Additive manufacturing最新文献

{"title":"Enabling robust and energy-efficient laser powder bed fusion of Cu alloys via Mo nanoparticle decoration","authors":"Guichuan Li ,&nbsp;Michel Smet ,&nbsp;Yagnitha Kandula ,&nbsp;Zhuangzhuang Liu ,&nbsp;Brecht Van Hooreweder ,&nbsp;Kim Vanmeensel","doi":"10.1016/j.addma.2025.104988","DOIUrl":"10.1016/j.addma.2025.104988","url":null,"abstract":"<div><div>Laser Powder Bed Fusion (PBF-LB) of copper and low-alloyed copper alloys remains challenging due to their low infrared absorptivity and high thermal conductivity. This study introduces a multi-faceted strategy integrating computational thermodynamics-guided alloy design, Mo nanoparticle surface decoration, and thermal process optimization to enable robust and energy-efficient PBF-LB processing of reflective Cu-based alloys. Surface decoration with 0.44 wt% Mo nanoparticles enhances laser energy absorption, enabling a 40–45 % reduction in the required laser volumetric energy density from 167 to 188–100–118 J/mm³ to achieve &gt; 99.1 % part density. Additionally, Mo addition improves the alloy’s resistance to precipitate coarsening while maintaining low solid solubility in Cu, thereby preserving electrical conductivity. In CuCrZr alloys, baseplate preheating to 300 °C promotes densification and in-situ precipitation of Cr and Cu_xZr_y phases during PBF-LB, enhancing both strength and conductivity. In contrast, Mo addition suppresses in-situ precipitation due to its sluggish diffusion in Cu and preferential partitioning into Cr and Cu_xZr_y phases. After direct age-hardening (450 °C, 9 h), the CuCrZrMo alloy exhibits a fine dispersion of Mo-doped nanoprecipitates, achieving a yield strength of 598 ± 7 MPa (vs. 576 ± 7 MPa for CuCrZr) while retaining high electrical conductivity (67–68 % IACS). This work highlights a synergistic alloy and process design strategy to address key PBF-LB challenges in Cu alloys, enabling their application in high-performance components requiring combined high mechanical strength and electrical conductivity.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"111 ","pages":"Article 104988"},"PeriodicalIF":11.1,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanism-driven process planning for continuous fiber-reinforced suspension lattice structures with complex path features via self-supporting suspension printing","authors":"Ke Dong ,&nbsp;Ziwen Chen ,&nbsp;Feirui Li ,&nbsp;Kaicheng Ruan ,&nbsp;Xueliang Xiao ,&nbsp;Pai Zheng ,&nbsp;Yi Xiong","doi":"10.1016/j.addma.2025.104980","DOIUrl":"10.1016/j.addma.2025.104980","url":null,"abstract":"<div><div>Continuous fiber-reinforced polymer additive manufacturing (CFRP-AM) enables the creation of a novel class of composite structures known as suspension lattices, formed by stacking distinct layer patterns via self-supporting suspension printing (SSSP). With hybrid topologies and complex internal channels, these structures open new avenues for structural enhancement and multifunctional integration. However, engineering suspension lattices with intricate corner path features remains challenging due to limited understanding of printing mechanisms and a lack of effective process planning methods to address manufacturing issues, like gravity-induced sagging and fiber-tension-induced turning slippage. This study proposes a mechanism-driven process planning method for architecting geometrically accurate and mechanically robust suspension lattices. The process is categorized into two phases (i.e., fabrication of primary skeletons and secondary elements) to decouple the structural complexity. The underlying printing mechanism is revealed through experimental characterization of diverse path features, which facilitates the development of physics-informed few-shot learning (PI-FSL) models for accurate prediction of printing quality. A slip transmission mechanism for sequential corner features is introduced that leverages PI-FSL models to quantify the influence of preceding path slippage on the subsequent path accuracy. Subsequently, these models are integrated with a genetic algorithm for path planning of suspension lattices. The proposed approach achieves high efficiency in three complex target patterns, as evidenced by desirable path accuracy with geometric deviations of less than 1.0 mm. Furthermore, the effectiveness of this method is demonstrated through two potential applications in creating two-and-a-half-dimensional (2.5D) lattices for battery enclosures and three-dimensional (3D) skeletons for drone protective cages.