Search NASA⌕ Search

SEARCH · Search NASA

Results for “robust optimization”

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 505 records · Page 28

Analytical Identification Method of Generalized Short‐Circuit Ratio Using Phasor Measurement Units

This paper introduces a novel analytical approach for the identification of the admittance matrix and the generalized short-circuit ratio (gSCR) in power systems integrated with renewable energy sources. The proposed method leverages voltage and current measurements from phasor measurement units (PMUs) to construct a least squares objective function, which is then solved using matrix calculus and partial derivatives. Unlike conventional optimization algorithms, this approach provides an analytical solution that substantially reduces data requirements, enabling the efficient and accurate identification of the gSCR with smaller datasets. Additionally, its fixed computational complexity allows for real-time updates as new data are collected, ensuring continuous refinement of the system of equations and enabling rapid, precise gSCR calculations. The method also exhibits strong robustness against measurement noise, making it well-suited for practical applications in dynamic power systems. The combination of reduced data requirements, real-time adaptability, noise robustness and fixed computational load establishes this method as a highly efficient and reliable tool for real-time power system stability analysis. Case studies on an EPRI 36-bus system demonstrate the method's effectiveness, highlighting its accuracy in closely matching true gSCR values, even under diverse disturbances and noisy conditions.

Han, Zelei [Hohai University, Nanjing (China)] (OR↗

Comprehensive AI-based System for Control, Sensor Estimation, and Fault Detection of Cascaded Multilevel Inverters

In this paper, an Artificial Intelligence-based (AI) system is proposed for an 11-level cascaded H-bridge multilevel inverter (MLI) with the aims of harmonic suppression and reliability enhancement. The system consists of three seamlessly integrated Neural Networks (NNs). First, a multilayer perceptron is used to generalize the optimal switching angles for selective harmonic elimination under non-equal DC voltages. Next, an autoencoder NN estimates the voltage sensor readings to address potential drifting. Finally, a perceptron NN detects inverter faults based solely on the output voltage of the MLI. Simulation scenarios were evaluated, and the results show that the proposed system provides a comprehensive solution for the robust operation of the MLI. The proposed solution is capable of minimizing the targeted harmonics orders with minimal impact on the fundamental voltage, even when the voltage sensor drifts. Furthermore, the inverter under fault conditions was successfully identified.

Rezende da Costa Reis Kimpara, Renata↗

EMSL Community Science Campaign Meeting: Critical Minerals and Materials - Rhizo Critical Campaign Breakout Session Report Summary

