Sol–gel and co-precipitation synthesized hybrid nanofluids for enhanced CNC turning of AISI 4340 steel: an experimental and machine learning approach

Machining high-strength alloys, such as AISI 4340 steel, presents significant challenges in terms of surface integrity, production efficiency, and heat dissipation. This study investigated the effects of a novel hybrid nanofluid of copper oxide (CuO) and aluminum oxide (Al₂O₃) nanoparticles to improve CNC turning of AISI 4340 steel. The experiments were conducted under a range of cutting conditions by varying the cutting speed, depth of cut and feed rate, along with the concentration of the hybrid nanofluid. A new methodology for preparing and applying the hybrid nanofluid demonstrated sufficient cooling and lubrication properties, enabling machining tests that improved upon traditional methods. The experimental study indicated that as the cutting speed and feed rate increased, the cutting temperature and surface roughness also increased significantly. Increasing the nanofluid concentration (0.25-0.45%) lowered the tool tip temperature and surface roughness due to increased thermal conductivity and formation of a protective tribological film. However, beyond 0.45% hybrid nanofluid concentration, the performance declined due to increased fluid viscosity and agglomeration of nanoparticles. An Artificial Neural Network (ANN) demonstrated significant predictive accuracy, with coefficients of determination (R²) of 0.864 for tool tip temperature, 0.828 for surface roughness, and 0.942 for material removal rate (MRR). The Genetic Algorithm (GA) determined the optimal nanofluid concentration of 0.4%, cutting speed of 80 m/min, feed rate of 0.07 mm/rev, and depth of cut of 0.4 mm. Experimental data confirmed ANN predictions with an error range of less than ± 2%, and confirmatory trials demonstrated that heat was dissipated, showing improved surface quality and MRR.