SEARCH · Engineering Papers

Results for “fast 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,063 records · Page 59

All sources NASA NTRS DOE OSTI

DOE OSTI2021

The curled wake model: a three-dimensional and extremely fast steady-state wake solver for wind plant flows

Abstract. Wind turbine wake models typically require approximations, such as wake superposition and deflection models, to accurately describe wake physics. However, capturing the phenomena of interest, such as the curled wake and interaction of multiple wakes, in wind power plant flows comes with an increased computational cost. To address this, we propose a new hybrid method that uses analytical solutions with an approximate form of the Reynolds-averaged Navier–Stokes equations to solve the time-averaged flow over a wind plant. We compare results from the solver to supervisory control and data acquisition data from the Lillgrund wind plant obtaining wake model predictions which are generally within 1 standard deviation of the mean power data. We perform simulations of flow over the Columbia River Gorge to demonstrate the capabilities of the model in complex terrain. We also apply the solver to a case with wake steering, which agreed well with large-eddy simulations. This new solver reduces the time – and therefore the related cost – it takes to simulate a steady-state wind plant flow (on the order of seconds using one core). Because the model is computationally efficient, it can also be used for different applications including wake steering for wind power plants and layout optimization.

17 WIND ENERGY↗

DOE OSTI2024

Deep Learning Image Segmentation for Atmospheric Rivers

Abstract The identification of atmospheric rivers (ARs) is crucial for weather and climate predictions as they are often associated with severe storm systems and extreme precipitation, which can cause large impacts on society. This study presents a deep learning model, termed ARDetect, for image segmentation of ARs using ERA5 data from 1960 to 2020 with labels obtained from the TempestExtremes tracking algorithm. ARDetect is a convolutional neural network (CNN)-based U-Net model, with its structure having been optimized using automatic hyperparameter tuning. Inputs to ARDetect were selected to be the integrated water vapor transport (IVT) and total column water (TCW) fields, as well as the AR mask from TempestExtremes from the previous time step to the one being considered. ARDetect achieved a mean intersection-over-union (mIoU) rate of 89.04% for ARs, indicating its high accuracy in identifying these weather patterns and a superior performance than most deep learning–based models for AR detection. In addition, ARDetect can be executed faster than the TempestExtremes method (seconds vs minutes) for the same period. This provides a significant benefit for online AR detection, especially for high-resolution global models. An ensemble of 10 models, each trained on the same dataset but having different starting weights, was used to further improve on the performance produced by ARDetect, thus demonstrating the importance of model diversity in improving performance. ARDetect provides an effective and fast deep learning–based model for researchers and weather forecasters to better detect and understand ARs, which have significant impacts on weather-related events such as floods and droughts.

Galea, Daniel↗

DOE OSTI2020

Advances in PFAS Monitoring and Remediation Using a Functionalized Material Approach

The growing global concerns about the effects to public health from human exposure to per- and polyfluoroalkyl substances (PFAS) motivates the development of strategies for reliable monitoring of PFAS in environmental streams, as well as for their rapid, effective removal if detected. For the continuous PFAS monitoring, an inexpensive, field-deployable, in situ sensor is urgently needed; yet the prevalent in situ techniques often struggle to strike a balance between the practical sensitivity and selectivity demands of the real world. Similarly, for effective PFAS removal, strategies for their fast, selective, and quantitative capture are desired, yet the present commercially available sorbents are unable to meet the requirements of rapid, quantitative capture of all PFAS components, and are notably inefficient in removing the more toxic smaller chains. To address these twin challenges, Pacific Northwest National Laboratory is developing strategies for improved detection and remediation of PFAS. For the rapid, selective, quantitative removal of PFAS from environmental streams, the strategy relies on designing capture probes with exclusively tailored electronic and spatial affinities for the PFAS that are able to selectively capture them from environmental streams. For the in situ detection and quantification of PFAS in complex, multicomponent matrices such as groundwater, the approach relies on the targeted capture of specific PFAS by these PFAS-specific capture probes immobilized on a platform. The platform acts as an electrode to directly measure PFAS concentration through a proportional change in electrical response upon their capture. A combination of optimization of platform design and incorporation of additional, sensitive detection modalities have allowed us to achieve detection limits as low as 0.5 ng/L for detection of PFAS compounds (compared to the 70 ng/L Health Advisory Limit of the U.S. Environmental Protection Agency).

