Melt Pool Research Articles

Very high cycle fatigue characteristics of laser beam powder bed fused AlSi10Mg: A systematic evaluation of part geometry

This study explores the influence of geometry and part size on defect distribution, melt pool size, and mechanical characteristics in laser beam powder bed fused (LB-PBF) AlSi10Mg. Five distinct geometries—hourglass, small rod, small block, large block, and large rod—were fabricated under identical process parameters. Fully reversed ultrasonic fatigue testing, operating at a frequency of 20 kHz, was conducted to assess the very high cycle fatigue properties. The findings indicated that part geometry had a major impact on the fatigue properties of the material in the very high cycle fatigue regime. Specimens machined from large rods and large blocks had the lowest porosity and highest fatigue resistance. Microstructural analysis indicated that hourglass, small rod, and small block specimens had shallower melt pools and overlap depths compared to other geometries. This observation suggests a higher cooling rate in specimens with smaller cross-sectional areas, leading to the increased presence of entrapped gas pores and a lack of fusion defects. Understanding the relationship between part geometry and fatigue properties in LB-PBF components offers insights for optimizing design and manufacturing processes in additive manufacturing applications.

Processing windows for Al-357 by LPBF process: a novel framework integrating FEM simulation and machine learning with empirical testing

PurposeThis study aims to develop a holistic method that integrates finite element modeling, machine learning, and experimental validation to propose processing windows for optimizing the laser powder bed fusion (LPBF) process specific to the Al-357 alloy.Design/methodology/approachValidation of a 3D heat transfer simulation model was conducted to forecast melt pool dimensions, involving variations in laser power, laser scanning speed, powder bed thickness (PBT) and powder bed pre-heating (PHB). Using the validated model, a data set was compiled to establish a back-propagation-based machine learning capable of predicting melt pool dimensional ratios indicative of printing defects.FindingsThe study revealed that, apart from process parameters, PBT and PHB significantly influenced defect formation. Elevated PHBs were identified as contributors to increased lack of fusion and keyhole defects. Optimal combinations were pinpointed, such as 30.0 µm PBT with 90.0 and 120.0 °C PHBs and 50.0 µm PBT with 120.0 °C PHB.Originality/valueThe integrated process mapping approach showcased the potential to expedite the qualification of LPBF parameters for Al-357 alloy by minimizing the need for iterative physical testing.

Investigation on the characteristics of porosity, melt pool in 316L stainless steel manufactured by laser powder bed fusion

Pores are among the primary defects in 316L stainless steel when fabricated through laser powder bed fusion (L-PBF). To better understand and precisely control the formation behavior of pores in the L-PBF-manufactured 316L stainless steel, effects of L-PBF process parameters on the melt pool and pore characteristics have been investigated. A method utilized for extreme values statistics analysis was also applied to investigate and predict the sizes of pores. Relationships among the count of measurements, the laser energy density, the reduced variate, and the maximum pore size were revealed. The findings showed an overall increase in melt pool depth as the laser energy densities was raised, yet the magnitude of this growth weakened as the laser energy density continued to increase. Conversely, it was discovered that the connection between the width of the melt pool and the density of laser energy exhibited a markedly less distinct correlation. As laser energy density escalated, there was a shift in the melt pool mode from conduction-based to a transitional phase, and upon further elevation of the laser energy density, it transitioned to keyhole mode. To obtain a reliable statistical analysis of pores, at least 40 measurements should be acquired for the estimation of the pore sizes by taking comprehensive consideration of time cost. Beside, in all three melt pool modes, at a fixed observation area, the maximum size of pores generally decreased with the escalation in laser energy densities.

Achieving efficient hardfacing on stainless steel using single SiC powder in laser directed energy deposition

Generally, in a laser hardfacing process, a mixture of ceramic and metal powder is used to clad a hard surface, resulting in enhanced wear characteristics of metal parts. This study proposes an efficient hardfacing process that uses a single and minimal amount of ceramic powder (0.079 g/min in this work). This process, named as Laser Directed Energy Deposition of Minimal Ceramic Powder (LDED-MCP), features that the melt pool is generated inwardly because only the substrate participates in forming the melt pool. Furthermore, due to the minimal powder flow rate used and sparse particle-melt pool collision events, ripple formations leading to the convective melt pool flow and inhomogeneous microstructures would be suppressed. Consequently, the produced layer is nearly flat and free of incompletely melted metallic particles, thus minimizing post-machining. For a 316 L substrate and SiC powder material combination, a crack-free layer about 560 μm thick with an average hardness of about 417 HV was created through process parameter optimization. This layer showed a eutectic structure composed of γ-austenite and chromium carbides, partially melted SiC particles between dendrites, and in-situ synthesized SiC nanoparticles decorating the cell walls. Through this work, near-net-shape hardfacing of stainless steels is realized through LDED-MCP process minimizing powder pre-processing and post surface machining.

