Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “optimal start”

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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

25 Years of Contamination Control on the James Webb Space Telescope

The James Webb Space Telescope (JWST) has actively been in process since 1996, and at last, on Christmas Day 2021, it launched. This launch was the fulfillment of an astounding level of work performed by thousands of people across the globe in dozens of disciplines. From the start, effective contamination control (CC) was considered essential for the JWST mission due to the large, exposed optics and tight sensitivity required to measure first light and faint signals at the dawn of the universe. This presentation will present the JWST mission and requirements overview, including mission requirements that led to optimizing performance for collecting light in the Near Infrared (NIR, 0.6μm) – Mid Infrared (MIR, 29μm) range. Molecular films absorb in the IR bands and can alter thermal emissivity, resulting in increased noise at the longer wavelengths (MIRI). Particles increase light scatter and background noise levels at the shorter wavelengths (NIRSpec, NIRCam and FGS). The passively cooled design of JWST led to an open architecture for the optical telescope element (OTE), presenting the challenge of maintaining cleanliness throughout assembly, integration, and test in a multitude of environments for over 2 decades. The presentation will describe CC for the mission starting with the first architecture in 1996, then introducing the specific areas of contamination control developed and advanced to keep JWST clean at an unsurpassed level of cleanliness.

Contamination Control↗
DOE OSTI2025

Synthesis‐Related Nanoscale Defects in Mo‐Based Janus Monolayers Revealed by Cross‐Correlated AFM and TERS Imaging

2D Janus transition metal dichalcogenides (TMDs) are promising candidates for various applications including non-linear optics, energy harvesting, and catalysis. These materials are usually synthesized via chemical conversion of pristine TMDs. Nanometer-scale characterization of the obtained Janus materials’ morphology and local composition is crucial for both the synthesis optimization and the future device applications. In this work, we present the results of cross-correlated atomic force microscopy (AFM) and tip-enhanced Raman spectroscopy (TERS) study of Janus monolayers synthesized by the hydrogen plasma-assisted chemical conversion of MoSe 2 and MoS 2 . We demonstrate that the choice of both the growth substrate and the starting TMD influences the residual strain, thereby shaping the nanoscale morphology of the resulting Janus material. Furthermore, by employing TERS imaging, we show the presence of nanoscale islands (≈20 nm across) of MoSe 2 - ${\mathrm{Mo}}_{{\mathrm{Se}}}^{\mathrm{S}}$ (MoS 2 -${\mathrm{Mo}}_{\mathrm{S}}^{{\mathrm{Se}}}$) vertical heterostructures originating from the bilayer nanoislands in the precursor monolayer crystals. The understanding of the origins of nanoscale defects in Janus TMDs revealed in this study can help with further optimization of the Janus conversion process towards uniform and wrinkle-/crack-free Janus materials. Moreover, this work shows that cross-correlated AFM and TERS imaging is a powerful and accessible method for studying nanoscale composition and defects in Janus TMD monolayers.

2D materials↗
DOE OSTI2021

Buffer concentration dramatically affects the stability of S-nitrosothiols in aqueous solutions

S-nitrosothiols (RSNOs) are an important group of nitric oxide (NO)-donating compounds with low toxicity and wide biomedical applications. In this paper, we, for the first time, demonstrate that the concentration of buffer remarkably affects the stability of RSNOs including naturally occurring S-nitrosoglutathione (GSNO) and synthetic S-nitroso-N-acetylpenicillamine (SNAP). For a solution with a high concentration of GSNO (e.g., 50 mM) and an initial near-neutral pH, the optimal buffer concentration is close to the GSNO concentration under our experimental conditions. A lower buffer concentration does not have adequate buffer capacity to resist the pH drop caused by GSNO decomposition. The decreased solution pH further accelerates GSNO decomposition because GSNO is most stable at near-neutral pH according to our density functional theory (DFT) calculations. A higher-than-optimal buffer concentration also reduces the GSNO stability because buffer ingredients including phosphate, Tris base, and HEPES consume NO/N 2 O 3 . In contrast to GSNO, the highest SNAP stability is obtained when the starting solution at a neutral pH does not contain buffer species, and the stability decreases as the buffer concentration increases. Furthermore, this is because SNAP is more stable at mildly acidic pH and the SNAP decomposition-induced pH drop stabilizes the donor. When the RSNO concentration is low (e.g., 1 mM), the buffer concentration also matters because any excess buffer accelerates the donor decomposition. Since the effect of buffer concentration was previously overlooked and suboptimal buffer concentrations were often used, this paper will aid in the formulation of RSNO solutions to obtain the maximum stability for prolonged storage and sustained NO release.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

