Abstract
In the directed energy deposition (DED) process, significant empirical testing is required to select the optimal process parameters. In this study, single-track experiments were conducted using laser power and scan speed as parameters in the DED process for titanium alloys. The results of the experiment confirmed that the deposited surface color appeared differently depending on the process parameters. Cross-sectional view, hardness, microstructure, and component analyses were performed according to the color data, and a color suitable for additive manufacturing was selected. Random forest (RF) and support vector machine multi-classification models were constructed by collecting surface color data from a titanium alloy deposited on a single track; the accuracies of the multi-classification models were compared. Validation experiments were performed under conditions that each model predicted differently. According to the results of the validation experiments, the RF multi-classification model was the most accurate.
Highlights
In the directed energy deposition (DED) process, significant empirical testing is required to select the optimal process parameters
The selection of process parameters is important in the DED process
Sampson et al studied the effects of the powder mass flow rate and path velocity changes on the molten p ool[26] The increase in the height and width of the single track with an increase in the powder feed rate is affected by the laser power; it cannot be assumed that the melt pool width increases as the powder feed rate increases
Summary
In the directed energy deposition (DED) process, significant empirical testing is required to select the optimal process parameters. Single-track experiments were conducted using laser power and scan speed as parameters in the DED process for titanium alloys. Metal AM technologies can be classified into powder bed fusion (PBF) and direct energy deposition (DED) processes. Scan speed, and powder feeding rate are process parameters applicable to the DED process. Depending on these parameters, the product quality such as the deposit height and width of the single-track, adhesion to the substrate, and porosity. Zhang et al studied the PBF process using SVM and a convolutional neural network (CNN) to identify and classify the deposition quality level, and compared the classification accuracy[20]. The effects of cooling rate during additive manufacturing can change the resulting microstructure which affects mechanical properties
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
