Additive Manufacturing System Research Articles

Coupling Coordination and Data Management for Additive Manufacturing Systems Based on Smart Logistics

Additive Manufacturing (AM) has rapidly advanced due to its benefits in reducing material consumption and resource requirements, offering significant opportunities for energy-efficient and environmentally friendly production. As manufacturing technologies evolve, there is growing interest in smart manufacturing, prompting both academia and industry to explore ways to enhance efficiency and sustainability. Effective logistics management plays a crucial role in this context, requiring precise data prediction and optimization. This article introduces a Smart Logistics service to foster dynamic coordination within the smart logistics ecosystem. The first step is to integrate smart logistics components that can communicate effectively and provide specific value-added services. This integration aims to support contemporary industrial and production environments by enhancing decision-making models. The second step involves applying the Coupling Coordination model to assess the development of logistics in conjunction with broader economic growth. This model helps in constructing a high-quality development index system for logistics, which is essential for evaluating the efficiency of logistics operations. The third step is to evaluate the coordination between the automotive, digitalization, and logistics sectors. This assessment provides insights into the overall development levels of cities and highlights the significant impact on sustainable growth within the automotive industry. The final step includes analyzing the progress of coupling coordination in Indian provinces, identifying the transition from minor imbalances to primary coordination, and forecasting that strong coordination will be achieved by 2025. This analysis underscores the potential for mutual growth and cooperation by elevating the logistics sector’s standards and strengthening inter-industry relationships.

Detection of Cyber-Physical Attacks in Additive Manufacturing: An LSTM-Based Autoencoder Method Utilizing Reconstruction Error Analysis from Side-Channel Monitoring

To identify cyber-physical threats in additive manufacturing systems, this study proposes an advanced technique utilizing data from side-channel monitoring. The method combines several key approaches for preprocessing, analyzing, and classifying time-series data, ensuring robust attack detection capabilities. A predefined Window Sliding (FWS) preprocessing method segments continuous time-series data into manageable windows of specified size, making analysis more efficient. Next, we employ Discrete Wavelet Transform (DWT) to extract features from each window, capturing essential information across various frequency bands. Particle Swarm Optimization (PSO) is then used to refine the DWT coefficients, isolating the most valuable features to enhance classification performance by focusing on the most informative characteristics. The optimal feature set is used to train a deep learning (DL) model capable of identifying anomalies through reconstruction errors, specifically an LSTM-A autoencoder. Our results demonstrate that this approach can distinguish between normal and attack scenarios with an accuracy rate of 99% when applied to side-channel attack detection in additive manufacturing. This method provides a scalable and adaptable solution to safeguard cyber-physical systems against sophisticated cyberattacks while improving detection accuracy.

Explaining the Anomaly Detection in Additive Manufacturing via Boosting Models and Frequency Analysis

Anomaly detection is an important feature in modern additive manufacturing (AM) systems to ensure quality of the produced components. Although this topic is well discussed in the literature, current methods rely on black-box approaches, limiting our understanding of why anomalies occur, making complex the root cause identification and the consequent decision support about the action to take to mitigate them. This work addresses these limitations by proposing a structured workflow designed to enhance the explainability of anomaly detection models. Using the wire arc additive manufacturing (WAAM) process as a case study, we examined 14 wall structures printed with INVAR36 alloy under varying process parameters, producing both defect-free and defective parts. These parts were classified based on surface appearance and welding camera images. We collected welding current and voltage data at a 5 kHz sampling rate and extracted features from both time and frequency domains using a knowledge-based approach. Isolation Forest, k-Nearest Neighbor, Artificial Neural Network, XGBoost, and LGBM models were trained on these features, and the results shown best performance of boosting models, achieving F1 scores of 0.927 and 0.945, respectively. These models presented higher performance compared to other models like k-Nearest Neighbor, whereas Isolation Forest and Artificial Neural Network posses lower performance due to overfitting, with an F1 score of 0.507 and 0.56, respectively. Then, by leveraging the feature importance capabilities of these models, we identified key signal characteristics that distinguish between normal and anomalous behavior, improving the explainability of the detection process and in general about the process physics.

