Development of Additive Manufacturing Design Based on Machine Learning: A Biomedical Engineering Approach

Additive manufacturing (AM) is a versatile and complex manufacturing technique that is extensively employed in the production of personalized biopolymer-orientated items and sophisticated medical architecture. One of the most developed AM techniques is selective laser melting (SLM), which uses a laser as an energy resource to completely melt successive layers of granular resources. SLM produces titanium-oriented alloys that are highly biocompatible and have exceptionally excellent physical qualities, which have led to their widespread usage in biomedical uses. An artificial neural network-based optimizing approach was established to enhance the standard of Ti-6Al-4V SLM-based parts and assist manufacturing professionals in selecting optimum process settings. The approach relates 4 primary procedure settings to two target characteristics of the part. To improve the system's accuracy throughout neural network training, several techniques were employed to address undesirable issues. The denseness and surface hardness values of the system's R2 of 99 percent demonstrated its effectiveness. After that, a selection system was developed that lets users select the best process variables for manufactured goods whose attributes satisfy particular user requirements. The optimum part quality produced by tests using the ideal process variables suggested by the optimizing approach was almost the same as those specified by the user, with only 0.9 to 4.4 percent of mistakes at the high, significantly confirming the system's dependability.