Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “operator complexity”

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 667 records · Page 37
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Building Initial Dynamic System Models for Digital Twins of the Cryogenic Moderator System at the ORNL Spallation Neutron Source

This work describes the initial development of dynamic system models of the cryogenic moderator system (CMS) of the Spallation Neutron Source (SNS) at ORNL as a part of the ORNL LDRD funded project Building TRANSFORM to Accelerate Digital Twin Applications for Nuclear Systems, LOIS 10563. The goal of the work is to start the dynamic system modeling effort with the end goal of using them for real-time applications as digital twins. The CMS is a cryogenic liquid hydrogen flow loop that provides moderation of the neutrons that are generated by the SNS. For optimal neutron production, the CMS needs to maintain a steady and controlled density of cryogenic hydrogen in the moderator section thus requiring precise temperature and pressure control. Due to the varied time scales and system characteristics, control of the system is complex, and diagnostics are also difficult. Difficulty in accessing the flow loop during operations, limited instrumentation and unknown design details of the equipment combine to make the case for having sophisticated digital twin models of the system. Operationally the CMS also provides a strong use case for digital twins due to the constant need of optimization and for troubleshooting/diagnostics. The large amount of data collected which are freely available for using in building the model and verifying and validating the model also makes it a great candidate for a proof-of-concept for digital twins. The project extends ORNL's capacity of development and implementation of the open-source dynamic system modeling tool TRANSFORM for engineering design and digital twin/real-time applications. Specific system configuration data for the CMS have been gathered and an initial dynamic model was created in the TRANSFORM library using Dymola as the solution platform. Models of increasing complexity are created to demonstrate the need for a multi-layered approach in digital twin modeling depending on the scale and phenomena being focused on. The dynamic modeling is shown to bring the dynamic operational aspects to the design process for systems as well as serve as a digital twin to the hardware and allow for models to be tuned and compared against real time operational data. These aims should help to push forward strategic goals of application of digital twins and increase the impact of ORNL systems modeling capabilities with TRANSFORM/Modelica for various advanced energy systems.

42 ENGINEERING↗
DOE OSTI2025

Scalability analysis of heavy-duty gas turbines using data-driven machine learning

With the increasing integration of variable renewable energy sources into power systems, the role of flexible power generation technologies like gas turbines (GT) in rapid grid balancing remains crucial. This sustained importance underscores the need for scaled and precise modeling of GT to ensure effective integration within evolving energy frameworks. While physics-driven GT models integrate thermodynamics, fluid dynamics, and combustion principles, they often rely on approximate mathematical representations to accommodate scaling that may not capture the actual complex dynamics for GTs and inertial effects associated to GTs with different ratings. In this study, a data-driven model is proposed using machine learning (ML) techniques to conduct GT scalability analysis and performance evaluation with high accuracy. The ML model, trained on data from various operating conditions and performance parameters, aims to uncover intricate relationships and patterns, resembling GT characteristics at different scales (ratings). The model is developed to capture complex system interaction and to adapt to changing operational scenarios at different capacities, providing valuable insights of power system dynamics. In this study, the real-time digital simulator platform was employed to generate training data for the ML model and assess its dynamic characteristics. The ultimate objective was to develop a detailed modeling framework based on governing equations and data-driven ML capable of predicting key performance indicators, in thermal systems such as GTs, including power output, speed, fuel consumption, and exhaust temperature under diverse operating conditions at different scales. The developed ML framework demonstrated high accuracy, with mean relative errors for GT power prediction, reference speed, exhaust temperature, and compressor pressure ratio (CPR) parameters consistently below 0.1% across typical load fluctuation scenarios. Maximum deviations were limited to approximately 0.5 K for exhaust temperature and 0.009 for CPR, underscoring the model’s ability to replicating dynamic GT behavior with high precision. The adaptability of the ML model enables its application across diverse operational conditions and its extension to other thermal systems. By leveraging advanced ML techniques, this study presents a robust and scalable modeling framework that enhances GT simulation precision, facilitating improved integration into evolving power systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Technical Assessment of the Application of Digital Twin and Prognostic Tools for Condition Monitoring