CryoDRGN-AI: neural ab initio reconstruction of challenging cryo-EM and cryo-ET datasets

Proteins and other biomolecules form dynamic macromolecular machines that are tightly orchestrated to move, bind, and perform chemistry. Cryo-electron microscopy (cryo-EM) and cryo-electron tomography (cryo-ET) can access the intrinsic heterogeneity of these complexes and are therefore key tools for understanding their function. However, 3D reconstruction of the collected imaging data presents a challenging computational problem, especially without any starting information, a setting termed ab initio reconstruction. Here, in this study, we introduce cryoDRGN-AI, a method leveraging an expressive neural representation and combining an exhaustive search strategy with gradient-based optimization to process challenging heterogeneous datasets. Using cryoDRGN-AI, we reveal new conformational states in large datasets, reconstruct previously unresolved motions from unfiltered datasets, and demonstrate ab initio reconstruction of biomolecular complexes from in situ data. With this expressive and scalable model for structure determination, we hope to unlock the full potential of cryo-EM and cryo-ET as a high-throughput tool for structural biology and discovery.

Levy, Axel [Stanford Univ., CA (United States); SL↗
NASA NTRS1987

Calibration of neural networks using genetic algorithms, with application to optimal path planning

Genetic algorithms (GA) are used to search the synaptic weight space of artificial neural systems (ANS) for weight vectors that optimize some network performance function. GAs do not suffer from some of the architectural constraints involved with other techniques and it is straightforward to incorporate terms into the performance function concerning the metastructure of the ANS. Hence GAs offer a remarkably general approach to calibrating ANS. GAs are applied to the problem of calibrating an ANS that finds optimal paths over a given surface. This problem involves training an ANS on a relatively small set of paths and then examining whether the calibrated ANS is able to find good paths between arbitrary start and end points on the surface.

Smith, Terence R.↗
NASA NTRS1991

Probabilistic composite analysis

Formal procedures are described which are used to computationally simulate the probabilistic behavior of composite structures. The computational simulation starts with the uncertainties associated with all aspects of a composite structure (constituents, fabrication, assembling, etc.) and encompasses all aspects of composite behavior (micromechanics, macromechanics, combined stress failure, laminate theory, structural response, and tailoring) optimization. Typical cases are included to illustrate the formal procedure for computational simulation. The collective results of the sample cases demonstrate that uncertainties in composite behavior and structural response can be probabilistically quantified.

Chamis, C. C.↗
NASA NTRS2020

An Algorithm for Hyperspectral Remote Sensing of Aerosols: 3. Application to the GEO-TASO Data in KORUS-AQ Field Campaign

This paper describes the third part of a series of investigations to develop algorithms for simultaneous retrieval of aerosol parameters and surface spectral reflectance from the data measured by GEOstationary Trace gas and Aerosol Sensor Optimization (GEO-TASO) instrument. Since the algorithm is designed for future hyperspectral and geostationary satellite sensors, such as Tropospheric Emissions: Monitoring of Pollution (TEMPO), it is applied to GEO-TASO data measured over the same area by different flights as part of the Korea-United Stated Air Quality Study (KORUS-AQ) field campaign in 2016. While GEO-TAOS has a spectral sampling interval of ~0.28 nm in the visible, its data is thinned through a band selection approach with consideration of atmospheric transmittance and different surface types, which yields 20 common spectral bands to be used by the algorithm. The algorithm starts with 4 common principal components (PCs) for surface spectral reflectance extracted from various spectral libraries, and the constraints of surface reflectance parameters and aerosol scattering models respectively from k- means clustering analysis of the Rayleigh-corrected GEO-TASO spectra and AERONET data. The algorithm then proceeds iteratively with an optimal estimation approach to update PCs and retrieve aerosol optical depth (AOD) until the best match between simulated and GEOS-TASO measured spectra is achieved. The spectral AODs are compared between those retrieved from GEO-TASO (x) and 7 AERONETS (y) in 440, 550, 550, 675 nm, respectively. The comparison reveals that iterative updates of surface spectral PCs (and so surface reflectance) yield significant enhancement in AOD retrievals, improving the mean linear fitting equations from y = 0.735x + 0.088 (without update of PCs) to y = 1.055x+ 0.01, and the Pearson correlation coefficient (𝑅𝑅2) from 0.54 to 0.76, respectively. Move case studies are need to further evaluate the algorithm for its application to TEMPO that carries a enhanced version of GEO-TASO instrument.

