Original scientific paper
https://doi.org/10.31534/engmod.2026.1.ri.03f
Cutting Force Prediction in Turning using Micro-Textured Tools
Shailesh Rao A.
orcid.org/0000-0001-6190-9857
; Department of Mechanical Engineering, Nitte (Deemed to be University), Nitte Meenakshi Institute of Technology (NMIT), Bengaluru, INDIA
*
Santosh Kumar
; Department of Industrial and Production Engineering, National Institute of Engineering, Mysuru 560008, Karnataka, INDIA
Suresh Kumar S.
; Department of Mechanical Engineering, National Institute of Engineering, Mysuru 560008, Karnataka, INDIA
Sathisha H.M.
; Department of Mechanical Engineering, National Institute of Engineering, Mysuru 560008, Karnataka, INDIA
Pavan Kumar B.K.
; Department of Mechanical Engineering, Ballari Institute of Technology and Management, Ballari 583104, Karnataka, INDIA
* Corresponding author.
Abstract
This study investigates the influence of rake-face micro-texturing on turning performance and develops predictive models for cutting force. Turning experiments on AISI 1014 mild steel were performed under four conditions: dry turning (A1), lubricated turning with a plain tool (A2), and lubricated turning with micro-dimple (A3) and micro-channel (A4) textured tools, at two cutting speeds (26 and 39 m/min) and two depths of cut (0.75 and 1 mm). For each test, the cutting force, vibration amplitude, surface roughness and chip saw-tooth distance were measured, while the tool-tip temperature and cutting power were derived from the measured quantities. The micro-channel tool (A4) consistently gave the lowest cutting force, temperature, power consumption and surface roughness, which is attributed to improved lubricant retention at the tool–chip interface. Spearman correlation analysis was used to identify the parameters most strongly associated with the cutting force. Further linear regression models relating the cutting force to input variables such as cutting speed, tool-tip temperature, power and vibration amplitude were developed. Building on the random forest model published in the authors’ preliminary study, a factorial analysis of variance and a leave-one-out cross-validated comparison of five machine learning models were then performed. The analysis confirms a statistically significant effect of the tool texture on the cutting force (p < 0.001), and multiple linear regression is found to perform best for this dataset (R² = 0.93, RMSE = 2.85 N), confirming the potential of data-driven models for selecting process parameters and tool texture in turning.
Keywords
micro-textured tool, turning, cutting force, machine learning
Hrčak ID:
351013
URI
Publication date:
17.7.2026.
Visits: 0 *