Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Architecture patterns”

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 235 records · Page 13

3D printing of void-free glass monoliths: rheological and geometric considerations

Direct ink writing (DIW) is a versatile additive manufacturing technique capable of printing 3D architectures from a broad range of materials. The key advantage of DIW is the ability to spatially control both the architecture and the composition of the printed part, which enables the production of components with previously unachievable combinations of functionalities. One emergent application space for DIW has been in additively manufactured glass optics, where a “green body” is patterned layer-by-layer by extruding a silica-based slurry through a microfluidic nozzle and then thermally consolidated to transparent glass. A critical aspect of the process is ensuring that the printed part is completely free of voids that can occur in the interstitial spaces between the extruded filaments. This outcome is governed by the interplay between ink rheology and strains imposed by the printing process and geometric packing of the filaments. Here, we explore the strain- and rate-dependent deformation events in the DIW process to determine conditions that enable the printing of void-free monoliths without sacrificing shape fidelity. We focus on yield stress fluids consisting of fumed silica nanoparticles dispersed in organic solvents at varied volume fractions to control the rheological properties. We investigate the printability of these ink materials as a function of print process variables and devise the appropriate dimensionless parameters that capture the geometry-dependent and rate-dependent effects on the deformation of the extruded ink. Lastly, we use these scaling arguments to construct a phase diagram for void-free monolith printability.

36 MATERIALS SCIENCE↗

One-pot ternary sequential reactions for photopatterned gradient multimaterials

Seamless multimaterial construction is a common motif in animal physiology. Such continuous mechanical gradients remain challenging to reproduce in engineered systems, as current resin chemistries typically result in a single fixed set of properties. As an alternative to single-property materials, we introduce a thiol-ene-epoxy-based photothermal reaction scheme that produces multimaterials by altering the polymer microstructure within a single resin. In this system, the photodosage during the first stage of processing dictates the extent of conversion for each subsequent reaction. As a result, our photochemistry can exhibit a diverse range of soft (Young’s modulus, E ~ 400 kPa; elongation, dL/L0 ~ 300%) and stiff (E ~ 1.6 GPa; dL/L 0 ~ 3%) mechanical properties. Furthermore, we pattern photostable and mechanically robust modulus gradients (d[E r, stiff /E r , soft] /dx > 1,000 mm -1 ) that exceed those found in squid beaks and human knee entheses. We demonstrate the ability to build intricate multimaterial architectures including a soft, wearable braille display.

36 MATERIALS SCIENCE↗

Selective-Area Remote Epitaxy of ZnO Microrods Using Multilayer–Monolayer-Patterned Graphene for Transferable and Flexible Device Fabrications

Here, selective-area remote epitaxy (SA-REpi) is demonstrated for fabricating mechanically releasable position-controlled ZnO microrod (MR) arrays from donor wafers in an arrayed form. Intaglio-patterned graphene, consisting of basal single-layer graphene (SLG) overlayered with multilayer graphene (MLG) patterned with perforated holes, is transferred onto a GaN/Al 2 O 3 wafer on which the hydrothermal synthesis is performed for growing ZnO MRs. The basal SLG area exposed through the MLG pattern yields ZnO MRs, whereas the MLG plateau inhibits the growth. The noncovalent remote epitaxial heterointerface enables the release of the MR overlayer in the arrayed form, and the original source wafer is refurbished for reproducibly repeating the SA-REpi. Density-functional theory calculations suggest that localized surface charge density is induced on the surface of SLG by the underlying GaN across ultrathin SLG, which possibly provides a driving force for precursor adatoms and the following remote epitaxy of ZnO. In contrast, the induction of the charge density redistribution does not clearly occur through MLG; so, that keeps the surface of MLG nearly charge-neutral. The diameter and spacing of ZnO MRs are controlled in a designed way by changing the pattern geometries. High-resolution scanning transmission electron microscopy reveals the remote heteroepitaxial relationship at an atomic level. The remote epitaxy is expected to provide an ideal platform to transfer the addressable spatial arrays of nano- or micro-architecture semiconductor components to arbitrary target surfaces directly after the growth without the assembly procedures.