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"111 ","pages":"Article 104980"},"PeriodicalIF":11.1,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrosion-resistant and heat-dissipative SiOC ultralight lattice for high-temperature EMI shielding","authors":"Shixiang Zhou ,&nbsp;Yijing Zhao ,&nbsp;Xiao Guo ,&nbsp;Udeshwari Jamwal ,&nbsp;Pon Janani Sugumaran ,&nbsp;Sreekanth Ginnaram ,&nbsp;Wentao Yan ,&nbsp;Jun Ding ,&nbsp;Yong Yang","doi":"10.1016/j.addma.2025.104964","DOIUrl":"10.1016/j.addma.2025.104964","url":null,"abstract":"<div><div>High-temperature electromagnetic interference (EMI) shielding material is essential for intense thermal or electromagnetic radiation applications. Ceramics are promising candidates but are often fabricated with increased density and thickness to achieve sufficient shielding effectiveness (SE). However, we present an unconventional strategy to enhance the SE of ceramics by reducing density realized through hierarchical lattice design. 3D-printed silicon oxycarbide (SiOC) with self-arrayed and corrosion-resistant carbon nanosheets was employed to materialize this design. As the density decreases from 2.73 to 0.53 g/cm³, the SE increases from 12.53 to 27.27 dB. The combined effects of densely arrayed carbon nanosheets and hierarchical design amplify multi-reflection/scattering, enabling enhanced EMI shielding at reduced density. Furthermore, this structure is capable of operation at 600 °C and oxygen corrosion environment even at an ultralow density of 0.29 g/cm³, achieving over 99 % shielding efficiency. It exhibits a low thermal expansion coefficient of 1.41 × 10⁻⁶/K at 600 °C, along with compressive strength, Young’s modulus, and energy absorption of 6.38 MPa, 3.02 GPa, and 8.14 kJ/cm³, respectively, ensuring mechanical, dimensional, and shielding robustness. The interconnected hollow spaces and exposed surfaces facilitate both active and passive heat dissipation, preventing thermal failure and extending the operational lifespan. Under airflow, the heated structure cools to 46.6 °C within 25 s, effectively reducing the operating temperature. This strategy provides a straightforward approach for fabricating high-temperature and lightweight EMI shielding ceramics through structural optimization, underscoring its potential for performance enhancement, cost reduction, and application expansion for extreme environments.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"111 ","pages":"Article 104964"},"PeriodicalIF":11.1,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-material nozzle geometry design optimization for bioprinting","authors":"Jun Sim,&nbsp;Wan Kyun Chung","doi":"10.1016/j.addma.2025.104959","DOIUrl":"10.1016/j.addma.2025.104959","url":null,"abstract":"<div><div>Multi-material additive manufacturing (AM) introduces complex challenges in maintaining stable and controllable flow within the printing nozzle, where flow disturbances such as backflow, excessive shear stress, and delayed material transitions can compromise print uniformity and cell viability. These issues are particularly pronounced when handling non-Newtonian, yield stress bioinks such as Herschel–Bulkley fluids. Motivated by on-the-fly material switching, we explicitly scope the optimization to a one-ink-on/one-ink-idle Y-junction in which one inlet is driven while the other remains idle. This study presents a simulation-driven optimization framework for multi-material Y-junction nozzle geometry aimed at improving backflow suppression, shear-stress minimization, and rapid material switching. A numerical model quantifies three key performance indices as backflow potential, maximum wall shear stress, and switching time index across a four dimensional design space. High fidelity CFD simulations generate training data for a Gaussian Process surrogate with a Matérn kernel, and Bayesian optimization efficiently identifies optimal geometries. The optimized designs achieve significant reductions in backflow, peak shear stress, and outlet refill time compared to baseline nozzles. Experimental validation comprising cell viability assays on high versus low shear designs, air filled backflow tests in a worst-case setup, and on-the-fly switching time measurements corroborates all three cost components. Our findings deliver a robust, scalable, and experimentally validated methodology for multi-material nozzle design, with broad implications for precision, speed, and biological functionality in extrusion-based bioprinting.