This report was prepared for the U.S. Nuclear Regulatory Commission (NRC) to present use cases of the application of advanced technologies toward meeting the current and future regulatory requirements for maintenance and condition monitoring of structures, systems, and components (SSCs). The advanced technologies considered in this work, collectively referred to as digital twin (DT) technologies, are advanced sensors and instrumentation, data analytics, machine learning and artificial intelligence (ML/AI), and physics-based models. The report presents two use cases of reactor coolant pumps (RCPs) and heat pipes in nuclear power plants (NPPs) with technical and regulatory considerations and opportunities in using advanced technologies for conditional monitoring. Key findings from the exploration of these considerations are as follows: - Uncertainties in sensor data and model predictions must be rigorously addressed through validation and verification processes - Regulatory compliance is paramount, necessitating data driven models to be developed in line with existing codes and standards, as well as considering potential future guidelines for advanced reactors - Explainability and transparency in ML/AI models are essential for developing operator trust and regulatory review, including methods that enhance the interpretability of complex data-driven predictions - Condition monitoring programs must be evaluated for their effectiveness in reducing maintenance-preventable function failures (MPFF) and aligning with plant performance criteria - The deployment of advanced technologies for condition monitoring could lead to a transition from periodic to continuous monitoring, thereby optimizing maintenance schedules - Collaborative efforts between industry stakeholders, regulatory bodies, and technology developers are crucial for the successful adoption of advanced technologies for condition monitoring systems in nuclear facilities In summary, the introduction of advanced technologies into condition monitoring programs represents a significant leap forward in the domain of NPP maintenance. By harnessing the capabilities of advanced sensors, data analytics, and ML/AI, NPP operators can transition from a time-based to a condition-based maintenance approach. This shift can potentially enhance the reliability and safety of critical plant components while optimizing maintenance efforts and minimizing unnecessary outages. The NRC is continuing to explore the regulatory aspects of advanced technologies as part of inservice inspection and inservice testing (ISI and IST) programs by pursuing additional research in this technical area.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

DLMP of Competitive Markets in Active Distribution Networks: Models, Solutions, Applications, and Visions

Traditionally, the electric distribution system operates with uniform energy prices across all system nodes. However, as the adoption of distributed energy resources (DERs) propels a shift from passive to active distribution network (ADN) operation, a distribution-level electricity market has been proposed to manage new complexities efficiently. In addition, distribution locational marginal price (DLMP) has been established in the literature as the primary pricing mechanism. The DLMP inherits the LMP concept in the transmission-level wholesale market but incorporates characteristics of the distribution system, such as high $R/X$ ratios and power losses, system imbalance, and voltage regulation needs. The DLMP provides a solution that can be essential for competitive market operation in future distribution systems. This article first provides an overview of the current distribution-level market architectures and their early implementations. Next, the general clearing model, model relaxations, and DLMP formulation are comprehensively reviewed. The state-of-the-art solution methods for distribution market clearing are summarized and categorized into centralized, distributed, and decentralized methods. Then, DLMP applications for the operation and planning of DERs and distribution system operators (DSOs) are discussed in detail. Finally, visions of future research directions and possible barriers and challenges are presented.

42 ENGINEERING↗
DOE OSTI2020

Allocation and Operation of A Hydropneumatic Energy Storage with Building Microgrid

Behind-meter application for a recently invented hydropneumatic Ground-Level Integrated Diverse Energy Storage (GLIDES) is focused in this research. Considering possible uncertainties from solar radiation and electricity load in a building microgrid, two-stage stochastic programming is adopted for 15-min operation and a mixed-integer nonlinear stochastic model is built with integrated energy systems of GLIDES, solar panel and power generating unit. In order to make the model computationally tractable, we use sample average approximate method to decrease associated complexity with sample size and improve solving efficiency. The experimental results in deterministic and stochastic operation indicate that best candidate solution from SAA are superior to the solution from expected value problem in terms of optimality gap and variance.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Phenomena Identification and Ranking Tables for High Temperature Gas-Cooled Microreactors

Micro-scaled high-temperature gas-cooled reactors (micro-HTGRs) offer a promising option for reliable power in remote or off-grid locations. While the safety characteristics of modular HTGRs have been widely studied, a micro-HTGR configuration alters several key thermal-fluid phenomena that govern both normal operation and passive decay-heat removal. In many proposed concepts, the reactor vessel is oriented horizontally and integrated into an ISO shipping container to enhance transportability and modular deployment. This report documents a Phenomena Identification and Ranking Table (PIRT) exercise focused on the thermal hydraulic safety phenomena relevant to all micro-HTGRs. The objective is to systematically identify, describe, and rank the importance, uncertainty, and modeling complexity of the key phenomena that control core and vessel temperatures during normal operation, pressurized conduction cooldown (PCC), and depressurized conduction cooldown (with air ingress) conditions.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Improving durability and performance of solid oxide electrolyzers by controlling surface composition on oxygen electrodes

