Laser-based Directed Energy Deposition (DED) is an industrially established AM process that is used for a variety of different contours, surfaces, repair and redesign purposes as well as the construction of complete components. The challenge here is that components become more and more complex, larger and therefore more difficult to build. This means that sometimes lengthy processes have to be carried out in a very robust, reproducible and cost-effective manner. In contrast to conventional production technology, numerous dynamic process influences and weld pool phenomena have a decisive influence on the resulting welding result in DED. Precise attention must therefore be paid to exact temperature-time curves, suitable path planning and solidification conditions in order to achieve a tightly toleranced contour accuracy of the resulting component and to obtain defect-free results. During this lecture, different monitoring and control approaches will be presented in order to come closer to the aforementioned goal. In addition to a variety of sensors and customized process tools, this can also be supported by the use of AI-based methods.

Laser-based additive manufacturing (LAM) offers the ability to produce near-net-shape metal parts with unparalleled energy efficiency and flexibility in both geometry and material selection. Despite advantages, these processes are inherently, as they are characterized by multiphysics interactions, multiscale phenomena, and highly dynamic behaviors, making their modeling and optimization particularly challenging. Artificial intelligence (AI) has emerged as a promising tool for enhancing the monitoring and control of additive manufacturing. This paper presents a systematic review of AI applications for real-time control of laser-based manufacturing processes, analyzing 16 relevant articles sourced from Scopus, IEEE Xplore, and Web of Science databases. The primary objective of this work is to contribute to the advancement of autonomous manufacturing systems capable of self-monitoring and self-correction, ensuring optimal part quality, enhanced efficiency, and reduced human intervention. Our findings indicate that 62.5 % of the 16 analyzed studies have deployed AI-driven controllers in real-world scenarios, with over 56 % using AI for control strategies, such as Reinforcement Learning. Furthermore, 62.5 % of the studies employed AI for process modeling or monitoring, which was integral to the development or data pipelines of the controllers. By defining a groundwork for future developments, this review not only highlights current advancements but also hints future innovations that will likely include AI-based controllers.

Zinc-based biomaterials are promising for bioresorbable applications; however, their low melting points pose challenges in laser-based additive manufacturing (AM). This study addresses this challenge by focusing on pre-heat temperature in laser-based powder bed fusion (PBF-LB) AM, a critical factor that significantly impacts final part properties. Unlike previous studies, this work systematically explores the pre-heat temperature’s role in shaping the process map, alongside laser power and scanning speed, for high-density zinc fabrication. The primary goal is to analytically generate parameter sets to avoid the vaporization temperature of zinc during the PBF-LB process and enhance the process’s stability. The proposed approach demonstrates a significant influence of the variation in pre-heat temperature on other input parameters range, such as power and scanning speed, thus enhancing the material’s processability both theoretically and next experimentally. For model validation, 20 specimens divided between three builds each with unique pre-heat temperatures were printed, revealing a direct correlation between increased pre-heat temperature and part density. Remarkably, high density was achieved even with low laser power and high scanning speed, reaching up to 99.96%. This emphasizes the role of pre-heat temperature in enhancing production speed without compromising part integrity. Mechanical properties, assessed by Vickers microhardness (31.4 ± 3.5–39.7 ± 3.3 HV). Control over pre-heat temperature shows promise in influencing part microstructure and grain morphology, critical for future studies.

A schlieren system, adapted for Laser Directed Energy Deposition, was used to monitor and analyze the process zone under various conditions, including deliberate contamination and parameter limits. This approach enabled the identification and correlation of process-induced defects with schlieren phenomena. Events and zones were characterized and qualitative categorized to validate schlieren monitoring as a diagnostic tool. Notably, a highly active and spatially confined schlieren formation was consistently observed above the melt pool. Using a tailored schlieren optical setup and simulations, schlieren patterns were linked to refractive index changes in process gases, enabling quantitative analysis. The refractive index within the hot gas dome over the molten pool was observed to range from 1.00000712 to 1.00875126, with fluctuation speeds reaching up to 210 m/s. As a result, a model was developed to describe the impact of refractive index dynamics on the performance of coaxial monitoring systems in laser processes. A case study using an exemplary imaging monitoring system demonstrated that schlieren phenomena can cause wavelength-dependent lateral geometric shifts of up to 228 µm, significantly affecting the accuracy of object-based monitoring outcomes. The findings offer critical insights into the complex interplay between refractive index variations and monitoring results, paving the way for refined monitoring strategies that enhance reliability and precision in laser cladding applications.

This work introduces Gen-JEMA, a generative approach based on joint embedding with multimodal alignment (JEMA), to enhance feature extraction in the embedding space and improve the explainability of its predictions. Gen-JEMA addresses these challenges by leveraging multimodal data, including multi-view images and metadata such as process parameters, to learn transferable semantic representations. Gen-JEMA enables more explainable and enriched predictions by learning a decoder from the embedding. This novel co-learning framework, tailored for directed energy deposition (DED), integrates multiple data sources to learn a unified data representation and predict melt pool images from the primary sensor. The proposed approach enables real-time process monitoring using only the primary modality, simplifying hardware requirements and reducing computational overhead. The effectiveness of Gen-JEMA for DED process monitoring was evaluated, focusing on its generalization to downstream tasks such as melt pool geometry prediction and the generation of external melt pool representations using off-axis sensor data. To generate these external representations, autoencoder (AE) and variational autoencoder (VAE) architectures were optimized using Bayesian optimization. The AE outperformed other approaches achieving a 38% improvement in melt pool geometry prediction compared to the baseline and 88% in data generation compared with the VAE. The proposed framework establishes the foundation for integrating multisensor data with metadata through a generative approach, enabling various downstream tasks within the DED domain and achieving a small embedding, allowing efficient process control based on model predictions and embeddings. 