An Investigation on Microstructural Characteristics and Comprehensive Performances of Equiatomic Ratio NiTi Shape‐Memory Alloy Produced by Selective Laser Melting

The present study utilizes selective laser melting (SLM) technology to fabricate NiTi alloy and investigates the deposition quality, microstructure, mechanical performances, and functional properties of the as‐deposited parts. The NiTi component is fabricated by SLM at a suitable energy density (60.61 J cm−3), resulting in favorable surface forming quality and only micron‐sized porosity defects present in the interior. Dense and fine B19’ martensite is distributed within the epitaxial B2 austenite matrix that grows in the height direction through the melt pool boundary, along with the nanoscale Ti2Ni precipitates dispersedly distribute at B19’ grain interiors and grain boundaries. Both tensile and compressive results indicate that the as‐deposited NiTi components acquire slightly inferior ductility but superior strength than that of traditionally manufactured NiTi alloys. The shape‐memory effect of NiTi components is significantly influenced by holding temperature, exhibiting good and stable shape‐memory effect above a holding temperature of 75 °C. Simultaneously, the compressive superelastic behavior of the NiTi component exhibits favorable stability, with a recoverable strain of ≈5.5%. Overall, the NiTi component fabricated in the present study exhibits favorable mechanical properties and functional performance attributed to its excellent deposition quality and dense microstructure.

Hot Crack Formation Mechanism and Inhibition of a Novel Cobalt-Based Alloy Coating during Laser Cladding.

Laser cladding provides advanced surface treatment capabilities for enhancing the properties of components. However, its effectiveness is often challenged by the formation of hot cracks during the cladding process. This study focuses on the formation mechanism and inhibition of hot cracks in a novel cobalt-based alloy (K688) coating applied to 304LN stainless steel via laser cladding. The results indicate that hot crack formation is influenced by liquid film stability, the stress concentration, and precipitation phases. Most hot cracks were found at 25°-45° high-angle grain boundaries (HAGBs) due to the high energy of these grain boundaries, which stabilize the liquid film. A flat-top beam, compared to a Gaussian beam, creates a melt pool with a lower temperature gradient and more mitigatory fluid flow, reducing thermal stresses within the coating and the fraction of crack-sensitive, high-angle grain boundaries (S-HAGBs). Finally, crack formation was significantly inhibited by utilizing a flat-top laser beam to optimize the process parameters. These findings provide a technical foundation for achieving high-quality laser cladding of dissimilar materials, offering insights into optimizing process parameters to prevent hot crack formation.

High-speed synchrotron X-ray imaging of melt pool dynamics during ultrasonic melt processing of Al6061

Ultrasonic processing of solidifying metals in additive manufacturing can provide grain refinement and advantageous mechanical properties. However, the specific physical mechanisms of microstructural refinement relevant to laser-based additive manufacturing have not been directly observed because of sub-millimeter length scales and rapid solidification rates associated with melt pools. Here, high-speed synchrotron X-ray imaging is used to observe the effect of ultrasonic vibration directly on melt pool dynamics and solidification of Al6061 alloy. The high temporal and spatial resolution enabled direct observation of cavitation effects driven by a 20.2 kHz ultrasonic source. We utilized multiphysics simulations to validate the postulated connection between ultrasonic treatment and solidification. The X-ray results show a decrease in melt pool and keyhole depth fluctuations during melting and promotion of pore migration toward the melt pool surface with applied sonication. Additionally, the simulation results reveal increased localized melt pool flow velocity, cooling rates, and thermal gradients with applied sonication. This work shows how ultrasonic treatment can impact melt pools and its potential for improving part quality.

