Predicting and Optimizing Shrinkage Rates in Zirconia Block Production Through Machine Learning

In the production of dental zirconia blocks, accurately predicting and optimizing the shrinkage rate after sintering is essential for manufacturing high-quality prosthetics. This study proposes a machine learning model that considers up to five different process conditions and raw material compositions to predict and deduce the optimal conditions for achieving the desired shrinkage rate. The model successfully analyzed various manufacturing data to accurately predict shrinkage rates and derive optimal process conditions. This approach suggests that significant improvements in product consistency and production efficiency can be achieved within the dental materials industry.