Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data driven optimization”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 685 records · Page 38
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

High-Throughput Microstructural Characterization and Process Correlation Using Automated Electron Backscatter Diffraction

The need to optimize the processing conditions of additively manufactured (AM) metals and alloys has driven advances in throughput capabilities for material property measurements such as tensile strength or hardness. High-throughput (HT) characterization of AM metal microstructure has fallen significantly behind the pace of property measurements due to intrinsic bottlenecks associated with the artisan and labor-intensive preparation methods required to produce highly polished surfaces. This inequality in data throughput has led to a reliance on heuristics to connect process to structure or structure to properties for AM structural materials. In this study, we show a transformative approach to achieve laser powder bed fusion (LPBF) printing, HT preparation using dry electropolishing and HT electron backscatter diffraction (EBSD). This approach was used to construct a library of > 600 experimental EBSD sample sets spanning a diverse range of LPBF process conditions for AM Kovar. This vast library is far more expansive in parameter space than most state-of-the-art studies, yet it required only approximately 10 labor hours to acquire. Build geometries, surface preparation methods, and microscopy details, as well as the entire library of >600 EBSD data sets over the two sample design versions, have been shared with intent for the materials community to leverage the data and further advance the approach. Using this library, we investigated process–structure relationships and uncovered an unexpected, strong dependence of microstructure on location within the build, when varied, using otherwise identical laser parameters.

Characterization and Analytical Technique↗
DOE OSTI2024

Deep learning of experimental electrochemistry for battery cathodes across diverse compositions

Artificial intelligence (AI) has emerged as a tool for discovering and optimizing novel battery materials. However, the adoption of AI in battery cathode representation and discovery is still limited due to the complexity of optimizing multiple performance properties and the scarcity of high-fidelity data. Here, we present a machine learning model (DRXNet) for battery informatics and demonstrate the application in the discovery and optimization of disordered rocksalt (DRX) cathode materials. We have compiled the electrochemistry data of DRX cathodes over the past 5 years, resulting in a dataset of more than 19,000 discharge voltage profiles on diverse chemistries spanning 14 different metal species. Learning from this extensive dataset, our DRXNet model can capture critical features in the cycling curves of DRX cathodes under various conditions. Our approach offers a data-driven solution to facilitate the rapid identification of novel cathode materials, accelerating the development of next-generation batteries for carbon neutralization.

25 ENERGY STORAGE↗
DOE OSTI2025

Expediting field-effect transistor chemical sensor design with neuromorphic spiking graph neural networks

Improving the sensitive and selective detection of analytes in a variety of applications requires accelerating the rational design of field-effect transistor (FET) chemical sensors. Achieving high-performance detection relies on identifying optimal probe materials that can effectively interact with target analytes, a process traditionally driven by chemical intuition and time-consuming trial-and-error methods. To address the difficulties in probe screening for FET sensor development, this work presents a methodology that combines neuromorphic machine learning (ML) architectures, specifically a hybrid spiking graph neural network (SGNN), with an enriched dataset of physicochemical properties through semi-automated data extraction using large language models. Achieving a classification accuracy of 0.89 in predicting sensor sensitivity categories, the SGNN model outperformed traditional ML techniques by leveraging its ability to capture both global physicochemical properties and sparse topological features through a hybrid modeling framework. Next-generation sensor design was informed by the actionable insights into the connections between material properties and sensing performance offered by the SGNN framework. Through virtual screening for the detection of per- and polyfluoroalkyl substances (PFAS) as a use case, the effectiveness of the SGNN model was further validated. Density functional theory simulations confirmed graphene as a promising active material for PFAS detection as suggested by the SGNN framework. By bridging gaps in predictive modeling and data availability, this integrated approach provides a strong foundation for accelerating advancements in FET sensor design and innovation.

