Scholarlink

<p>The increasing uses of alloy steels in high-precision engineering has emphasized the critical importance of surface integrity, as surface quality directly dictates the fit accuracy and wear resistance of mechanical components. This research presents a comparative investigation and predictive modeling of cutting forces (Fx​,Fy​,Fz​) and surface roughness (Ra​,Rt​,Rz​) in the hard turning of 100Cr6 steel (60 HRC) using CC650 ceramic insert. Utilizing a 2<sup>3</sup> full factorial design, Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models were developed to analyze the impact of cutting speed (Vc​), feed rate (f), and depth of cut (ap​). Quantitative results demonstrate exceptionally high predictive accuracy for both approaches, with correlation coefficients (R<sup>2</sup>) reaching approximately 1 for MLR and exceeding 0.9999 for ANN. A rigorous residual analysis reveals a negligible precision gap of 10<sup>− 10</sup>, indicating that while both models are highly reliable, the MLR approach offers superior simplicity and computational efficiency for industrial applications. Specifically, the study identifies the feed rate as the dominant factor for surface topography, while the depth of cut significantly influences the cutting force components. These findings provide a high-precision framework for optimizing machining parameters and ensuring superior surface integrity in the production of high-performance mechanical components.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Investigation and predictive modeling of cutting forces and surface roughness in hard turning of 100Cr6 steel: a MLR and ANN approach

  • 期刊论文

  • 发表日期：

    2026年5月13日

查看全文
  • Faouzi Hamza,
  • Hamid Hamadache,
  • Abdelmoumene Guedri

摘要

The increasing uses of alloy steels in high-precision engineering has emphasized the critical importance of surface integrity, as surface quality directly dictates the fit accuracy and wear resistance of mechanical components. This research presents a comparative investigation and predictive modeling of cutting forces (Fx​,Fy​,Fz​) and surface roughness (Ra​,Rt​,Rz​) in the hard turning of 100Cr6 steel (60 HRC) using CC650 ceramic insert. Utilizing a 23 full factorial design, Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models were developed to analyze the impact of cutting speed (Vc​), feed rate (f), and depth of cut (ap​). Quantitative results demonstrate exceptionally high predictive accuracy for both approaches, with correlation coefficients (R2) reaching approximately 1 for MLR and exceeding 0.9999 for ANN. A rigorous residual analysis reveals a negligible precision gap of 10− 10, indicating that while both models are highly reliable, the MLR approach offers superior simplicity and computational efficiency for industrial applications. Specifically, the study identifies the feed rate as the dominant factor for surface topography, while the depth of cut significantly influences the cutting force components. These findings provide a high-precision framework for optimizing machining parameters and ensuring superior surface integrity in the production of high-performance mechanical components.