Optimizing the Performance of High-Speed Machining on 15CDV6 HSLA Steel in Terms of Green Manufacturing Using Response Surface Methodology and Artificial Neural Network

The execution of sustainable manufacturing methods to make machining processes more eco-friendly is a difficult task that has attracted significant attention from the industrial area for a long time. As one of the leading manufacturing processes, machining can have a profound impact on the environment, society, and financial aspects. In a specific scenario, recognizing reasonable machining conditions to supply cutting fluids utilizing eco-friendly methods is at present a significant focal point of academic and industrial sector research. This study is to investigate the optimal operational parameters such as speed, feed rate, and cutting depth during high-speed machining of 15CDV6 HSLA steel under near-dry (green machining) and flood lubrication using response surface methodology and an artificial neural network that leads to better performance measures like tool-chip interface temperature, specific energy, yield strength, and percentage elongation. Initially, tensile samples were prepared on wire EDM, further high-speed machining has been carried out on CNC milling using a mechanical carbide cutter to improve performance. The results showed that an improvement in tool-chip interface temperature (0.9–12%), specific energy (0.8–12%), yield strength (1.8–3.2%), and percentage elongation (1.0–8.9%) using green machining has been witnessed and confirmed that green machining is an alternative of the flood to enhance the strength while reducing the specific energy in addition to eco-friendly. Moreover, the comparative analysis between RSM and ANN results determined that the ANN delivers more precise results and confirms its adequacy when its correlation coefficients are large, and root mean square errors are small compared to those obtained through the RSM.