The “Critical Minerals Biogeochemistry in the Rhizosphere – Ultramafic Soils (Rhizo Critical)” campaign breakout (BO) session was organized to identify major knowledge gaps and fundamental research needs in rhizosphere microbiology and geochemistry that, if addressed, could transform our ability to recover critical minerals from ultramafic soil systems. We sought to identify significant challenges that must be surmounted in the pursuit of deeper science knowledge. Our ultimate goal is to understand this landscape well enough to identify and prioritize opportunities for EMSL to make the greatest impact with Environmental Transformations and Interactions (ETI) science area research campaigns focused on the biogeochemical processes controlling the behavior of critical minerals and materials in the rhizosphere. The increasing demand for critical materials and minerals (CMM) in the U.S. has heightened interest in low-grade ores with much attention on ultramafic soils, which contain valuable metals such as nickel (Ni), chromium (Cr), manganese, cobalt (Co), and copper (Lee et al., 2025; DOE CMM Report, 2023) used in advanced battery, magnet, wiring and wind turbines, and stainless steel technologies. Metal hyperaccumulating plants grown in ultramafic soils can extract economically valuable concentrations of CMMs through the process of phytomining. This technology has evolved from phytoremediation, which involves using plants to cleanse contaminated environments by removing, detoxifying, or stabilizing pollutants like metals and organic compounds. Hyperaccumulator plants are capable of storing metals in their living tissues at concentrations hundreds to thousands of times higher than those found in 'normal' plants. For instance, while the average concentration of Ni in the dry matter of plants growing in typical soils is usually less than 5 µg g?¹, Ni hyperaccumulation is defined by concentrations exceeding 1,000 µg g?¹ (Corzo Remigio et al., 2020; Reeves et al., 2018). Phytomining research has primarily focused on Ni (Rylott and van der Ent, 2025), for which the U.S. has very limited conventional mines in operation. Most soils typically contain Ni concentrations ranging from 7 to 50 mg kg-1, whereas serpentine soils exhibit significantly higher levels, with Ni content often ranging between 700 and 8,000 mg kg-1 (Sobczyk et al., 2017). While more than 500 plant species in over 50 different families have been identified as Ni hyperaccumulators (Kidd et al., 2018), Ni phytomining (and phytominng in general) remains largely untested because most studies are short-term, small-scale, and conducted under simplified or artificially enriched conditions, so they fail to capture the low metal concentrations, environmental variability, and management constraints that would be needed for a field-scale demonstration. Few hyperaccumulator species have been validated as true “metal crops,” and their biomass production, stress tolerance, and rooting characteristics are usually too poor to yield economically meaningful metal outputs. Critically, the basic mechanisms of metal uptake, transport, and sequestration, especially as shaped by belowground processes such as root exudation, rhizosphere chemistry, and root–microbe interactions that control metal mobility and bioavailability (Montreemuk et al., 2023; Kidd et al., 2018; Durand et al., 2023; Alford et al., 2010), are still only partially understood, and downstream metal recovery from biomass is rarely optimized. Because these limitations stem from gaps in fundamental knowledge rather than from a failure of the concept itself (Rylott and van der Ent, 2025; van der Ent et al., 2015), there is a strong need for basic science that dissects plant metal homeostasis, rhizosphere and microbial processes, and their integration with soil chemistry and process engineering to design more robust, scalable phytomining systems.

Ahkami, Amirhossein↗

Rational Electrolyte Design for Elevated-Temperature and Thermally Stable Lithium-Ion Batteries with Nickel-Rich Cathodes

As the energy density of lithium-ion batteries (LIBs) increases, the shortened cycle life and the increased safety hazard of LIBs are drawing increasing concerns. To address such challenges, a series of localized high-concentration electrolytes (LHCEs) based on a solvating-solvent mixture of tetramethylene sulfone and trimethyl phosphate and a high flash-point diluent 1H,1H,5H-octafluoropentyl 1,1,2,2-tetrafluoroethyl ether were designed. The LHCEs exhibited non-flammability and greatly suppressed heat release at high temperatures, which would potentially improve the safety performance of the LIBs. Moreover, the optimal LHCE achieved capacity retentions of 87.1% and 81.7% in graphite||LiNi 0.8 Mn 0.1 Co 0.1 O 2 cells after 500 cycles at 25 °C and 45 °C, respectively, which were significantly better than the conventional electrolyte, whose capacity retentions were only 75.2% and 38.5% under the same condition. Mechanistic studies revealed that the LHCE not only formed a more robust solid electrolyte interphase, but also exhibited improved anodic stability, compared with the conventional electrolyte. Further, this work sheds light in rational electrolyte design for high energy density LIBs with high battery performance and low safety concerns.

25 ENERGY STORAGE↗

Efficient Berry phase calculation via adaptive variational quantum computing approach

We present an adaptive variational quantum algorithm to estimate the Berry phase accumulated by a nondegenerate ground state under cyclic, adiabatic evolution of a time-dependent Hamiltonian. Our method leverages cyclic adiabatic evolution of the Hamiltonian and employs adaptive variational quantum algorithms for state preparation and evolution, optimizing circuit efficiency while maintaining high accuracy. We benchmark our approach on dimerized Fermi–Hubbard chains with four sites, demonstrating precise Berry phase simulations in both noninteracting and interacting regimes. Our results show that circuit depths reach up to 106 layers for noninteracting systems and increase to 279 layers for interacting systems due to added complexity. In addition, we demonstrate the robustness of our scheme across a wide range of parameters governing adiabatic evolution and variational algorithms. These findings highlight the potential of adaptive variational quantum algorithms for advancing quantum simulations of topological materials and computing geometric phases in strongly correlated systems.