Tropospheric Emissions: Monitoring of Pollution (T↗
DOE OSTI2025

Optimizing spin dressing sensitivity for the nEDMSF experiment

nEDMSF aims to measure the neutron electric dipole moment (d n ) with unprecedented precision. In this paper we explore the experiment's sensitivity when operating with an implementation of the critical dressing method in which the angle between the neutron and Helium-3 spins (ϕ 3n ) is subjected to a square modulation by an amount ϕ d (the “dressing angle”). Several parameters can be tuned to optimize sensitivity. We find roughly 10% improvement over a previous estimate, resulting primarily from the addition of a waiting period between the π/2 pulse that initiates d n -driven ϕ 3n growth and the start of ϕ3n modulation. We find negligible further improvement by allowing ϕ d to vary continuously over the course of a run, and no degradation resulting from the addition of an in situ background measurement into each ϕ3n modulation sequence. A complete simulation confirms a 300 live-day sensitivity ofσ = 1.45×10 -28 e ·cm. At this level of sensitivity, σ ϕ3n0 = 1 mrad precision on the initial n/ 3 He angle difference is not negligible.

47 OTHER INSTRUMENTATION↗
DOE OSTI2026

Deep learning-assisted modeling for χ (2) nonlinear optics

Modeling second-order (χ(2)) nonlinear optical processes remains computationally expensive due to the need to resolve fast field oscillations and simulate wave propagation using methods such as the split-step Fourier method (SSFM). This can become a bottleneck in real-time applications, such as high-repetition-rate laser systems requiring rapid feedback and control. We present a long short-term memory-based surrogate model trained on SSFM simulations generated from a start-to-end model of the photocathode drive laser at SLAC National Accelerator Laboratory’s Linac Coherent Light Source II. The model achieves over 250× speedup while maintaining high fidelity, enabling future real-time optimization and laying the foundation for data-integrated modeling frameworks and digital twins of laser systems.

Accelerator Physics (physics.acc-ph)↗
DOE OSTI2021

Electrical Energy Storage Data Submission Guidelines, Version 2

Energy storage technologies are positioned to play a substantial role in power delivery systems. They have the potential to serve as an effective new resource to maintain reliability and allow for increased penetration of renewable energy. However, because of their relative infancy, there is a lack of knowledge about how these resources truly operate over time. A data analysis can help ascertain the operational and performance characteristics of these emerging technologies. Rigorous testing and a data analysis are important for all stakeholders to ensure a safe, reliable system that performs predictably on a macro level. Standardizing testing and analysis approaches to verify the performance of energy storage devices, equipment, and systems when integrating them into the grid will improve the understanding and benefit of energy storage over time from technical and economic vantage points. Demonstrating the life-cycle value and capabilities of energy storage systems begins with the data that the provider supplies for the analysis. After a review of energy storage data received from several providers, some of these data have clearly shown to be inconsistent and incomplete, raising the question of their efficacy for a robust analysis. This report reviews and proposes general guidelines, such as sampling rates and data points, that providers must supply for a robust data analysis to take place. Consistent guidelines are the basis of a proper protocol and ensuing standards to (1) reduce the time that it takes for data to reach those who are providing the analysis; (2) allow them to better understand the energy storage installations; and (3) enable them to provide a high-quality analysis of the installations. The report is intended to serve as a starting point for what data points should be provided when monitoring. Readers are encouraged to use the guidance in the report to develop specifications for new systems, as well as enhance current efforts to ensure optimal storage performance. As battery technologies continue to advance and the industry expands, the report will be updated to remain current.