Fabrication and characterization of austenite-ferrite stainless steel bimetals by twin wire arc additive manufacturing

In this work, gas metal arc welding (GMAW) based twin wire arc additive manufacturing (TWAAM) system has been employed to deposit to wire materials simultaneously to fabricate austenite-ferrite stainless steel (AFSS) bimetal of austenite stainless steel (SS304L) and ferrite stainless steel (SS430L). A combination of high voltage and wire feed with low torch speed and gas flow resulted in optimal deposition as determined through response surface analysis based on experimental data of single-track bimetal bead on plate depositions. Mechanical and microstructural characterization of the AFSS bimetal was carried out using tensile test, hardness tests, fractography, SEM with EDS, and phase analysis. Tensile properties of the AFSS bimetal were seen to improved with the yield strength of 343 MPa, ultimate strength of 613 MPa and elongation of 67%, and a hardness value of 225 HV. The interface of the AFSS bimetal was found defects free and microstructures contained both austenite and ferrite phases with higher amounts of Ni-content. The fracture morphology of the fabricated AFSS bimetal was seen to contain dimple sizes lying between that of individual steels and resulted in higher elongation than that of the pure ferrite steel. This study demonstrated defects free fabrication of bimetallic structures with unique microstructural features and enhanced mechanical properties.

Rapid Prototyping of Multiscale Flexible Printed Circuit Boards with NeXus, a Robotic Additive Manufacturing System

Abstract This paper demonstrates the NeXus system, a multi-scale robotic additive manufacturing platform developed at the Louisville Automation and Robotics Research Institute (LARRI), as a rapid prototyping tool through additively manufacturing a multi-layer flexible printed circuit board (FPC) with a printed strain sensor and soldered Surface Mounted Devices (SMD). Manufacturing of the demonstrator requires the application and curing of multiple materials with specialized properties, tools for automated assembly, and software advances to streamline the process enabling the use of industry-standardized programs to command the NeXus system. Additive manufacturing processes supported by the NeXus include Aerosol Jet printing (AJP) for fine feature silver conducting lines, direct write ink-jet printing for insulating materials, and Intense Pulsed Light (IPL) for curing materials between depositions. The NeXus system transports and manipulates parts using a 5-DOF high-precision positioner. Solder paste deposition and pick-and-place (PnP) procedures are performed by a 4-DOF Selective Compliance Articulated Robot Arm (SCARA). Conversion methods between traditional PCB design software and production-ready command scripts were developed to translate basic drawings into command scripts. Multilayer structures with AJP 50-micron wide lines, an insulating bridge with a thickness of around 100 microns, and SMDs soldered to silver AJP pads, were integrated within the demonstrator. An operational amplifier, and other SMDs, reduce the complexity of the accompanying control circuit and amplifies the sensor?s response by 1,830 times. The successful fabrication of the demonstrator FPC highlights the rapid prototyping ability of the NeXus System.

Investigation on titanium wire melting through high-frequency induction heating for additive manufacturing process

ABSTRACT A high-frequency induction heating (HFIH) system is a novel and clean heat source that can potentially melt high melting point material to develop the wire feed-based additive manufacturing (AM) process. The present study establishes the optimised coil parameters, including coil geometry for melting the titanium wire using induction heating. A fully coupled electromagnetic-thermal-fluid flow model is established to analyse the temperature profile of the wire. The wire feed velocity (0.012 m/s) is incorporated in the coupled model using the deformed mesh method. Optimised wire diameter and coil parameters, such as a three-turn helical coil with a circular cross-section, coil turn spacing of 1.5 mm, and a coupling distance of 4 mm, melt the 3.6 mm titanium wire rapidly and create the molten droplet. The results suggest that the optimised coil parameters improve the magnetic flux density, which enhances joule heating in the wire. However, the conical-spiral coil geometry of the three-turn fails to melt the wire completely. In contrast, the helical coil of the three-turn melts the wire completely. The maximum velocity of the molten metal is found as 0.25 m/s. Effectively, the heat transfer and material flow analysis drives to develop the potential additive manufacturing system.