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"111 ","pages":"Article 104959"},"PeriodicalIF":11.1,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Laser induced keyhole reshaping in laser powder bed fusion of aluminum alloy","authors":"Shiwei Hua,&nbsp;Yangyi Pan,&nbsp;Qinghu Guo,&nbsp;Guoqing Zhang,&nbsp;Fang Dong,&nbsp;Chen Zhang,&nbsp;Sheng Liu","doi":"10.1016/j.addma.2025.104993","DOIUrl":"10.1016/j.addma.2025.104993","url":null,"abstract":"<div><div>Conventional powder bed fusion by laser beam (PBF-LB) utilizing high beam energy often generates unstable keyhole dynamics, leading to pore formation and compromised mechanical performance, especially for aluminum alloys. To address this limitation, we propose a novel Laser Keyhole Reshaping technology enhanced PBF-LB (LKRS-PBF-LB) strategy, integrating pulsed and continuous lasers to stabilize keyhole morphology. Experimental and computational analyses reveal that pulsed-laser-induced shockwaves dynamically reverse keyhole wall pressures, expanding the keyhole diameter (43→58 μm) and stabilizing its shape (J→I transition), thereby reducing porosity by an order of magnitude (3.63 %→0.14 %). Keyhole stabilization concurrently suppresses spattering by mitigating vapor pressure fluctuations and lowering peak pressures. Numerical simulations demonstrate enhanced melt flow and attenuated thermal gradients, promoting columnar-to-equiaxed transition and grain refinement. The LKRS-processed samples exhibited simultaneous enhancement in tensile strength (59.6 % increase) and ductility (0.78 %→2 %), attributable to porosity elimination and grain refinement. This approach introduces a novel keyhole reshaping technique that mitigates intrinsic instability, thereby enabling new avenues for advanced additive manufacturing with enhanced performance.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"111 ","pages":"Article 104993"},"PeriodicalIF":11.1,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient part-scale thermal modeling of laser powder bed fusion via a multilevel finite element framework","authors":"S.M. Elahi,&nbsp;J.P. Leonor,&nbsp;R.Y. Wu,&nbsp;G.J. Wagner","doi":"10.1016/j.addma.2025.104897","DOIUrl":"10.1016/j.addma.2025.104897","url":null,"abstract":"<div><div>In this work, we show that a multilevel finite element algorithm previously demonstrated for linear problems can, using a novel time integration method and other improvements, give efficient and accurate part-scale simulations of real additive manufacturing processes. The GPU-optimized multilevel finite element framework (GO-MELT) uses multiple moving meshes to simulate thermal behavior in laser powder bed fusion (LPBF) processes; fixed mesh sizes and data structures allow straightforward implementation of this algorithm on GPU hardware. Building on this framework, we introduce key advancements including G-code parsing for complex laser paths, temperature-dependent material properties with distinct definitions for powder, solid, and fluid states, and time step subcycling across levels to manage computational loads effectively. These improvements enable precise simulation across the different material states encountered in LPBF while minimizing computational cost. Verification studies show that first-order time convergence is preserved even in the presence of nonlinearities, and the fidelity of the enhanced framework is validated against well-established experimental benchmarks, including in-situ X-ray diffraction data for Hastelloy-X and time above melting measurements from the NIST AM-Bench cantilever model. Computational tests demonstrate that our approach achieves an average execution time of 1.8 ms per time step, enabling a high-fidelity thermal simulation of 350 million time steps to be solved on a single GPU in 7.3 days, comparable to published simulations on much larger parallel systems. An analysis of thermal decay times can be used to further reduce simulation time by limiting simulation to time-points of interest. These results underscore the potential of this algorithm for advancing real-time process optimization and part quality improvement in LPBF.