36 MATERIALS SCIENCE↗

Brachypodium SPEECHLESS2 Promoter Drives Expression of a Synthetic EPF to Reduce Stomatal Density in Sugarcane Without Pleiotropic Effects

Stomata are microscopic pores that regulate the exchange of CO 2 and water vapour, making them a major target for engineering plants with improved intrinsic water use efficiency (iWUE). Proof-of-concept studies have demonstrated the potential to increase iWUE by reducing stomatal density (SD) and stomatal conductance (g sw ) by ubiquitously expressing EPIDERMAL PATTERNING FACTOR (EPF) family genes. However, unwanted effects on leaf, stem and reproductive traits are often observed when EPFs are misexpressed in this fashion. We sought to test if these effects result from pleiotropy and to identify a targeted promoter that can circumvent the side effects while retaining the desired reduction in SD. A previously reported synthetic EPF (EPF syn ) was expressed in sugarcane ( Saccharum spp.) using two putatively tissue-specific promoters from Brachypodium distachyon (BdCESA7p and BdSPCH2p) and a ubiquitous control from Zea mays (ZmUBI4p). BdSPCH2p control reduced SD to statistically equivalent levels as ZmUBI4p on the abaxial (23%) and adaxial (23%) leaf surfaces. ZmUB4p and BdCESA7p induce expression in four tissue types often associated with pleiotropic effects in EPF-expressing low SD plants. Transgenic plants carrying either the BdCESA7p or ZmUBI4p EPF syn cassettes displayed leaf chlorosis, reduced leaf nitrogen and chlorophyll content, and altered stem architecture. However, transgenic events harboring the BdSPCH2p EPF syn cassette restricted EPF syn expression to the stomatal development zone and leaf nodal tissues and produced transgenic plants without the associated pleiotropic effects. These results represent an important step toward engineering low-SD crops since they show that targeted gene expression can engineer stomatal patterning without impairing agronomically important traits.

59 BASIC BIOLOGICAL SCIENCES↗

Propagation Pattern for Moment Representation of the Lattice Boltzmann Method

A propagation pattern for the moment representation of the regularized lattice Boltzmann method (LBM) in three dimensions is presented. Using effectively lossless compression, the simulation state is stored as a set of moments of the lattice Boltzmann distribution function, instead of the distribution function itself. An efficient cache-aware propagation pattern for this moment representation has the effect of substantially reducing both the storage and memory bandwidth required for LBM simulations. This article extends recent work with the moment representation by expanding the performance analysis on central processing unit (CPU) architectures, considering how boundary conditions are implemented, and demonstrating the effectiveness of the moment representation on a graphics processing unit (GPU) architecture.

42 ENGINEERING↗

Hybrid PDES Simulation of HPC Networks Using Zombie Packets

Although high-fidelity network simulations have proven to be reliable and cost-effective tools to peer into architectural questions for high-performance computing (HPC) networks, they incur a high resource cost. The time spent in simulating a single millisecond of network traffic in the highest detail can take hours, even for static, well-behaved traffic patterns such as uniform random. Surrogate models offer a significant reduction in runtime, yet they cannot serve as complete replacements and should only be used when appropriate. Thus, there is a need for hybrid modeling, where high-fidelity simulation and surrogates run side-by-side. Here, we present a surrogate model for HPC networks in which: packets bypass the network, while the network state is left untouched, i.e., suspended. To bypass the network, we use historical data to estimate the arrival time at which every packet should be scheduled at; to suspend the network, all in-flight packets are scheduled to arrive at their destinations, and are kept in the system to awaken as zombies when switching back to high-fidelity. Speedup for a hybrid model is relative to the proportion of surrogate to high-fidelity. This light-weight surrogate obtained up to 76× speedup. Keeping the zombies in the network showed an increase in the accuracy of the high-fidelity simulation on restart when compared to restarting the network from an empty state.

HPC networks↗

Position Papers for the ASCR Workshop on the Management and Storage of Scientific Data

The purpose of this workshop is to identify priority research directions in the area of data management for high-performance and scientific computing above and beyond HPC’s traditional "the parallel file system is the data-management system" model. Supporting the breadth of the DOE mission, including the explosion of AI uses and the growing needs of experimental and observational science, motivates revisiting our assumptions about data management. There are many facets of this topic to explore including: (1) Interfaces for accessing data that resides on traditional persistent storage as well as memory devices; (2) Storage-system architecture design that supports scientific workflows on varied hierarchical storage and networking devices; (3) Devising metadata management infrastructure to support FAIR principles (Findability, Accessibility, Interoperability, and Reusability); (4) Capturing provenance information about scientific data; (5) Utilizing AI to learn I/O patterns of emerging workloads for efficient data management; (6) Providing data management support for AI and complex workflows; and (7) Understanding the overlap between traditional storage systems and I/O (SSIO) efforts and data management. While the program committee has identified these topics as important areas for discussion, we welcome position papers from the community that propose additional topics of interest for discussion at the workshop. The workshop agenda will include breakout sessions for discussing these and selected topic areas to inform priority research directions for data management for high-performance and scientific computing.

