Prediction of Surface Roughness in Additive Manufacturing Using Artificial Neural Networks

Abstract

In this work, we applied an Artificial Neural Networks (ANN) approach for prediction of the part surface roughness for 3D printing technology. A small number of neurons was used for building ANN model with the help of MATLAB environment. The predicted values are found to be in excellent agreement with the experimental data with average error value of 8%.In addition, we compared the proposed ANN model to another regression-based approach. Results show that the proposed model has high accuracy in comparison to statistical approach. Therefore, we can use ANN model to predict the part surface roughness for 3D printing technology.