Mootz, Martin [Ames Laboratory (AMES), Ames, IA (U↗

Scale-up Unlearnable Examples Learning with High-performance Computing

Recent advancements in AI models, like ChatGPT, are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources (e.g., a single workstation). To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE’s unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. The use of Summit’s high-performance GPUs, along with the efficiency of the DDP framework, facilitated rapid updates of model parameters and consistent training across nodes. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications. The source code is publicly available at https: // github. com/ hrlblab/ UE_ HPC .

Zhu, Yanfan [Vanderbilt University, Nashville, TN,↗

Optimizing and Exploring Untapped Micro-Hydro Hybrid Systems: a Multi-Objective Approach for Crystal Lake as a Large-Scale Energy Storage Solution

Increasing electricity demand and concerns about climate change and fossil fuel consumption have highlighted the importance of renewable energy resources and storage systems. This paper proposes a method for exploring untapped pumped hydro storage potentials to accommodate intermittent renewable energy generation profiles. Hourly measured data from 2022 in Benzie County, Michigan, United States, were gathered for system sizing and a thorough, realistic analysis. By employing the multi-objective grey wolf optimization algorithm, we formulated optimal sizing and energy-management strategies for three different scenarios. Unlike similar studies, the 3rd with triple objective functions (OFs) scenario aims to maximize both reliability and ecological OFs while minimizing the cost OF. It has shown promising results with multiple solutions, considering economic, environmental, and reliability factors. A case study conducted in Crystal Lake, Michigan, revealed that although Crystal Lake would function only as a micro-hydro power facility, it is a promising and huge storage unit with a substantial storage capacity of around 14.9734GWh. The system investigated is significant in the USA due to its rapid deployment capabilities, minimal construction requirements, and ease of integration with the distribution grid. The fuzzy logic method was employed to identify the best non-dominant solution among the other solutions. Furthermore, these outcomes include a notably low levelized cost of energy at 0.046147$/kWh, a robust index of reliability of 99.705%, and a significant reduction in CO₂ emissions amounting to 7.9142×10 3 tons/year, when considering the triple OFs. The paper’s methodology provides valuable insights for regions aiming to utilize renewable energy from untapped storage sources.

13 HYDRO ENERGY↗

A machine learning framework for accurate and robust analysis of radiation detector pulses

The microscopic properties of atomic nuclei are used to study various scientific questions. They are essential for understanding the fundamental forces of nature and the chemical evolution of the universe. Detecting decay radiation from radioactive nuclei makes it possible to probe these fundamental nuclear properties. Detector waveform traces may contain additional information about the radiation. Generally, advanced signal processing techniques are needed to extract this additional information, often involving fitting the waveform with model response functions using non-linear least-squares optimization with second-order gradient methods. While this is a powerful technique, it is also computationally expensive, leading to slow processing time, which scales with the volume of data. To address this problem, we have developed a machine learning (ML) approach that infers the characteristics of traces from a model detector response function. In particular, we are interested in classifying whether a single recorded trace consists of one or two pulse constituents and estimating the pulse parameters. Furthermore, our proposed ML method can precisely extract the pulses’ parameters, such as energy and timing information, and accurately classify the pulse multiplicity of a trace. Unlike non-learning-based approaches, our ML approach uses neural networks that are significantly faster at inference, as they do not require any optimization during this stage.

Curve fitting↗

Toward a Balanced Description of Ground and Excited States with Transcorrelated F12 Methods

By correlating only the 1-particle states occupied in the reference determinant, the conventional design for the single-reference R12/F12 explicitly correlated methods biases them toward the ground-state description, thereby making the treatment of response properties of the ground state, and energies and other properties of excited states less robust. While the use of multireference methods and/or extensions of the standard SP-projected geminals can achieve a more balanced description of ground and excited states, here we show that the same goals can be achieved by extending the action of F12 correlators to the occupied and valence unoccupied 1-particle states only. This design choice reflects the strong dependence of the optimal correlation length scale of the F12 ansatz on the orbital energies/structure, and helps to avoid the unphysical raising of the ground-state energy if the F12 geminals are used to correlate pairs of all 1-particle states. The improved F12 geminal design is incorporated into the unitary transcorrelation framework to produce a unitary 2-body Hamiltonian that incorporates the short-range dynamical correlation physics for ground and low-energy excited states in a balanced manner. This explicitly correlated effective Hamiltonian reduces the basis set requirement on the correlation-consistent basis cardinal number by 1 or more over the uncorrelated counterpart for the description of ground-state coupled-cluster singles and doubles (CCSD) energies, vertical excitation energies, and harmonic vibrational frequencies of equation-of-motion CCSD low-energy excited states.

