A Prediction Model for Maximum Stress of Additive Manufacturing Lattice Structures Based on Voting-Cascading

This paper proposes an ensemble learning prediction model (Voting-Cascading) for metal additive manufacturing lattice structure maximum stress prediction. Multiple estimators are merged for training and prediction, drawing inspiration from ensemble learning, and the cascade concept is employed to learn more about the data. Lastly, a combination of the soft voting approaches yields the final prediction result. According to the experimental findings, the suggested model's root mean square error on the test set is 9.5, which is better than several ensemble learning models.