97 MATHEMATICS AND COMPUTING↗

Report for the ASCR Workshop on the Management and Storage of Scientific Data

The purpose of this workshop is to identify priority research directions in the area of data management for high-performance and scientific computing above and beyond HPC’s traditional "the parallel file system is the data-management system" model. Supporting the breadth of the DOE mission, including the explosion of AI uses and the growing needs of experimental and observational science, motivates revisiting our assumptions about data management. There are many facets of this topic to explore including: (1) Interfaces for accessing data that resides on traditional persistent storage as well as memory devices; (2) Storage-system architecture design that supports scientific workflows on varied hierarchical storage and networking devices; (3) Devising metadata management infrastructure to support FAIR principles (Findability, Accessibility, Interoperability, and Reusability); (4) Capturing provenance information about scientific data; (5) Utilizing AI to learn I/O patterns of emerging workloads for efficient data management; (6) Providing data management support for AI and complex workflows; and (7) Understanding the overlap between traditional storage systems and I/O (SSIO) efforts and data management. While the program committee has identified these topics as important areas for discussion, we welcome position papers from the community that propose additional topics of interest for discussion at the workshop. The workshop agenda will include breakout sessions for discussing these and selected topic areas to inform priority research directions for data management for high-performance and scientific computing.

97 MATHEMATICS AND COMPUTING↗

Evolution of connectivity architecture in the Drosophila mushroom body

Brain evolution has primarily been studied at the macroscopic level by comparing the relative size of homologous brain centers between species. How neuronal circuits change at the cellular level over evolutionary time remains largely unanswered. Here, using a phylogenetically informed framework, we compare the olfactory circuits of three closely related Drosophila species that differ in their chemical ecology: the generalists Drosophila melanogaster and Drosophila simulans and Drosophila sechellia that specializes on ripe noni fruit. We examine a central part of the olfactory circuit that, to our knowledge, has not been investigated in these species—the connections between projection neurons and the Kenyon cells of the mushroom body—and identify species-specific connectivity patterns. We found that neurons encoding food odors connect more frequently with Kenyon cells, giving rise to species-specific biases in connectivity. These species-specific connectivity differences reflect two distinct neuronal phenotypes: in the number of projection neurons or in the number of presynaptic boutons formed by individual projection neurons. Finally, behavioral analyses suggest that such increased connectivity enhances learning performance in an associative task. Our study shows how fine-grained aspects of connectivity architecture in an associative brain center can change during evolution to reflect the chemical ecology of a species.

59 BASIC BIOLOGICAL SCIENCES↗

Forecasting high-dimensional spatio-temporal systems from sparse measurements

This paper introduces a new neural network architecture designed to forecast high-dimensional spatio-temporal data using only sparse measurements. The architecture uses a two-stage end-to-end framework that combines neural ordinary differential equations (NODEs) with vision transformers. Initially, our approach models the underlying dynamics of complex systems within a low-dimensional space; and then it reconstructs the corresponding high-dimensional spatial fields. Many traditional methods involve decoding high-dimensional spatial fields before modeling the dynamics, while some other methods use an encoder to transition from high-dimensional observations to a latent space for dynamic modeling. In contrast, our approach directly uses sparse measurements to model the dynamics, bypassing the need for an encoder. This direct approach simplifies the modeling process, reduces computational complexity, and enhances the efficiency and scalability of the method for large datasets. We demonstrate the effectiveness of our framework through applications to various spatio-temporal systems, including fluid flows and global weather patterns. Although sparse measurements have limitations, our experiments reveal that they are sufficient to forecast system dynamics accurately over long time horizons. Our results also indicate that the performance of our proposed method remains robust across different sensor placement strategies, with further improvements as the number of sensors increases. This robustness underscores the flexibility of our architecture, particularly in real-world scenarios where sensor data is often sparse and unevenly distributed.