Solid oxide electrolysis cell (SOEC) is a promising technology for high-efficiency energy conversion, enabling the production of hydrogen, syngas, synthetic fuels, and various commodity chemicals. Unlike traditional thermochemical processes, SOECs operate at elevated temperatures (600-850°C), benefiting from favorable thermodynamics and reaction kinetics. This makes them highly energy efficient compared to alkaline or polymer electrolyte membrane (PEM) electrolysis technologies. However, despite these advantages, SOECs face significant challenges related to performance degradation over time. A primary issue is the degradation of the oxygen electrode due to strontium (Sr) segregation and impurity poisoning from chromium (Cr) and sulfur (S). This is because the pathway to deposition of Cr and S include the reaction of Cr and S with the segregated SrO at the surface. Sr segregation leads to the formation of insulating compounds such as SrCrO4 and SrSO4, which block active sites, reduce oxygen exchange rates, and compromise the electrode's electrochemical stability. The degradation mechanisms involve complex interactions between the electrode material's surface chemistry, microstructure, and the operating environment. Sr segregation is particularly problematic because it facilitates the deposition of Cr and S impurities, exacerbating performance losses. Addressing these issues is critical to enhancing the durability and economic viability of SOEC technology. The primary goal of this project is to improve the durability and performance of SOECs by controlling the surface composition of the oxygen electrode. This is achieved by suppressing Sr segregation, thereby mitigating impurity poisoning pathways. The project aims to enhance the oxygen exchange rate, improve cell stability, and extend the operational lifespan of SOECs without necessitating major changes to electrode chemistry or stack components.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2020

The Molybdenum Oxide Interface Limits the High-Temperature Operational Stability of Unencapsulated Perovskite Solar Cells

Here, we report on the improved operational stability of unencapsulated perovskite solar cells (PSCs) aged in an ambient atmosphere at elevated temperatures (70 °C) for >1000 h under constant illumination and bias at 30–50% relative humidity. We identify a previously unseen interfacial degradation mechanism concerning the use of a MoO x interlayer, which was originally added to increase operational stability. Specifically, the hole-transport layer/MoO x interface buckles under illumination at 70 °C, which leads to delamination and rapid losses of short-circuit current density corresponding to an average $t_{80}$ of ~55 h. By judiciously evaluating various hole-transport layers, interlayers, and contacts, we find that replacing the MoO x with a VO x interlayer, regardless of the other components in the solar cell, alleviates this buckling issue due to its higher activation barrier toward crystallization, leading to significant gains in PSC operational stability. Unencapsulated devices aged in an ambient atmosphere with a VO x interlayer retain 71% of their initial PCE on average after constant illumination and bias at 70 °C for 1100 h ($t_{80}$ ~ 645 h). Currently, this is the highest temperature reported for the operational stability of unencapsulated n-i-p PSCs aged in air. Identification of a new facet of the complex degradation mechanisms in PSCs will allow for targeted acceleration testing to speed the deployment of low-cost, long-lasting electricity generation under realistic operating temperatures.

14 SOLAR ENERGY↗
DOE OSTI2024

Scale-bridging Optimization Framework for Desalination Integrated Produced Water Networks

Produced water (PW) management poses a major challenge to U.S. oil and gas development. Due to freshwater scarcity and PW injection curtailments, desalination may become a necessity in some parts of the country. Integrating rigorous desalination process models within a produced water network for co-optimization of desalination design and network operation can be challenging to scale-up due to computational complexity. In this work we use the trust region filter framework to decompose the integrated optimization problem into an optimization master problem consisting of the network model and simplified surrogates for the desalination units and an optimization sub problem for the rigorous desalination unit model. The approach is demonstrated on a multiperiod produced water network from the PARETO library with thermal desalination units.