25 ENERGY STORAGE↗
DOE OSTI2024

Using interfaces to: create strongly-coupled magnetic-ferroelectrics

Starting at the level of electrons and atoms our long-term goal is to rationally design complex oxide heterostructures and interface-materials with targeted emergent behaviors. This is not a matter of simply optimizing material parameters, but rather begins with understanding a mechanism to control the interplay between the diverse microscopic degrees of freedom prevalent in complex oxides in order to create targeted macroscopic phenomena and ends with the design of new material realizations. These realizations are in turn created with atomic-layer precision, structurally assessed to see that they are the intended realization, and finally their relevant properties are measured. During this program we have developed the scientific ideas necessary to apply this materials-by-design paradigm to the creation of materials offering electrical control of magnetism. At the heart of our approach lies a partnership between theory, synthesis, and characterization. These are the areas of expertise of the three co-PIs, who have worked closely together since their arrival at Cornell. During this project bold ideas on where to put the atoms to provide electrical control of magnetism were met with the latest methods of synthesis science and electron microscopy in an attempt create targeted new multiferroics. Our work applying this materials-by-design methodology to multiferroics has enjoyed multiple successes. The Co-PIs have invented new mechanisms for multiferroics, which provide strong coupling between polarization and magnetism, and reduced them to practice. Specifically, we pioneered multiferroics based on spin-phonon coupling, rotation-driven multiferroicity, and novel geometric multiferroics. Importantly, the latter two of these mechanisms enable the deterministic switching of magnetism by an applied electric field, which is key to the application of multiferroics to future device technologies. Most recently, we performed detailed theoretical analysis on a system involving the combination of magnetoelectric and colossal magnetoresistance behaviors and predict that electrical control of a metal-insulator transition is possible in appropriately strained SmBaMn2O6. The research enabled by this grant led to 63 publications in leading refereed journals including Nature, Nature Materials, Physical Review Letters, and Advanced Materials demonstrating a materials-by-design paradigm to the creation of materials offering electrical control of magnetism.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Optimization and Multimachine Learning Algorithms to Predict Nanometal Surface Area Transfer Parameters for Gold and Silver Nanoparticles

Interactions between gold metallic nanoparticles and molecular dyes have been well described by the nanometal surface energy transfer (NSET) mechanism. However, the expansion and testing of this model for nanoparticles of different metal composition is needed to develop a greater variety of nanosensors for medical and commercial applications. In this study, the NSET formula was slightly modified in the size-dependent dampening constant and skin depth terms to allow for modeling of different metals as well as testing the quenching effects created by variously sized gold, silver, copper, and platinum nanoparticles. Overall, the metal nanoparticles followed more closely the NSET prediction than for Förster resonance energy transfer, though scattering effects began to occur at 20 nm in the nanoparticle diameter. To further improve the NSET theoretical equation, an attempt was made to set a best-fit line of the NSET theoretical equation curve onto the Au and Ag data points. An exhaustive grid search optimizer was applied in the ranges for two variables, 0.1≤C≤2.0 and 0≤α≤4, representing the metal dampening constant and the orientation of donor to the metal surface, respectively. Three different grid searches, starting from coarse (entire range) to finer (narrower range), resulted in more than one million total calculations with values C=2.0 and α=0.0736. The results improved the calculation, but further analysis needed to be conducted in order to find any additional missing physics. With that motivation, two artificial intelligence/machine learning (AI/ML) algorithms, multilayer perception and least absolute shrinkage and selection operator regression, gave a correlation coefficient, R2, greater than 0.97, indicating that the small dataset was not overfitting and was method-independent. This analysis indicates that an investigation is warranted to focus on deeper physics informed machine learning for the NSET equations.

Demers, Steven M. E. (ORCID:0000000192213246)↗
NASA NTRSDate not supplied

Towards and Effective Method for the Analysis of Meteoritic Amides

The study of meteoritic organics in carbonaceous chondrites has shown how these extraterrestrial materials record valuable information about the formation of the Solar System and their potential as sources of starting materials for prebiotic organic synthesis [1]. In this study, a method for the analysis and quantification of aliphatic amides, a class of compounds that may have been precursors for other meteoritic organics, has been optimized and tested.