RAVEN: development of a novel robotic additive manufacturing system towards small-scale fabrication of complex scaffolds for regenerative medicine

ABSTRACT Recent technological advances in the field of Additive Manufacturing (AM) and the increasing need in Regenerative Medicine (RM) for devices that better and better mimic native tissue architecture are showing limitations in the current scaffolds fabrication techniques. A switch from the typical layer-by-layer approach is needed to achieve precise control on fibres orientation and pores dimension and morphology. In this work a new AM apparatus, the RAVEN (Robot-Assisted Volumetric ExtrusioN) system, is presented. RAVEN is based on a 7-DOF robotic arm and an extruder and allows for volumetric extrusion of polymeric filaments. The development process, namely the robotic motion optimisation, the optimisation towards small-scale trajectories, the custom-made hardware/software interfaces, and the different printing capabilities are hereby presented. The successful results are promising towards future advanced applications in which the ability of the robot to change its configuration while printing will be crucial.

Determination of the Optimum Architecture of Additively Manufactured Magnetic Bioactive Glass Scaffolds for Bone Tissue Engineering and Drug-Delivery Applications.

For better bone regeneration, precise control over the architecture of the scaffolds is necessary. Because the shape of the pore may affect the bone regeneration, therefore, additive manufacturing has been used in this study to fabricate magnetic bioactive glass (MBG) scaffolds with three different architectures, namely, grid, gyroid, and Schwarz D surface with 15 × 15 × 15 mm3 dimensions and 70% porosity. These scaffolds have been fabricated using an in-house-developed material-extrusion-based additive manufacturing system. The composition of bioactive glass was selected as 45% SiO2, 20% Na2O, 23% CaO, 6% P2O5, 2.5% B2O3, 1% ZnO, 2% MgO, and 0.5% CaF2 (wt %), and additionally 0.4 wt % of iron carbide nanoparticles were incorporated. Afterward, MBG powder was mixed with a 25% (w/v) Pluronic F-127 solution to prepare a slurry for fabricating scaffolds at 23% relative humidity. The morphological characterization using microcomputed tomography revealed the appropriate pore size distribution and interconnectivity of the scaffolds. The compressive strengths of the fabricated grid, gyroid, and Schwarz D scaffolds were found to be 14.01 ± 1.01, 10.78 ± 1.5, and 12.57 ± 1.2 MPa, respectively. The in vitro study was done by immersing the MBG scaffolds in simulated body fluid for 1, 3, 7, and 14 days. Darcy's law, which describes the flow through porous media, was used to evaluate the permeability of the scaffolds. Furthermore, an anticancer drug (Mitomycin C) was loaded onto these scaffolds, wherein these scaffolds depicted good release behavior. Overall, gyroid-structured scaffolds were found to be the most suitable among the three scaffolds considered in this study for bone tissue engineering and drug-delivery applications.

Best practices for machine learning strategies aimed at process parameter development in powder bed fusion additive manufacturing

AbstractThe process parameters used for building a part utilizing the powder-bed fusion (PBF) additive manufacturing (AM) system have a direct influence on the quality—and therefore performance—of the final object. These parameters are commonly chosen based on experience or, in many cases, iteratively through experimentation. Discovering the optimal set of parameters via trial and error can be time-consuming and costly, as it often requires examining numerous permutations and combinations of parameters which commonly have complex interactions. However, machine learning (ML) methods can recommend suitable processing windows using models trained on data. They achieve this by efficiently identifying the optimal parameters through analyzing and recognizing patterns in data described by a multi-dimensional parameter space. We reviewed ML-based forward and inverse models that have been proposed to unlock the process–structure–property–performance relationships in both directions and assessed them in relation to data (quality, quantity, and diversity), ML method (mismatches and neglect of history), and model evaluation. To address the common shortcomings inherent in the published works, we propose strategies that embrace best practices. We point out the need for consistency in the reporting of details relevant to ML models and advocate for the development of relevant international standards. Significantly, our recommendations can be adopted for ML applications outside of AM where an optimum combination of process parameters (or other inputs) must be found with only a limited amount of training data.

