摘要：Abstract This paper aims to predict the three-dimensional surface topography for future machined parts based on high definition metrology (HDM). HDM can measure the 3D topography of previously machined surfaces with high resolution and large field of view, containing rich spatial-temporal information of the machined surfaces. Therefore, a space-time autoregressive integrated moving average (STARIMA) model is adopted to describe the spatial-temporal characteristics and predict the future surface. The model was validated by an experiment on the engine block face milling process. The results show a good agreement between the predicted surface and the real surface with an average forecast error of 0.181 micrometer for an area with 80×80 sites. The proposed surface topography prediction method can be used for the early warning of surface quality deterioration and pre-control of the manufacturing process.
