Comparing the Predictability of Soft Computing and Statistical Techniques for the Prediction of Tensile Strength of Additively Manufactured Carbon Fiber Polylactic Acid Parts

The objective of this study is to investigate the influence of input factors, namely layer height (LH), print speed (PS), and infill line direction (ID), on the tensile strength (TS) of polymer components fabricated using fused deposition modelling. The primary objective of this study is to construct a robust prediction model for TS utilising soft computing methodologies, namely a two-layered feed-forward backpropagation algorithm and a hybrid neural network-integrated fuzzy interface system (FIS). The specimens utilised for analysis were fabricated using carbon fibre fibre-reinforced polylactic acid (CF-PLA) composites per the ASTM D638 standard. A dataset is generated using a C27 orthogonal array to capture variations in LH, PS, and ID techniques. In this study, two soft computing methodologies, namely an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS), are employed to effectively describe the fused deposition process and accurately predict the TS of the printed objects. The performance of these strategies is evaluated in comparison to the response surface methodology (RSM). The findings imply an inverse correlation between the TS and the LH, indicating that decreasing the LH can improve the structural integrity of the printed components. Furthermore, The ID region's effect depends on the tensile force's orientation. Infill lines aligned at 0 degrees had the highest TS, while those at 90 degrees had the lowest. The results of this study show how input variables affect the strength of additively produced (AM) polymer components. Soft computing methods enable AM parameter optimisation and accurate TS forecasts. The ANFIS method predicted tensile strength better than ANN and RSM. The negative relationship between LH and TS emphasises the importance of choosing the right LH for mechanical qualities.