Intelligent hybrid optimization of sustainable machining parameters for Inconel 718 using ANN driven evolutionary and swarm algorithms

The present study investigates the sustainable machining performance of Inconel 718 under different lubrication environments, including dry, minimum quantity lubrication (MQL), Nano-MQL, and cryogenic CO₂ conditions. Experiments were designed using a Taguchi L 16 orthogonal array to evaluate the influence of cutting speed, feed rate, and lubrication strategy on cutting force, tool wear, surface roughness, and temperature. An artificial neural network (ANN) model was developed to predict machining responses, and hybrid optimization frameworks combining ANN with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) were implemented for multi-objective optimization. The ANN model demonstrated high prediction accuracy (R² > 0.97). Among the optimization approaches, the ANN–GA model achieved superior performance with a success rate of 86.7%, while ANN–PSO exhibited faster convergence. Cryogenic CO₂ machining significantly improved performance, reducing key responses by up to 43% compared to dry machining. The proposed hybrid framework provides an efficient and sustainable approach for optimizing machining parameters of Inconel 718, contributing to improved machining performance and environmentally responsible manufacturing.