MQL Strategies Applied in Ti-6Al-4V Alloy Milling-Comparative Analysis between Experimental Design and Artificial...

Area of Science:

• Materials Science and Engineering
• Manufacturing Processes
• Tribology

Background:

• Titanium alloys like Ti-6Al-4V are crucial in aerospace and biomedical fields.
• Their excellent properties are offset by poor machinability, necessitating advanced processing techniques.
• Minimum Quantity Lubrication (MQL) offers an environmentally friendly and efficient lubrication strategy.

Purpose of the Study:

• To investigate the effects of different lubrication strategies under MQL on Ti-6Al-4V alloy milling.
• To optimize milling parameters (speed, feed rate, depth of cut) for improved machinability.
• To compare the predictive capabilities of artificial neural networks (ANN) with traditional experimental design.

Main Methods:

• Milling experiments were conducted on Ti-6Al-4V using a custom MQL prototype valve.
• A factorial experimental design varied speed, feed rate, and depth of cut.
• Cutting forces, torque, and surface roughness were measured.
• Desirability optimization and multilayer perceptron ANNs were employed for analysis.

Main Results:

• Feed rate and depth of cut were identified as the most influential parameters on machining outcomes.
• MQL with graphite-based cutting fluid significantly reduced surface roughness.
• ANN models demonstrated comparable predictive accuracy to the factorial experimental design.

Conclusions:

• Optimized MQL parameters, particularly feed rate and depth of cut, enhance Ti-6Al-4V machinability.
• Graphite-containing MQL is effective for reducing surface roughness in Ti-6Al-4V milling.
• ANNs provide a viable alternative for predicting milling performance, complementing traditional methods.