Sculptured parts, characterized by interconnected and bounded parametric surface patches, are widely used in aerospace, automobile, shipbuilding and plastic mold industries due to their functional and aesthetic properties. However, adoption of these sculptured surfaces on mechanical products increases the complexity of manufacturing and puts forward a challenge to achieve high machining quality and productivity, as well as low machining cost.

Machining of sculptured parts is mostly carried out on a milling machine. The milling process can be divided into:​ rough cut (roughing) and fine cut (finishing) operations. Rough machining is used to remove excess stock material, while finish machining is aimed at generating adequate tool paths for producing the final shape of the part. When a sculptured part is machined from prismatic stock, a large amount of rough cut, up to 90 percent of the total machining, is required. Cutting time reduction in rough machining can considerably improve the efficiency of sculptured part machining, lower production cost.

This research focuses on the productivity improvement of sculptured part rough milling machining that is affected essentially by CNC tool path and machining parameters. Two major strategies, machining path strategy and machining parameter strategy are investigated. A number of new methods are introduced to generate highly productive CNC tool path and machining parameters.

Study on machining path strategy involves approaches of generating 2½D CNC tool path trajectory, creating new tool path patterns, and automatically identifying optimal tool path pattern. While research on machining parameter strategy focuses on the minimization of cutting time, based upon the changing part geometry during machining and manufacturing constraints. A method that incorporates an existing milling process model into the cutting parameter optimization to predict instantaneous cutting force and identify the most effective cutting parameters is introduced. An improved model cofficient determination scheme using numerical optimization and artificial neural network techniques is developed, and extensive cutting tests are carried to allow the milling process model to fit into the cutting parameter optimization. A method for the automated formulation and solution of the cutting time minimization problem is also introduced to allow important machining parameters, including the number of cutting layers, depth of cut, feed rate and cross-cutting depth, to be determined without human intervention.

The research directly contributes to automated sculptured part machining, and has a great potential to produce significant economical benefits to manufacturing industry. The study also establishes a platform for further research and development on intelligent sculptured part machining.