequency fixed-coupling transmon qubits, we demonstrate the capability to generate novel pulse sequences that outperform the standard cross-resonance gates in both fidelity and gate duration, while maintaining a comparable susceptibility to stochastic unitary noise. We further showcase an augmentation in training and input information that allows our agent to adapt its pulse design abilities to drifting hardware characteristics, importantly, with little to no additional optimization. Our results exhibit clearly the advantages of unbiased adaptive-feedback learning-based optimization methods for transmon gate design.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