Ferreira, Rodrigo Pires [Univ. of Chicago, IL (Uni↗
NASA NTRS2026

Hydrology Copilot: A Cloud-Native Ai System for Hydrological Data Analysis

The emergence of AI-driven Earth observation systems promises to broaden access to petabyte-scale geospatial data beyond domain specialists. However, translating this vision into operational scientific infrastructure requires addressing fundamental challenges in data virtualization, code transparency, and domain-specific reasoning. We present Hydrology Copilot, a cloud-native AI framework for natural-language-driven analysis of Earth observation data. To demonstrate operational capabilities at scale, we implement the system using NASA's North American Land Data Assimilation System version 3 (NLDAS-3), which provides surface meteorological forcing and land-surface model output across North and Central America at 1-km resolution, from which drought diagnostics are derived. The system integrates five core contributions: (1) scalable data virtualization using Kerchunk-based cloud optimized access, achieving a 1.5 to 4.6 times improvement in I/O latency across benchmark queries spanning regional single-day extractions (4.6 times speedup) to continental monthly aggregations (1.5 times speedup); (2) transparent code generation through Microsoft Azure AI Foundry agents that expose executable Python workflows for scientific verification; (3) persistent conversational memory enabling multi-turn analytical discourse across sessions; (4) intelligent query validation that enforces dataset boundaries and resolves ambiguous requests before execution; and (5) a multi-agent architecture coordinating query parsing, code generation, and visualization. We evaluate the system through drought-monitoring workflows, demonstrating reliable code generation, accurate results validated against reference computations and the operational U.S. Drought Monitor, and efficient operation across increasingly complex tasks. By bridging natural-language interfaces with rigorous hydrological analysis, Hydrology Copilot advances beyond proof-of-concept demonstrations to provide a deployable framework for operational Earth science applications.

Data virtualization↗
NASA NTRS1972

Supervisory sampling and control: Sources of suboptimality in a prediction task

A process supervisor is defined as a person who decides when to sample the process input and what values of a control variable to specify in order to maximize (minimize) a given value function of input sampling period, control setting, and process state. Presented experimental data in such a process where the value function is a time-averaged sampling cost plus mean squared difference between input and control variable. The task was unpaced prediction of the output of a second order filter driven by white noise. Experimental results, when compared to the optical strategy, reveal several consistently suboptimal behaviors. One is a tendency not to choose a long prediction interval even though the optimal strategy dictates that one should. Some results are also interpreted in terms of those input parameters according to which each subjects' behavior would have been nearest optimal. Differences of those parameters from actual input parameters served to quantify how subjects' prediction behavior differed from optimal.

Sheridan, T. B.↗
NASA NTRS2005

International Space Station Electric Power System Performance Code-SPACE

The System Power Analysis for Capability Evaluation (SPACE) software analyzes and predicts the minute-by-minute state of the International Space Station (ISS) electrical power system (EPS) for upcoming missions as well as EPS power generation capacity as a function of ISS configuration and orbital conditions. In order to complete the Certification of Flight Readiness (CoFR) process in which the mission is certified for flight each ISS System must thoroughly assess every proposed mission to verify that the system will support the planned mission operations; SPACE is the sole tool used to conduct these assessments for the power system capability. SPACE is an integrated power system model that incorporates a variety of modules tied together with integration routines and graphical output. The modules include orbit mechanics, solar array pointing/shadowing/thermal and electrical, battery performance, and power management and distribution performance. These modules are tightly integrated within a flexible architecture featuring data-file-driven configurations, source- or load-driven operation, and event scripting. SPACE also predicts the amount of power available for a given system configuration, spacecraft orientation, solar-array-pointing conditions, orbit, and the like. In the source-driven mode, the model must assure that energy balance is achieved, meaning that energy removed from the batteries must be restored (or balanced) each and every orbit. This entails an optimization scheme to ensure that energy balance is maintained without violating any other constraints.

