.png){kind=icon}
.png){kind=icon}
Return
Optimizing and predicting additive manufacturing parameters using a variational autoencoder combined with data stratification
.png){kind=icon}
PRE
AI
DOI：10.1007/s40964-025-01358-0.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study proposes a new approach to predict and optimize additive manufacturing parameters using a variational autoencoder (VAE) model combined with a clustering-based data stratification method. The data set consists of 1,366 samples from the CIRTECH additive manufacturing Center at HUTECH University, which encompasses 20 features divided into three groups: geometric parameters, printing process parameters, and printing outcomes. The proposed method integrates RF to predict process outcomes (such as time and material consumption) and MLP to optimize input parameters based on these predictions. The results indicate that the prediction model achieved high precision with R2 = 0.98 and RMSE = 0.16. Although the reverse model had modest performance (R2 = 0.24), the overall system ensured stable and reliable prediction capabilities. This approach helps reduce dependence on manual testing, save materials, and improve production efficiency. The study opens up potential applications to optimize the additive manufacturing process and other manufacturing sectors.
Keywords:
Additive manufacturing optimization
Variational autoencoder
Machine learning
Data stratification
RF
MLP
Geometric parameters
Production efficiency
Prediction model
Material consumption reduction
Journal
P
IF:
5.4
Papers:
1.8K
Citations:
3.2K
Organization
View more organizations