Hardness Prediction of Laser Powder Bed Fusion Product Based on Melt Pool Radiation Intensity

Abstract

The quality stability and batch consistency of laser powder bed fusion products are key issues that must be solved in additive manufacturing. The melt pool radiation intensity data of laser powder bed fusion contain a significant amount of forming process information, and studies have shown that the analysis of melt pool radiation intensity using data-driven methods can achieve online quality judgment; however, there are still speed and accuracy problems. In this study, we propose a data-driven model for hardness predictions of laser powder bed fusion products based on process parameters fused with power spectrum features of melt pool intensity data, which quickly and accurately predicts the microhardness of laser powder bed fusion specimens and can make constructive guidance for closed-loop feedback quality regulation in practical production. The effects of three integrated learning models, Random Forest, XGBoost and LightGBM, are also compared. The results indicate that random forest has the highest prediction accuracy in this dataset; however, it has the limitation of slow training and prediction speeds. The LightGBM algorithm has the fastest training and prediction speeds, about 1.4% and 4.4% of the random forest, respectively; however, the prediction accuracy is lower than that of random forest and XGBoost. XGBoost has the best overall comparative performance with adequate training and prediction speeds, about 23.7% and 37.9% of the random forest, respectively, while ensuring a specified prediction accuracy, which is suitable for application in engineering practices.

Surface Roughness of Interior Fine Flow Channels in Selective Laser Melted Ti-6Al-4V Alloy Components

“…Subsequently, the data from Table 2 (groups d–g) were further subjected to a robust Random Forest Machine Learning (RF-ML) regression model, employing a supervised learning approach. This model was trained on labeled data, where the target variable was the measured channel surface roughness associated with each set of process parameters (laser power, scan speed, and layer thickness) to closely examine the interactions between the parameters [ 79 ] and to optimize with increased accuracy [ 80 , 81 ]. The RF-ML model employed in this study was meticulously developed through a series of carefully structured steps, beginning with data preprocessing.…”

Review of Visual Measurement Methods for Metal Vaporization Processes in Laser Powder Bed Fusion

“…liquid surface [74], causing unstable melt pool flow and droplet splashing, increasing porosity and other defects. At the same time, metal vaporization causes volatile alloying elements to evaporate, resulting in alloy composition segregation, which affects the chemical composition, microstructure, and properties of the part [75].…”

“…The vapor expansion creates vapor recoil pressure on the molten surface [ 72 ], which increases its penetration depth and creates a gas-filled or plasma-filled depression, often referred to as a keyhole [ 51 ]. Porosity defects are caused by keyhole collapse, trapping shielding gas in the melt pool [ 73 ] and creating porosity defects, while the high saturation vapor pressure of alloying elements exerts recoil pressure on the melt pool liquid surface [ 74 ], causing unstable melt pool flow and droplet splashing, increasing porosity and other defects. At the same time, metal vaporization causes volatile alloying elements to evaporate, resulting in alloy composition segregation, which affects the chemical composition, microstructure, and properties of the part [ 75 ].…”

Prediction of mechanical properties of LPBF built part based on process monitoring and Gaussian process regression

“…Experimental evaluation demonstrated that in-process sensing reduced the predicted root mean square error (RMSE) by 44% and improved the coefficient of determination (R 2 ) by 22.6% compared to a model that utilized only process parameters and material properties as inputs. Zhang et al [12] collected the melt pool radiation intensity data from the K438 powder printing process and processed this data to obtain nine features based on the power spectrum. These features were then combined with process parameter information (laser power, scan speed, scan pitch) and layer information to form the input features.…”