Hojnicki, Jeffrey↗
DOE OSTI2025

Physics-informed machine learning for building performance simulation-A review of a nascent field

Building performance simulation (BPS) is critical for understanding building dynamics and behavior, analyzing the performance of the built environment, optimizing energy efficiency, improving demand flexibility, and enhancing building resilience. However, conducting BPS is not trivial. Traditional BPS relies on accurate building energy models, which are primarily physics-based and heavily dependent on detailed building information, expert knowledge, and case-by-case model calibrations, significantly limiting their scalability. With the development of sensing technology and the increased availability of data, there is growing attention and interest in data-driven BPS. However, purely data-driven models often suffer from limited generalization ability and a lack of physical consistency, resulting in poor performance in real-world applications. To address these limitations, recent studies have begun integrating physics priors into data-driven models, a methodology known as physics-informed machine learning (PIML). PIML is an emerging field where its definitions, methodologies, evaluation criteria, application scenarios, and future directions remain open. To bridge those gaps, this study systematically reviews the state-of-the-art PIML for BPS, offering a comprehensive definition of PIML and comparing it to traditional BPS approaches regarding data requirements, modeling effort, performance, and computational cost. We also summarize the commonly used methodologies, validation approaches, application domains, available data sources, open-source packages, and testbeds. In addition, this study provides a general guideline for selecting appropriate PIML models based on BPS applications. Finally, this study identifies key challenges and outlines future research directions, providing a solid foundation and valuable insights to advance R&D of PIML in BPS.

Jiang, Zixin↗
DOE OSTI2025

From bench to biofactory: high-throughput technologies and automated workflows to accelerate biomanufacturing

Microbial production of target molecules has advanced significantly in recent years driven by innovations in enzyme engineering, DNA synthesis, and genomic editing. However, to access the massive potential of microbial production, a vast parametric space remains to be investigated to optimize these biobased processes for a robust bioeconomy. Here, we review the current state of the art, some key challenges and possible solutions. We see a critical role of automation, high-throughput technologies, self-driving and cloud labs, and data management to enable Artificial Intelligence/Machine Learning and mechanistic models to overcome the design space challenges and accelerate the development of novel bio-based solutions. Accurate models will expedite the development and scale-up of engineered microbes for a range of final products from many starting materials.

Petzold, Christopher J↗
DOE OSTI2025

Uncovering multiscale structure-property correlations via active learning in scanning tunneling microscopy

Atomic arrangements and local sub-structures fundamentally influence emergent material functionalities. These structures are conventionally probed using spatially resolved studies and the property correlations are deciphered by a researcher based on sequential explorations, thereby limiting the efficiency and scope. Here we demonstrate a multi-scale Bayesian deep-learning based framework that automatically correlates material structure with its electronic properties using scanning tunneling microscopy (STM) measurements in real-time. Its predictions are used to autonomously direct exploration toward regions of the sample that optimize a given material property. This method is deployed on a low-temperature ultra-high vacuum STM to understand the structure-property relationship in a europium-based semimetal, EuZn 2 As 2 , a promising candidate relevant to magnetism-driven topological phenomena. The framework employs a sparse-sampling approach to efficiently construct the scalar-property space using minimal measurements, about 1–10% of the data required in standard hyperspectral methods. Moreover, we formulate the problem hierarchically across length scales, implementing autonomous workflow to locate mesoscopic and atomic structures that correspond to a target material property. This framework offers the choice to design scalar-property from the spectroscopic data to steer sample exploration. Our findings reveal correlations of the electronic properties unique to surface terminations, local defect density, and point defects.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Development of Steady-State and Dynamic Mass and Energy Constrained Neural Networks for Distributed Chemical Systems Using Noisy Transient Data

The paper presents the development of algorithms for mass and energy constrained neural network models that can exactly conserve the overall mass and energy of distributed chemical process systems, even though the noisy transient data used for optimal model training violate the same. In contrast to approximately satisfying mass and energy balance constraints of a system by soft penalization of objective function, algorithms have been developed for solving equality-constrained nonlinear optimization problems, thus providing the guarantee of exactly satisfying the system mass and energy conservation laws. For developing dynamic mass-energy constrained network models for distributed systems, hybrid series and parallel dynamic-static neural networks have been leveraged. The developed algorithms for solving both the training and forward problems are validated using both steady-state and dynamic data in the presence of various noise characteristics. The developed data-driven algorithms are flexible to exactly satisfy mass and energy balance constraints for dynamic chemical processes if the system holdup information is available. The proposed network structures and algorithms are applied to the development of data-driven lumped and distributed models of an adiabatic superheater/reheater system, a nonisothermal continuous stirred tank reactor, as well as an electrically heated plug-flow reactor system where one form of energy gets transformed to another. It has been observed that the mass-energy constrained neural networks yield a root mean squared error of <1% with respect to the system truth for the case studies evaluated in this work.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2000