Hamiltonians↗

Synthesis and transport properties of epitaxial Bi (111) films on GaAs (111) substrates

In recent decades, the growth of ultrathin epitaxial bismuth (Bi) films on various substrates has garnered interest due to their unique electronic properties. We report upon the growth and electrical transport properties of epitaxial Bi (111) films in the thickness range of 5–32 nm deposited directly on GaAs (111) substrates, without a buffer layer. The quality of Bi films is found to depend on conditions for substrate treatment using Ar + ion-milling and annealing. Substrates milled at low ion beam currents display poor surface reconstruction after annealing, which hinders the growth of high-quality films. In contrast, substrates milled under optimized conditions led to reconstructed surfaces upon annealing, resulting in epitaxial Bi films with predominantly single-domain orientation. Although epitaxial films formed in both cases, transport measurements indicated significantly higher conductivity for films grown on optimally treated substrates. Measurements at low temperatures suggest that the transport properties are dominated by a surface state with high mobility electrons. Magneto-transport measurements suggest that conductivity and mobility improve progressively with increasing film thickness. For the thinnest 5 nm film, a hole-like state emerges, presumably as the electron-like state is gapped out. These results provide a robust methodology for growing high-quality epitaxial Bi films on GaAs (111) and offer insights into their unique transport properties and our ability to tune them.

Atomic force microscopy↗

Predictive Modeling and Uncertainty Quantification in Condition Monitoring of Active Components: A Reactor Coolant Pump Use Case

This work develops data-driven models for onset of thermal barrier leakage in reactor coolant pumps. It incorporates uncertainty quantification to enhance the reliability and robustness of pre- dictions. Using synthetic data generated by the Generic Pressurized Water Reactor simulator, realistic degradation scenarios were simulated across lifecycle stages—beginning, middle, and end of life. Key variables, including differential pressure, flow rate, vibration, and temperatures, were analyzed using machine learning framework. The fully connected neural network models demonstrated exceptional performance, achieving R2 scores exceeding 0.99 and root mean square errors as low as around 8.23 × 10-2 gallon per minute (gpm) for the three stages of the lifecy- cle. UQ analysis further validated the model’s robustness, with narrow uncertainty bounds during steady-state operations and appropriately wider bounds during transitional phases, reflecting the physical behavior of the system. This work addresses important gaps in real-time condition moni- toring and regulatory compliance by integrating advanced condition monitoring technologies with UQ into IST programs. The ability to detect thermal barrier leakage early and quantify prediction reliability supports optimizing maintenance strategies while ensuring nuclear power plants’ safe and reliable operation.

99 - GENERAL AND MISCELLANEOUS↗

Constrained or unconstrained? Neural-network-based equation discovery from data

Throughout many fields, practitioners often rely on differential equations to model systems. Yet, for many applications, the theoretical derivation of such equations and/or the accurate resolution of their solutions may be intractable. Instead, recently developed methods, including those based on parameter estimation, operator subset selection, and neural networks, allow for the data-driven discovery of both ordinary and partial differential equations (PDEs), on a spectrum of interpretability. The success of these strategies is often contingent upon the correct identification of representative equations from noisy observations of state variables and, as importantly and intertwined with that, the mathematical strategies utilized to enforce those equations. Specifically, the latter has been commonly addressed via unconstrained optimization strategies. Representing the PDE as a neural network, we propose to discover the PDE (or the associated operator) by solving a constrained optimization problem and using an intermediate state representation similar to a physics-informed neural network (PINN). The objective function of this constrained optimization problem promotes matching the data, while the constraints require that the discovered PDE is satisfied at a number of spatial collocation points. We present a penalty method and a widely used trust-region barrier method to solve this constrained optimization problem, and we compare these methods on numerical examples. Our results on several example problems demonstrate that the latter constrained method outperforms the penalty method, particularly for higher noise levels or fewer collocation points. This work motivates further exploration into using sophisticated constrained optimization methods in scientific machine learning, as opposed to their commonly used, penalty-method or unconstrained counterparts. For both of these methods, we solve these discovered neural network PDEs with classical methods, such as finite difference methods, as opposed to PINNs-type methods relying on automatic differentiation. Here, we briefly highlight how simultaneously fitting the data while discovering the PDE improves the robustness to noise and other small, yet crucial, implementation details.