97 MATHEMATICS AND COMPUTING↗

Neural Architecture and Feature Search for Predicting the Ridership of Public Transportation Routes

Accurately predicting the ridership of public-transit routes provides substantial benefits to both transit agencies, who can dispatch additional vehicles proactively before the vehicles that serve a route become crowded, and to passengers, who can avoid crowded vehicles based on publicly available predictions. The spread of the coronavirus disease has further elevated the importance of ridership prediction as crowded vehicles now present not only an inconvenience but also a public-health risk. At the same time, accurately predicting ridership has become more challenging due to evolving ridership patterns, which may make all data except for the most recent records stale. One promising approach for improving prediction accuracy is to fine-tune the hyper-parameters of machine-learning models for each transit route based on the characteristics of the particular route, such as the number of records. However, manually designing a machine-learning model for each route is a labor-intensive process, which may require experts to spend a significant amount of their valuable time. To help experts with designing machine-learning models, we propose a neural-architecture and feature search approach, which optimizes the architecture and features of a deep neural network for predicting the ridership of a public-transit route. Our approach is based on a randomized local hyper-parameter search, which minimizes both prediction error as well as the complexity of the model. We evaluate our approach on real-world ridership data provided by the public transit agency of Chattanooga, TN, and we demonstrate that training neural networks whose architectures and features are optimized for each route provides significantly better performance than training neural networks whose architectures and features are generic.

Ayman, Afiya↗

Highly-scalable GPU-accelerated compressible reacting flow solver for modeling high-speed flows

Emerging supercomputing systems utilize a combination of central processing units (CPUs) and graphics processing units (GPUs) in an effort to reach exascale capabilities while minimizing the energy footprint of operating such systems. Such heterogeneous machines introduce new challenges for fluids solvers because the hardware architecture and operation of a GPU are fundamentally different from conventional CPUs. In this work, a general approach for efficient implementation of finite-volume based reacting flow solvers on such heterogeneous systems is presented. Three main challenges, namely, data access pattern, thread divergence, and thread safety, are addressed. Since compressible reacting flows require special methods to deal with chemical reactions, hyperbolic and nonlinear convection terms, and the presence of turbulence, specific algorithms that ensure GPU-based efficiency are developed. The approach is demonstrated on the widely available OpenFOAM open source software by modifying core algorithms for GPU accessibility. The scalability of the resulting solver, is demonstrated using practical test cases, including flow through a scramjet engine and the dynamics of a rotating detonation engine. Here, the solver provides near-ideal scaleup on a large number of GPUs (>3000), and extremely efficient use of the GPUs, with throughput nearly a constant even when processing a large number of control volumes.

42 ENGINEERING↗

Si/SiGe QuBus for single electron information-processing devices with memory and micron-scale connectivity function

The connectivity within single carrier information-processing devices requires transport and storage of single charge quanta. Single electrons have been adiabatically transported while confined to a moving quantum dot in short, all-electrical Si/SiGe shuttle device, called quantum bus (QuBus). Here we show a QuBus spanning a length of 10 μm and operated by only six simply-tunable voltage pulses. We introduce a characterization method, called shuttle-tomography, to benchmark the potential imperfections and local shuttle-fidelity of the QuBus. The fidelity of the single-electron shuttle across the full device and back (a total distance of 19 μm) is (99.7 ± 0.3) %. Using the QuBus, we position and detect up to 34 electrons and initialize a register of 34 quantum dots with arbitrarily chosen patterns of zero and single-electrons. The simple operation signals, compatibility with industry fabrication and low spin-environment-interaction in 28 Si/SiGe, promises long-range spin-conserving transport of spin qubits for quantum connectivity in quantum computing architectures.

97 MATHEMATICS AND COMPUTING↗

Comparative genomic and transcriptomic analyses of trans-kingdom pathogen Fusarium solani species complex reveal degrees of compartmentalization