Qualitative Discovery in Medical Databases

Implication rules have been used in uncertainty reasoning systems to confirm and draw hypotheses or conclusions. However a major bottleneck in developing such systems lies in the elicitation of these rules. This paper empirically examines the performance of evidential inferencing with implication networks generated using a rule induction tool called KAT. KAT utilizes an algorithm for the statistical analysis of empirical case data, and hence reduces the knowledge engineering efforts and biases in subjective implication certainty assignment. The paper describes several experiments in which real-world diagnostic problems were investigated; namely, medical diagnostics. In particular, it attempts to show that: (1) with a limited number of case samples, KAT is capable of inducing implication networks useful for making evidential inferences based on partial observations, and (2) observation driven by a network entropy optimization mechanism is effective in reducing the uncertainty of predicted events.

Maluf, David A.↗
NASA NTRSDate not supplied

Next Generation Exercise Device (NGED): Advancing Exercise Capabilities for Future Space Missions Through Biomechanical Modeling

BACKGROUND As space exploration extends to long-duration missions on the Moon and Mars, maintaining astronaut health and fitness becomes increasingly critical. The Next Generation Exercise Device (NGED), developed and tested by the HumanWorks Lab in NASA Johnson Space Center's (JSC) Software, Robotics, and Simulation Division, aims to address this challenge through innovative approaches. This study presents the development and evaluation of an NGED system, focusing on its adaptability to various mission scenarios, including prospective use in a Lunar Pressurized Rover (LPR). Central to this project is the application of biomechanical modeling to optimize exercise efficacy and safety in microgravity and partial gravity environments. The project is a collaborative effort with the Human Health and Performance group at Johnson Space Center, ensuring a comprehensive approach to astronaut well-being that integrates biomechanical principles with practical exercise solutions. The NGED represents the next generation of exercise capabilities for missions in space, on the Moon and Mars, with a specific focus on applications such as the LPR. METHODS AND RESULTS Data collection for NGED development was conducted with two motor-driven Beyond Power Voltra I [1] systems and a custom test structure to allow placement of the cable-based devices on the ground, at shoulder height, and overhead. The collection was performed in JSC’s Prototype Immersive Technology (PIT) Lab, utilizing an OptiTrack motion capture system and AMTI force platform, to enable detailed biomechanical analysis via OpenSim [2,3]. Motion capture data were collected for three subjects representing different body types and statures. The marker set used was an enhanced version of the full-body Plug-in Gait marker set [4], with additional markers strategically placed for the primary objective of informing exercise volume requirements. Subjects performed a series of 17 exercises, carefully selected to engage various muscle groups, including novel spaceflight exercises such as skiing (ergometer style), lateral pulldowns, wood chops, triceps extensions, and flies, with load variations ranging from 10 to 90 pounds to maintain kinematic form. This comprehensive approach allowed for a thorough evaluation of the NGED's performance across a wide range of motions and loads. The biomechanical modeling and analysis were conducted using a modified OpenSim Full Body Rajagopal Model [4,5] and also scaled to the maximum and minimum anthropometry provided in NASA-STD-3001 [6]. Volumetric convex hulls were generated based on model marker trajectories and aggregated into geometric assemblies. These can be placed in models of vehicle designs to assess fit to protect for exercise as well as to adapt NGED exercise to fit available space. Preliminary findings from the collection indicate that the NGED prototype demonstrates significant adaptability across varying user anthropometrics and exercise types. The device showed consistent performance in load-bearing exercises, with subjects able to perform exercises effectively while maintaining proper biomechanical form. CONCLUSION NGED represents a forward-looking advancement in exercise capabilities for future space missions. In the future, this system can be used to capture valuable metrics (e.g., isometric mid-thigh pull for force output measurements, assessments of postural muscle strength, overall isometric strength). Its versatility in accommodating various exercises and user physiques, coupled with the ability to provide targeted biomechanical loading, makes it a promising approach for maintaining astronaut health during long-duration missions to the Moon and Mars. Future work will focus on refining the NGED based on initial biomechanical findings, leveraging the detailed insights provided by motion capture and analysis techniques. Particular emphasis will be placed on optimizing its use within the confined spaces of a LPR and other space habitats. This work contributes significantly to NASA's goals of supporting human health and performance in deep space exploration, paving the way for sustainable long-term presence beyond Low Earth Orbit through advanced, biomechanically-informed exercise solutions.

