Nanocomposite coatings like TiAlCrSiN, synthesized by physical vapor deposition, present promising potential to increase tool performance during challenging cutting applications. This study focuses on wear prognosis of cemented carbide inserts with TiAlCrSiN coatings for turning quenched and tempered 42CrMo4 steel. The purpose is to understand and predict the effect of coating architecture and thickness on tool wear. Two coating architectures, monolayer TiAlCrSiN and bilayer TiAlCrSiN/TiAlCrSiON with thickness s = ~2.0 µm and s = ~4.0 µm, are considered. Turning trials were carried out with cutting speed v c = 120 m/min, feed f = 0.25 mm and depth of cut a p = 1.5 mm. Cutting forces and flank wear VB were measured over cutting length l c , while tool damage was characterized by scanning electron microscopy analysis. Moreover, a machine learning (ML) approach combining process data, damage analysis and coating characteristics for wear prediction was developed. Higher coating thickness extends the tool life by delaying the transition between linear increase and progressive zones of tool wear curve. Oxygen incorporation reduces indentation hardness H IT and abrasive wear resistance for bilayer variant. However, workpiece material adhesion decreases with oxynitride top layer. This contributes to comparable tool performance for bilayer and monolayer variants until the transition to progressive wear zone. The ML based prediction framework shows promising potential to learn correlations between process data and tool wear until the transition to progressive wear zone. The prediction ability in terms of coating influence on the transition to progressive tool wear remains limited. The study provides promising basis for data-based understanding and prediction of coated tool wear behavior.
Bobzin et al. (Thu,) studied this question.