Engineering-Guided Deep Learning of Melt-Pool Dynamics for Additive Manufacturing Quality Monitoring

Abstract Additive manufacturing (AM) fabricates three-dimensional parts via layer-by-layer deposition and solidification of materials. Due to the complexity of this process, advanced sensing is increasingly employed to facilitate system visibility, leading to a large amount of high-dimensional and complex-structured data. While deep learning brings attractive characteristics for data-driven process monitoring and quality prediction, it is currently limited in the ability to assimilate engineering knowledge and offer model interpretability for understanding process–quality relationships. In addition, due to spatiotemporal correlations in AM, a melt-pool anomaly observed during fabrication is not always indicative of abnormal quality characteristics. There is a pressing need to go beyond pointwise analysis of melt pools and consider spatiotemporal effects for quality analysis. In this paper, we propose a novel feature learning framework guided by engineering knowledge for AM quality monitoring. First, engineering knowledge is integrated with deep learning to delineate various sources of process variations and extract melt-pool features that reflect quality-related relationships. Second, a 3D neighborhood model is designed to characterize spatiotemporal variations of melt pools based on their domain-informed features. The resulting 3D neighborhood profiles enable us to go beyond pointwise analysis of melt pools for capturing process–quality relationships. Finally, we built a regression model to predict internal density variations using 3D neighborhood profiles. Our experiments demonstrate that the proposed framework significantly outperforms traditional hand-crafted method and black-box learning in both the ability to provide quality-related features and predict internal density variations.

In situ x-ray imaging to understand subsurface behavior during continuous wave laser drilling

A limited understanding regarding the underlying dynamics and mechanisms of material removal during continuous wave laser drilling has presented significant challenges in achieving precision and process control. To address this, we employed high-fidelity, in situ synchrotron x-ray imaging to reveal previously unknown material behaviors during continuous wave laser drilling with power modulation. Our findings highlight that high-aspect ratio drill holes are achieved when the laser modulation frequency falls within the range of 8–12 kHz, provided that the laser average power and modulation amplitude levels meet the specified limits. Under these conditions, we identified a material removal mechanism driven by incremental accumulation of recoil pressure that gradually pushes material upward from deep within the substrate to the surface. This mechanism manifested as a low-frequency fluctuation in the vapor depression depth, resulting in periodic instances of material ejection. Furthermore, our study underscores that rapid expansion of the melt pool and the widening of the drill hole opening can impede effective material removal by redirecting energy from material ejection to increasing the melt pool size. This investigation contributes essential insights into the subsurface dynamics involved in the drilling of high-aspect ratio holes, furthering our fundamental understanding of this intricate process.

Photodiode-based porosity prediction in laser powder bed fusion considering inter-hatch and inter-layer effects

Laser powder bed fusion, while promising, faces hurdles in certifying fabricated parts due to cost and complexity, with in-process monitoring emerging as a potential solution. Existing models focus on predicting defects at a given location using the monitoring signals from solely that same location. Hence, these models treat each track or layer independently of the previous and subsequent ones, neglecting potential interdependencies. This study proposed an in-situ, photodiode-based monitoring approach considering inter-hatch and inter-layer effects on porosity formation - factors often overlooked in existing research. Two Ti-6Al-4 V cuboids (10×10×5 mm3) were built with optimized process parameters, with the melt pool continuously monitored at 20 kHz via a co-axially mounted photodiode. The monitoring system captured the integral radiation in the near-infrared spectrum within a field of view centered on the melt pool. The porosity is assessed by X-ray computed tomography (X-CT), serving as ground truth to build supervised machine learning (ML) models. This study considered physical phenomena occurring during the printing process, including remelting of lack of fusion pores by the subsequent layer, keyholes penetrating the current layer hence introducing pores in the layer below, and overlap between adjacent scan tracks. These considerations are critical for a holistic understanding of pore formation mechanisms. Photodiode signals and computed tomography volumes were cropped using windows of four sizes to test the model's pore localization capability. A machine learning model, specifically a Convolutional Neural Network (CNN) - Long Short-Term Memory (LSTM) network, was trained to predict porosities using these window sequences. The CNN extracted spatial features from photodiode signals, addressing inter-hatch effects, while the LSTM captured temporal dependencies across layers, addressing inter-layer effects. The results, with the Area Under the Receiver Operating Characteristic curve (AUC) of 0.91 for pores exceeding 8000 μm3 in volume and 100 μm2 in cross-sectional area, demonstrate the feasibility of the proposed model in detecting pores-level defects. This high defect prediction and positioning accuracy are essential for process control, providing real-time status of the region of interest and informing the controller of pore positions, thus facilitating intra-layer or inter-layer correction.

