Search NASA⌕ Search

SEARCH · Search NASA

Results for “tuning technique”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS1985

Resistive Fine Tuning of Resonant Circuit

Simple fixed-inductance/fixed-capacitance tank circuit modified for fine adjustment of resonant frequency by addition of small inductance with potentiometer across it. Additional winding built into full winding as integral part or added externally. Technique provides quick way of tuning reactance out of power-transformer circuit to maximize power transfer or to adjust frequency of oscillator. Applications include rotary transformers, servo amplifiers, and analog computer modules.

Mclyman, C. W.↗
NASA NTRS2005

An Optimal Orthogonal Decomposition Method for Kalman Filter-Based Turbofan Engine Thrust Estimation

A new linear point design technique is presented for the determination of tuning parameters that enable the optimal estimation of unmeasured engine outputs such as thrust. The engine s performance is affected by its level of degradation, generally described in terms of unmeasurable health parameters related to each major engine component. Accurate thrust reconstruction depends upon knowledge of these health parameters, but there are usually too few sensors to be able to estimate their values. In this new technique, a set of tuning parameters is determined which accounts for degradation by representing the overall effect of the larger set of health parameters as closely as possible in a least squares sense. The technique takes advantage of the properties of the singular value decomposition of a matrix to generate a tuning parameter vector of low enough dimension that it can be estimated by a Kalman filter. A concise design procedure to generate a tuning vector that specifically takes into account the variables of interest is presented. An example demonstrates the tuning parameters ability to facilitate matching of both measured and unmeasured engine outputs, as well as state variables. Additional properties of the formulation are shown to lend themselves well to diagnostics.

Litt, Jonathan S.↗
NASA NTRS2007

An Optimal Orthogonal Decomposition Method for Kalman Filter-Based Turbofan Engine Thrust Estimation

A new linear point design technique is presented for the determination of tuning parameters that enable the optimal estimation of unmeasured engine outputs, such as thrust. The engine's performance is affected by its level of degradation, generally described in terms of unmeasurable health parameters related to each major engine component. Accurate thrust reconstruction depends on knowledge of these health parameters, but there are usually too few sensors to be able to estimate their values. In this new technique, a set of tuning parameters is determined that accounts for degradation by representing the overall effect of the larger set of health parameters as closely as possible in a least squares sense. The technique takes advantage of the properties of the singular value decomposition of a matrix to generate a tuning parameter vector of low enough dimension that it can be estimated by a Kalman filter. A concise design procedure to generate a tuning vector that specifically takes into account the variables of interest is presented. An example demonstrates the tuning parameters ability to facilitate matching of both measured and unmeasured engine outputs, as well as state variables. Additional properties of the formulation are shown to lend themselves well to diagnostics.

Litt, Jonathan S.↗
NASA NTRS2007

An Optimal Orthogonal Decomposition Method for Kalman Filter-Based Turbofan Engine Thrust Estimation

A new linear point design technique is presented for the determination of tuning parameters that enable the optimal estimation of unmeasured engine outputs, such as thrust. The engine s performance is affected by its level of degradation, generally described in terms of unmeasurable health parameters related to each major engine component. Accurate thrust reconstruction depends on knowledge of these health parameters, but there are usually too few sensors to be able to estimate their values. In this new technique, a set of tuning parameters is determined that accounts for degradation by representing the overall effect of the larger set of health parameters as closely as possible in a least-squares sense. The technique takes advantage of the properties of the singular value decomposition of a matrix to generate a tuning parameter vector of low enough dimension that it can be estimated by a Kalman filter. A concise design procedure to generate a tuning vector that specifically takes into account the variables of interest is presented. An example demonstrates the tuning parameters ability to facilitate matching of both measured and unmeasured engine outputs, as well as state variables. Additional properties of the formulation are shown to lend themselves well to diagnostics.

Litt, Jonathan S.↗
NASA NTRS1993

Transient Faults in Computer Systems

A powerful technique particularly appropriate for the detection of errors caused by transient faults in computer systems was developed. The technique can be implemented in either software or hardware; the research conducted thus far primarily considered software implementations. The error detection technique developed has the distinct advantage of having provably complete coverage of all errors caused by transient faults that affect the output produced by the execution of a program. In other words, the technique does not have to be tuned to a particular error model to enhance error coverage. Also, the correctness of the technique can be formally verified. The technique uses time and software redundancy. The foundation for an effective, low-overhead, software-based certification trail approach to real-time error detection resulting from transient fault phenomena was developed.

