Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “adaptive learning”

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 91 records · Page 5

Adaptive Circuit Learning for Quantum Metrology

Quantum sensing is an important application of emerging quantum technologies. We explore whether a hybrid system of quantum sensors and quantum circuits can surpass the classical limit of sensing. In particular, we use optimization techniques to search for encoder and decoder circuits that scalably improve sensitivity under given application and noise characteristics. Furthermore, our approach uses a variational algorithm that can learn a quantum sensing circuit based on platform-specific control capacity, noise, and signal distribution. The quantum circuit is composed of an encoder which prepares the optimal sensing state and a decoder which gives an output distribution containing information of the signal. We optimize the full circuit to maximize the Signal-to-Noise Ratio (SNR). Furthermore, this learning algorithm can be run on real hardware scalably by using the "parameter-shift" rule which enables gradient evaluation on noisy quantum circuits, avoiding the exponential cost of quantum system simulation. We demonstrate up to 13.12x SNR improvement over existing fixed protocol (GHZ), and 3.19x Classical Fisher Information (CFI) improvement over the classical limit on 15 qubits using IBM quantum computer. More notably, our algorithm overcomes the decreasing performance of existing entanglement-based protocols with increased system sizes.

42 ENGINEERING↗

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

In superconducting magnets, the irreversible transition of a portion of the conductor to resistive state is called a “quench.” Having large stored energy, magnets can be damaged by quenches due to localized heating, high voltage, or large force transients. Unfortunately, current quench protection systems can only detect a quench after it happens, and mitigating risks in Low Temperature Superconducting (LTS) accelerator magnets often requires fast response (down to ms). Additionally, protection of High Temperature Superconducting (HTS) magnets is still suffering from prohibitively slow quench detection. In this study, we lay the groundwork for a quench prediction system using an auto-encoder fully-connected deep neural network. After dynamically trained with data features extracted from acoustic sensors around the magnet, the system detects anomalous events seconds before the quench in most of our data. While the exact nature of the events is under investigation, we show that the system can “forecast” a quench before it happens under magnet training conditions through a randomized experiment. This opens up the way of integrated data processing, potentially leading to faster and better diagnostics and detection of magnet quenches

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Ferroelectric FET-based context-switching FPGA enabling dynamic reconfiguration for adaptive deep learning machines

Field programmable gate array (FPGA) is widely used in the acceleration of deep learning applications because of its reconfigurability, flexibility, and fast time-to-market. However, conventional FPGA suffers from the trade-off between chip area and reconfiguration latency, making efficient FPGA accelerations that require switching between multiple configurations still elusive. Here, we propose a ferroelectric field-effect transistor (FeFET)–based context-switching FPGA supporting dynamic reconfiguration to break this trade-off, enabling loading of arbitrary configuration without interrupting the active configuration execution. Leveraging the intrinsic structure and nonvolatility of FeFETs, compact FPGA primitives are proposed and experimentally verified. The evaluation results show our design shows a 63.0%/74.7% reduction in a look-up table (LUT)/connection block (CB) area and 82.7%/53.6% reduction in CB/switch box power consumption with a minimal penalty in the critical path delay (9.6%). Besides, our design yields significant time savings by 78.7 and 20.3% on average for context-switching and dynamic reconfiguration applications, respectively.

97 MATHEMATICS AND COMPUTING↗

Adaptive local learning in sampling based motion planning for protein folding

Background: Simulating protein folding motions is an important problem in computational biology. Motion planning algorithms, such as Probabilistic Roadmap Methods, have been successful in modeling the folding landscape. Probabilistic Roadmap Methods and variants contain several phases (i.e., sampling, connection, and path extraction). Most of the time is spent in the connection phase and selecting which variant to employ is a difficult task. Global machine learning has been applied to the connection phase but is inefficient in situations with varying topology, such as those typical of folding landscapes. Results: We develop a local learning algorithm that exploits the past performance of methods within the neighborhood of the current connection attempts as a basis for learning. It is sensitive not only to different types of landscapes but also to differing regions in the landscape itself, removing the need to explicitly partition the landscape. We perform experiments on 23 proteins of varying secondary structure makeup with 52–114 residues. We compare the success rate when using our methods and other methods. We demonstrate a clear need for learning (i.e., only learning methods were able to validate against all available experimental data) and show that local learning is superior to global learning producing, in many cases, significantly higher quality results than the other methods. Conclusions: We present an algorithm that uses local learning to select appropriate connection methods in the context of roadmap construction for protein folding. Our method removes the burden of deciding which method to use, leverages the strengths of the individual input methods, and it is extendable to include other future connection methods.