Naik, Sakshi↗
DOE OSTI2020

Medium Energy Electron Flux in Earth's Outer Radiation Belt (MERLIN): A Machine Learning Model

The radiation belts of the Earth, filled with energetic electrons, comprise complex and dynamic systems that pose a significant threat to satellite operation. While various models of electron flux both for low and relativistic energies have been developed, the behavior of medium energy (120–600 keV) electrons, especially in the MEO region, remains poorly quantified. At these energies, electrons are driven by both convective and diffusive transport, and their prediction usually requires sophisticated 4D modeling codes. In this paper, we present an alternative approach using the Light Gradient Boosting (LightGBM) machine learning algorithm. The Medium Energy electRon fLux In Earth's outer radiatioN belt (MERLIN) model takes as input the satellite position, a combination of geomagnetic indices and solar wind parameters including the time history of velocity, and does not use persistence. MERLIN is trained on >15 years of the GPS electron flux data and tested on more than 1.5 years of measurements. Tenfold cross validation yields that the model predicts the MEO radiation environment well, both in terms of dynamics and amplitudes o f flux. Evaluation on the test set shows high correlation between the predicted and observed electron flux (0.8) and low values of absolute error. The MERLIN model can have wide space weather applications, providing information for the scientific community in the form of radiation belts reconstructions, as well as industry for satellite mission design, nowcast of the MEO environment, and surface charging analysis.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Nonlinear ionization dynamics of hot dense plasma observed in a laser-plasma amplifier

Understanding the behaviour of matter under conditions of extreme temperature, pressure, density and electromagnetic fields has profound effects on our understanding of cosmologic objects and the formation of the universe. Lacking direct access to such objects, our interpretation of observed data mainly relies on theoretical models. However, such models, which need to encompass nuclear physics, atomic physics and plasma physics over a huge dynamic range in the dimensions of energy and time, can only provide reliable information if we can benchmark them to experiments under well-defined laboratory conditions. Due to the plethora of effects occurring in this kind of highly excited matter, characterizing isolated dynamics or obtaining direct insight remains challenging. High-density plasmas are turbulent and opaque for radiation below the plasma frequency and allow only near-surface insight into ionization processes with visible wavelengths. Here, the output of a high-harmonic seeded laser-plasma amplifier using eight-fold ionized krypton as the gain medium operating at a 32.8 nm wavelength is ptychographically imaged. A complex-valued wavefront is observed in the extreme ultraviolet (XUV) beam with high resolution. Ab initio spatio-temporal Maxwell–Bloch simulations show excellent agreement with the experimental observations, revealing overionization of krypton in the plasma channel due to nonlinear laser-plasma interactions, successfully validating this four-dimensional multiscale model. This constitutes the first experimental observation of the laser ion abundance reshaping a laser-plasma amplifier. The presented approach shows the possibility of directly modelling light-plasma interactions in extreme conditions, such as those present during the early times of the universe, with direct experimental verification.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Distributed deep learning training using silicon photonic switched architectures

The scaling trends of deep learning models and distributed training workloads are challenging network capacities in today’s datacenters and high-performance computing (HPC) systems. We propose a system architecture that leverages silicon photonic (SiP) switch-enabled server regrouping using bandwidth steering to tackle the challenges and accelerate distributed deep learning training. In addition, our proposed system architecture utilizes a highly integrated operating system-based SiP switch control scheme to reduce implementation complexity. To demonstrate the feasibility of our proposal, we built an experimental testbed with a SiP switch-enabled reconfigurable fat tree topology and evaluated the network performance of distributed ring all-reduce and parameter server workloads. The experimental results show up to 3.6× improvements over the static non-reconfigurable fat tree. Our large-scale simulation results show that server regrouping can deliver up to 2.3× flow throughput improvement for a 2× tapered fat tree and a further 11% improvement when higher-layer bandwidth steering is employed. The collective results show the potential of integrating SiP switches into datacenters and HPC systems to accelerate distributed deep learning training.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Comprehensive Analysis of Streaming and Shutdown Dose Rate Experiments at JET with ORNL Fusion Neutronics Workflows