C Wang↗
DOE OSTI2024

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. Here, in this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.

artificial intelligence↗
DOE OSTI2025

A hybrid surrogate modeling framework for the Digital Twin of a Fluoride-salt-cooled High-temperature Reactor (FHR)

While nuclear energy is a non-greenhouse-gas emitting energy source, expensive operational costs due to the high-level of safety requirements decreases their competitiveness in the sustainable energy market. Advanced reactor concepts paired with Digital Twins aim to increase the commercialization gains of nuclear energy by reducing operational costs, increasing reactor reliability and enhancing power generation. To support Digital Twin tasks such as real-time autonomous control, proactive maintenance monitoring or optimizing power demand operations, a fast and accurate virtual representation of the Nuclear Power Plant (NPP) is required. The computational cost of high-fidelity, physics-based models are unsuitable for real-time analysis or scalability. Here, in this work, a hybrid surrogate modeling framework is developed fora Fluoride-salt-cooled High-temperature Reactor (FHR) that leverages physics-inspired models for key reactor components and uses data-driven methods for rapid system state space prediction. The Xenon reactivity feedback model is integrated to inform the surrogate model about the reactor core and the homologous pump theory model is the basis for representing pump degradation. Using a detailed, two dimensional thermal hydraulics model to generate data on the FHR, we train a network of Vectorized Autoregressive Moving-Average with eXogenous input (VARMAX) models to predict the remaining state values. The result is a surrogate model that provides a detailed reactor state representation of 41 system states and a pump degradation analysis. The framework is applied to Load Follows profiles, yielding high accuracy and a speedup that is more than 4000x faster compared to the higher- fidelity thermal hydraulics model, enabling real-time operational intelligence and applications in long horizon predictions. While the surrogate model framework is demonstrated for the particular case of FHR, the hybrid physical/data-driven modeling approach including the network of surrogates and the underlying modularity has the potential to be applied to other physical asset systems.

Digital Twins↗
DOE OSTI2026

Cracking the code of multi-layer films to promote circularity in single-use plastic packaging

Multi-layer film packaging (MLF) revolutionized food preservation by combining diverse material layers to optimize barrier properties, mechanical strength, and shelf-life. These materials are essential for transporting perishables across various climates and allow for access to fresh goods in “food deserts”, but they pose significant recycling challenges due to their structural complexity. This perspective examines key structure-property relationships governing barrier performance and highlights innovations in material design. We explore how machine learning can predict performance metrics and propose recyclable alternatives, integrating data-driven approaches with material science insights. By challenging the status quo of MLF design, we advocate for circularity in food packaging, inspiring innovation at the intersection of sustainability, material science, and artificial intelligence.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Optimizing Direct Air Capture Solvents to Minimize Energy Consumption of CO 2 Release in a Carbonate Electrolyzer