Masson, Gerald M.↗
DOE OSTI2020

An Applied Strategy for Using Empirical and Hybrid Models in Online Monitoring

The monitoring of plant equipment for failure prediction is one of the key contributors to operation and maintenance (O&M) costs for a nuclear power plant (NPP) because O&M monitoring depends on labor-intensive activities that are required to meet high equipment reliability standards. These activities rely primarily on humans for information gathering, condition diagnosis, and predictive analysis. Online monitoring aims to automate these activities by relying on sensors to replace human information gathering and machine learning to replace human analysis and decision making. To facilitate automated monitoring, a systematic strategy for anomaly detection is needed to optimally use the available sensor data, empirical models, and physics-supported models. This strategy is essential to provide credible reasoning on why and when an empirical (i.e., purely data-driven) versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. The extant methods usually adopt an ad hoc trial-and-error approach that, in addition to being time-consuming and costly, is also highly subjective; it is impacted by the background and the skill set of the personnel making the decisions. Thus, such an approach cannot guarantee an optimum outcome. This represents the motivation of the current research effort, which is focused on devising a scientifically supported strategy for the optimum selection of anomaly detection methods. This report presents a detailed assessment of the main anomaly detection techniques within the empirical or hybrid method streams. Empirical methods include pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The listed techniques within these two streams represent the vast majority of techniques performed for anomaly detection. Using the techniques as outcomes, a strategy was developed to enable a systematic decision-making process to lead to one of these techniques. The strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability and suitability for training and testing, cause-effect, entropy inference, and model fitting. Each of these decision points in the strategy is explained in detail in this report with examples, along with the scientific basis behind the decisions and outcomes in common and simplified terminology. The strategy is developed for use by any NPP staff with basic engineering or science knowledge. A user-friendly graphical state flow diagram was also developed as a visual presentation of the strategy. The strategy was tested and demonstrated through two pilot projects for the application of anomaly detection at an NPP. Each pilot had two use cases: an initial case in which certain decisions were made that resulted in one or more empirical techniques and a revised use case where one or more key decisions were modified resulting in using a set of hybrid methods.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Leveraging Natural Language Processing and Generative Models in Molecular Chemistry: Property Prediction and Novel Compound Generation

The accurate prediction of molecular properties is important for the rational design and the advancement of green chemistry and sustainable materials research. However, the predictive power of traditional computational chemistry methods is limited due to computational restrictions. Here, in this study, we examine an alternative approach to the accurate prediction of properties of organic compounds: natural language processing (NLP)-based molecular embedding. Using viscosity, partition coefficient (log P), and enthalpy of vaporization as test properties through a survey of comprehensive datasets comprising 5695 data points for viscosity, 25 870 data points for log P, and 2296 data points for enthalpy of vaporization. These are important properties for the design of greener, safer, and sustainable chemical processes. Models were trained using NLP methods such as Mol2vec and fine-tuned ChemBERTa, and results were compared with traditional input featurization techniques such as Morgan fingerprints and quantum chemistry derived sigma profiles and DFT features. Among the various machine learning models, Mol2vec demonstrated superior predictive capabilities, achieving the highest correlation coefficient (R 2 = 0.945) and lowest RMSE (0.106 mPa s) for viscosity, as well as high accuracy for log P and enthalpy of vaporization predictions. These findings establish the Mol2vec featurization technique, graph-convolutional neural networks (GCNN), and fine-tuned ChemBERTa model as powerful tools for predictive modeling of organic compounds properties, offering a significant improvement over previously used featurization techniques and opening up strategies for very-high-throughput computational screening. Finally, we integrated ML models with hybrid language-model-based generative adversarial networks (LM-GAN) to generate novel molecular sequences with desirable properties for different research applications. The ability to computationally design solvents with lower viscosity, lower log P, and lower enthalpy of vaporization offers a data-driven route to accelerating the discovery of sustainable alternatives to traditionally toxic solvents.