Jose L Ramirez--Colon↗
NASA NTRSDate not supplied

Developing A Continuous Ozone Record Through the SAGE and Aura Missions With NASA Reanalysis Products

During the last quarter of the 20th century, the Stratospheric Aerosol and Gas Experiment (SAGE) missions were crucial in monitoring the loss and the subsequent recovery of the stratospheric ozone layer. Due to the employed solar occultation and self-calibration method, the SAGE monitors have produced stable data throughout the lifetime of each instrument. However, over ten years passed between the end of the SAGE II and SAGE III/M3M missions in 2005 and the launch of SAGE III/ISS instrument in 2017, leaving a gap in the data that much be bridged in order to assess the trends in the ozone record. Reanalysis products, such as the Modern-Era Retrospective analysis for Research and Applications, version 2 (MERRA-2), are attractive candidates for trend analysis due to the statistically optimized combination of multiple observing systems and the regular temporal and spatial coverage. In this study, we explore using the SAGE records to develop a stable reanalysis data product, suitable for trend analysis, from the start of the SAGE II record in 1984 through the present. Changes in the assimilated observation systems can introduce discontinuities within the MERRA-2 ozone record, such as in 2004 when the MERRA-2 system shifted from assimilating ozone retrievals collected by SBUV instruments to those collected by instruments onboard the Aura satellite. We follow the radiative transfer procedure outlined by Wargan et al. (2018) to address discontinuities in the MERRA-2 ozone dataset at the 2004 transition and during the Aura record. SAGE II ozone profiles are used to address discontinuities in upper stratospheric ozone associated with changes in the MERRA-2 meteorological observing system in 1998 and 1995. Lastly, we will use the resulting bias-corrected MERRA-2 ozone fields to assess the relative performance of the data from different SAGE sensors.

SAGE↗
DOE OSTI2026

Intelligent Experiments through Real-Time AI: Fast Data Processing and Autonomous Detector Control for High-Energy Nuclear Experiments

The aim of this project is to develop software and hardware for fast real-time data processing and autonomous detector control and calibration for the sPHENIX and the future EIC experiments. Below summarizes Georgia Tech team efforts in the past year: 1. We developed a real-time clustering algorithm and FPGA-based pipeline architecture for processing fired pixel data from ALPIDE sensors in sPHENIX experiments. Our Columnar Clustering Co-Design introduces a hardware-aware, stream-friendly approach that segments pixel data by column pairs using a Column Pair Clustering (CPC) strategy, followed by Cluster Stitching to merge adjacent subclusters. Implemented in Vitis HLS, the pipeline comprises five stages—read-in, subclustering, stitching, analysis, and write-out—connected by tagged HLS streams with custom end-of-event signaling for robust synchronization. We designed a pipelined dataflow model optimized for throughput, low latency, and minimal buffering, enabling scalable clustering across events of arbitrary size. Our system maintains spatial precision via center-of-mass and shape key extraction and efficiently handles edge cases such as fragmented or nested clusters. Compared against DBSCAN in both software and hardware, our approach demonstrates competitive performance under FPGA constraints. 2. We also conducted a comprehensive algorithm-to-hardware co-design of connected component analysis tailored for sPHENIX experiments, focusing on real-time, low-latency processing using FPGAs and High-Level Synthesis (HLS). Starting from a Python-based particle tracking pipeline, the team translated the core logic—graph traversal via DFS and Union-Find—into an HLS-compatible C++ model, replacing dynamic memory and recursion with static arrays and pipelined control flow. The final design includes a fully streamed and dataflow-compatible Union-Find kernel optimized across five iterations, incorporating loop pipelining, array partitioning, AXI/FIFO interface tuning, and function flattening. Experimental results show up to 14.8× speedup over the CPU baseline, reducing per-graph latency to 1.58 μs and demonstrating strong resource efficiency with only ~7k LUTs and zero BRAM usage. The design maintains functional correctness against the Python reference using a Python-based C-simulation framework and Mean Squared Error metrics. This work validates the potential of HLS-driven FPGA designs for edge-level HEP data acquisition, laying a scalable foundation for future integration with real-time detector pipelines and multi-graph processing systems.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Experimental study on kinetic oxidation of graphite IG-110 by steam

