Filtern
Dokumenttyp
Schlagworte
- Additive manufacturing (6)
- Artificial neural network (4)
- Laser metal deposition (4)
- DED (3)
- Design of experiments (3)
- Quality assurance (3)
- Cladding parameter (2)
- Data preparation (2)
- Inconel 718 (2)
- Laser cladding (2)
Organisationseinheit der BAM
Directed energy deposition (DED) has been in industrial use as a coating process for many years. Modern applications include the repair of existing components and additive manufacturing. The main advantages of DED are high deposition rates and low energy input. However, the process is influenced by a variety of parameters affecting the component quality. Artificial neural networks (ANNs) offer the possibility of mapping complex processes such as DED. They can serve as a tool for predicting optimal process parameters and quality characteristics. Previous research only refers to weld beads: a transferability to additively manufactured three-dimensional components has not been investigated. In the context of this work, an ANN is generated based on 86 weld beads. Quality categories (poor, medium, and good) are chosen as target variables to combine several quality features. The applicability of this categorization compared to conventional characteristics is discussed in detail. The ANN predicts the quality category of weld beads with an average accuracy of 81.5%. Two randomly generated parameter sets predicted as “good” by the network are then used to build tracks, coatings,walls, and cubes. It is shown that ANN trained with weld beads are suitable for complex parameter predictions in a limited way.
Prognose von Qualitätsmerkmalen durch Anwendung von KI-Methoden beim Directed 10 Energy Deposition
(2022)
Dieser Beitrag enthält die Ergebnisse eines im Rahmen der DVS Forschung entwickelten Ansatzes zur Qualitätssicherung im Directed Energy Deposition. Es basiert auf der Verarbeitung verschiedener während des Prozesses gesammelter Sensordaten unter Anwendung Künstlicher Neuronale Netze (KNN). So ließen sich die Qualitätsmerkmale Härte und Dichte auf der Datenbasis von 50 additiv gefertigten Probenwürfel mit einer Abweichung < 2 % vorhersagen. Des Weiteren wurde die Übertragbarkeit des KNN auf eine Schaufelgeometrie untersucht. Auch hier ließen sich Härte und Dichte hervorragend prognostizieren (Abweichung < 1,5 %), sodass der Ansatz als validiert betrachtet werden kann.
With additive manufacturing in the powder bed, the component size is limited by the installation space. Joint welding of additively manufactured parts offers a possibility to remove this size limitation. However, due to the specific stress and microstructure state in the additively built material, it is unclear to what extent existing evaluation rules of joint welding are also suitable for welds on additive components. This is investigated using laser beam welding of additively manufactured pipe joints. The welds are evaluated by means of visual inspection, metallographic examinations as well as computed tomography. The types of defects found are comparable to conventional components. This is an indicator that existing evaluation regulations also map the possible defects occurring for weld seams on additive components.
The Directed Energy Deposition process is used in a wide range of applications including the repair, coating or modification of existing structures and the additive manufacturing of individual parts. As the process is frequently applied in the aerospace industry, the requirements for quality assurance are extremely high. Therefore, more and more sensor systems are being implemented for process monitoring. To evaluate the generated data, suitable methods must be developed. A solution, in this context, was the application of artificial neural networks (ANNs). This article demonstrates how measurement data can be used as input data for ANNs. The measurement data were generated using a pyrometer, an emission spectrometer, a camera (Charge-Coupled Device) and a laser scanner. First, a concept for the extraction of relevant features from dynamic measurement data series was presented. The developed method was then applied to generate a data set for the
quality prediction of various geometries, including weld beads, coatings and cubes. The results were compared to ANNs trained with process parameters such as laser power, scan speed and powder mass flow. It was shown that the use of measurement data provides additional value. Neural networks trained with measurement data achieve significantly higher prediction accuracy, especially for more complex geometries.
Additive manufacturing promises a high potential for the maritime sector. Directed Energy Deposition (DED) in particular offers the opportunity to produce large-volume maritime components like propeller hubs or blades without the need of a costly casting process. The post processing of such components usually generates a large amount of aluminum bronze grinding waste. The aim of the presented project is to develop a sustainable circular AM process chain for maritime components by recycling aluminum bronze grinding waste to be used as raw material to manufacture ship Propellers with a laser-powder DED process. In the present paper, grinding waste is investigated using a dynamic image Analysis system and compared to commercial DED powder. To be able to compare the material quality and to verify DED process parameters, semi-academic sample geometries are manufactured.