The influence of adjustable ring-mode laser on the formation of intermetallic compounds and mechanical properties of ultra-thin Al-Cu lap welded joints

Aluminum-copper dissimilar welding is a highly demanded connection process; however, welding defects and the excessive growth of intermetallic compounds (IMCs) cause pose challenges for its application. This study uses an adjustable ring-mode (ARM) laser technology to achieve lap welding of ultra-thin Al-Cu plates. Lap-welding experiments were conducted using three laser modes—fixed core power, fixed ring power, and varying welding speed—to investigate the evolution of material mixing, intermetallic compound distribution, and joint strength under different modes. Our results indicate that the high energy density of the core laser is beneficial for increasing the penetration depths of joints, whereas the large action area of the ring laser is beneficial for improving the stabilities of melt pools. The joint action of the adjustable ring-mode (ARM) laser increased the melting width and depth of the joint, and the mixing of Al and Cu was controlled in the Al-Cu mixed zone at the upper part of the weld, to limit element mixing in the Cu-rich zone of the weld interface and suppress the distribution of intermetallic compounds. In addition, the ring laser induced the aluminum in the upper part of the molten pool to invade from both sides of the interface to the bottom, forming a certain Al invasion depth. This limited the accumulation of intermetallic compounds at the interface, optimized the path of shear fracture propagation, and improved the shear strength of the joint. This study provides a research basis for further exploring the material flow mechanism and optimizing the intermetallic compound distribution during the Al-Cu adjustable ring-mode (ARM) laser dissimilar welding process.

Microstructural evolution in laser powder bed fusion of water-atomized high-carbon low-alloy steel: Analysis of melting mode effects

Medium/High‑carbon steels are considered susceptible to cracking during rapid cooling in laser powder bed fusion (LPBF) applications. Also, water-atomized (WA) steel powders, containing oxides, have been associated with porosity defects during this process. In this study, LPBF was employed to process WA high‑carbon low-alloy steel powders under three operational regimes – conduction, transition, and keyhole modes. Analyses based on the scaling law of keyhole stability, melt pool dimensions, and x-ray computed tomography (XCT) suggested that processing under the transition mode closely resembled a stable keyhole, enabling the successfully printing of water-atomized powders to a density of 99.93 %. Subsequent heat treatment, hardness, and residual stress assessments presented a prominent structural softening and relief of compressive stress under the transition mode. This was attributed to the intense in-situ tempering and re-austenitization that occurred within each layer. Under this condition, with no post heat treatment, an ultimate tensile strength of 1250 MPa with >2.6 % elongation was achieved. Finally, the ball-on-disk test showed that wear performance of the printed steels was primarily governed by the tribo-oxides, with a limited influence from the microstructural variation.

Study on Microstructure and High-Temperature Mechanical Properties of Al-Mg-Sc-Zr Alloy Processed by LPBF

Al-Mg-Sc-Zr alloy processed via laser powder bed fusion (LPBF) is poised for significant application in aerospace, where its high-temperature capabilities are paramount for the safety and longevity of engineered structures. This study offers a systematic examination of the alloy’s high-temperature tensile properties in relation to its microstructure and precipitate phases, utilizing experimental approaches. The LPBF-processed Al-Mg-Sc-Zr alloy features a bimodal microstructure, with columnar grains in the melt pool’s interior and equiaxed grains along its boundary, conferring exceptional properties. The application of well-calibrated processing parameters has yielded an alloy with an impressive relative density of 99.8%, nearly fully dense. Following a thermal treatment of 350 °C for 4 h, the specimens were subjected to tensile tests at both room and elevated temperatures. The data reveal that the specimens exhibit a tensile strength of 560.6 MPa and an elongation of 11.1% at room temperature. A predictable decline in tensile strength with rising temperature is observed: at 100 °C, 150 °C, 200 °C, and 250 °C; the respective strengths and elongations are 435.1 MPa and 25.8%, 269.4 MPa and 20.1%, 102.8 MPa and 47.9%, 54.0 MPa and 72.2%. These findings underpin the technical rationale for employing LPBF-processed Al-Mg-Sc-Zr alloy in aerospace applications.