Background: The Fusarium solani species complex (FSSC) comprises fungal pathogens responsible for mortality in a diverse range of animals and plants, but their genome diversity and transcriptome responses in animal pathogenicity remain to be elucidated. We sequenced, assembled and annotated six chromosome-level FSSC clade 3 genomes of aquatic animal and plant host origins. We established a pathosystem and investigated the expression data of F. falciforme and F. keratoplasticum in Chinese softshell turtle (Pelodiscus sinensis) host. Results: Comparative analyses between the FSSC genomes revealed a spectrum of conservation patterns in chromosomes categorised into three compartments: core, fast-core (FC), and lineage-specific (LS). LS chromosomes contribute to variations in genomes size, with up to 42.2% of variations between F. vanettenii strains. Each chromosome compartment varied in structural architectures, with FC and LS chromosomes contain higher proportions of repetitive elements with genes enriched in functions related to pathogenicity and niche expansion. We identified differences in both selection in the coding sequences and DNA methylation levels between genome features and chromosome compartments which suggest a multi-speed evolution that can be traced back to the last common ancestor of Fusarium. We further demonstrated that F. falciforme and F. keratoplasticum are opportunistic pathogens by inoculating P. sinensis eggs and identified differentially expressed genes also associated with plant pathogenicity. These included the most upregulated genes encoding the CFEM (Common in Fungal Extracellular Membrane) domain. Conclusions: The high-quality genome assemblies provided new insights into the evolution of FSSC chromosomes, which also serve as a resource for studies of fungal genome evolution and pathogenesis. This study also establishes an animal model for fungal pathogens of trans-kingdom hosts.

59 BASIC BIOLOGICAL SCIENCES↗

New principles of self‐organization created through the interplay of DNA condensates, microtubules, and motors

Bioinspired design—which holds great promise for a new generation of materials that are robust to defects, scalable under green manufacture, environmentally responsive, and programmably reconfigurable—requires mastery over molecular self-organization. Yet, from its specific mechanisms to most general architectures, the principles governing self-organization remain poorly understood and not even fully enumerated. For living systems, one obvious architectural principle is the modular reuse of a few simple molecular components in myriad combinations to achieve more complex phenomena. For example, the mechanical tasks of a cell are driven by the nonequilibrium dynamics of cytoskeletal filaments and molecular motors—the same filaments and motors, reprogrammed by a variety of modulators, perform tasks ranging from cell movement to division. Similarly, many compartmentalization tasks are performed by liquid-like condensates of simple components, which act as membraneless organelles to localize particular molecules in space and time (e.g. for gene regulation or RNA processing). In a few cases, condensates combine and interact with the cytoskeleton to create still more complex phenomena, e.g. the nucleation of microtubule asters from the centrosome (a protein condensate) to form the mitotic spindle during cell division. Very little is known about the fundamental mechanisms of such filament-plus-condensate phenomena. Despite few examples, the landscape of behaviors that can be achieved through the combination of condensates, filaments, and motors appears vast. However, exploration has been hindered by a lack of systems that have sufficiently programmable and dynamically tunable interactions between component condensates, filaments, and motors. We proposed to combine programmable DNA condensates, filamentous microtubules, and light-controlled motors into self-organizing systems whose principles go beyond those that have been observed in nature. In one limit, our systems will use microtubules and motors to create the molecular analog of a network of roads, which will organize droplets of DNA condensates capable of carrying molecular cargo. DNA condensates coupled to motors will flow from one microtubule aster hub to another, with their direction and timing controlled by DNA circuits. In another limit, microtubules will swim through bulk DNA condensates and exhibit strong interactions with boundaries between different types of condensates. Microtubule swimmers will reflect, get trapped, or refract at boundaries, under a mechanical analog of the classical optical index of refraction. DNA condensates having different mechanical indexes of refraction will be used to construct the analog of optical lenses, so that microtubule swimmers can be manipulated like light—collimated, diffracted, focused, and sorted based on properties analogous to wavelength. These two limits define two new architectures, within which multiple new mechanistic principles for self-organization will be discovered and explored. To explore these architectures, the motor-based coupling between DNA condensates and filaments will be controlled in time and space through the use of opto-proteins that create reversible links between DNA condensates and motors upon illumination. For each principle of interest, patterns of light will create virtual experiments by defining patterns of activity where DNA condensates walk along filaments, or filaments swim through condensates, and patterns of inactivity which will serve either as controls, or as boundary conditions vital to create the desired phenomena. This research serves the goals of Basic Energy Sciences Biomolecular Material Program by elucidating the principles by which the emergent, nonequilibrium behavior of collections of DNA condensates, motors, and microtubules can be programmed by environmental light patterns to create complex motion and materials transport. Because DNA condensates can be readily coupled to virtually any high performance nanomaterial, from carbon nanotubes, to metal nanoparticles, to light harvesting systems, this work provides a path to the construction, self-maintenance and reconfiguration of materials relevant to the Department of Energy.

