Volume 11 Issue 2 ( June )

In the present work, models have been generated for prediction of flexural strength, in terms of four input parameters i.e. temperature of the extruder, density of the infill, printing speed, and layer height, for 3D printed samples prepared using the Fused Deposition Modelling (FDM) technique. The filament used for printing the specimen is that of Poly Lactic Acid (PLA). Regression and Artificial Neural Networks (ANN) have been used to build mathematical models by utilizing the experimental data obtained for Taguchi L16 Orthogonal array. Value of R- square for regression is 86.92. Additionally, the percentage deviation between experimental values and model predicted values have been calculated as per ANN model and the variation is 4.06 percent. Hence ANN model can be used for determination of flexural strength for any combination of four input parameters under study.

Keywords: Fused deposition modeling (FDM); Poly Lactic Acid (PLA); Artificial Neural Network (ANN)