Graphite is proposed for use in High-temperature Gas-cooled Reactors (HTGRs) as the fuel matrix, neutron moderator/reflector, and core structural material. One important property of nuclear grade graphite is their resistance to oxidation in high-temperature environment. Extensive investigation has been performed in the literature for graphite oxidation by air. However, available experimental data are still limited for graphite oxidation by steam under conditions comparable to a postulated steam ingress accident in HTGRs. In this study, the oxidation rate of graphite IG-110 by steam was measured at temperatures from 850 to 1100 °C with the steam partial pressure varying from 0.5 to 20.0 kPa and the hydrogen partial pressure varying from 0 to 2.0 kPa. Further analysis confirms the oxidation process in this present study is dominated by the chemical kinetics, which lends credit to the data for being used to develop numerical models. It was observed that the increase of the kinetic oxidation rate with the steam partial pressure tends to become less apparent if the steam partial pressure keeps increasing. In addition, it was found that the partitioning of hydrogen inhibits the graphite-steam reaction process even with the steam partial pressure up to 20.0 kPa. However, this inhibiting effect starts to become saturated when the hydrogen partial pressure exceeds 1.0 kPa. The oxidation rates were fitted to the conventional Langmuir-Hinshelwood (LH) and Boltzmann-enhanced Langmuir-Hinshelwood (BLH) models by a multivariable optimization algorithm. The BLH model exhibits a better accuracy than the LH model within the specified experimental conditions. The predicted oxidation rate using the BLH model shows a mean relative difference of about 24% with the maximum difference of about 55% when compared with our experimental data.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

Autonomous Molecular Structure Imaging with High-Resolution Atomic Force Microscopy for Molecular Mixture Discovery

Due to its single-molecule sensitivity, high-resolution atomic force microscopy (HR-AFM) has proved to be a valuable and uniquely advantageous tool to study complex molecular mixtures, which hold promise for developing clean energy and achieving environmental sustainability. However, significant challenges remain to achieve the full potential of the sophisticated and time-consuming experiments. Automation combined with machine learning (ML) and artificial intelligence (AI) is key to overcoming these challenges. Here we present Auto-HR-AFM, an AI tool to automatically collect HR-AFM images of petroleum-based mixtures. In this study, we trained an instance segmentation model to teach Auto-HR-AFM how to recognize features in HR-AFM images. Auto-HR-AFM then uses that information to optimize the imaging by adjusting the probe-molecule distance for each molecule in the run. Auto-HR-AFM is the initial tool that will lead to fully automated scanning probe microscopy (SPM) experiments, from start to finish. This automation will allow SPM to become a mainstream characterization technique for complex mixtures, an otherwise unattainable target.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Towards Generalizable and Efficient Circuit Topology Design: A Graph-Transformer-based Surrogate Model with Curriculum Learning

Unlike circuit parameter and sizing optimizations, the automated design of analog circuit topologies poses significant challenges for learning-based approaches. One challenge arises from the combinatorial growth of the topology space with circuit size, which limits the topology optimization efficiency. Moreover, traditional circuit evaluation methods are time-consuming, while the presence of data discontinuity in the topology space makes the accurate prediction of circuit performance exceptionally difficult for unseen topologies. To tackle these challenges, we design a novel Graph-Transformer-based Network (GTN) as the surrogate model for circuit evaluation, offering a substantial acceleration in the speed of circuit topology optimization without sacrificing performance. Our GTN model architecture is designed to embed voltage changes in circuit loops and current flows in connected devices, enabling accurate performance predictions for circuits with unseen topologies. To address the cold start problem when scaling GTN to large-scale circuits, we further introduce a curriculum learning strategy that progressively trains GTN from small-scale to large-scale circuits. This approach enables the model to first learn fundamental physical principles from simpler topologies and gradually adapt to complex configurations, effectively bridging the circuit complexity gap and improving prediction accuracy. Taking the power converter circuit design as an experimental task, our GTN model significantly outperforms an analytical approach and baseline methods directly utilizing graph neural networks. Furthermore, GTN achieves less than 5% relative error and 196× speed-up compared with high-fidelity simulation. Notably, our GTN surrogate model empowers an automatic circuit design framework to discover circuits of comparable quality to those identified through high-fidelity simulation while reducing the time required by up to 98.2%. With curriculum learning, the enhanced GTN achieves a 51% improvement for performance prediction of large-scale circuits compared to the GTN model without this strategy. These advancements establish GTN as a scalable framework for automated analog circuit design across varying circuit complexity levels.

Lu, Haoshu [New Jersey Institute of Technology (NJ↗