Data-driven discovery↗

Bridging paradigms: Designing for HPC-Quantum convergence

Here, this paper presents a comprehensive software stack architecture for integrating quantum computing (QC) capabilities with High-Performance Computing (HPC) environments. While quantum computers show promise as specialized accelerators for scientific computing, their effective integration with classical HPC systems presents significant technical challenges. We propose a hardware-agnostic software framework that supports both current noisy intermediate-scale quantum devices and future fault-tolerant quantum computers, while maintaining compatibility with existing HPC workflows. The architecture includes a quantum gateway interface, standardized APIs for resource management, and robust scheduling mechanisms to handle both simultaneous and interleaved quantum–classical workloads. Key innovations include: (1) a unified resource management system that efficiently coordinates quantum and classical resources, (2) a flexible quantum programming interface that abstracts hardware-specific details, (3) A Quantum Platform Manager API that simplifies the integration of various quantum hardware systems, and (4) a comprehensive tool chain for quantum circuit optimization and execution. We demonstrate our architecture through implementation of quantum–classical algorithms, including the variational quantum linear solver, showcasing the framework’s ability to handle complex hybrid workflows while maximizing resource utilization. This work provides a foundational blueprint for integrating QC capabilities into existing HPC infrastructures, addressing critical challenges in resource management, job scheduling, and efficient data movement between classical and quantum resources.

97 MATHEMATICS AND COMPUTING↗

Online LIBS–ML Framework for Dynamic Characterization of Heterogeneous Waste-Derived Gasification Feedstocks

LIBS−ML framework for real time feedstock characterization during continuous conveyor transport Heterogeneous waste derived feedstocks (e.g., waste coal, biomass and blends) introduce rapid variability in heating value and ash chemistry that affect gasifier operation, yet conventional laboratory characterization techniques are too slow to support proactive control. To address this gap, this study reports on an online, in situ, dynamic characterization framework that couple’s laser-induced breakdown spectroscopy (LIBS) with leakage safe machine learning (ML) regression to deliver real time, decision quality predictions of gasifier relevant properties. A controlled sample matrix spanning two different waste coals, two different biomasses, and engineered blends under two particle size conditions were constructed and benchmarked using standardized laboratory analyses for proximate/ultimate properties and ash composition. LIBS spectra were acquired dynamically as material flowed on a conveyor belt, using high energy 1064 nm laser ablation and shot averaging to improve repeatability and precision. Supervised regression models (multi layer perceptron (MLP) /artificial neural network (ANN), random forest (RF), and support vector regression (SVR)) and an optimized weighted ensemble were trained on emission line feature sets using nested cross validation with Bayesian hyperparameter tuning and validated against an independent hold out set. The proposed LIBS−ML workflow achieves near laboratory predictive fidelity across parametric targets (including higher heating value (HHV), ash content, fixed carbon, sulfur, major ash forming oxides, and initial deformation temperature (IDT)), with the weighted ensemble providing a robust default predictor under dynamic measurement conditions. These results demonstrate a practical pathway for real time feedstock characterization that can enable feedforward adjustments and more resilient gasifier operation for variable quality waste derived fuels.

