Investigation of the Influence of Machining Parameters on Surface Roughness in Turning Operations - Machine Learning Application

Aug 4, 2026

Upload by Ophelia

Turning operations depend on machining parameters, with surface roughness a key quality criterion. This study examines how cutting speed and feed rate affect surface roughness during aluminum alloy 6082 (AA6082) turning. Experiments used uncoated cemented carbide tools at constant depth of cut (0.5 mm), varying cutting speed (240–360 m/min) and feed rate (0.05–0.15 mm/rev). In addition to parameters, temperature, cutting forces, revolution, current, voltage, and power were measured and used to build a dataset for multiple machine learning models. Gradient Boosting achieved the best prediction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Surface quality and roughness optimization in turning

AI/ML for manufacturing quality prediction

Methods (Experimental design)

Machining parameters and measurement variables

Dataset construction

Machine Learning Modeling

Model evaluation and metrics

Best-performing algorithm

Results and Conclusions

ISSN 1330-3651 (Print), ISSN 1848-6339 (Online) [https://doi.org/10.17559/TV-20250501002635](https://doi.org/10.17559/TV-20250501002635) [Received: 1 May 2025](Received: 1 May 2025); Accepted: 22 September 2025 Original scientific paper Investigation of the Influence of Machining Parameters on Surface Roughness in Turning Operations and Machine Learning Application Metin ZEYVELİ, Murat AYDIN* Abstract: The performance of turning operations gradually depends on the machining parameters, and the most important parameter is the surface roughness quality. In this study, the effect of cutting speed and feed rate on the surface roughness in aluminium alloy 6082 (AA6082) machining, which is widely used in the automotive and aerospace sectors, was investigated experimentally and by machine learning prediction. In the experiments, three different cutting speeds (240, 300, and 360 m/min), three different feed rates (0 .05, 0. 1, and 0.15 mm/rev), and a constant depth of cut (0 .5 mm) were used as machining parameters. In addition to machining parameters, the temperature, cutting forces, revolution, current, voltage, and power were measured. The workpiece was machined using uncoated cemented carbide cutting tools. Experimental results showed that the surface roughness increased with increasing feed rate and decreased with increasing cutting speed. The complete dataset was created from experiments by selecting measurements and machining parameters as inputs and surface roughness as output. Various machine learning models were implemented on this dataset, and different metric scores were used to select the best prediction performance of the machine learning models. Gradient Boosting (GB) exhibited superior prediction performance compared to the other tested algorithms, with an R2 score of 0.98560. The GB model emerged as the most precise and accurate, characterized by the highest R2 score, the lowest root mean squared error (0 . 12095), the lowest mean absolute error (0 .09804), and the lowest mean squared error (0 .01463) scores, respectively. Keywords: CNC turning; machinability; machine learning; surface roughness 1 INTRODUCTION The improvement of surface quality of machined parts is the primary objective in manufacturing, especially in turning operations. These processes, defined by material removal to achieve particular geometries, have various parameters to influence final surface quality, namely called surface roughness. Some studies have reported on surface quality and dimensional accuracy optimization. This study comprehensively evaluated the dimensional deviation, flank wear, and surface roughness during the dry turning of C45 steel [1] . A surface roughness of 0.297 μm was achieved in Inconel 625 alloy at a feed rate of 0.1 mm/rev and a corner radius of 0.8 mm [2] . The negative effects of vibration on surface quality were demonstrated through simulations [3] . A minimum roughness value of Ra = 0.238 μm was achieved in the machining of AISI steel with CVDcoated tools [4] . In addition, other studies focused on cutting tool performance and coating technologies for dry turning. A study reported that TiN-coated tools provided 30 times longer life than uncoated tools in the machining of AISI D2 steel and provided 90.5% cost savings [5] . Similarly, the performance of TiCN-based cermet and carbide cutting tools in the dry turning of tempered martensitic stainless steel was investigated, and the effects of the cutting speed, feed rate, and side cutting edge angle on the tool life were demonstrated [6] . PVD, CVD, and MT-CVD coating technologies have been compared for the machining of AISI 4140 steel [7] . Furthermore, the superiority of PVD-coated tools in the machining of Incoloy 825 has been demonstrated [8] . The optimum cutting speed for TiN+AlCrN-coated tungsten carbide and Al₂O₃ + TiC ceramic tools was 220 m/min [9] . The adaptation of artificial intelligence (AI) and machine learning (ML) into conventional man

FAQs

Which machining parameters were investigated for AA6082 turning and how did they affect surface roughness?

Cutting speed and feed rate were varied. Surface roughness increased with higher feed rate and decreased with higher cutting speed.

What additional signals were measured besides cutting speed and feed rate?

Temperature, cutting forces, revolution, current, voltage, and power were measured alongside the machining parameters.

Which machine learning model showed the best surface roughness prediction performance?

Gradient Boosting (GB) outperformed the other tested algorithms, achieving an R2 score of 0.98560 with the lowest reported error metrics.

Aug 4, 2026

Upload by Ophelia