Effect of subgrain microstructure on the mechanical properties of Invar 36 specimens prepared by laser powder bed fusion

Invar 36 samples were fabricated via laser powder bed fusion (LPBF) at various energy densities. In this work, a parameter range for the preparation of full-density Invar 36 samples was determined. The microstructural evolution and tensile properties of the materials were studied in the as-LPBFed state, and the role of subgrain structures on the fracture mechanism was investigated. According to the results of this analysis, as the energy density increased, the density first increased and then decreased. The maximum density (99.94 %) reached 65 J/mm3, and the simple density reached full density at 40–90 J/mm3. Due to constitutional supercooling, the microstructure of the alloy is composed of cellular subgrains and columnar subgrains. Columnar subgrains grow perpendicular to the boundary of the molten pool to the center of the molten pool, while cellular subgrains primarily exist in the remelting area of the molten pool. In the full density range, the ultimate tensile strength of the samples reaches 437–484 MPa, and differences in the morphology, distribution, and micronicomechanical properties of the subgrains are responsible for the differences in macroscopic properties. At 40, 65, and 90 J/mm3, the elastic moduli of the columnar subgrains are approximately 155.1 GPa, 161 GPa, and 162.4 GPa, respectively; the elastic moduli of the cellular subgrains are approximately 136.2 GPa, 140.2 GPa, and 139.9 GPa, respectively, which means that in the elastic deformation stage, the columnar subgrains are more resistant to elastic deformation; in the plastic deformation stage, different subgrains have different effects on crack propagation; the columnar subgrains grow perpendicularly to the melt pool boundary, which has a hindering effect on the extension of microcracks; and the cellular subgrains have a homogeneous grain size so that the microcracks can be easily extended along the cellular subgrain boundaries.

Microstructure and mechanical properties of 316L stainless steel manufactured by multi-laser selective laser melting (SLM)

The microstructure and mechanical properties of 316L stainless steel samples manufactured by dual-laser selective laser melting technology, were investigated in compare with that of the single-laser scanning samples. It was found that the porosity of the dual-laser overlap samples was lower than that of single laser forming samples due to the different laser energy density absorbed by the powders. Furthermore, it was found that the crystal structure and crystal orientation of both zones were similar. From the TEM observation, it was noted that the number density of nano-oxides in the overlap zone was higher than that in the single laser forming zone. This reason was suggested as the difference of the oxygen content inside the melt pool during the forming process. The strength and microhardness of the single-laser samples was lower than that of the dual-laser overlap samples, but the elongation was higher. By analyzing the strengthening mechanism, it was revealed that Orowan strengthening was the main reason for the difference. These results could guide the large-size component manufactured using the muti-laser selective laser melting technology.

Closed-Loop Control of Melt Pool Temperature during Laser Metal Deposition.

Laser metal deposition (LMD) is a technology for the production of near-net-shape components. It is necessary to control the manufacturing process to obtain good geometrical accuracy and metallurgical properties. In the present study, a closed-loop control method of melt pool temperature for the deposition of small Ti6Al4V blocks in open environment was proposed. Based on the developed melt pool temperature sensor and deposition height sensor, a closed-loop control system and proportional-integral (PI) controller were developed and tested. The results show that with a PI temperature controller, the melt pool temperature tends to the desired value and remains stable. Compared to the deposition block without the controller, a flatter surface and no oxidation phenomenon are obtained with the controller.

Thermokinetics driven microstructure and phase evolution in laser-based additive manufacturing of Ti-25wt.%Nb and its performance in physiological solution

A bio-compatible Ti-25 wt% Nb alloy fabricated from a blend of pure elemental powders using laser powder bed fusion additive manufacturing technique. The present work investigated the effects of processing conditions on the evolution of microstructures and its consequential material attributes, such as mechanical properties and corrosion performance. Thermal management strategies comprising laser powers of 200 W and 300 W in complement with a shorter scan length (1 mm) and substrate preheating above β-transus temperature (1123 K) were considered to achieve complete dissolution of niobium particles. The microstructure in the 200 W sample showed thin α′′ martensite needles in β matrix while martensite laths in the 300 W condition appear coarse and were twice the area fraction compared to that in 200 W build. On the other hand, microstructures in the heated substrate sample exhibited the evolution of α and β phases. A multi-scale finite element method based thermo-kinetic model spanning from melt pool scale to the component scale was incorporated to understand the mechanism of the evolution of microstructures during liquid–solid and solid–solid state transformation. Electrochemical performance in the simulated body fluid of the printed alloys was found to be significantly affected by the presence of martensite fractions. Both mechanical and corrosion behaviors were favorably influenced by adoption of the substrate preheating during additive manufacturing due to promotion of diffusional transformation of β to α at the expense of martensitic transformation.