Biomass↗

A Measurement-Based Adaptive Voltage Regulation Method Considering Topology Changes

This paper proposes an online adaptive data-driven distributed energy resource (DER) dispatch optimization method for voltage control considering topology changes. By using a local sensitivity factor (LSF)-enabled voltage control, traditional DER control can be reformulated into a linear programming (LP) problem, leading to faster computation speeds. Power injection alteration and topology changes are two common operational changes in the distribution network that can affect the LSF and voltage control performance. To address this issue, a robust estimation method is developed to adjust the sensitivity matrix at each time step for the time-varying power injection changes. When topology changes occur, only the allocated predominant LSF submatrices are updated based on measurement data, allowing for a fast adaptation to the system reconfiguration. Results obtained from a real distribution feeder in Southern California demonstrate its robustness as compared to traditional volt-var control and constant LSF matrix dispatch control methods.

DERs↗

Neural operator transformers capture bifurcating drift-wave turbulence in fusion plasma simulations

Self-consistent modeling of turbulence-driven transport is critical for optimizing confinement in magnetically confined fusion plasmas, such as tokamaks and stellarators. In particular, capturing the long-term co-evolution of turbulence, flow, and background plasma profiles remains computationally challenging. Direct numerical simulation of these multiscale, highly nonlinear processes is often demanding and impractical for real-time control or design optimization. To address this bottleneck, we investigate transformer-based neural operator partial differential equation surrogates for emulating the dynamics of drift-wave turbulence bifurcation mediated by zonal flows, using the modified Hasegawa–Wakatani (MHW) model as a prototypical system. We find that the finetuned neural operator model has excellent performance in capturing the multi-spatiotemporal-scales of MHW turbulence bifurcation and is robust to testing on rare and out-of-distribution dynamics. Specifically, we demonstrate that a single unified model accurately predicts both quasi-steady-state turbulence and a wide range of dynamical transition processes, such as nonlinear saturation, spontaneous suppression of turbulence, and the emergence of macroscopic zonal flows, over time horizons vastly exceeding the local turbulence correlation time. This computationally efficient approach establishes a strong foundation for fast, AI-based modeling of complex, multiscale phenomena in magnetized fusion plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Polarization transmission in the Hadron Storage Ring of the Electron-Ion Collider

The successful operation of the future Electron-Ion Collider is contingent on maintaining high hadron beam polarization up to 275 GeV. The Hadron Storage Ring lattice, however, features a symmetry-breaking interaction region that excites strong, nonsystematic spin resonances, posing a significant threat to polarization preservation. This paper systematically investigates two complementary strategies to ensure high polarization transmission. The first method involves optimizing the vertical betatron phase advance between Siberian snakes to orchestrate a cancellation of depolarizing kicks across the ring. We demonstrate through simulations that both dynamic and fixed-optics solutions based on this principle can successfully preserve polarization through the strongest resonances. The second, more powerful approach involves optimizing the snake rotation axes to suppress resonance driving terms at their source. We revisit established symmetric configurations, such as the Lee-Courant schemes, and introduce a novel, highly symmetric “Doubly Lee-Courant” (DLC) scheme, which enforces a local 𝜋 spin phase advance across every consecutive pair of snakes. Our analysis reveals a clear performance hierarchy, with the DLC configuration providing an exceptionally robust and energy-insensitive baseline for polarization preservation. We conclude that a hybrid strategy, using a DLC snake scheme as a symmetric foundation and betatron phase tuning for fine corrections, offers the most effective path forward for the EIC and future high-energy polarized-beam facilities.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Adaptive Reinforcement Learning Control for Power Distribution in Multi-Output Resonant Converters

This paper presents an adaptive reinforcement learning (ARL)-based control framework for efficient power distribution in a multi-output resonant converter for UAV applications. The proposed system is based on a high-frequency isolated resonant architecture, where a single energy source supplies multiple propulsion loads through independently controlled output rectifiers, addressing the need for coordinated multi-motor power management. The ARL framework dynamically allocates output power by learning optimal phase-shift control actions under varying load demands and operating conditions. The agent autonomously determines control parameters that maximize conversion efficiency while ensuring accurate power sharing among multiple outputs. In addition, the proposed approach enables adaptive operation without requiring detailed system modeling or manual tuning. Experimental results demonstrate stable and efficient performance over a wide range of operating conditions, confirming the effectiveness and robustness of the learning-based control strategy for multi-output resonant converter system.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