Stainless steel (SS) and Titanium alloy (Ti) are the most commonly used materials in many industrial fields such as the automotive and aerospace industry. Stainless steel has good corrosion resistance and titanium alloy has an extremely lightweight characteristic. The combination of both materials has become a tremendous innovation in the industrial sector. Resistance spot welding which has commonly applied in many industrial fields is a good consideration to join these two dissimilar materials due to the high efficiency that could be achieved by using this method. However, the way of joining these dissimilar materials should be carefully considered due to the significant difference in mechanical properties between SS and Ti. In the present study, 3 mm of SS316L and Ti6Al4V sheets were joint under the resistance spot welding method with an aluminum interlayer. The optimized welding parameters were provided under the Taguchi method L9 orthogonal array along with the mechanical properties’ investigation. The optimum welding parameters were 11 kA of weld current, 30 Cycles of welding time, and 5 kN of electrode force which produced 8.83 kN tensile-shear load of the joint. The mechanical structure analysis shows the different morphology between stainless steel and titanium interfaces and the intermetallic compound layer was formed on the SS/Al and Al/Ti interfaces. The EDX analysis shows the atomic diffusion-reaction on the application of aluminum as an interlayer on the SS/Ti joint.

Friction drilling is a green hole-making process that zealously utilizes the heat generated from the friction between the rotating conical tool and workpiece to create a bushing without generating chip. The difficult-to-machine materials with unique metallurgical properties have been developed to meet the demands of extreme applications. However, the major challenges of friction drilling on difficult-to-machine materials are the hole diameter accuracy, petal formation and tool wear. In this study, the effects of process parameters such as spindle speed and feed rate on bushing height and shape, hardness and tool wear in friction drilling of titanium alloy Ti-6Al-4V were experimentally investigated using tungsten carbide tool. Optical photographs have also been analyzed for better understanding of the chipless friction drilling process for different parametric settings. Experimental results indicated that the spindle speed has great influences for achieving better bushing formation and prolong the tool life. It was confirmed that the low spindle speed and low feed rate have great influences for achieving better bushing shape and height, prolong tool life and lower hardness that located adjacent to the hole wall. It also was discovered that the low thermal conductivity of Ti-6Al-4V caused to improper increment of frictional heat and surface temperature. This disadvantage leads to unsatisfactory bushing formation. This work demonstrated the performances of chipless friction drilling used on difficult-to-machine material that can offer a great prospective for a new product design and manufacturing.

The evolving technology has pushed machine learning techniques to replace human smartness. A machine learning model is capable of learning and replicating like our brain. This approach of data-driven model is implemented to predict the cutting force in machining of Ti6Al4V. Titanium alloys are commonly used in high strength applications due to their excellent properties. These same properties make the machining of the titanium alloy complicated. An attempt has been made for finding the cutting force under minimum quantity lubrication (MQL). MQL is a sustainable manufacturing-based lubrication system. Taguchi’s approach was used to attain a full factorial design for combination of different parameters. Accordingly, a neural network (NN) model was developed which was capable of predicting cutting forces based on the trained model. The proposed model could be implemented to find optimal parameters in shortest duration, thereby eliminating the need for experimental computations.