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"109 ","pages":"Article 104897"},"PeriodicalIF":11.1,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel integrated forming process for fabricating complex thin-walled AlSi10Mg alloy tubular parts via laser powder bed fusion and hot gas forming","authors":"Jiangkai Liang ,&nbsp;Gaoning Tian ,&nbsp;Quan Gao ,&nbsp;Wei Du ,&nbsp;Yanli Lin ,&nbsp;Zhubin He","doi":"10.1016/j.addma.2025.104936","DOIUrl":"10.1016/j.addma.2025.104936","url":null,"abstract":"<div><div>Currently, both additive manufacturing technologies and fluid pressure forming process face significant challenges in fabricating large-sized, complex thin-walled metal components. To address these challenges, this paper introduces a novel integrated forming process that utilizes laser powder bed fusion (LPBF) preforming and hot gas forming (HGF). This method employs LPBF technology to fabricate near-net-shape preforms, which are subsequently subjected to HGF treatment to realize micro-scale precise deformation. This study systematically investigates the performance of AlSi10Mg alloy thin-walled preforms prepared by LPBF, along with the characteristics of the formed parts following the HGF process. Furthermore, subsequent heat treatment protocols are employed to improve the microstructural properties of the formed parts. Compared to the direct LPBF technology, this method exhibits marked enhancements in dimensional accuracy and density of the fabricated parts, effectively controlling dimensional deviations and substantially reducing porosity. Ultimately, the process culminates in the fabrication of complex thin-walled AlSi10Mg alloy parts characterized by a superior microstructure and mechanical properties. Specifically, the formed parts, measuring 165 mm with a wall thickness of 1.2 mm, achieve a dimensional accuracy of ± 0.24 mm and a maximum wall thickness reduction rate of less than 14.2 %, while attaining an impressive density of 99.93 %. Additionally, the parts exhibit excellent uniformity concerning the distribution and morphology of the precipitated phases, along with the shape and structure of the grains. Following solution heat treatment, the formed parts exhibited tensile strengths of 282 MPa at room temperature and 186 MPa at 230 °C, accompanied by elongations of 15.9 % and 11.7 %, respectively. This favorable combination of strength and ductility renders these materials well-suited for engineering applications that demand high overall mechanical performance. However, aging heat treatment after solution treatment resulted in a significantly improved of the mechanical properties. The tensile strengths increased to 350 MPa at room temperature and 201 MPa at 230°C, while the elongations were concurrently reduced to 6.9 % and 10.1 %, respectively. Such a property profile makes these materials particularly suitable for specialized applications where high strength is prioritized over ductility. The feasibility of LPBF-prepared preforms via the subsequent HGF process was systematically confirmed, thereby establishing a foundational basis for the prospective application of this integrated forming methodology.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"110 ","pages":"Article 104936"},"PeriodicalIF":11.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiometric temperature measurement for metal additive manufacturing via temperature emissivity separation","authors":"Ryan W. Penny,&nbsp;A. John Hart","doi":"10.1016/j.addma.2025.104904","DOIUrl":"10.1016/j.addma.2025.104904","url":null,"abstract":"<div><div>Emission of blackbody radiation from the meltpool and surrounding area in laser powder bed fusion (LPBF) makes this process visible to a range of optical monitoring instruments intended for online process and quality assessment. Yet, these instruments have not proven capable of reliably detecting the finest flaws that influence LPBF component mechanical performance, limiting their adoption. One hindrance lies in interpreting measurements of radiance as temperature, despite the physical link between these variables being readily understood as a combination of Planck’s Law and spectral emissivity. Uncertainty in spectral emissivity arises as it is nearly impossible to predict and can be a strong function of wavelength; in turn, this manifests uncertainty in estimated temperatures and thereby obscures the LPBF process dynamics that indicate component defects. This paper presents temperature emissivity separation (TES) as a method for accurate retrieval of optically-measured temperatures in LPBF. TES simultaneously calculates both temperature and spectral emissivity from spectrally-resolved radiance measurements and, as the latter term is effectively measured, more accurate process temperatures result. Using a bespoke imaging spectrometer integrated with an LPBF testbed to evaluate this approach, three basic TES algorithms are compared in a validation experiment that demonstrates retrieval of temperatures accurate to <span><math><mrow><mo>±</mo><mn>28</mn></mrow></math></span> K over a 1000 K range. A second investigation proves industrial feasibility through fabrication of an LPBF test artifact. Temperature data are used to study the evolution of fusion process boundary conditions, including a decrease in cooling rate as layerwise printing proceeds. A provisional correlation of temperature fields to component porosity assessed by 3D computed tomography demonstrates in situ optical detection of micron-scale porous defects in LPBF.