Predicting defects in laser powder bed fusion using in-situ thermal imaging data and machine learning

Laser powder bed fusion (LPBF) is a widely used Additive Manufacturing (AM) process involving a high-powered laser to fuse metal powder and build up successive layers to create complex structures. Process parameter selection significantly impacts the dimensional characteristics of the melt pool morphology, including its depth and width, which is vital to the final print quality. Accurately predicting the melt-pool depth is critical for ensuring the quality of the final product. Various methods for different materials have been investigated, for example, thermal image analysis, analytical methods like scaling law, machine learning, and so on. However, most of the promising results are only studies for one material, and it is not necessarily fully applied to another material. In this paper, our study involves utilizing machine learning models to make predictions of melt-pool depth in the LPBF process and compare their performance to an analytical approach based on scaling law with Nickel alloys IN625 and IN718. We trained three different machine learning models which are Gaussian Process Regression (GPR), Support Vector Machines (SVM), and Neural Networks (NN), and evaluated their performance using R-squared error and Root Mean Squared Error (RMSE) against the performance of the analytical scaling law. Our results show that the machine learning models outperform the scaling law approach significantly. This study demonstrates the potential of machine learning for improving the accuracy of melt-pool depth prediction in LPBF and provides insights into the strengths and limitations of different machine learning models for this task.

Laser powder bed fusion (LPBF) is a key technique in metal additive manufacturing (AM) that enables the fabrication of parts with complex geometries and enhanced mechanical properties. Despite its advantages, LPBF's susceptibility to defects remains a challenge, directly linked to melt pool instability. Real-time melt pool monitoring (MPM) systems offer immediate feedback on melt pool states, which is crucial for identifying potential defects during the LPBF process. Recently, machine learning (ML)-based approaches with these monitoring systems have been introduced for real-time process anomaly detection and classification. However, one major hurdle is the requirement for large volumes of labeled and balanced data for ML model development, which is necessary for accurate process outlier identification and categorization. To address the issues, this article introduces a self-supervised learning-based visual transformer (SiT) for multilabel classification of melt pool anomalies, such as abnormal sizes, irregular shapes, spatters, and plumes. Experiments reveal that the self-supervised approach, with an average F1 score of 0.979, surpasses the performance of the supervised approach, which has an average F1 score of 0.836 across all classification cases, particularly in imbalanced datasets. The SiT model efficiently classifies multiple anomalies simultaneously, without extensive manual labeling, addressing data imbalance and enhancing MPM systems' efficiency and reliability. This advancement marks a significant contribution to improving part quality in LPBF processes.

In recent years, there has been widespread adoption of machine learning (ML) technologies to unravel intricate relationships among diverse parameters in various additive manufacturing (AM) techniques. These ML models excel at recognizing complex patterns from extensive, well-curated datasets, thereby unveiling latent knowledge crucial for informed decision-making during the AM process. The collaborative synergy between ML and AM holds the potential to revolutionize the design and production of AM-printed parts. This review delves into the challenges and opportunities emerging at the intersection of these two dynamic fields. It provides a comprehensive analysis of the publication landscape for ML-related research in the field of AM, explores common ML applications in AM research (such as quality control, process optimization, design optimization, microstructure analysis, and material formulation), and concludes by presenting an outlook that underscores the utilization of advanced ML models, the development of emerging sensors, and ML applications in emerging AM-related fields. Notably, ML has garnered increased attention in AM due to its superior performance across various AM-related applications. It is envisioned that the integration of ML into AM processes will significantly enhance 3D printing capabilities across diverse AM-related research areas.

Advancements in understanding the microstructure and properties of additive manufacturing Ti-6Al-4V alloy: A comprehensive review

Laser-based metal additive manufacturing (MAM), particularly laser powder bed fusion (LPBF) and laser directed energy deposition (L-DED), is a transformative technology enabling the production of complex, high-performance metal components with precision and minimal waste. However, its wider adoption is hindered by challenges in ensuring repeatability and consistency due to the complex, dynamic nature of the process. Closed-loop systems with in-situ monitoring and control have gained attention for quality assurance, where machine learning (ML) models are crucial for correlating sensor data with process state diagnosis and facilitating control actions. This review adopts an ML perspective to elucidate the role of ML in closed-loop control systems. It first outlines sensor data types and preprocessing methods used as ML datasets, then discusses roles and applications of ML models for in-situ monitoring, highlighting limitations and potential solutions. An ML-based closed-loop control framework is also presented, with emphasis on the integration of ML in the control component. Finally, future development directions of advanced ML approaches are envisioned. This review provides new insights into enhancing the role of ML models in laser-based MAM closed-loop control systems, serving as a crucial aid in the development of intelligent control systems.