Electrochemical additive manufacturing of interdigitated structures using a multi-anode system with independently-controlled anodes

Interdigitated parts are used across a multitude of engineering applications. The overlapping, intertwined structures pose a challenge for fabrication using conventional additive manufacturing techniques, especially at small size scales. Electrochemical additive manufacturing (ECAM) has been shown to successfully create overhanging parts at the small scale without reliance on support structures. This study extends the ECAM capabilities into demonstration of the fabrication of interdigitated parts by the use of a multi-anode electrochemical additive manufacturing system. The ECAM process is operated by a tool head consisting of multiple anodes independently controlled by individual channels on an in-house-built multipotentiostatic system. Each anode is independently switched into active (anodic) or inactive (open-circuit) mode using a predefined, coded pattern controlling the custom electronics. While each tool is in anodic mode, its current contribution into the overall deposition process is tracked independently as well. Each independent tool can deposit material extending from regions deposited by itself or neighboring tools. The entire multi-head tool is controllably moved by a 3-axis translation system. An interdigitated comb geometry relevant to practical engineering applications is fabricated using this system. This geometry is built using a parallelized voxel-by-voxel tool path with characteristic electrode activation patterns at each position of the tool head. It was found that a purely closed-loop control with no time limit yielded a qualitatively better geometry than a control system with a 10-minute time limit applied. This study overall demonstrates the working principle of a multi-anode system and its ability to fabricate parts interdigitated structures. This study therefore advances the capabilities of ECAM as a valuable additive manufacturing process that can fabricate a variety of challenging parts for relevant engineering applications.

Additive Manufacturing of Tough Silicone Via Large-Scale, High-Viscosity Vat Photopolymerization

Abstract In this work, a large-scale, high-viscosity vat photopolymerization additive manufacturing system is designed and fabricated to print 3D structures as large as 370 × 300 × 370 mm3 out of high-viscosity, low-reactivity elastomeric resins. A detailed overview is presented of the printer's design and capabilities, including a resin processing sub-system that stores and spreads high-viscosity resin; a roll-to-roll variable tensioning system to mitigate the separation forces after printing each layer; and a light patterning system that generates high-intensity light patterns across an area of 370 × 300 mm2 with a resolution of 3840 × 4320 pixels. The ability to print with both high-viscosity and low-reactivity resins and resins that require high-intensity light enables additive manufacturing of new classes of materials that could not be printed previously using vat photopolymerization techniques. These materials include highly reinforced silica nanoparticle composites, high-molecular-weight polymers such as silicones and acrylate or methacrylate resins, and low-reactivity resins such as photocurable platinum-catalyzed liquid silicone rubber.

Genetic Algorithm-Based Data-Driven Process Selection System for Additive Manufacturing in Industry 4.0.

Additive manufacturing (AM) has impacted the manufacturing of complex three-dimensional objects in multiple materials for a wide array of applications. However, additive manufacturing, as an upcoming field, lacks automated and specific design rules for different AM processes. Moreover, the selection of specific AM processes for different geometries requires expert knowledge, which is difficult to replicate. An automated and data-driven system is needed that can capture the AM expert knowledge base and apply it to 3D-printed parts to avoid manufacturability issues. This research aims to develop a data-driven system for AM process selection within the design for additive manufacturing (DFAM) framework for Industry 4.0. A Genetic and Evolutionary Feature Weighting technique was optimized using 3D CAD data as an input to identify the optimal AM technique based on several requirements and constraints. A two-stage model was developed wherein the stage 1 model displayed average accuracies of 70% and the stage 2 model showed higher average accuracies of up to 97.33% based on quantitative feature labeling and augmentation of the datasets. The steady-state genetic algorithm (SSGA) was determined to be the most effective algorithm after benchmarking against estimation of distribution algorithm (EDA) and particle swarm optimization (PSO) algorithms, respectively. The output of this system leads to the identification of optimal AM processes for manufacturing 3D objects. This paper presents an automated design for an additive manufacturing system that is accurate and can be extended to other 3D-printing processes.