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"110 ","pages":"Article 104904"},"PeriodicalIF":11.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Convolutional autoencoder frameworks for projection multi-photon 3D printing","authors":"Ishat Raihan Jamil ,&nbsp;Jason E. Johnson ,&nbsp;Xianfan Xu","doi":"10.1016/j.addma.2025.104929","DOIUrl":"10.1016/j.addma.2025.104929","url":null,"abstract":"<div><div>Projection multi-photon 3D printing is an emerging technique for fabricating micro-nano structures at exceptionally high speeds. It leverages the use of a digital micromirror (DMD) to project and print entire 2D layers at once, offering higher throughput and scalability than conventional point-by-point laser scanning. While two photon polymerization is widely regarded as an outstanding method for achieving high dimensional accuracy at the nanoscale, the projection aspect introduces a new set of challenges, such as under-printing due to oxygen inhibition. The inherently complex photopolymerization dynamics make it difficult to model and simulate efficiently. To address this, we introduce a data-driven methodology employing deep learning to build a surrogate model of the printing process and an inverse model for 2D DMD pattern optimization to achieve desirable printed shapes. By printing diverse shapes morphed by various parametrization schemes, we built a dataset for training convolutional encoder-decoder (autoencoder) neural networks. The trained surrogate accurately maps input DMD patterns to their final printed geometries, capturing nonlinearities introduced by process physics. Inverting the inputs and outputs further enabled us to train an inverse model for generating pre-compensated DMD patterns to print desirable target geometries. Experimental findings demonstrate that this deep learning approach accurately predicts printed outputs and enhances dimensional accuracy in the printing of 2D layers. Our results reveal a viable approach to overcome inhibition-induced constraints, enabling more accurate projection-based multi-photon printing at the micro and nanoscale.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"110 ","pages":"Article 104929"},"PeriodicalIF":11.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144880392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-layer thermal history prediction framework for directed energy deposition based on extended physics-informed neural networks (XPINN)","authors":"Bohan Peng,&nbsp;Ajit Panesar","doi":"10.1016/j.addma.2025.104953","DOIUrl":"10.1016/j.addma.2025.104953","url":null,"abstract":"<div><div>This paper presents an eXtended physics-informed neural networks (XPINN)-based framework for predicting the temperature history during a multi-layer Directed Energy Deposition (DED) process. The proposed XPINN-based framework, advancing from its PINN-based counterpart, demonstrates significant accuracy improvement, around <span><math><mrow><mn>50</mn><mo>%</mo></mrow></math></span> reduction in RMSE and maximum absolute error, and extended capability of temperature history prediction with domain decomposition for more complex configurations such as interpass time, void, and interruption of scan that are prevalent in real-life DED designs. It is validated via a series of 2D benchmark tests against numerical simulations with an increasing degree of complexity. The effect of different domain decompositions is compared and discussed. Strategies that improve the training outcome are also proposed and analysed. With the enhanced capability of working on more complex configurations while retaining the characteristic availability of derivative information, the proposed framework brings process-ware design optimisation based on scientific machine learning (SciML) techniques one step closer to the application to real-life additive manufacturing applications.</div></div>","PeriodicalId":7172,"journal":{"name":"Additive manufacturing","volume":"110 ","pages":"Article 104953"},"PeriodicalIF":11.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}