Understanding coaxial photodiode-based multispectral pyrometer measurements at the overhang regions in laser powder bed fusion for part qualification

Coaxial photodiode monitoring sensors provide a digital signature at the melt pool level in laser powder bed fusion (L-PBF), facilitating faster part qualification. However, current signatures are plagued by significant noise and signal variation and show counterintuitive trends such as a decrease in measured temperature near overhang surfaces. This paper investigates the behavior of coaxial photodiode-based melt pool monitoring (PD-MPM) thermal measurements at overhang regions by conducting a combination of experiments and multiphysics simulations. High-speed in situ synchrotron X-ray imaging is coupled with a coaxial photodiode system to enable comparison of the observed melt pool phenomena and monitoring signals during double-track AlSi10Mg experiments. A multiphysics model is developed to simulate the melt pool dynamics and concurrent sensor signals throughout the process. We propose a surrogate model that clarifies the correlation between sensor signals and melt pool temperature. Both experimental and simulation results emphasize the significant impacts of laser energy and keyhole formation on solid-liquid interface discontinuities and PD-MPM signals. Results reveal that a boiling region with a relatively smaller projected area, as near an overhang, can lead to a decrease in the measured melt pool temperature, even when the true peak temperature remains constant, meaning that PD-MPM temperature measurements cannot be used to estimate absolute melt pool temperature. Consequently, in overhang regions, interaction between the melt pool and underlying powder results in an abruptly deforming melt pool and a pronounced decrease in both individual photodiode intensities and overall measured melt pool temperature. This work illustrates how to correctly interpret the coaxial photodiode monitoring signals in L-PBF by uncovering the intricate dynamics within the melt pool, particularly in challenging overhang regions, and pave the foundation for data-driven part qualification.

Data-driven prediction of future melt pool from built parts during metal additive manufacturing

Smart manufacturing in metal additive manufacturing (MAM) relies on real-time process optimization through the prediction of unbuilt parts using data from built parts. Melt pool dynamics are intimately associated with the development of various microstructures during the MAM. In this paper, we demonstrate the idea by establishing a machine learning (ML) model to predict the melt pool of future parts, based on the experimental data from the National Institute of Standards and Technology (NIST) where 80 % is used for the training (built parts) and 20 % for testing (future parts). The ML model integrates both data denoising and predictive modeling. First, a convolutional neural network (CNN) is used to process a large dataset of raw melt pool images, enabling the automatic removal of noises (e.g., splash and plume) and thereof extraction of high-quality melt pool data. Following that, a novel data-driven melt pool model based on multi-layer perceptron (MLP) is trained by incorporating raw, long scanning history as input features, which best accounts for the effects of printing history (e.g., intertrack heating) on melt pool development. It takes complete advantage of MLP in handling high-dimensional regression problems in conjunction with a large dataset. Upon testing under various manufacturing conditions, the average relative error magnitude (AREM) of predicting melt pool size drops to 2.8 %, compared to 14.8 % of the prior art – the Neighboring Effect Modeling Method model (NBEM). This research thus represents a significant step towards reliable melt-pool-guided AM process optimization for smart manufacturing, enabled by advanced, flexible, and maximum use of ML techniques.

Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition

Multi-fidelity (MF) modeling is a powerful statistical approach that can intelligently blend data from varied fidelity sources. This approach finds a compelling application in predicting melt pool geometry for laser-directed energy deposition (L-DED). One major challenge in using MF surrogates to merge a hierarchy of melt pool models is the variability in input spaces. To address this challenge, this paper introduces a novel approach for constructing an MF surrogate for predicting melt pool geometry by integrating models of varying complexity, that operate on heterogeneous input spaces. The first thermal model incorporates five input parameters i.e., laser power, scan velocity, powder flow rate, carrier gas flow rate, and nozzle height. In contrast, the second thermal model can only handle laser power and scan velocity. A mapping is established between the heterogeneous input spaces so that the five-dimensional space can be morphed into a pseudo two-dimensional space. Predictions are then blended using a Gaussian process-based co-kriging method. The resulting heterogeneous multi-fidelity Gaussian process (Het-MFGP) surrogate not only improves predictive accuracy but also offers computational efficiency by reducing evaluations required from the high-dimensional, high-fidelity thermal model. The tested Het-MFGP yields an R2 of 0.975 for predicting melt pool depth. This surpasses the comparatively modest R2 of 0.592 achieved by a GP trained exclusively on high-dimensional, high-fidelity data. Similarly, in the prediction of melt pool width, the Het-MFGP excels with an R2 of 0.943, outshining the GP's performance, which registers a lower R2 of 0.588. The results underscore the benefits of employing Het-MFGP for modeling melt pool behavior in L-DED. The framework successfully demonstrates how to leverage multimodal data and handle scenarios where certain input parameters may be difficult to model or measure.