Novel additive lamination manufacturing system for rapid fabrication of large-scale reinforced structural members

PurposeAdditive lamination manufacturing (ALM), as a novel additive manufacturing technology, builds up the geometry via the lamination of fiber-reinforced polymer (FRP) fabric laterally, rendering it suitable for fabricating large-scale Stay-in-Place concrete formwork. This paper aims to investigate the control parameters and structure performance of ALM and assess its application for the fabrication of large-scale concrete formwork.Design/methodology/approachBased on previous feasibility studies, this research systematically investigates the control and material parameters that influence horizontal and vertical extrusion speeds, as well as the overall quality of ALM. Once the system parameters are established, a series of prototypes are fabricated and tested to validate the tensile strength of the formwork and its reinforcement capabilities. In addition, this study assesses the potential geometric freedom and implementation constraints of ALM.FindingsThis research identifies the essential control parameters for path planning in ALM and examines their impact on fabrication. In addition, this paper evaluates ALM’s strengths and limitations in producing concrete formwork for large-scale concrete structures, comparing these to industry benchmarks.Originality/valueA critical challenge in additive manufacturing lies in its scalability and compatibility with existing construction processes. In comparison to concrete, FRP offers advantages such as being lighter, easier to handle and providing surface protection and reinforcement. These qualities make FRP superior for formwork and compatible with existing building standards. Despite its advantages and potential, the current path planning and control model in 3D printing do not apply to ALM due to its novel build-up process. Also, the performance of fabricated parts as part of integrated large-scale structures is yet to be studied.

Three-Dimensional Printing with Earthen Materials: A Settlement-Scale Design Experience

This case study originates as a design experiment for a sustainable housing system built on-site. The context is Niamey, the capital of Niger. The study takes into account the environmental issues in the construction sector and aims to find a solution capable of meeting housing, environmental, and economic needs. In the field of earthen construction, the most important developments have been achieved in manufacturing methods. In particular, the use of an additive digital manufacturing system, such as large-scale 3D printing, allows the construction of complex shapes derived from structural and thermal studies, maintaining a high degree of automation in the construction process, reducing construction times and labor costs. This paper investigates the possibility of responding to housing and environmental needs with a settlement system made almost entirely of printed earth, maintaining the highest possible degree of automation. Starting from a study on the state of the art of 3D printing in architecture and printable earthen compounds, the design choices of similar cases are analyzed to understand the construction techniques, potentials, and limitations of the medium. Finally, a design proposal is developed based on the definition of a fully printable functional module, which, upon aggregation, determines the characteristics of the final settlement. This implies a radical change of approach compared to previous prototyping of 3D-printed earthen buildings, as the design of the single functional module is not an exercise that finds completion in itself, but is oriented to the scale of the settlement right from the definition of its basic geometric characteristics. In other words, the settlement is no longer the result of the serial aggregation of independent basic units, but arises spontaneously from the juxtaposition of functional modules designed to interact with each other and merge into a single residential complex. The settlement is, therefore, the large-scale replication of the alternation between full and empty spaces, that characterizes the single functional module and, even more importantly, the replication can take multiple forms. In fact, the full and empty spaces of the functional module are planned to allow multiple combinations of aggregation. This introduces a certain degree of customization into the growth dynamics of the settlement, a factor that is entirely new compared to previous proposals by repeatable modules. No less important are the environmental implications, as designing for the scale of the settlement allows the low carbon footprint typical of earth-based construction to be extended from the single building to the entire settlement.