A Web-based automated manufacturability analyzer and recommender for additive manufacturing (MAR-AM) via a hybrid Machine learning model

On the Use of Machine Learning for Additive Manufacturing Technology in Industry 4.0 Yaser M. Banadaki Abstract Additive manufacturing (AM) is a crucial component of a smart factory that promises to change traditional supply chains. However, the parts built using state-of-the-art 3D printers have noticeable unpredictable mechanical properties. In this paper, a machine learning (ML) model is proposed as a promising approach to improve the underlying failure phenomena in the AM process. The paper also describe how a ML model can be distributed to form an interactive learning network of smart AM components to fulfil the Industry 4.0 requirements including self-organization, distributed control, communication, and real-time decision-making capability. Full Text: PDF DOI: 10.15640/jcsit.v7n2a7

Additive manufacturing (AM) of hot-work tool steels such as H13 offers unique opportunities for producing complex, conformally cooled tools with reduced production time and material waste. In this study, five metal AM technologies—Fused Deposition Modeling and Sintering (FDMS, Desktop Metal Studio System and Zetamix), Binder Jetting (BJ), Laser Powder Bed Fusion (LPBF), and Directed Energy Deposition (DED)—were compared in terms of microstructure, porosity, and post-processing heat treatment response. The as-printed microstructures revealed distinct differences among the technologies: FDMS and BJ exhibited high porosity (6–9%), whereas LPBF and DED achieved near-full densification (<0.1%). Samples with sufficiently low porosity (BJ, LPBF, DED) were subjected to tempering and quenching treatments to evaluate hardness evolution and microstructural transformations. The satisfactory post-treatment hardness was observed in both tempered and quenched and tempered BJ samples, associated with secondary carbide precipitation, while LPBF and DED samples retained stable martensitic structures with hardness around 600 HV0.5. Microstructural analyses confirmed the dependence of phase morphology and carbide distribution on the thermal history intrinsic to each AM process. The study demonstrates that while FDMS and BJ are more accessible and cost-effective for low-density prototypes, LPBF and DED offer superior density and mechanical integrity suitable for functional tooling applications.

Additive manufacturing of WC reinforced maraging steel 300 composites by cold spraying and selective laser melting

This work presents a decision-making methodology that allows the merging of quantitative and qualitative decision variables for selecting the optimal metal Additive Manufacturing (AM) technology. The approach is applied on two competing technologies in the field of metal AM industry, i.e., the metal extrusion AM process (metal FFF) and the Laser Powder Bed Fusion process (LPBF) with single and multiple lasers, which represent the benchmark solution currently on the market. A comprehensive techno-economical comparison is presented where the two processes are analysed in terms of process capabilities (quality, easiness of use, setup time, range of possible materials, etc.) and costs, considering two different production scenarios and different parts’ geometries. In the first scenario, the AM system is assumed to be dedicated to one single part production while in this second scenario, the AM system is assumed to be saturated, as devoted to producing a wide mix of part types. For each scenario, two different part types made of 17–4 PH stainless steel are considered as a reference to investigate the effect of shape complexity, part size and production times to select the best technology when metal FFF and LPBF must be considered. The first part type refers to an extrusion die, to represent typical shapes of interest in the tooling industry, while the second part type is an impeller which can be used in many different industrial sectors, ranging from oil and gas to aerospace. In order to include quantitative and qualitative criteria, a decision-making model based on Analytic Hierarchy Process (AHP) is proposed as the enabler tool for decision making. The proposed approach allows to determine the most effective solution depending on the different production configurations and part types and can be used as a guideline and extended to include other technologies in the field of metal AM. On the other side, the critical discussion of the criteria selected, and the results achieved allow to highlight the pros and cons of the competing technologies, thus defining the existing limits to define directions for future research.