Directed Energy Deposition (DED) is a free-form metal additive manufacturing process characterized as toolless, flexible, and energy-efficient compared to traditional processes. However, it is a complex system with a highly dynamic nature that presents challenges for modeling and optimization due to its multiphysics and multiscale characteristics. Additionally, multiple factors such as different machine setups and materials require extensive testing through single-track depositions, which can be time and resource-intensive. Single-track experiments are the foundation for establishing optimal initial parameters and comprehensively characterizing bead geometry, ensuring the accuracy and efficiency of computer-aided design and process quality validation. We digitized a DED setup using the Robot Operating System (ROS 2) and employed a thermal camera for real-time monitoring and evaluation to streamline the experimentation process. With the laser power and velocity as inputs, we optimized the dimensions and stability of the melt pool and evaluated different objective functions and approaches using a Response Surface Model (RSM). The three-objective approach achieved better rewards in all iterations and, when implemented in a real setup, allowed to reduce the number of experiments and shorten setup time. Our approach can minimize waste, increase the quality and reliability of DED, and enhance and simplify human-process interaction by leveraging the collaboration between human knowledge and model predictions.

This study presents an approach for in-situ monitoring of laser powder bed fusion. Using standard laser optics, coaxial high-resolution multispectral images of powder beds are acquired in a pre-objective scanning configuration. A continuous overview image of the entire 114 × 114 mm powder bed can be generated, detecting objects down to 20 µm in diameter with a maximum offset of 22–49 µm. Multispectral information is obtained by capturing images at 6 different wavelengths from 405 nm to 850 nm. This allows in-line determination of the absorbance of the powder bed with a maximum deviation of 2.5% compared to the absorbance spectra of established methods. For the qualification of this method, ray tracing simulations on powder surfaces and tests with 20 different powders have been carried out. These included different particle sizes, aged and oxidized powders.

The large class science mission NewATHENA, rescoped by the European Space Agency (ESA) in November 2023, will explore the hot and energetic universe using advanced X-ray technology. The key components of the telescope will be hundreds of Silicon Porous Optics (SPO) modules arranged in an optical bench with a diameter of around 2.7 metres. Considering the overall size, the delicate cell structure and the high aspect ratio in combination with the material-related challenges of Ti6Al4V, additive manufacturing using Direct Energy Deposition (DED) is a promising alternative to conventional processing. In addition to discussing fundamental challenges (e.g. shielding), the development of a highperformance hybrid DED process and associated equipment for robust long-term production will be presented. The developed end-to-end manufacturing approach will be verified by manufacturing and analysing test specimens, geometric demonstrators and representative large breadboards [1], [2].

Laser-induced ablation of drops from a metal wire enables the sequential deposition of voxels, for additive manufacturing. Striving for the goal of controlled, reproducible drop transfer, for this new technique, further trends and phenomena have been studied. Different modes of drop growth along with necking have been observed. Rather reproducible was a growing pending drop underneath the wire tip until separation for a certain size. In contrast, initial transients from the laser-induced recoil pressure can lead to a quick separation of a smaller drop. Initiation of a swinging cycle can also cause drop ablation after one cycle. For too fast wire feeding, the wire underpins the melt for a while in a spoon-like manner. Apart from the drop size, the different modes affect the scatter of the flight trajectory and landing position, as important optimization criteria, for controlled 3D-printing.

Within this study, the alloy NiAl–2.5Ta–7.5Cr is investigated as a new matrix material for cBN-reinforced abrasive turbine blade tip coatings as currently used NiCoCrAlY matrix alloys suffer from insufficient strength at the high operating temperatures. Laser-based directed energy deposition with blown powder was applied to produce cBN reinforced NiAl-based coatings on monocrystalline CMSX-4 substrates. For this, powdery titanium-coated cBN and NiAl–2.5Ta–7.5Cr material were co-injected into the process zone to achieve an in situ formation of a NiAl–2.5Ta–7.5Cr/cBN composite. In order to overcome challenges such as cracking susceptibility, inductive preheating of the substrate up to 800 °C was used. Optical and scanning electron microscopy, energy dispersive X-ray spectroscopy, as well as electron backscatter diffraction were applied to analyse the fabricated samples’ microstructure. Additionally, the mechanical properties were evaluated by means of microhardness mappings. This work demonstrates the feasibility of in situ forming a metal matrix composite with a homogeneous distribution of cBN particles. The results show the beneficial effect of high-temperature preheating on the crack formation. However, the study also reveals challenges such as cracking induced by the injected cBN particles as well as severe intermixing of substrate and coating, which yields spatially resolved deviations in the chemical composition and resulting variations in microstructure and hardness.