SPM-SeCTIS: Severity Pattern Matching for Secure Computable Threat Information Sharing in Intelligent Additive Manufacturing

Sharing Cyber Threat Intelligence (CTI) enables organisations to work together to defend against cyberattacks. However, current methods often fail to adequately protect sensitive information, leading to security risks, especially in Intelligent Additive Manufacturing (IAM) systems. In these systems, the security and privacy of incident data collected by IoT devices are essential, as revealing threat information, such as types, impacts, and organisational interests, could be harmful. To address these challenges, we propose the Severity Pattern Matching for a Secure Computable Threat Information Sharing System (SPM-SeCTIS). This system is designed to maintain privacy by allowing intermediaries to pass along threat information without accessing sensitive details, such as the type or severity of the threats. SPM-SeCTIS ensures that attackers cannot determine which incidents organisations are interested in or what specific threats they monitor. The system employs Homomorphic Encryption (HE) to conduct threat pattern matching on encrypted data, keeping sensitive information confidential even during analysis. Our performance tests indicate that SPM-SeCTIS operates efficiently, requiring minimal time for encryption and decryption processes. Additionally, the system scales effectively, handling a large number of subscribers and incidents with ease. Compared to existing methods, SPM-SeCTIS provides improved security measures and better overall performance, making it a robust solution for protecting sensitive threat information.

Evaluating the performance of Bi58Sn42 mold produced by material extrusion additive manufacturing system for agile manufacturing

PurposeThe purpose of this study is to produce a low-cost sheet metal forming mold made from the low melting point Bi58Sn42 (bismuth) alloy by using an open-source desktop-type material extrusion additive manufacturing system and to evaluate the performance of the additively manufactured mold for low volume sheet metal forming. Thus, it was aimed to develop a fast and inexpensive die tooling methodology for low-volume batch production.Design/methodology/approachInitially, the three-dimensional printing experiments were performed to produce the sheet metal forming mold. The encountered problems during the performed three-dimensional printing experiments were analyzed. Accordingly, both tunings in process parameters (extrusion temperature, extrusion multiplier, printing speed, infill percentage, etc.) and customizations on the extruder head of the available material extrusion additive manufacturing system were made to print the Bi58Sn42 alloy properly. Subsequently, the performance of the additively manufactured mold was evaluated according to the dimensional change that occurred on it during the performed pressing operations.FindingsResults showed that the additively manufactured mold was rigid enough and proved to have sufficient strength in sheet metal forming operations for low-volume production.Originality/valueAlternative mold production was carried out using open-source material extrusion system for low volume sheet metal part production. Thus, cost effective solution was presented for agile manufacturing.

Morphological, mechanical and biological assessment of PCL/pristine graphene scaffolds for bone regeneration

Scaffolds are physical substrates for cell attachment, proliferation, and differentiation, ultimately leading to the regeneration of tissues. They must be designed according to specific biomechanical requirements such as mechanical properties, surface characteristics, biodegradability, biocompatibility, and porosity. The optimal design of a scaffold for a specific tissue strongly depends on both materials and manufacturing processes. Polymeric scaffolds reinforced with electro-active particles could play a key role in tissue engineering by modulating cell proliferation and differentiation. This paper investigates the use of an extrusion additive manufacturing system to produce PCL/pristine graphene scaffolds for bone tissue applications. PCL/pristine graphene blends were prepared using a melt blending process. Scaffolds with regular and reproducible architecture were produced with different concentrations of pristine graphene. Scaffolds were evaluated from morphological, mechanical, and biological view. The results suggest that the addition of pristine graphene improves the mechanical performance of the scaffolds, reduces the hydrophobicity, and improves cell viability and proliferation.

