Modelling and Prediction of Surface Roughness in CNC Turning Process using Neural Networks

Šarić, Tomislav; Vukelić, Đorđe; Šimunović, Katica; Svalina, Ilija; Tadić, Branko; Prica, Miljana; Šimunović, Goran

doi:10.17559/tv-20200818114207

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A combination of small feed [29] and corner radius [30], and efficient cooling and lubrication [31], generally leads to good surface quality. Moreover, the use of wiper turning inserts instead of their conventional counterparts, also yields good finished surface [32]. Vibration minimization will also improve surface roughness [33].…”

Section: Introductionmentioning

confidence: 99%

Optimization of Surface Roughness Based on Turning Parameters and Insert Geometry

Vukelić¹,

Prica²,

Ivanov³

et al. 2022

Int. j. simul. model.

View full text Add to dashboard Cite

This study is focused on dry longitudinal turning of AISI steel using CVD coated cutting inserts. The machining was conducted at different levels of cutting speed, feed, depth of cut, corner radius, rake, inclination and approach angles. Surface roughness was measured after each experiment, and statistical analysis was used to derive an empirical, regression model for arithmetical mean surface roughness. The regression model was used to theoretically minimize surface roughness, followed by additional verification experiments. The 95 % confidence interval constructed using ten additional batteries of experiments, contained the theoretically predicted minimum roughness of Ra = 0.238 μm. The mean absolute prediction error of the optimal roughness equals 0.006 μm. The results reveal practical applicability of the developed model.

show abstract