ChemBERTa↗
DOE OSTI2023

Tuning Organic Semiconductor Packing and Morphology through Non-equilibrium Solution Processing (Final Report)

Organic semiconductors (OSCs) are a promising candidate to produce low-cost, large area, and flexible electronics. There has previously been successful development of organic field effect transistors (OFETs), photovoltaics (OPV), and bioelectronics using OSCs. Solution processing of these materials allows for the fabrication of large-area devices in the kinetic crystallization regime. The charge transport capabilities have been shown to depend on the morphology and molecular packing of the OSC within thin films. Our hypothesis is that solution processing conditions may significantly impact OSC morphology and as a result the charge transport. Therefore, this work has focused on obtaining a fundamental understanding of the morphology and molecular packing of OSCs for optimal device performance. Through our work, we have gained a better understanding of how these structural conditions were influenced by the solution processing conditions. Our studies have led to a more systematic understanding of the various parameters that impact OSC morphology. Solution processing leads to non-equilibrium films, thus allowing for the formation of diverse morphologies that are inaccessible by other fabrication methods. Previously, our group has focused on tuning the morphology of small-molecular OSCs [53, 55-57]. However, little work had been devoted to polymer OSCs. There was a lack of detailed studies characterizing the solution-state of polymer OSCs in terms of their conformation, degree of entanglement, polymer aggregation, and chain relaxation dynamics. The solution state properties are also likely to be influenced by the rigidity and molecular weight of the polymer OSCs investigated. Thus, we have focused our attention on gaining a better insight of polymer OSC films and solution processing methods. Through this proposal, our approach is to investigate the correlation between solution-state properties and the morphology of the resulting polymer OSC films. We worked three specific aims: investigate the effects of 1) polymer OSC solution-state properties on final film morphology; 2) molecular additives on the solution-state and final film properties; 3) controlled pre-aggregation in the solution-state in the final film morphology. More rigid and planar polymer backbones should promote interchain charge transport and more efficient interchain hopping between polymer chains. Through tailoring the polymer backbone, polymer sidechains, and molecular weight, we expected the altered solution-state properties to affect the final film morphology. In addition, reducing the entanglements and promoting chain alignment will likely prevent charge carrier trapping through conformation disorders. We thus studied different mechanisms, such as molecular additives, to reduce entanglements in solution. Devices fabricated from these solutions were expected to have improved charge transport abilities. In addition to tailoring the solution-state characteristics of the polymer OSCs, we investigated the effect of solution processing methods on the molecular packing and morphology of polymer OSC films. Two main solution processing techniques, e.g., spin-coating and solution shearing, were employed to fabricate OFETs. Spin coating was employed to prepare OSC films, which produce isotropic films. This technique creates several parameters to tune such as spin coating speed, acceleration, and time. Additionally, our research group developed the solution shearing method, which consists of the solution initially sandwiched between two plates. By sliding the top plate, the solution front is exposed and drying begins. This technique allows for the creation of aligned large crystalline domains. Solution shearing consists of different processing parameters which can affect the final morphology, such as shearing speed, substrate temperature and temperature gradient, distance between both plates, and the tilt angle of the top plate. Due to the complexity of the polymer systems investigated, numerous techniques were employed to characterize the polymer OSC solution state and films. All the materials were characterized using the DOE supported synchrotron X-ray scattering facilities at the Stanford Synchrotron Radiation Lightsource (SSRL). Using grazing incidence X-ray scattering (GIXS) and Near Edge X-ray Absorption Fine Structure (NEXAFS) techniques, the crystalline structure and molecular orientations of the thin films were measured. Optical absorption (UV-Vis) spectroscopy was employed to determine the aggregation state in solution and films of the polymer systems. Polarized UV-Vis also allowed for the determination of the relative degree of polymer chain alignment for solution sheared films. Additionally, various other techniques were used to investigate other properties within the film, such as atomic force microscopy (AFM) and solution rheology. Finally, the device performance is quantified through the fabrication and characterization of OFETs, which will highlight the effects of morphology on charge transport.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Time-of-flight detection of terahertz phonon-polariton

A polariton is a fundamental quasiparticle that arises from strong light-matter interaction and as such has attracted wide scientific and practical interest. When light is strongly coupled to the crystal lattice, it gives rise to phonon-polaritons (PPs), which have been proven useful in the dynamical manipulation of quantum materials and the advancement of terahertz technologies. Yet, current detection and characterization methods of polaritons are still limited. Traditional techniques such as Raman or transient grating either rely on fine-tuning of external parameters or complex phase extraction techniques. To overcome these inherent limitations, we propose and demonstrate a technique based on a time-of-flight measurement of PPs. We resonantly launch broadband PPs with intense terahertz fields and measure the time-of-flight of each spectral component with time-resolved second harmonic generation. The time-of-flight information, combined with the PP attenuation, enables us to resolve the real and imaginary parts of the PP dispersion relation. We demonstrate this technique in the van der Waals magnets NiI 2 and MnPS 3 and reveal a hidden magnon-phonon interaction. We believe that this approach will unlock new opportunities for studying polaritons across diverse material systems and enhance our understanding of strong light-matter interaction.