Per- and poly-fluorinated alkyl substances (PFAS),↗

DOE OSTI2020

Advances in PFAS Monitoring and Remediation Using a Functionalized Material Approach - 20080

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

The FRB-searching Pipeline of the Tianlai Cylinder Pathfinder Array

This paper presents the design, calibration, and survey strategy of the Fast Radio Burst (FRB) digital backend and its real-time data processing pipeline employed in the Tianlai Cylinder Pathfinder Array. The array, consisting of three parallel cylindrical reflectors and equipped with 96 dual-polarization feeds, is a radio interferometer array designed for conducting drift scans of the northern celestial semi-sphere. The FRB digital backend enables the formation of 96 digital beams, effectively covering an area of approximately 40 square degrees with the 3 dB beam. Our pipeline demonstrates the capability to conduct an automatic search of FRBs, detecting at quasi-real-time and classifying FRB candidates automatically. The current FRB searching pipeline has an overall recall rate of 88%. During the commissioning phase, we successfully detected signals emitted by four well-known pulsars: PSR B0329+54, B2021+51, B0823+26, and B2020+28. We report the first discovery of an FRB by our array, designated as FRB 20220414A. We also investigate the optimal arrangement for the digitally formed beams to achieve maximum detection rate by numerical simulation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

Working Principle of an Ionic Liquid Interlayer During Pressureless Lithium Stripping on Li 6.25 Al 0.25 La 3 Zr 2 O 12 (LLZO) Garnet‐Type Solid Electrolyte

Abstract Solid‐state‐batteries employing lithium metal anodes promise high theoretical energy and power densities. However, morphological instability occurring at the lithium/solid–electrolyte interface when stripping and plating lithium during cell cycling needs to be mitigated. Vacancy diffusion in lithium metal is not sufficiently fast to prevent pore formation at the interface above a certain current density during stripping. Applied pressure of several MPa can prevent pore formation, but this is not conducive to practical application. This work investigates the concept of ionic liquids as “self‐adjusting” interlayers to compensate morphological changes of the lithium anode while avoiding the use of external pressure. A clear improvement of the lithium dissolution process is observed as it is possible to continuously strip more than 70 μm lithium (i. e., 15 mAh cm −2 charge) without the need for external pressure during assembly and electrochemical testing of the system. The impedance of the investigated electrodes is analyzed in detail, and contributions of the different interfaces are evaluated. The conclusions are corroborated with morphology studies using cryo‐FIB‐SEM and chemical analysis using XPS. This improves the understanding of the impedance response and lithium stripping in electrodes employing liquid interlayers, acting as a stepping‐stone for future optimization.

Fuchs, Till↗

DOE OSTI2022

Analytical and Numerical Analysis of Lithium Plating Onset in Single and Bilayer Graphite Electrodes during Fast Charging

Lithium plating is commonly observed in anodes charged at fast rates, and can lead to capacity loss and battery safety issues. The increased risk of plating has been attributed to transport limitations, and architectured electrodes may reduce plating risk. However, while theoretical studies have shown that reaction non-uniformity arises due to interplay of transport limitations, anode open circuit voltage behavior and reaction kinetics, its effect on lithium plating has not been studied. We use analytic and numerical simulations to predict onset of plating in graphite anode half-cells at high C-rates and demonstrate how anodes with layered porosities can delay plating. Simplified analytical models identify trends for plating onset and predictions are calibrated against numerical models. A calibrated numerical model of graphite demonstrates qualitative agreement with analytical model predictions. This reaction inhomogeneity mechanism occurs in the absence of lithium ion depletion, indicating that these mechanisms may contribute to capacity loss independently or simultaneously. A bilayer model of graphite exhibits delayed plating onset, and an optimization procedure is presented. This theoretical work presents quantitative and mechanistic insight on how reaction inhomogenity affects lithium metal plating onset and can be used as a guide to engineer anodes resistant to lithium plating.

