Machine learning based optimization method for vacuum carburizing process and its application

This paper develops an optimized prediction method based on machine learning for optimal process parameters vacuum carburizing. The critical point is data expansion through a few and data, which leads to optimizing carburization in heat treatment. extends the volume by constructing neural network with augmentation presence of small samples. In this paper, database 213 expanded 2116800 prediction. Finally, we found carburizing vast database. relative error three targets less than that target obtained simulation corresponding parameters. 5.6%, 1%, 0.02%, respectively. Compared simulations actual experiments, saves much computational time. It provides large amount referable parameter while ensuring certain level accuracy.