condensed-matter physics↗
DOE OSTI2025

Simulation-Based Inference for Neutrino Interaction Model Parameter Tuning

High-energy physics experiments studying neutrinos rely heavily on simulations of their interactions with atomic nuclei. Limitations in the theoretical understanding of these interactions typically necessitate ad hoc tuning of simulation model parameters to data. Traditional tuning methods for neutrino experiments have largely relied on simple algorithms for numerical optimization. While adequate for the modest goals of initial efforts, the complexity of future neutrino tuning campaigns is expected to increase substantially, and new approaches will be needed to make progress. In this paper, we examine the application of simulation-based inference (SBI) to the neutrino interaction model tuning for the first time. Using a previous tuning study performed by the MicroBooNE experiment as a test case, we find that our SBI algorithm can correctly infer the tuned parameter values when confronted with a mock data set generated according to the MicroBooNE procedure. This initial proof-of-principle illustrates a promising new technique for next-generation simulation tuning campaigns for the neutrino experimental community.

Tame-Narvaez, Karla Maria [Fermilab]↗
DOE OSTI2025

Simulation-based inference for neutrino interaction model parameter tuning

High-energy physics experiments studying neutrinos rely heavily on simulations of their interactions with atomic nuclei. Limitations in the theoretical understanding of these interactions typically necessitate ad hoc tuning of simulation model parameters to data. Traditional tuning methods for neutrino experiments have largely relied on simple algorithms for numerical optimization. While adequate for the modest goals of initial efforts, the complexity of future neutrino tuning campaigns is expected to increase substantially, and new approaches will be needed to make progress. In this paper, we examine the application of simulation-based inference (SBI) to the neutrino interaction model tuning for the first time. Using a previous tuning study performed by the MicroBooNE experiment as a test case, we find that our SBI algorithm can correctly infer the tuned parameter values when confronted with a mock data set generated according to the MicroBooNE procedure. This initial proof-of-principle illustrates a promising new technique for next-generation simulation tuning campaigns for the neutrino experimental community.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
NASA NTRS1993

Control system design for flexible structures using data models

The dynamics and control of flexible aerospace structures exercises many of the engineering disciplines. In recent years there has been considerable research in the developing and tailoring of control system design techniques for these structures. This problem involves designing a control system for a multi-input, multi-output (MIMO) system that satisfies various performance criteria, such as vibration suppression, disturbance and noise rejection, attitude control and slewing control. Considerable progress has been made and demonstrated in control system design techniques for these structures. The key to designing control systems for these structures that meet stringent performance requirements is an accurate model. It has become apparent that theoretically and finite-element generated models do not provide the needed accuracy; almost all successful demonstrations of control system design techniques have involved using test results for fine-tuning a model or for extracting a model using system ID techniques. This paper describes past and ongoing efforts at Ohio University and NASA MSFC to design controllers using 'data models.' The basic philosophy of this approach is to start with a stabilizing controller and frequency response data that describes the plant; then, iteratively vary the free parameters of the controller so that performance measures become closer to satisfying design specifications. The frequency response data can be either experimentally derived or analytically derived. One 'design-with-data' algorithm presented in this paper is called the Compensator Improvement Program (CIP). The current CIP designs controllers for MIMO systems so that classical gain, phase, and attenuation margins are achieved. The center-piece of the CIP algorithm is the constraint improvement technique which is used to calculate a parameter change vector that guarantees an improvement in all unsatisfied, feasible performance metrics from iteration to iteration. The paper also presents a recently demonstrated CIP-type algorithm, called the Model and Data Oriented Computer-Aided Design System (MADCADS), developed for achieving H(sub infinity) type design specifications using data models. Control system design for the NASA/MSFC Single Structure Control Facility are demonstrated for both CIP and MADCADS. Advantages of design-with-data algorithms over techniques that require analytical plant models are also presented.