Mijailovic, Aleksandar S.↗

DOE OSTI2024

A deep learning approach to fast analysis of collective Thomson scattering spectra

Fast analysis of collective Thomson scattering ion acoustic wave features using a deep convolutional neural network model is presented. The network was trained from spectra to predict the plasma parameters, including ion velocities, population fractions, and ion and electron temperatures. A fully kinetic particle-in-cell simulation was used to model a laboratory astrophysics experiment and simulate a diagnostic image of the ion acoustic wave feature. Network predictions were compared with Bayesian inference of the plasma model parameters for both the simulated and experimentally measured images. Both approaches were fairly accurate predicting the simulated image and the network predictions matched a good portion of the Bayesian results for the experimentally measured image. The Bayesian approach is more robust to noise and motivates future work to train deep learning models with realistic noise. The advantage of the deep learning model is making thousands of predictions in a few hundred milliseconds, compared to a few seconds to minutes per prediction for the optimization and Bayesian approaches presented here. The results demonstrate promising capabilities of deep learning models to analyze Thomson data orders of magnitude faster than conventional methods when using the neural network for standalone analysis. If more rigorous analysis is needed, neural network predictions can be used to quickly initialize other optimization methods and increase chances of success. This is especially useful when the dataset becomes very large or highly dimensional and manually refining initial conditions for the entire dataset are no longer tractable.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2020

NASA’s first ground-based Galactic Cosmic Ray Simulator: Enabling a new era in space radiobiology research

With exciting new NASA plans for a sustainable return to the moon, astronauts will once again leave Earth’s protective magnetosphere only to endure higher levels of radiation from galactic cosmic radiation (GCR) and the possibility of a large solar particle event (SPE). Gateway, lunar landers, and surface habitats will be designed to protect crew against SPEs with vehicle optimization, storm shelter concepts, and/or active dosimetry; however, the ever penetrating GCR will continue to pose the most significant health risks especially as lunar missions increase in duration and as NASA sets its aspirations on Mars. The primary risks of concern include carcinogenesis, central nervous system (CNS) effects resulting in potential in-mission cognitive or behavioral impairment and/or late neurological disorders, degenerative tissue effects including circulatory and heart disease, as well as potential immune system decrements impacting multiple aspects of crew health. Characterization and mitigation of these risks requires a significant reduction in the large biological uncertainties of chronic (low-dose rate) heavy-ion exposures and the validation of countermeasures in a relevant space environment. Historically, most research on understanding space radiation-induced health risks has been performed using acute exposures of monoenergetic single-ion beams. However, the space radiation environment consists of a wide variety of ion species over a broad energy range. Using the fast beam switching and controls systems technology recently developed at the NASA Space Radiation Laboratory (NSRL) at Brookhaven National Laboratory, a new era in radiobiological research is possible. NASA has developed the “GCR Simulator” to generate a spectrum of ion beams that approximates the primary and secondary GCR field experienced at human organ locations within a deep-space vehicle. The majority of the dose is delivered from protons (approximately 65%–75%) and helium ions (approximately 10%–20%) with heavier ions (Z ≥ 3) contributing the remainder. The GCR simulator exposes state-of-the art cellular and animal model systems to 33 sequential beams including 4 proton energies plus degrader, 4 helium energies plus degrader, and the 5 heavy ions of C, O, Si, Ti, and Fe. A polyethylene degrader system is used with the 100 MeV/n H and He beams to provide a nearly continuous distribution of low-energy particles. A 500 mGy exposure, delivering doses from each of the 33 beams, requires approximately 75 minutes. To more closely simulate the low-dose rates found in space, sequential field exposures can be divided into daily fractions over 2 to 6 weeks, with individual beam fractions as low as 0.1 to 0.2 mGy. In the large beam configuration (60 × 60 cm 2 ), 54 special housing cages can accommodate 2 to 3 mice each for an approximately 75 min duration or 15 individually housed rats. On June 15, 2018, the NSRL made a significant achievement by completing the first operational run using the new GCR simulator. This paper discusses NASA’s innovative technology solution for a ground-based GCR simulator at the NSRL to accelerate our understanding and mitigation of health risks faced by astronauts. Ultimately, the GCR simulator will require validation across multiple radiogenic risks, endpoints, doses, and dose rates.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Evaluation of Minimum NOx Emission From Ammonia Combustion