Measuring thermomechanical response of large-format printed polymer composite structures via digital image correlation

Large-format additive manufacturing (LFAM) is a branch of additive manufacturing (AM) research with the ability to create large structures typically measuring several meters in scale. LFAM is advantageous for tooling applications, not only because it offers the ability to create complex geometries not easily made using subtractive manufacturing processes, but the cost savings of pelletized feedstock used by these systems result in larger parts printed at faster speeds than traditional AM systems. Fiber reinforced polymer (FRP) is a commonly used feedstock material in LFAM structures because it reduces the distortion experienced during printing. However, FRP introduces highly anisotropic thermomechanical properties and contributes to a nonhomogeneous microstructure that can result in critical distortion of dimensions during tooling. Measuring the global thermomechanical response of LFAM structures requires a more representative method that accounts for not only anisotropic properties but also the nonhomogeneous nature of the final part. This is where traditional techniques to measure thermomechanical response, such as thermomechanical analysis (TMA), fall short as they assume homogeneity. This study evaluated the coefficient of thermal expansion (CTE) of LFAM structures as measured by TMA as compared to a novel digital image correlation oven (DIC Oven) system. The LFAM structures were made from 20 % by weight carbon fiber reinforced acrylonitrile butadiene styrene (CF-ABS). TMA measurements showed significant variations in CTE across a single LFAM bead, confirming the need for a global technique that captures overall thermomechanical response. The CTE values measured using the DIC Oven compared well to average TMA values obtained from localized measurements across the sample. The DIC Oven was also used to quantify the effects of different layer orientations on thermomechanical properties, which cannot be easily captured using TMA. A predictive model was also developed by using localized TMA values across an LFAM bead to predict the overall thermomechanical response of an LFAM structure.

Machine learning techniques for quality assurance in additive manufacturing processes

Additive manufacturing (AM) processes have revolutionized manufacturing industries by enabling the production of complex geometries with reduced material waste and lead times. However, ensuring the quality of AM parts remains a significant challenge due to the complexity of the process and inherent variability in material properties. This review investigates the use of artificial intelligence (AI) to enhance quality assurance in AM processes, focusing on specific machine learning techniques such as convolutional neural networks for defect detection, support vector machines for classification of material properties, and reinforcement learning for real-time process optimization. The AI-driven methodologies are applied to predict defects, optimize process parameters, and monitor real-time production quality, utilizing large datasets generated from sensors and in-situ monitoring systems. The study demonstrates significant improvements in the accuracy of defect detection, the reliability of material property classification, and the efficiency of process optimization. In addition, it addresses challenges such as data pre-processing, model interpretability, and integration with existing AM systems. The findings highlight the potential of AI to transform quality assurance in AM and outline future research directions for further integration and enhancement of AI techniques in AM.

Additively manufactured, long, serpentine submillimeter channels by combining binder jet printing and liquid-phase sintering

Metallic microfluidic devices made from powder-bed additive manufacturing systems have received increasing attention, but their feasible channel geometry and complexity are often limited by lack of an effective approach to removing trapped powder particles within the channels or conduits of the sintered parts. Here, we present an innovative approach to fabricating long serpentine, high-aspect-ratio submillimeter channels made of stainless steel 316L (SS) by binder jet printing (BJP) and liquid-phase sintering. We leverage the unique nature of the BJP process, that is printing and consolidation steps are decoupled, enabling us to join two or more parts during the sintering step. Instead of constructing the channel device as a single part, we print multiple parts for easy powder removal and later join them to form enclosed channels. The key innovation lies in adding sintering additives like boron nitrides (BN) to the SS stock powder—at the SS/BN interfaces, liquid phase is locally generated at temperature much lower than the SS melting temperature, facilitating the bonding of the multiple parts as well as the consolidation of parts for near-full density. We systematically vary the sintering temperature to show how it affects the joining quality and the channel shape distortion. The joining quality such as the fracture strengths of the joined samples is measured by a pull test while the shape distortion is characterized by various imaging techniques. The feasibility of the proposed approach is demonstrated by fabricating a 400-mm-long, fully enclosed serpentine channel with a rectangular cross-section of 0.5 mm in width and 1.8 mm in height. The pressure drop across this 3D-printed SS serpentine channels is measured for air flow and compared to a standard gas flow model, showing that the device is free of leakage or clogs.