Laserstrahlschweißen additiv gefertigter Bauteile: Einsetzbarkeit bestehender Bewertungsvorschriften
(2021)
Bei der additiven Fertigung im Pulverbett ist die Bauteilgröße durch den Bauraum begrenzt. Das Verbindungsschweißen additiv gefertigter Teile bietet eine Möglichkeit diese Größenbegrenzung aufzuheben. Aufgrund des spezifischen Spannungs- und Gefügezustands im additiv aufgebauten Teil ist jedoch unklar, inwiefern bestehende Bewertungsvorschriften des Verbindungsschweißens auch für Schweißnähte an additiv gefertigten Bauteilen geeignet sind. Dies wird anhand des Laserstrahlschweißens additiv gefertigter Rohrverbindungen untersucht. Die Schweißnähte werden mittels visueller Prüfung, metallografischer Untersuchungen sowie Computertomografie ausgewertet. Die festgestellten Fehlerarten sind vergleichbar zu konventionellen Bauteilen. Dies ist ein Indikator dafür, dass bestehende Bewertungsvorschriften die möglichen auftretenden Defekte auch für Schweißnähte an additiven Bauteilen abbilden.
Additive manufacturing, and therefore directed energy deposition, is
gaining more and more interest from industrial users. However, quality assurance for the components produced is still a challenge. Machine learning, especially using artificial neuronal networks, is a potential method for ensuring a high-quality standard. Based on process Parameters and monitoring data, part quality can be predicted. A further advantage is the ability to constantly learn and adopt to slight process changes.
First tests using artificial neural networks focus on the prediction of track geometry. The results show that even a small data set is enough to provide high accuracy in the predictions. In this work, an artificial neural network for the predictive analysis of relative density in laser powder cladding has been developed. A central composite experimental design is used to generate 19 data sets. Input variables are laser power, feed rate and powder mass flow. Cubes are built up where density is considered as a target value. Several neural networks are trained and evaluated with these data sets. Different topologies and initial weights are considered. The best network reaches a confidence level of around 90 % for the prediction of relative density based on the process parameters. Finally, the optimization of the generalization performance is investigated. To this purpose, methods of variation in error limit as well as cross-validation are applied. In this way, density is predictable by an artificial neural network with an accuracy of about 95 %.
The Directed Energy Deposition process is used in a wide range of applications including the repair, coating or modification of existing structures and the additive manufacturing of individual parts. As the process is frequently applied in the aerospace industry, the requirements for quality assurance are extremely high. Therefore, more and more sensor systems are being implemented for process monitoring. To evaluate the generated data, suitable methods must be developed. A solution, in this context, was the application of artificial neural networks (ANNs). This article demonstrates how measurement data can be used as input data for ANNs. The measurement data were generated using a pyrometer, an emission spectrometer, a camera (Charge-Coupled Device) and a laser scanner. First, a concept for the extraction of relevant features from dynamic measurement data series was presented. The developed method was then applied to generate a data set for the quality prediction of various geometries, including weld beads, coatings and cubes. The results were compared to ANNs trained with process parameters such as laser power, scan speed and powder mass flow. It was shown that the use of measurement data provides additional value. Neural networks trained with measurement data achieve significantly higher prediction accuracy, especially for more complex geometries.
The process of laser metal deposition can be applied in many ways. Mostly, it is relevant to coating, for repair welding and for additive manufacturing. To increase the effectiveness and the productiveness, a good process understanding is necessary. Statistical test planning is effectual and often used for this purpose. For financial and temporal reasons, a restriction of the test space is reasonable. In this case, it is recommended to use a D-optimal experimental design which is practically applied to extend existing test plans or if process Limits are known. This paper investigates the applicability of a D-optimum experimental design for the laser metal deposition. The results are compared to the current results of a full factorial test plan.
Known restrictions are used for the limitation of the test space. Ti6Al4 is utilized as Substrate material and powder. Comparable results of the D-optimal experimental design and of the full factorial test plan can be demonstrated. However, 80 % of time can be saved by the experimental procedure. For this reason, the application of D-optimal experimental design for laser metal deposition is recommend.
Laser metal deposition (LMD) is an established technology for two-dimensional surface coatings. It offers high deposition rates, high material flexibility, and the possibility to deposit material on existing components. Due to these features, LMD has been increasingly applied for additive manufacturing of 3D structures in recent years. Compared to previous coating applications, additive manufacturing of 3D structures leads to new challenges regarding LMD process knowledge. In this paper, the process steps for LMD as additive manufacturing technology are described. The experiments are conducted using titanium alloy Ti-6Al-4Vand Inconel 718. Only the LMD nozzle is used to create a shielding gas atmosphere. This ensures the high geometric flexibility needed for additive manufacturing, although issues with the restricted size and quality of the shielding gas atmosphere arise. In the first step, the influence of process parameters on the geometric dimensions of single weld beads is analyzed based on design of experiments. In the second step, a 3D build-up strategy for cylindrical specimen with high dimensional accuracy is described. Process parameters, travel paths, and cooling periods between layers are adjusted. Tensile tests show that mechanical properties in the as-deposited condition are close to wrought material. As practical example, the fir-tree root profile of a turbine blade is manufactured. The feasibility of LMD as additive technology is evaluated based on this component.