Abstract Ammonia (NH3) is being explored as a hydrogen carrier with no carbon emissions. However, if burned directly as NH3, rather than being completely decomposed back to N2/H2, the fuel-bound nitrogen comes with a potentially significant NOx emissions penalty. Indeed, several existing studies are showing ammonia combustion NOx emissions that exceed current natural gas fueled, DLN technologies by one to two orders of magnitude. Therefore, it is important to establish the theoretical minimum NOx emissions for an ammonia combustor, to determine how much NOx levels can be reduced via further technology development. In other words, the purpose of this work is not to analyze the performance of a specific combustor but, rather, the fundamental limits of what is achievable. This study quantifies this minimum NOx level for a two-stage combustor system for a given combustor exit temperature and residence time, with a constraint on unburned fuel levels. As expected, the optimum configuration is a rich front end combustor to burn and crack ammonia with significant H2 production, followed by an NO relaxation reactor, followed by a lean stage that consumes the remaining H2. The optimum residence time and stoichiometry of each zone are determined in the fast mixing limit, which essentially balances between NOx production in the primary and secondary zones. These results show minimum NOx levels are in 200–400 ppm range at 1 bar, but drop to levels of ∼25 ppm at 20 bar. These NOx emissions are dominated by NOx production in the primary stage which relaxes to equilibrium levels quite slowly. As processes controlling NOx relaxation to equilibrium in the primary stage dominate overall NO emission levels, combustor NOx sensitivities are essentially opposite that of natural gas fired, DLN systems. Specifically, NOx values drop with increased combustor residence time, increased pressure, and increased combustor exit temperature. These results also suggest that the most important strategy for NOx minimization is to provide sufficient relaxation time after the primary zone for NOx to approach equilibrium—this can be done via kinetic means to accelerate this relaxation rate, such as enhancing pressure or temperature, or increasing residence times. Indeed, this work shows that low pressure combustors specifically optimized for ammonia will have residence times that are one to two orders of magnitude larger than current natural gas systems. By doing so, NOx levels below 10 ppm may be achievable. Finally, we discuss the sensitivity of these values to uncertainties in ammonia kinetics.

Engineering↗

DOE OSTI2022

Characterization of Low Gain Avalanche Detector Prototypes’ Response to Gamma Radiation

Motivated by the need for fast timing detectors to withstand up to 2 MGy of ionizing dose at the High Luminosity Large Hadron Collider, prototype low gain avalanche detectors (LGADs) have been fabricated in a single pad configuration, 2 × 2 arrays, and related p-i-n diodes, and exposed to Co-60 sources for study. Devices were fabricated with a range of dopant layer concentrations, and for the arrays, a variety of inter-pad distances and distances from the active area to the edge. Measurements of capacitance versus voltage and leakage current versus voltage have been made to compare pre- and post-irradiation characteristics in gain layer depletion voltage, full bulk depletion voltage, and breakdown voltage. Conclusions are drawn regarding the effects of the gammas on both surface and interface states and on their contribution to acceptor removal through non-ionizing energy loss from Compton electrons or photoelectrons. Comparison of the performances of members of the set of devices can be used to optimize gain layer parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