Current experimental fusion systems and conceptual designs of fusion pilot plants (FPPs) are growing in complexity and size. Several radiation metrics are crucial to the safe operation of fusion machines, including neutron flux streaming through openings and the shutdown dose rate (SDDR). Most current designs of advanced experimental fusion systems—and the most probable candidates for FPPs—are based on the tokamak concept, which is prone to neutron streaming through the myriad openings needed for diagnostic and support systems. SDDR is caused by decay gamma rays from radionuclides that become activated by neutrons during the operation of a fusion system that use deuterium-deuterium (DD), tritium-tritium, or deuterium-tritium plasma. Because computational tools have become essential for determining these radiation metrics, they must be validated against reliable and applicable experimental data. Experiments at the Joint European Torus (JET) provide a unique source of experimental data for validating computational tools and nuclear data used to determine SDDR and neutron fluxes in streaming-dominated geometries. Here, this paper presents the comprehensive analysis of the high-performance DD JET SDDR, and streaming experiments performed using Oak Ridge National Laboratory (ORNL) fusion workflows. The computational results were compared with experimental results that consist of online SDDR measurements with ionization chambers and neutron fluence streaming measurements using thermoluminescent detectors. The ratio of calculated-to-experimental SDDR values ranges from 0.6 to 2.5, and the streaming results range from 0.5 to 8.0. Future work will include analyzing the JET 2021 DTE2 campaign alongside the integration of the Shift Monte Carlo transport code into all ORNL fusion neutronics workflows.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Toward simulating quantum field theories with controlled phonon-ion dynamics: A hybrid analog-digital approach

Quantum field theories are the cornerstones of modern physics, providing relativistic and quantum mechanical descriptions of physical systems at the most fundamental level. Simulating real-time dynamics within these theories remains elusive in classical computing. This provides a unique opportunity for quantum simulators, which hold the promise of revolutionizing our simulation capabilities. Trapped-ion systems are successful quantum-simulator platforms for quantum many-body physics and can operate in digital, or gate-based, and analog modes. Inspired by the progress in proposing and realizing quantum simulations of a number of relativistic quantum field theories using trapped-ion systems, and by the hybrid analog-digital proposals for simulating interacting boson-fermion models, we propose hybrid analog-digital quantum simulations of selected quantum field theories, taking recent developments to the next level. On one hand, the semi-digital nature of this proposal offers more flexibility in engineering generic model interactions compared with a fully-analog approach. On the other hand, encoding the bosonic fields onto the phonon degrees of freedom of the trapped-ion system allows a more efficient usage of simulator resources, and a more natural implementation of intrinsic quantum operations in such platforms. This opens up new ways for simulating complex dynamics of e.g., Abelian and non-Abelian gauge theories, by combining the benefits of digital and analog schemes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Instrumentation and methods for efficient time-resolved X-ray crystallography of biomolecular systems with sub-10 ms time resolution

Time-resolved X-ray crystallography has great promise to illuminate structure–function relations and key steps of enzymatic reactions with atomic resolution. The dominant methods for chemically-initiated reactions require complex instrumentation at the X-ray beamline, significant effort to operate and maintain this instrumentation, and enormous numbers (∼10 5 –10 9 ) of crystals per time point. We describe instrumentation and methods that enable high-throughput time-resolved study of biomolecular systems using standard crystallography sample supports and mail-in X-ray data collection at standard high-throughput cryocrystallography synchrotron beamlines. The instrumentation allows rapid reaction initiation by mixing of crystals and substrate/ligand solution, rapid capture of structural states via thermal quenching with no pre-cooling perturbations, and yields time resolutions in the single-millisecond range, comparable to the best achieved by any non-photo-initiated method in both crystallography and cryo-electron microscopy. Our approach to reaction initiation has the advantages of simplicity, robustness, low cost, adaptability to diverse ligand solutions and small minimum volume requirements, making it well suited to routine laboratory use and to high-throughput screening. We report the detailed characterization of instrument performance, present structures of binding of N -acetylglucosamine to lysozyme at time points from 8 ms to 2 s determined using only one crystal per time point, and discuss additional improvements that will push time resolution toward 1 ms.

Indergaard, John A. (ORCID:000000022367699X)↗
DOE OSTI2024

Uncertainty-Aware, Structure-Preserving Machine Learning Approach for Domain Shift Detection From Nonlinear Dynamic Responses of Structural Systems

