Deposition angle prediction of Fused Deposition Modeling process using ensemble machine learning.

In present study, artificial intelligence systems intertwine with mechanical systems for reducing the manufacturing time and cost of products. In Fused Deposition Modeling (FDM) optimum value of deposition angle significantly varies with product geometry; hence, prediction and validation is performed using ensemble based random forest machine learning model. The training data is generated using different shapes and geometries whereas correlation based feature selection technique is employed to explore the crucial features of products. To check the effectiveness of the random forest model K-fold cross validation method is used. The empirical evaluation shows a prediction accuracy of 94.57%, remarkably superior than other methods. The proposed robust model efficiently predicts the optimum deposition angle for any geometry which would further enhance the applicability of digitally manufactured products.