Nickel-based alloys are widely used in the aerospace industry, nuclear reactors and the automotive industry. These alloys exhibit excellent physical and chemical properties at high temperatures. However, nickel-based alloys are difficult to machine materials with high hardness and low thermal conductivity, which results in high cutting forces during machining. Additionally, increasing demand for mesoscale components in the industry has opened a door for research in this field. This paper focuses on meso-scale milling of Inconel 718 alloy. Aiming at the problem of high cutting forces, meso-scale milling experiments of Inconel 718 alloy were conducted. Due to its high strength and work-hardening characteristics, proper tool coating and process parameters should be selected. In this work, TiAlN, TiSiN, and nACo coatings were selected. Taguchi's L9 orthogonal array was employed for conducting experiments in a dry environment. In this paper, feed per tooth, cutting velocity, depth of cut, and tool coatings are considered as input parameters, and their effects on cutting forces are analysed through the statistical technique of analysis of variance (ANOVA) to figure out the most important process parameters.

Sustainable machining of Inconel 718, a nickel-based superalloy that is highly valuable in aerospace, is faced with the challenge that it has high energy requirements and poor machinability. In this study, a new energy consumption map and combined energy-morphology framework is proposed which draws a correlation between a specific cutting energy (SCE) and the mechanics of chip formation. Detailed experimental profiling maintained over a variety of cutting speeds (25–75 m/min ) and feed rates (0.05–0.20 mm/rev) demonstrates a SCE profile with a high-energy ridge of greater than 3.0 J/mm³ at lower feed rates, and a low-energy trough of less than 2.0 J/mm³ at higher speeds and feeds. Quantitative measurements of chip morphology suggest that low-SCE conditions are coupled with fine serrations, shear bands of less than 24 μm, compression ratios of less than 1.2, and relatively large included angles hence indicating efficient thermally assisted shear localization. The best processing window of 62.5–75 m/min and 0.10–0.15 mm/rev was found that allows to save energy and at the same time improve chip control. The derived energy-morphology map is a viable tool of shop-floor decision making, which helps to achieve energy-efficient machining.

Meso-scale ultrasonic vibration-assisted end milling (UVAEM) is an advanced manufacturing technique. UVAEM of Inconel 718 superalloy presents significant modeling challenges due to complex thermo-mechanical interactions and meso-scale size effects. This study introduces a machine learning framework that systematically compares Gaussian Process Regression (GPR), Support Vector Regression (SVR), Random Forest (RF), and Ridge Regression for predicting cutting force, tool wear, and surface roughness, thereby contributing to sustainable manufacturing. Experiments followed a Taguchi L16 orthogonal array with two replicates (n = 32), varying cutting speed (10–40 m/min), feed rate (0.01–0.025 mm/tooth), depth of cut (0.10–0.25 mm), vibration amplitude (0–9 μm), and tool coating (TiAlN, TiSiN, nACo, Uncoated). Tool coating was one-hot encoded, and strict leave-one-out cross-validation (LOOCV) with within-fold standardization ensured unbiased generalization metrics. Following nested hyperparameter tuning, SVR achieved the highest accuracy (R² = 0.9552, 0.9473, 0.9294), marginally outperforming GPR (R² = 0.9543, 0.9420, 0.9290). Ridge regression was competitive for tool wear (R² = 0.9235), while random forest ranked last due to limited ensemble diversity at n = 32. Pearson correlation identified depth of cut as the dominant driver of cutting force and surface roughness (r = 0.767, 0.759), cutting speed as the primary driver of tool wear (r = 0.663), and vibration amplitude as consistently beneficial across all three responses. SVR and GPR are recommended as reliable surrogate models for process optimization in UVAEM of Inconel 718.