In this paper, a complete framework is proposed to realize on-line monitoring of surface quality based on machining mechanism and multi-sensor fusion. Off-line experiments and on-line modeling are integrated together to obtain the effective features to characterize the relation between the surface quality and sensor information. Vibration, force and acoustic emission signal are selected and different sensors are mounted to obtain enough information from the machining process. In addition, parametric and non parametric methods are used to extract the features which are sensitive to surface quality and insensitive to the cutting parameters. After the features are selected, methods based on hybrid intelligence are presented to build the relationship between the surface quality and the corresponding features. The establishment of the whole framework provides an effective means to realize the online monitoring of surface quality during the milling process.© (2010) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.