60 APPLIED LIFE SCIENCES↗

From Cell to System: Accelerated hpc Simulations of BESS Aging under Frequency Regulation and Arbitrage use cases

Lithium-ion battery energy storage systems (BESS) packs have emerged as a leading solution for grid-scale energy storage, enhancing resiliency and balancing load fluctuations. Yet, experimental characterization of large-format LIB packs-particularly to assess performance and degradation over hundreds of cycles - demands substantial hardware investment and multi-year testing campaigns. In this work, we couple a hierarchical, physics-based modeling framework agnostic to electrode chemistries with high-performance computing to accelerate systems level evaluation by upto two orders of magnitude. Building on the open-source liionpack platform, we implement cell, module, and pack-scale electrochemical models enriched with mechanistic aging mechanisms and deploy them on an HPC cluster to simulate 150−200kWh systems over 500 - 1,000 cycles with in days. We subject these virtual B ESS to both constant-current cycling and realistic grid service profiles spanning frequency regulation, ramp-rate support, and energy arbitrage-and quantify the resulting degradation patterns. Our results reveal that localized cell aging can induce substantial nonuniformity at module and pack levels, with service-specific cycling protocols driving distinct aging modes. This rapid, multiscale modeling approach provides a powerful design-space exploration tool for optimizing electrical architecture, control strategies, and operational schedules to prolong pack lifetime and lower total cost of ownership.

Ayalasomayajula, Surya [ORNL] (ORCID:0009000860788↗

Machine Learning for Automated Weld Quality Monitoring and Control

Resistance Spot Welding (RSW) is a critical process in the automotive industry, valued for its cost-effectiveness, short cycle time, and robustness. However, achieving consistent high-quality joints remains challenging due to the complex interplay of various factors, like materials, processes, and manufacturing uncertainties, etc. Under the collaborative project between Oak Ridge National Laboratory (ORNL) and General Motors (GM), we have developed a robust and expansible machine learning (ML) framework aimed at enhancing quality control in RSW. By harnessing the power of machine learning, we have developed the ability to ensure every aspect of the welding process, from the initial process design stage to the final weld joint quality. The framework operates by analyzing a variety of data streams, including in-line process signals, process parameters, materials, and postprocessed weld joint data. Through this analysis, the models have been trained to detect deviations from optimal quality standards, leveraging their ability to identify signature data patterns and anomalies within in-line signals and construct complex correlations between these signals and weld quality parameters. Meanwhile, the machine learning framework is designed to adapt to a variety of materials, including high strength steels and aluminum alloys, etc. Its flexible architecture facilitates the incorporation of diverse data sources and features, enabling precise modeling and prediction across a broad range of material properties and weld quality variables. The expansible ML frameworks represent a promising transformation in weld quality monitoring and control, empowering industry to achieve high levels of efficiency, consistency, and reliability in manufacturing.

99 GENERAL AND MISCELLANEOUS↗

Machine Learning for Automated Weld Quality Monitoring and Control

Resistance Spot Welding (RSW) is a critical process in the automotive industry, valued for its cost-effectiveness, short cycle time, and robustness. However, achieving consistent high-quality joints remains challenging due to the complex interplay of various factors, like materials, processes, and manufacturing uncertainties, etc. Under the collaborative project between Oak Ridge National Laboratory (ORNL) and General Motors (GM), we have developed a robust and expansible machine learning (ML) framework aimed at enhancing quality control in RSW. By harnessing the power of machine learning, we have developed the ability to ensure every aspect of the welding process, from the initial process design stage to the final weld joint quality. The framework operates by analyzing a variety of data streams, including in-line process signals, process parameters, materials, and postprocessed weld joint data. Through this analysis, the models have been trained to detect deviations from optimal quality standards, leveraging their ability to identify signature data patterns and anomalies within in-line signals and construct complex correlations between these signals and weld quality parameters. Meanwhile, the machine learning framework is designed to adapt to a variety of materials, including high strength steels and aluminum alloys, etc. Its flexible architecture facilitates the incorporation of diverse data sources and features, enabling precise modeling and prediction across a broad range of material properties and weld quality variables. The expansible ML frameworks represent a promising transformation in weld quality monitoring and control, empowering industry to achieve high levels of efficiency, consistency, and reliability in manufacturing.

42 ENGINEERING↗