Process Parameters Optimization to Improve Dimensional Accuracy of Stereolithography Parts

Stereolithography process limits wider applications due to low dimensional accuracy comparing with CNC. To improve accuracy and reduce part distortion, understanding the physics involved in the relationship between the setup input parameters and the part dimensional accuracy is prerequisite. In this paper, a model is proposed to find and optimize important parameters to achieve a high accuracy and also, to prediction dimensional accuracy with various values of parameters. For this purpose, the result of a previous study is used. It is found in Stereolithography these factors, respectively, have a most impact on dimensional accuracy in parts built SLA: layer thickness, hatch style, hatch spacing, hatch fill cure depth and hatch overcure. The proposed neural network model in this paper is able to predict dimensional accuracy with about 6 percents error.