Irwin, R. Dennis↗
DOE OSTI2022

Mitigate: An Adaptive Network Data Anonymization Tool Using Condensation-Based Differential Privacy

Modern network devices collect a large amount of data that can be analyzed to identify bottlenecks, anomalies, cyber-attacks, etc. Therefore, there is often a need to analyze such collections of network data quite often by an external expert or by the research community. However, these collections of data contain sensitive, proprietary information. In order for the network data to be shared, it must first be anonymized. The overall objective of this project is to develop an innovative privacy management tool to anonymize network data and achieve sufficient privacy, acceptable data utility, and efficient data analysis at the same time. No existing anonymization methods can achieve all of these at the same time. The core of this technology is a differential private clustering algorithm that provides strong privacy protection, preserves data properties important for subsequent analysis, and allows the party receiving the anonymized data to conduct analysis directly on anonymized data without the need of decryption or any extra processing. The research carried out was to design, implement and verify a solution to this problem by completing the following tasks: 1) developing the core technology; 2) developing a context based method that automatically recommends fields that must be anonymized; 3) conducted experiments showing superior results using our approach compared to existing tools, and 4) developed an intuitive but basic user interface. The research that was conducted generated novel algorithmic techniques that utilize state-of-the-art methods such as condensation, differential privacy preservation, clustering, automated tuning based on contextual awareness, and recommendation techniques to specify columns to users for anonymization leading to optimal privacy that allows research analysis on the dataset. Experiments were conducted to evaluate the efficacy of these novel algorithmic techniques by performing analysis on original non-anonymized datasets, then conducting analysis on the same yet anonymized datasets and comparing the results of the analyses. Overall, the anonymized analysis results were within 1% of the original results, verifying that the generated technology not only guarantees a high level of privacy but also enables research analysis as if it were conducted on the original dataset. Potential applications of this technology include anonymization of any type of structured network datasets that contain sensitive identifiers, such as IP addresses, that can be used in multiple applications. For example, to create an AI or machine learning model for cyber security, e.g., to detect attacks, or for performance analysis, e.g., identify bottlenecks or predict performance. In addition, a market analysis that was conducted for potential applications of this technology identified a broader range of applications of our anonymization technology beyond the network sector that includes healthcare, banking, insurance, securities, finance (FISB), data brokering, cloud services, ad sales, and government.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Modeling of deposit formation in mesoporous substrates via atomic layer deposition: Insights from pore‐scale simulation

Atomic layer deposition (ALD) has been a promising technique in fabricating membranes and tuning their properties with a precision at the atomic level. Fabrication of zeolitic imidazolate framework (ZIF) membranes using the ligand-induced permselectivation (LIPS) method starts with the formation of an oxide in a mesoporous substrate by ALD and is followed by the transformation of this oxide to ZIF using imidazolate vapor treatment. The objective of the ALD step is to block the mesopores with a thin deposit, that is, one with small penetration depth and small thickness on the top surface of the substrate. Unlike typical ALD on nonporous substrates, where all available sites react per ALD cycle, thin deposit formation in a mesoporous substrate requires that only a small fraction of the available deposition sites (i.e., close to the substrate surface) is subjected to ALD. Consequently, reactant dosing and duration of pulses are important process variables which, together with diffusion and reaction kinetics determine the deposit structure. Quantitative understanding of the interplay of these variables and phenomena can enable the rational design of ALD within mesoporous substrates. Here, we extend our earlier modeling effort considering the coexistence of ALD both inside the pores and on the external surface of the substrate. Finite-volume based models were developed and validated to simulate the two distinct modes of deposition cycle by cycle. The total mass uptake of the substrate with ALD cycles can be predicted using the combined surface deposition and pore reaction–diffusion models as affirmed by in situ quartz crystal microbalance experimental data. The ALD reactor model combined with the deposition model can accurately capture the number of ALD cycles needed to block the pores of the substrate. Based on the model, we designed a modified ALD process and examined the performance of the corresponding LIPS membranes. Furthermore, the present modeling work provides a new understanding of the deposit formation via ALD within mesoporous substrates for a variety of membrane applications.

atomic layer deposition↗
DOE OSTI2020

Direct Envelope Modeling of Load-Resonant Inverter for Wireless Power Transfer Applications

This paper presents the application of direct envelope modeling technique to primary side LCC tuned resonant wireless power transfer system. The method adapted here decomposes the HF resonant inverter output to a fundamental component and two dominant sidebands. The small-signal dutycycle-to-primary-coil-current-envelope transfer function of a primary side LCC tuned WPT system is then derived as the summation of the responses to the fundamental and the sideband components. The theoretical and simulation results are in good agreement indicating the validity of the approach to be applied to WPT systems.