Assessment of MOOSE-Based Tools for Calculating Radial Core Expansion

Radial core expansion in liquid-metal cooled fast reactor systems is a well-known phenomenon that produces strong reactivity feedback effects. An inherently safe reactor design takes advantage of negative reactivity feedback in accident scenarios by utilizing a core restraint system which produces a bowed shape that allows for radial expansion of the fuel regions. Detailed modeling and simulation of core radial expansion itself as well as subsequent reactivity feedback is a challenging task involving contact of many fuel assembly elements and physics feedback from neutronics, thermal hydraulics, and thermal mechanical response. A variety of physics codes have been developed to model aspects of radial core expansion but in general invoke geometrical or physics approximations. No code system currently exists which tightly and robustly couples these physics with enough detail to fully resolve the complex core radial expansion reactivity feedback effects. The future availability of such a code system is of vital importance to fully understanding the reactivity feedback effects that occur due to radial expansion, and consequently to optimizing the design of the core restraint system. A high-fidelity code will also be used to benchmark existing lower fidelity, faster running models to understand their benefits, limitations, and range of applications. A code development path using MOOSE-based tools is proposed in order to leverage the detailed geometry capabilities and natural tight coupling and robustness of MOOSE-based applications for modeling this complex phenomena. While simulation of the full phenomenon involves several physics, an assessment has been initiated on the capabilities and readiness of the currently available Tensor Mechanics module within MOOSE for calculation of the structural mechanical responses which occur within the reactor core. This report focuses on modeling the force-deformation response which mimics the physics of a duct contact deformation, as well as differential thermal expansion which produces a thermal bowed shaped for the fuel assemblies in a core. Simple examples were initially performed such as simple supported beam bending under load. The complexity of examples was progressively increased to better mimic the duct behavior by including a differential thermal example and inclusion of hexagonal cross-sections in the geometry. Further assessment of the structural mechanical response simulation capability is still required for modeling duct contact interactions and irradiation creep and swelling. Companion thermal hydraulic and neutronics assessments will also be required; these activities are planned for future years. Finally, integration of the multiple physics components through MOOSE is required to predict the core radial expansion and subsequent feedback effects.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2022

Role of defects in ultra-high gain in fast planar tin gallium oxide UV-C photodetector by MBE

Here we report ultra-high responsivity of epitaxial (Sn x Ga 1–x ) 2 O 3 (TGO) Schottky UV-C photodetectors and experimentally identified the source of gain as deep-level defects, supported by first principles calculations. Epitaxial TGO films were grown by plasma-assisted molecular beam epitaxy on (–201) oriented n-type β-Ga 2 O 3 substrates. Fabricated vertical Schottky devices exhibited peak responsivities as high as 3.5 ×10 4 A/W at –5 V applied bias under 250 nm illumination with sharp cutoff shorter than 280 nm and fast rise/fall time in milliseconds order. Hyperspectral imaging cathodoluminescence (CL) spectra were examined to find the mid-bandgap defects, the source of this high gain. Irrespective of different tin mole fractions, the TGO epilayer exhibited extra CL peaks at the green band (~2.20 eV) not seen in β-Ga 2 O 3 along with enhancement of the blue emission-band (~2.64 eV) and suppression of the UV emission-band. Based on hybrid functional calculations of the optical emission expected for defects involving Sn in β-Ga 2 O 3 , V Ga –Sn complexes are proposed as potential defect origins of the observed green and blue emission-bands. Such complexes behave as acceptors that can efficiently trap photogenerated holes and are predicted to be predominantly responsible for the ultra-high photoconductive gain in the Sn-alloyed Ga 2 O 3 devices by means of thermionic emission and electron tunneling. Regenerating the V Ga –Sn defect complexes by optimizing the growth techniques, we have demonstrated a planar Schottky UV-C photodetector of the highest peak responsivity.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Air Conditioning Systems Fault Detection and Diagnosis-Based Sensing and Data-Driven Approaches