Mathematical & Computational Biology↗

Machine Learning for Adaptive Model Refinement to Bridge Scales

This whitepaper is responsive to focal area (2) Predictive modeling through the use of AI techniques and AI-derived model components: the use of AI and other tools to design a prediction system comprising of a hierarchy of models (e.g., AI driven model/component/parameterization selection). Here we describe scale-aware ML models for adaptive model refinement that allow us to bridge the spatial and/or temporal scales in simulation models and observation data for capturing and predicting extreme water cycles.

58 GEOSCIENCES↗

Adapting Technology Learning Curves for Prospective Techno-Economic and Life Cycle Assessments of Emerging Carbon Capture and Utilization Pathways

Comparisons of emerging carbon capture and utilization (CCU) technologies with equivalent incumbent technologies are necessary to support technology developers and to help policy-makers design appropriate long-term incentives to mitigate climate change through the deployment of CCU. In particular, early-stage CCU technologies must prove their economic viability and environmental reduction potential compared to already-deployed technologies. These comparisons can be misleading, as emerging technologies typically experience a drastic increase in performance and decrease in cost and greenhouse gas emissions as they develop from research to mass-market deployment due to various forms of learning. These changes complicate the interpretation of early techno-economic assessments (TEAs) and life cycle assessments (LCAs) of emerging CCU technologies. The effects of learning over time or cumulative production themselves can be quantitatively described using technology learning curves (TLCs). While learning curve approaches have been developed for various technologies, a harmonized methodology for using TLCs in TEA and LCA for CCU in particular is required. To address this, we describe a methodology that incorporates TLCs into TEA and LCA to forecast the environmental and economic performance of emerging CCU technologies. This methodology is based on both an evaluation of the state of the art of learning curve assessment and a literature review of TLC approaches developed in various manufacturing and energy generation sectors. Additionally, we demonstrate how to implement this methodology using a case study on a CO 2 mineralization pathway. Finally, commentary is provided on how researchers, technology developers, and LCA and TEA practitioners can advance the use of TLCs to allow for consistent, high-resolution modeling of technological learning for CCU going forward and enable holistic assessments and fairer comparisons with other climate technologies.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Rule-based mechanisms of learning for intelligent adaptive flight control

How certain aspects of human learning can be used to characterize learning in intelligent adaptive control systems is investigated. Reflexive and declarative memory and learning are described. It is shown that model-based systems-theoretic adaptive control methods exhibit attributes of reflexive learning, whereas the problem-solving capabilities of knowledge-based systems of artificial intelligence are naturally suited for implementing declarative learning. Issues related to learning in knowledge-based control systems are addressed, with particular attention given to rule-based systems. A mechanism for real-time rule-based knowledge acquisition is suggested, and utilization of this mechanism within the context of failure diagnosis for fault-tolerant flight control is demonstrated.

Handelman, David A.↗

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.↗

Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. Here, in this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Practical Aspects of Real-Time Modeling for the Learn-To-Fly Concept

Practical aspects of autonomous onboard real-time modeling for the NASA Learn-to-Fly concept are examined using flight data from two subscale test aircraft. A practical real-time global nonlinear aerodynamic modeling method is developed and explained, along with the multiple-input excitation needed for effective real-time modeling. Critical issues for integrating real-time global nonlinear aerodynamic modeling and local linear modeling with the real-time learning adaptive control and guidance elements of the Learn-to-Fly algorithm are identified and discussed. Real-time modeling results from NASA Learn-to-Fly flight demonstrations are presented and evaluated using model fit metrics and prediction tests.

Morelli, Eugene A.↗