Abstract: In order to quickly and accurately obtain the strength of mask exposal rapid prototyping system components, traditional polynomial and BP neural network were deployed to establish components strength models in this study. The modeling results reveal that the maximum deviation and average deviation of the quadratic polynomial model are confirmed to be 9.563 2 and 2.381 2 MPa, respectively. Meanwhile, the maximum deviation and average deviation of the BP neural network model are determined to be 4.997 and 0.843 5 MPa, respectively. Comparison between the two models demonstrates that the BP neural network model is superior to the quadratic polynomial model in calculation results and performs good predictive ability. Therefore, BP neural network can be used to establish the strength model of mask exposal rapid prototyping system components.