The air conditioning (AC) system is the primary building end-use contributor to the peak demand for energy. The energy consumed by this system has grown as fast as it has in the last few decades, not only in the residential section but also in the industry and transport sectors. Therefore, to combat energy crises, urgent actions on energy efficiency should be taken to support energy security. Consequently, the faults in AC system components increase energy consumption due to the degradation of the system’s performance and the losses in the energy conversion procedure. In this work, AC system fault detection and diagnosis (FDD) methods are investigated to propose analytic tools to identify faults and provide solutions to those problems. The analysis of existing work shows that data-driven approaches are more accurate for both soft and hard fault detection and diagnosis in AC systems. Therefore, the proposed methods are not accurate for simultaneous fault detection, while in some works, authors tested the method with several faults separately without investigating scenarios that combine more than one fault. Moreover, this study shows that integrating data-driven approaches requires deploying an optimal sensing and measurement architecture that can detect a maximum number of faults with minimally deployed sensors. The new sensing, information, and communication technologies are discussed for their integration in AC system monitoring in order to optimize system operation and detect faults.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

Transient fuel performance analysis for the preliminary fuel concept of general atomics fast modular reactor

This study investigates the transient fuel performance of General Atomics Fast Modular Reactor (GA-FMR) during accident scenarios, focusing on the behavior of its innovative fuel system that combines high-assay low enriched uranium dioxide (HALEUO2) fuel with SiGA® ceramic matrix composite silicon carbide cladding. The preliminary fuel design’s response was analyzed during reactivity-initiated accidents (RIA) and loss of coolant accidents (LOCA) using BISON fuel performance analysis code, which included both the diffusion enhanced and BISON-FASTGRASS coupled UO 2 models. The RIA analysis demonstrated that effective reactivity control reduced fuel temperature, though with transient fission gas release resulting in additional tensile stress state on the cladding. LOCA simulations revealed differing predictions between the two models: the BISON UO 2 model showed more transient fission gas release but minimal pellet expansion, while the BISON-FASTGRASS UO 2 model predicted less pronounced fission gas release but more fuel swelling and thermal expansion, potentially leading to pellet-cladding mechanical interaction. Here, these findings highlight critical areas for fuel design optimization and identify knowledge gaps requiring further experimental and computational investigation to advance GA-FMR fuel development.

Lee, Soon K. [Argonne National Laboratory (ANL), A↗

DOE OSTI2025

Potential Supply Chain and Cost Reduction Strategies for Advanced Nuclear Reactors

This milestone represents a level of effort to provide recommendations for a supply chain plan and establish relationships between advanced reactor companies and large companies in the oil & gas and chemical industries. It represents a starting point to develop the plan with options, general equipment lists, and rough associated cost estimates of major equipment and the associated systems needed. This effort will provide an opportunity to leverage the experience that oil & gas and chemicals companies possess in large capital equipment procurement, modularization, acquisition and installation. Potential supply chain solutions will be discussed and preliminary options for worldwide manufacturers will be elucidated. The goal of this effort will be to leverage the years of accumulated experience in the oil & gas and chemical industries in the area of capital equipment acquisition to understand the potential supply chain options and to reduce potential acquisition costs by optimizing the supply chain options for advanced nuclear reactor modularization, manufacturing and acquisition.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2022

Electrochemical and Material Characterization of Laser Micro-Structured Thick Battery Electrodes

By first exploring the limitations of thick planer electrodes, advanced predictive models were prepared to identify optimal electrode patterns for improved cycling performance. Herein, the impact of electrode laser patterning will be discussed in detail. First, materials characterization techniques (SEM-EDS, XRD) were used to explore the effect ultrafast laser ablation had on the electrode materials' morphology and structure. Next, the improvements in the patterned electrodes' electrochemical cycling performances and degrees of wetting will be compared to a pristine baseline case. Finally, the correlation between experimentally obtained data and model predictions will be presented and discussed.

battery↗

DOE OSTI2021

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