Galigekere, Veda Prakash↗
DOE OSTI2022

Optimizing Sensor Count and Placement to Detect Bond Wire Lift-Offs and Surface Defects in High-Power IGBT Modules Using Low-Cost Piezo-Electric Resonators

This manuscript presents the most recent results and findings to identify bond wire lift-offs and surface defects in high-power isolated gate bipolar junction transistor (IGBT) modules. The authors of this manuscript formerly proposed a low-cost, piezoelectric resonator-based measurement unit to detect bond wire related degradation in larger IGBT modules. Since high-power IGBT modules are expensive, it was apparent that evaluating our proposed method by inducing controlled damage to fresh (new) IGBTs may not be cost-effective especially when multiple sets of data need to be captured by inducing damage to different levels. In order to overcome this limitation, IGBT bond wires have been mimicked using a 3D printed enclosure, a PCB, and copper wires with dimensions very closely resembling a real IGBT. Using this method, multiple test devices can be built at the cost of a real IGBT, and the proposed technique could be fine-tuned without damaging expensive, real IGBTs. Our recent findings can be used to determine real IGBT degradation and bond wire lift-offs using only two sensors, as opposed to six transducers used in the first iteration of the setup. In addition to optimizing the sensor count, we have also identified the best possible locations of these sensors by attempting multiple placements inside the IGBT casing.

condition monitoring↗
DOE OSTI2024

In situ tuning of optomechanical crystals with nano-oxidation

Optomechanical crystals are a promising device platform for quantum transduction and sensing. Precise targeting of the optical and acoustic resonance frequencies of these devices is crucial for future advances on these fronts. However, fabrication disorder in these wavelength-scale nanoscale devices typically leads to inhomogeneous resonance frequencies. Here we achieve in situ , selective frequency tuning of optical and acoustic resonances in silicon optomechanical crystals via electric field-induced nano-oxidation using an atomic-force microscope. Our method can achieve a tuning range >2nm (0.13%) for the optical resonance wavelength in the telecom C-band, and >60MHz (1.2%) for the acoustic resonance frequency at 5 GHz. The tuning resolution of 1.1 pm for the optical wavelength and 150 kHz for the acoustic frequency allows us to spectrally align multiple optomechanical crystal resonators using a pattern generation algorithm. Our results establish a method for precise post-fabrication tuning of optomechanical crystals. This technique can enable coupled optomechanical resonator arrays, scalable resonant optomechanical circuits, and frequency matching of microwave-optical quantum transducers.

Hatipoglu, Utku (ORCID:0000000205119196)↗
DOE OSTI2025

LLMs for Mfg.—On the State of Large Language Models and Applications to Manufacturing

Additive Manufacturing (AM), referred to as 3D printing, has emerged as a key pillar of Industry 4.0 enabling layer-by-layer fabrication of intricate geometries from CAD models. In parallel, Large Language Models (LLMs), deep learning models for natural language generation trained on vast text corpora, have demonstrated unprecedented capabilities in understanding and generating human-like text. The convergence of these trends opens new opportunities at the intersection of AM and AI/ML, where LLMs can assist engineers and researchers in design, manufacture planning, and knowledge discovery. Recent academic work has begun to explore LLM applications in AM and adjacent fields, such as material science, mechanical engineering, and design for additive manufacturing. This exploration ranges from intelligent process planning to domain-specific knowledge retrieval. This survey provides a comprehensive review of current developments, focusing on peer-reviewed literature contributions that apply, adapt, and advance LLMs in general and domain-specific domains. We analyze state-of-the-art (SOTA) techniques, such as fine-tuning foundational models for specific domains, retrieval-augmented generation (RAG) pipelines, knowledge graph integration, and delve into the architectures and evaluation methods employed. The goal of this survey is to inform researchers and practitioners of the current capabilities and limitations of LLMs in general and in domain-specific applications, and to outline how these models are being tailored to meet the requirements of these applications.

36 MATERIALS SCIENCE↗