An advanced study on the application of artificial neural networks in the abrasive waterjet machining of titanium nanocomposites

Titanium metal matrix composites (TiMMCs) are challenging to process because of hard Titanium particles. Increased cutting speed results in lower roughness values and longer tool life when grinding or turning. To solve this issue, artificial neural networks are employed in this study to forecast the geometrical properties of a microchannel created by abrasive water jet machining titanium-metal matrix composites (AWJM). This work determines the ideal values for four AWJM control parameters for cutting TiMMCs: Water fly mass, distance from water and object, stream rate, and navigation speed. Artificial Neuro-Fuzzy Logic Algorithm is used to achieve the desired process outputs (responses)—material ejection rate, cut surface roughness, kerf width, and kerf point. Interaction plots are generated to examine further how changing one or more AWJM process parameters affects the measured responses, and the analysis of variance is used to isolate the contributions of each process variable. The roughness of the cut surface and rate of material ejection, which is predominantly influenced by standoff distance, speed of navigation, and titanium nitride particles, were shown to be the AWJM variables that the proposed model was most successful in predicting and optimizing. The abrasive machining and optimization outcomes give a data foundation for many industrial applications. The results were validated by doing the confirmation test with optimized cutting parameters.