Key points are not available for this paper at this time.
Forecasting the performance of machining operations heavily rely on the determination of real-life conditions in digital models. Such an approach maximizes productivity and minimizes time and cost outcomes. Aluminum alloys have broad utilization in the metal industry since their lightweight structure and relatively high strength compose an excellent mix. In this context, this paper addresses these critical topics with focusing on the performance assessment of machinability indicators. The evaluation of the performance contributions of cutting mediums that is, dry and MQL were done on machining results. Lastly, machine learning algorithm based on linear regression was tested on the estimation ability of machining outcomes. One of the prominent results from this study is the distinct achievement of MQL method against dry cutting for all experimental lines. Second is the near-excellent structure of the machine learning strategies, which makes it possible to predict machinability characteristics; specifically, decision tree and KNN classifiers achieved testing accuracies of 0.75, 1.00, 1.00, and 1.00 for cutting speed, feed rate, depth of cut, and machining medium, respectively. The paper differs from the previous works by applying various machine learning approaches for achieving maximum machinability for AA7075 alloys under sustainable environment. This paper is expected to analyze the turning Al alloys by using effective models and methods in sustainable and smart manufacturing.
Kuntoğlu et al. (Thu,) studied this question.