Complex structural systems deployed for aerospace, civil, or mechanical applications must operate reliably under varying operational conditions. Structural health monitoring (SHM) systems help ensure the reliability of these systems by providing continuous monitoring of the state of the structure. SHM relies on synthesizing measured data with a predictive model to make informed decisions about structural states. However, these models—which may be thought of as a form of a digital twin—need to be updated continuously as structural changes (e.g., due to damage) arise. We propose an uncertainty-aware machine learning model that enforces distance preservation of the original input state space and then encodes a distance-aware mechanism via a Gaussian process (GP) kernel. The proposed approach leverages the spectral-normalized neural GP algorithm to combine the flexibility of neural networks with the advantages of GP, subjected to structure-preserving constraints, to produce an uncertainty-aware model. This model is used to detect domain shift due to structural changes that cannot be observed directly because they may be spatially isolated (e.g., inside a joint or localized damage). This work leverages detection theory to detect domain shift systematically given statistical features of the prediction variance produced by the model. The proposed approach is demonstrated on a nonlinear structure being subjected to damage conditions. In conclusion, it is shown that the proposed approach is able to rely on distances of the transformed input state space to predict increased variance in shifted domains while being robust to normative changes.

Algorithms↗
DOE OSTI2022

Effect of Thermal Expansion Coefficient, Viscosity and Melting Range in Simulation of PCM Embedded Heat Exchangers With and Without Fins

Phase change material heat exchangers (PCMHX) have an important role in integrating renewable energy systems. PCMHX can offer high storage density at various temperatures of interest and can be used for grid load shifting purposes. Numerical models enable engineers to estimate PCMHX performance for different design parameters and operating conditions. Modeling phase change phenomena is challenging due to the complex time-dependent nature of the process. The accuracy of models is highly sensitive to PCM thermo-physical properties. Thermal expansion coefficient (β), viscosity (μ) and melting temperature range (MR) of a PCM are important properties, especially when natural convection is not negligible. In PCMHX modeling, using less than accurate values for these properties can have significant impact on the simulation outcomes. These properties and discussions thereof are not readily available in the literature. This paper presents a brief review of the literature and a numerical study investigating the model sensitivity to the above-mentioned properties for PCMHX with and without fins. CFD is used to evaluate the charging (melting) phenomena. The study quantifies the impact of uncertainty in these properties on the melting rate and temperature profile. Constant wall temperature was considered as heat source with no heat loss to ambient. Here, the results show that β and μ has significant effect on the melting rate and evolution of the melting front. For a non-finned domain when comparing results for different published values of β and μ, the deviation in melting time can be up to 12.9% and 57.6% respectively. For high wall temperatures, change in melting range did not impact melting time. But when the wall temperature is reduced, up to 9.8% deviation in melting time is observed.

CFD↗
DOE OSTI2025

Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker–Planck Equations

The Fokker-Planck (FP) equation is a foundational partial differential equation (PDE) in stochastic processes involving Brownian motions. However, the curse of dimensionality (CoD) poses a formidable challenge when dealing with high-dimensional FP equations. Although Monte Carlo simulation and (vanilla) Physics-Informed Neural Networks (PINNs) have shown the potential to tackle CoD, both methods exhibit significant numerical errors in high dimensions when dealing with the probability density function (PDF) associated with Brownian motion. The point-wise PDF values tend to decrease exponentially as dimensionality increases, surpassing the precision of numerical simulations and resulting in substantial errors. In addition, due to its massive sampling, Monte Carlo fails to offer fast sampling. Modeling the logarithm likelihood (LL) via vanilla PINNs transforms the FP equation into a notoriously difficult Hamilton-Jacobi-Bellman (HJB) equation, which is impractical for PINN learning, whose error grows rapidly with dimension. To this end, we propose a novel approach utilizing a score-based solver to fit the score function in stochastic differential equations (SDEs). The score function, defined as the gradient of the LL, plays a fundamental role in inferring LL and PDF and enables fast SDE sampling, offering an effective means to overcome the CoD. Three fitting methods, Score Matching (SM), Sliced Score Matching (SSM), and Score-PINN, are introduced, each contributing unique advantages in computational complexity, accuracy, and generality. The proposed score-based SDE solver operates in two stages: first, employing score matching or Score-PINN to acquire the score function; and second, solving the LL via an ordinary differential equation (ODE) using the obtained score function. Comparative evaluations across these methods showcase varying trade-offs. The proposed methodology is evaluated across diverse SDEs, including anisotropic Ornstein-Uhlenbeck processes, geometric Brownian motion, and Brownian motion with varying eigenspace. We also test various distributions, including Gaussian, Log-normal, Laplace, and Cauchy distributions. The numerical results demonstrate the score-based SDE solver’s stability, speed, and performance across different experimental settings, solidifying its potential as a solution to CoD for high-dimensional FP equations.

97 MATHEMATICS AND COMPUTING↗