On the role of complexity in machining time estimation

Abstract Early cost estimation of machined parts is difficult as it requires detailed process information that not usually available during product design. Parametric methods address this issue by estimating machining time from predictors related to design choices. One them complexity, defined a function dimensions and tolerances an analogy with theory. However, complexity has only limited correlation unless restrictive assumptions are made on part types processes. The objective the paper improve combining additional parameters. For purpose, first shown three factors influence (part size, area features, work material) fully captured alone. Then optimal set selected regression analysis estimates sample using existing feature-based method. proposed parametric model predict average percentage error 25% compared baseline method, over wide range geometries Therefore, accurate enough support comparison alternatives well bidding make-or-buy decisions.