Addressing climate change by carbon management is critical to achieving the goal of net zero carbon emissions by 2050. In this work, we examined the electrochemically-driven recovery of CO 2 during alkaline solvent regeneration for solvent-based direct air capture. A mathematical model was developed by incorporating carbonate chemistry with water electrolysis to predict the energy consumption per unit of CO 2 released. The predicted results were consistent with the experimental data, in which the experimental work was achieved by characterizing alkalinity and carbon loading values of solvent collected from a flow carbonate electrolyzer. Through this study, we learned that minimizing the energy expended on CO 2 release can be achieved by using an anolyte with a lower alkalinity, increasing the electric charge input to the electrolyzer, and reducing the ohmic resistance of the electrolyzer. Furthermore, using a supporting electrolyte, e.g., Na 2 SO 4 in the present work, effectively compensates for the higher ohmic resistance from using an anolyte with a lower alkalinity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1994

Unique strategies for technical information management at Johnson Space Center

In addition to the current NASA manned programs, the maturation of Space Station and the introduction of the Space Exploration programs are anticipated to add substantially to the number and variety of data and documentation at NASA Johnson Space Center (JSC). This growth in the next decade has been estimated at five to ten fold compared to the current numbers. There will be an increased requirement for the tracking and currency of space program data and documents with National pressures to realize economic benefits from the research and technological developments of space programs. From a global perspective the demand for NASA's technical data and documentation is anticipated to increase at local, national, and international levels. The primary users will be government, industry, and academia. In our present national strategy, NASA's research and technology will assume a great role in the revitalization of the economy and gaining international competitiveness. Thus, greater demand will be placed on NASA's data and documentation resources. In this paper the strategies and procedures developed by DDMS, Inc., to accommodate the present and future information utilization needs are presented. The DDMS, Inc., strategies and procedures rely on understanding user requirements, library management issues, and technological applications for acquiring, searching, storing, and retrieving specific information accurately and quickly. The proposed approach responds to changing customer requirements and product deliveries. The unique features of the proposed strategy include: (1) To establish customer driven data and documentation management through an innovative and unique methods to identify needs and requirements. (2) To implement a structured process which responds to user needs, aimed at minimizing costs and maximizing services, resulting in increased productivity. (3) To provide a process of standardization of services and procedures. This standardization is the central theme of the strategic approach. It will allow Division level Data and Documentation Libraries (DDL's) to function independently and optimize efficiency at the Directorate level. This process also facilitates interconnectivity between Division level DDL's and makes them transparent to the users. (4) To implement the process of 'cost savings', and at the same time the objective is to gain substantial improvement in the organization, categorization, and preservation of JSC-generated data and documentation, and (5) To find, locate, retrace, restore, and preserve the Center-generated crucial scientific and technical information that has been and is being provided by the engineers and scientists of JSC. This is important to the preservation of 'lessons learned'. Preliminary estimates of the possible cost savings which will result from the implementation of this process will also be discussed in this paper.

Krishen, Vijay↗
DOE OSTI2023

Adaptive Data-Driven Model Predictive Control for Heat Pipe Microreactors

To establish a technical basis for self-regulating microreactors, a model predictive control (MPC) system is investigated to proactively respond to anomalies and disturbances in anticipation of potential deviations from operating setpoints. Due to the difficulty of developing a physics-based surrogate model that can accurately match plant data in various operating conditions, machine learning algorithms are used in MPC, which allow for learning from both simulation and operation data, thus efficiently describing the targeted transient with arbitrary accuracy. However, one of the biggest concerns in applying ML algorithms like artificial neural networks (ANNs) is that the predictive capabilities of ANN are limited by training data. If there are gaps between the training and target domain, the accuracy of an ANN can degrade significantly when it is used to predict unseen data. To improve the predictive capability of ANN and enable a confident use of data-driven MPCs outside the training data, this study proposes an adaptive data-driven MPC framework. The system will monitor the discrepancy between plant responses and surrogate predictions, fine-tune the ANN-based surrogate when a large discrepancy is detected, and continue MPC operation with updated surrogates. The framework is demonstrated on a point kinetic model for microreactors. The hyperparameters of the update strategy, including layers to update, error thresholds, learning rate discount, and number of data points used for fine-tuning, are optimized so the simulated microreactor is able to follow changes in setpoint with the smallest of deviations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