Correlation analysis of cutting force and acoustic emission signals for tool condition monitoring

Identification and estimation of cutting tool wear and surface roughness of the machined surface are important in the milling process. This paper presents the correlation analysis of cutting force, acoustic emission signals, tool life, and surface roughness. We present the details of the dominant features discovery, which have a high correlation with tool wear and surface roughness. The best compound features found by the correlation analysis are verified by multiple regression models and are used to construct fault estimation models. A case study of tool wear and surface roughness estimation is presented. The good agreement between the estimation results of real tool wear and surface roughness data demonstrates the usability of acoustic emission signals in tool condition monitoring.