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Fundamental requirements of a machine learning operations platform for industrial metal additive manufacturing

Additive manufacturing (AM) enables the production of customized and complex metal parts, providing greater flexibility than traditional mass production. However, maintaining consistent product quality for AM processes remains challenging due to process variability and heat emission fluctuations, which can cause defects such as overheating. Overheating occurs when non-uniform temperature distributes across the printed parts, leading to issues such as structural weaknesses. Predicting heat emissions accurately is essential to preventing such issues, but AM facilities, particularly small- and medium-sized enterprises (SMEs), generate limited and heterogeneous datasets due to unique configurations and privacy concerns, making traditional centralized predictive model training paradigms impractical. Federated learning (FL) offers a privacy-preserving solution, it alleviates data privacy and data scarcity concerns by enabling collaborative learning across decentralized datasets while keeping data local. However, its performance suffers under heterogeneous client data and varied computational resources. This creates a need to address data heterogeneity while maintaining both global model performance and individual client personalization. We propose FedScope-KD, a novel heterogeneity-aware FL framework designed to balance the scope of global and personalized learning. Client heterogeneity level is quantified prior to the FL training, to improve the model weight aggregation during training. This is achieved through component decomposition and knowledge distillation. The framework decomposes client data into process-invariant representations, which capture the fundamental nature of the laser powder bed fusion (LPBF) process, and process-variant representations, which reflect local, client-specific configuration settings. This decomposition ensures that global models benefit from collaborative learning on the homogeneous data representations, while personalized predictions remain tailored to client-specific heterogeneous data representations. A knowledge distillation (KD) mechanism further enhances the framework by efficiently transferring process-invariant knowledge from a global teacher model to local student models. We compare the heterogeneity index generation and calculate the Dynamic Time Warping (DTW) distance for both inter-client variant and invariant components. The variant components exhibit greater distances between clients, reflecting their inherent heterogeneity, while the invariant components are more closely aligned across clients. This pattern demonstrates the effectiveness of the decomposition process in separating heterogeneous and homogeneous information. The heterogeneity index is further used for weight aggregation during FL training. The framework’s performance is validated through a comparison with baseline FL methods such as FedAvg, as well as centralized and individual learning paradigms. Performance metrics include personalized performance and global accuracy with MSE. Through experiments on heat emission datasets in the LPBF process, we show that FedScope-KD successfully addresses the challenges of data heterogeneity and resource constraints, providing a robust solution of predictive modeling for SMEs.

This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.

In the Laser Powder Bed Fusion (L-PBF) process, 3D components with complex geometries are fabricated in a layer-by-layer fashion by using a controlled laser beam to selectively melt particular regions of the metal powder bed. However, due to the stochastic nature of the L-PBF process, the top surface roughness of each solidified layer tends to be different even when the optimal processing conditions for the different positions on the build plate are employed. As a result, the mechanical properties of the built components frequently vary from one component to the next. Accordingly, this study proposes an Intelligent Additive Manufacturing Architecture (IAMA) for controlling the surface roughness of each build layer through an appropriate adjustment of the laser re-melting parameters. The IAMA architecture comprises five modules, namely In-Situ Metrology (ISM), Ex-Situ Metrology (ESM), Automatic Virtual Metrology (AVM), Additive Manufacturing Simulation (AMS) and Intelligent Compensator (IC). The feasibility of the proposed architecture is demonstrated by comparing the top surface roughness of cubic and mechanical strengths of tensile test samples built using the proposed method with those built using a traditional L-PBF approach without surface roughness control. It is found that the samples fabricated using the IAMA approach have an average top surface roughness of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.6~\mu \text{m}$ </tex-math></inline-formula> and a standard deviation is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.7~\mu \text{m}$ </tex-math></inline-formula> . By contrast, the samples produced using the traditional L-PBF approach have an average surface roughness of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$13.45~\mu \text{m}$ </tex-math></inline-formula> and a standard deviation of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2.5~\mu \text{m}$ </tex-math></inline-formula> . In addition, the specimens produced with the assistance of IAMA architecture have an average tensile strength of 1013 MPa with a standard deviation of 69.5 MPa, while those printed without surface roughness control have an average tensile strength of 903 MPa with a standard deviation of 101.4 MPa Note to Practitioners—As L-PBF produce part in a layer-by-layer manner, therefore, the roughness on the top surface of previous layer have a strong influence on the printing quality of current layer. The variations of surface roughness will lead to the fluctuation of mechanical properties of the fabricated components. Additionally, to the best of author’s knowledge, current commercial L-PBF machines can not actively control the surface roughness of samples during the process. The proposed IAMA in this work can predict and control the roughness on the top surface of each layer during L-PBF process. Therefore, the constructed architecture has strong potential for integrating into the commercial L-PBF machine for controlling the surface roughness on the top of the parts during the manufacturing process. As a result, the quality of the fabricated components is expected to be in consistent. Accordingly, L-PBF machine equipped with IAMA will have a strong potential in applying for mass production of the components in aerospace and automobile industries.