Experimental investigation of the turning performance of high-pressure die-cast WE54 magnesium alloys under dry and minimum quantity lubrication conditions

Abstract

The increasing demand for lightweight materials in the automotive and aerospace industries has driven interest in magnesium alloys, such as WE54, due to their high strength-to-weight ratio and potential for improved fuel efficiency. However, machining magnesium alloys presents challenges regarding surface quality, tool wear, and process optimization. This study addresses these issues by evaluating the turning performance of WE54 alloy under dry and minimum quantity lubrication (MQL) conditions. This study focuses on the cutting parameters: speed, feed, and depth of cut. The primary response variables optimized using the multi-objective optimization technique are surface roughness, cutting force, and material removal rate. A Taguchi L18 orthogonal array design and the statistical method analysis of variance (ANOVA) were used to understand the effect of the parameters on the response variables. Under MQL, a better surface roughness value of 0.53 μm was achieved compared to 0.70 μm under dry conditions. The Techniques for Order Preferences by Similarity to Ideal Solution analysis finds that S = 100, f = 0.2, and d = 0.75 under MQL machining are the optimum parameters with maximum closeness coefficient value (0.7581), a combined measure of the response variables. According to the ANOVA results, the machining condition is the most influential factor on the closeness coefficient, contributing 34.80%, followed by feed and cutting speed. In addition, artificial neural networks (ANNs) have been used to predict the closeness coefficient value based on the input parameters. The ANN model showed good prediction accuracy with an R-squared value of 0.92017. Overall, utilization of the MQL has shown positive effects in reducing cutting force and surface roughness. This research exceeds previous studies by integrating experimental work, statistical analysis, and neural networks to better understand and improve the machining of WE54 using eco-friendly lubrication methods.